8762 files changed+47012−5718624
5762 more files changed are not listed.
.agents/skills/builtin-skills/SKILL.mddeleted−42
@@ -1,42 +0,0 @@
1−---
2−name: builtin-skills
3−description:
4− Use when creating a new builtin skill for Crush, editing an existing builtin
5− skill (internal/skills/builtin/), or when the user needs to understand how the
6− embedded skill system works.
7−---
8−
9−# Builtin Skills
10−
11−Crush embeds skills directly into the binary via `internal/skills/builtin/`.
12−These are always available without user configuration.
13−
14−## How It Works
15−
16−- Each skill lives in `internal/skills/builtin/<skill-name>/SKILL.md`.
17−- The tree is embedded at compile time via `//go:embed builtin/*` in
18− `internal/skills/embed.go`.
19−- `DiscoverBuiltin()` walks the embedded FS, parses each `SKILL.md`, and sets
20− paths with the `crush://skills/` prefix (e.g., `crush://skills/jq/SKILL.md`).
21−- The View tool resolves `crush://` paths from the embedded FS, not disk.
22−- User skills with the same name override builtins (last occurrence wins in
23− `Deduplicate()`).
24−
25−## Adding a New Builtin Skill
26−
27−1. Create `internal/skills/builtin/<skill-name>/SKILL.md` with YAML frontmatter
28− (`name`, `description`) and markdown instructions. The directory name must
29− match the `name` field.
30−2. No extra wiring needed — `//go:embed builtin/*` picks up new directories
31− automatically.
32−3. Add a test assertion in `TestDiscoverBuiltin` in
33− `internal/skills/skills_test.go` to verify discovery.
34−4. Build and test: `go build . && go test ./internal/skills/...`
35−
36−## Existing Builtin Skills
37−
38−| Skill | Directory | Description |
39−| -------------- | ----------------------- | ------------------------------------------ |
40−| `crush-config` | `builtin/crush-config/` | Crush configuration help |
41−| `crush-hooks` | `builtin/crush-hooks/` | Authoring, configuring and debugging hooks |
42−| `jq` | `builtin/jq/` | jq JSON processor usage guide |
.agents/skills/shell-builtins/SKILL.mddeleted−72
@@ -1,72 +0,0 @@
1−---
2−name: shell-builtins
3−description: Use when creating a new shell builtin command for Crush (internal/shell/), editing an existing one, or when the user needs to understand how commands are intercepted in Crush's embedded shell.
4−---
5−
6−# Shell Builtins
7−
8−Crush's shell (`internal/shell/`) uses `mvdan.cc/sh/v3` for POSIX shell
9−emulation. Commands can be intercepted before they reach the OS by adding
10−**builtins** — functions handled in-process.
11−
12−## How Builtins Work
13−
14−Builtins live in `builtinHandler()` in `internal/shell/run.go`. This is an
15−`interp.ExecHandlerFunc` middleware registered in `standardHandlers()`
16−**before** the block handler, so builtins run even for commands that would
17−otherwise be blocked. The same handler chain is shared by the stateful
18−`Shell` type and the stateless `Run` entrypoint used by the hook runner,
19−so builtins are available identically in the `bash` tool and in hooks.
20−
21−The handler is a switch on `args[0]`. Each case either handles the command
22−inline or delegates to a helper function.
23−
24−## Adding a New Builtin
25−
26−1. **Add the case** to the switch in `builtinHandler()` in `run.go`.
27−2. **Get I/O from the handler context**, not from `os.Stdin`/`os.Stdout`.
28− This ensures the builtin works with pipes and redirections:
29− ```go
30− case "mycommand":
31− hc := interp.HandlerCtx(ctx)
32− return handleMyCommand(ctx, args, hc.Stdin, hc.Stdout, hc.Stderr)
33− ```
34−3. **Implement the handler** in its own file (e.g.,
35− `internal/shell/mycommand.go`). The function signature must accept a
36− `context.Context` as the first parameter, plus args, stdin, stdout, and
37− stderr:
38− ```go
39− func handleMyCommand(ctx context.Context, args []string, stdin io.Reader, stdout, stderr io.Writer) error {
40− // args[0] is the command name ("mycommand"), args[1:] are arguments.
41− // Write output to stdout, errors to stderr.
42− // Return nil on success, or interp.ExitStatus(n) for non-zero exit codes.
43− }
44− ```
45−4. **Poll `ctx` in every unbounded loop.** Builtins that iterate over
46− input, emit values in a generator-style loop, or do any other work
47− that can exceed a few milliseconds MUST check `ctx.Err()` on each
48− iteration and return it verbatim when non-nil. Hook timeouts rely on
49− this: an unbounded builtin that never polls ctx cannot be interrupted
50− by a hook's `timeout_sec`, and the hook runner will have to abandon
51− the goroutine (see `internal/hooks/runner.go`). Returning `ctx.Err()`
52− (not `interp.ExitStatus(n)`) lets callers distinguish "command exited
53− non-zero" from "we ran out of time".
54− ```go
55− for _, item := range items {
56− if err := ctx.Err(); err != nil {
57− return err
58− }
59− // ... process item
60− }
61− ```
62−5. **Return values**: return `nil` for success, `interp.ExitStatus(n)` for
63− non-zero exit codes, or `ctx.Err()` on cancellation. Write error
64− messages to `stderr` before returning.
65−6. **No extra wiring needed** — `builtinHandler()` is already registered
66− in `standardHandlers()`.
67−
68−## Existing Builtins
69−
70−| Command | File | Description |
71−|---------|------|-------------|
72−| `jq` | `jq.go` | JSON processor using `github.com/itchyny/gojq` |
.envrcdeleted−1
@@ -1 +0,0 @@
1−use flake
.github/CODEOWNERSnew file+1
@@ -0,0 +1 @@
1+*.go @charmbracelet/everyone
.github/cla-signatures.json−1120
@@ -975,1126 +975,6 @@
975975 "created_at": "2025-12-19T12:14:08Z",
976976 "repoId": 987670088,
977977 "pullRequestNo": 1675
978− },
979− {
980− "name": "Mr777x-enf",
981− "id": 248610315,
982− "comment_id": 3682737876,
983− "created_at": "2025-12-22T16:07:47Z",
984− "repoId": 987670088,
985− "pullRequestNo": 1694
986− },
987− {
988− "name": "yuguorui",
989− "id": 6182414,
990− "comment_id": 3687495909,
991− "created_at": "2025-12-23T17:59:11Z",
992− "repoId": 987670088,
993− "pullRequestNo": 1709
994− },
995− {
996− "name": "aeroxy",
997− "id": 2761307,
998− "comment_id": 3693734613,
999− "created_at": "2025-12-27T06:01:58Z",
1000− "repoId": 987670088,
1001− "pullRequestNo": 1723
1002− },
1003− {
1004− "name": "nikolayk812",
1005− "id": 23297850,
1006− "comment_id": 3704102069,
1007− "created_at": "2026-01-01T21:00:07Z",
1008− "repoId": 987670088,
1009− "pullRequestNo": 1748
1010− },
1011− {
1012− "name": "mohaanymo",
1013− "id": 244024658,
1014− "comment_id": 3725028621,
1015− "created_at": "2026-01-08T18:01:11Z",
1016− "repoId": 987670088,
1017− "pullRequestNo": 1799
1018− },
1019− {
1020− "name": "zyriab",
1021− "id": 2111910,
1022− "comment_id": 3725966281,
1023− "created_at": "2026-01-08T21:44:05Z",
1024− "repoId": 987670088,
1025− "pullRequestNo": 1801
1026− },
1027− {
1028− "name": "aleksclark",
1029− "id": 607132,
1030− "comment_id": 3729687747,
1031− "created_at": "2026-01-09T16:28:21Z",
1032− "repoId": 987670088,
1033− "pullRequestNo": 1811
1034− },
1035− {
1036− "name": "jeis4wpi",
1037− "id": 42679190,
1038− "comment_id": 3735501265,
1039− "created_at": "2026-01-11T19:19:03Z",
1040− "repoId": 987670088,
1041− "pullRequestNo": 1827
1042− },
1043− {
1044− "name": "uppet",
1045− "id": 110209,
1046− "comment_id": 3738688581,
1047− "created_at": "2026-01-12T13:58:05Z",
1048− "repoId": 987670088,
1049− "pullRequestNo": 1830
1050− },
1051− {
1052− "name": "andreasdotorg",
1053− "id": 153248,
1054− "comment_id": 3740767910,
1055− "created_at": "2026-01-12T22:16:05Z",
1056− "repoId": 987670088,
1057− "pullRequestNo": 1841
1058− },
1059− {
1060− "name": "kuxoapp",
1061− "id": 254052994,
1062− "comment_id": 3747622477,
1063− "created_at": "2026-01-14T04:18:44Z",
1064− "repoId": 987670088,
1065− "pullRequestNo": 1864
1066− },
1067− {
1068− "name": "mhpenta",
1069− "id": 183146177,
1070− "comment_id": 3749703014,
1071− "created_at": "2026-01-14T14:02:04Z",
1072− "repoId": 987670088,
1073− "pullRequestNo": 1870
1074− },
1075− {
1076− "name": "huaiyuWangh",
1077− "id": 34158348,
1078− "comment_id": 3785195950,
1079− "created_at": "2026-01-22T15:58:33Z",
1080− "repoId": 987670088,
1081− "pullRequestNo": 1943
1082− },
1083− {
1084− "name": "akitaonrails",
1085− "id": 2840,
1086− "comment_id": 3786408984,
1087− "created_at": "2026-01-22T19:57:59Z",
1088− "repoId": 987670088,
1089− "pullRequestNo": 1945
1090− },
1091− {
1092− "name": "mcowger",
1093− "id": 1929548,
1094− "comment_id": 3787591535,
1095− "created_at": "2026-01-23T00:44:49Z",
1096− "repoId": 987670088,
1097− "pullRequestNo": 1950
1098− },
1099− {
1100− "name": "jerilynzheng",
1101− "id": 15837981,
1102− "comment_id": 3788071777,
1103− "created_at": "2026-01-23T04:00:52Z",
1104− "repoId": 987670088,
1105− "pullRequestNo": 1951
1106− },
1107− {
1108− "name": "AnyCPU",
1109− "id": 2059051,
1110− "comment_id": 3791901071,
1111− "created_at": "2026-01-23T19:14:55Z",
1112− "repoId": 987670088,
1113− "pullRequestNo": 1967
1114− },
1115− {
1116− "name": "billycao",
1117− "id": 543122,
1118− "comment_id": 3793624061,
1119− "created_at": "2026-01-24T03:06:50Z",
1120− "repoId": 987670088,
1121− "pullRequestNo": 1971
1122− },
1123− {
1124− "name": "gdamjan",
1125− "id": 81654,
1126− "comment_id": 3795660594,
1127− "created_at": "2026-01-24T22:42:46Z",
1128− "repoId": 987670088,
1129− "pullRequestNo": 1978
1130− },
1131− {
1132− "name": "oug-t",
1133− "id": 252025851,
1134− "comment_id": 3811704206,
1135− "created_at": "2026-01-28T14:42:29Z",
1136− "repoId": 987670088,
1137− "pullRequestNo": 2022
1138− },
1139− {
1140− "name": "liannnix",
1141− "id": 779758,
1142− "comment_id": 3815867093,
1143− "created_at": "2026-01-29T07:05:12Z",
1144− "repoId": 987670088,
1145− "pullRequestNo": 2043
1146− },
1147− {
1148− "name": "bittoby",
1149− "id": 218712309,
1150− "comment_id": 3824931235,
1151− "created_at": "2026-01-30T17:52:15Z",
1152− "repoId": 987670088,
1153− "pullRequestNo": 2065
1154− },
1155− {
1156− "name": "ijt",
1157− "id": 15530,
1158− "comment_id": 3832667774,
1159− "created_at": "2026-02-02T03:06:23Z",
1160− "repoId": 987670088,
1161− "pullRequestNo": 2080
1162− },
1163− {
1164− "name": "khalilgharbaoui",
1165− "id": 8024057,
1166− "comment_id": 3832796060,
1167− "created_at": "2026-02-02T04:04:04Z",
1168− "repoId": 987670088,
1169− "pullRequestNo": 2081
1170− },
1171− {
1172− "name": "acmacalister",
1173− "id": 1024755,
1174− "comment_id": 3837172797,
1175− "created_at": "2026-02-02T19:27:08Z",
1176− "repoId": 987670088,
1177− "pullRequestNo": 2095
1178− },
1179− {
1180− "name": "zhiquanchi",
1181− "id": 29973289,
1182− "comment_id": 3845838711,
1183− "created_at": "2026-02-04T07:39:06Z",
1184− "repoId": 987670088,
1185− "pullRequestNo": 2112
1186− },
1187− {
1188− "name": "inquam",
1189− "id": 1265038,
1190− "comment_id": 3849304908,
1191− "created_at": "2026-02-04T19:22:33Z",
1192− "repoId": 987670088,
1193− "pullRequestNo": 2124
1194− },
1195− {
1196− "name": "nickgrim",
1197− "id": 8376,
1198− "comment_id": 3852565144,
1199− "created_at": "2026-02-05T10:17:46Z",
1200− "repoId": 987670088,
1201− "pullRequestNo": 2131
1202− },
1203− {
1204− "name": "francescoalemanno",
1205− "id": 50984334,
1206− "comment_id": 3858464719,
1207− "created_at": "2026-02-06T07:16:50Z",
1208− "repoId": 987670088,
1209− "pullRequestNo": 2142
1210− },
1211− {
1212− "name": "biisal",
1213− "id": 153633053,
1214− "comment_id": 3866503536,
1215− "created_at": "2026-02-08T08:15:11Z",
1216− "repoId": 987670088,
1217− "pullRequestNo": 2164
1218− },
1219− {
1220− "name": "mishudark",
1221− "id": 211144,
1222− "comment_id": 3866939317,
1223− "created_at": "2026-02-08T10:27:09Z",
1224− "repoId": 987670088,
1225− "pullRequestNo": 2165
1226− },
1227− {
1228− "name": "portertech",
1229− "id": 149630,
1230− "comment_id": 3878650318,
1231− "created_at": "2026-02-10T15:39:14Z",
1232− "repoId": 987670088,
1233− "pullRequestNo": 2183
1234− },
1235− {
1236− "name": "wallacegibbon",
1237− "id": 22029486,
1238− "comment_id": 3890517245,
1239− "created_at": "2026-02-12T11:58:04Z",
1240− "repoId": 987670088,
1241− "pullRequestNo": 2203
1242− },
1243− {
1244− "name": "PHPCraftdream",
1245− "id": 14233546,
1246− "comment_id": 3893502046,
1247− "created_at": "2026-02-12T21:34:20Z",
1248− "repoId": 987670088,
1249− "pullRequestNo": 2212
1250− },
1251− {
1252− "name": "maxbrunet",
1253− "id": 32458727,
1254− "comment_id": 3905030983,
1255− "created_at": "2026-02-15T19:14:26Z",
1256− "repoId": 987670088,
1257− "pullRequestNo": 2229
1258− },
1259− {
1260− "name": "0xarcher",
1261− "id": 18182408,
1262− "comment_id": 3907297580,
1263− "created_at": "2026-02-16T09:16:57Z",
1264− "repoId": 987670088,
1265− "pullRequestNo": 2236
1266− },
1267− {
1268− "name": "julienrbrt",
1269− "id": 29894366,
1270− "comment_id": 3920039276,
1271− "created_at": "2026-02-18T10:37:53Z",
1272− "repoId": 987670088,
1273− "pullRequestNo": 2246
1274− },
1275− {
1276− "name": "erikstmartin",
1277− "id": 50041,
1278− "comment_id": 3937646631,
1279− "created_at": "2026-02-20T23:35:55Z",
1280− "repoId": 987670088,
1281− "pullRequestNo": 2274
1282− },
1283− {
1284− "name": "Jaylonnet",
1285− "id": 101283545,
1286− "comment_id": 3944717192,
1287− "created_at": "2026-02-23T13:12:50Z",
1288− "repoId": 987670088,
1289− "pullRequestNo": 2293
1290− },
1291− {
1292− "name": "mavaa",
1293− "id": 1224973,
1294− "comment_id": 3966463081,
1295− "created_at": "2026-02-26T12:56:51Z",
1296− "repoId": 987670088,
1297− "pullRequestNo": 2314
1298− },
1299− {
1300− "name": "aisk",
1301− "id": 699636,
1302− "comment_id": 3968065934,
1303− "created_at": "2026-02-26T17:23:44Z",
1304− "repoId": 987670088,
1305− "pullRequestNo": 2315
1306− },
1307− {
1308− "name": "detro",
1309− "id": 114508,
1310− "comment_id": 3976601253,
1311− "created_at": "2026-02-28T07:36:40Z",
1312− "repoId": 987670088,
1313− "pullRequestNo": 2326
1314− },
1315− {
1316− "name": "taoeffect",
1317− "id": 138706,
1318− "comment_id": 3979067985,
1319− "created_at": "2026-03-01T04:22:00Z",
1320− "repoId": 987670088,
1321− "pullRequestNo": 2333
1322− },
1323− {
1324− "name": "vmfu",
1325− "id": 80844805,
1326− "comment_id": 3980616480,
1327− "created_at": "2026-03-01T17:51:04Z",
1328− "repoId": 987670088,
1329− "pullRequestNo": 2337
1330− },
1331− {
1332− "name": "ZeitbyteRepo",
1333− "id": 187110998,
1334− "comment_id": 4025287397,
1335− "created_at": "2026-03-09T17:00:06Z",
1336− "repoId": 987670088,
1337− "pullRequestNo": 2390
1338− },
1339− {
1340− "name": "seroperson",
1341− "id": 3791221,
1342− "comment_id": 4047392328,
1343− "created_at": "2026-03-12T14:53:20Z",
1344− "repoId": 987670088,
1345− "pullRequestNo": 2401
1346− },
1347− {
1348− "name": "xulongwu4",
1349− "id": 16892446,
1350− "comment_id": 4062024320,
1351− "created_at": "2026-03-15T02:30:55Z",
1352− "repoId": 987670088,
1353− "pullRequestNo": 2410
1354− },
1355− {
1356− "name": "nghiant03",
1357− "id": 102637959,
1358− "comment_id": 4077213520,
1359− "created_at": "2026-03-17T18:41:50Z",
1360− "repoId": 987670088,
1361− "pullRequestNo": 2421
1362− },
1363− {
1364− "name": "whatnick",
1365− "id": 491396,
1366− "comment_id": 4102155868,
1367− "created_at": "2026-03-21T03:49:12Z",
1368− "repoId": 987670088,
1369− "pullRequestNo": 2449
1370− },
1371− {
1372− "name": "Alex-wuhu",
1373− "id": 57132813,
1374− "comment_id": 4106451941,
1375− "created_at": "2026-03-22T15:26:05Z",
1376− "repoId": 987670088,
1377− "pullRequestNo": 2454
1378− },
1379− {
1380− "name": "hongquan",
1381− "id": 314607,
1382− "comment_id": 4112122644,
1383− "created_at": "2026-03-23T16:51:09Z",
1384− "repoId": 987670088,
1385− "pullRequestNo": 2462
1386− },
1387− {
1388− "name": "faelis",
1389− "id": 91593249,
1390− "comment_id": 4113326932,
1391− "created_at": "2026-03-23T19:57:54Z",
1392− "repoId": 987670088,
1393− "pullRequestNo": 2465
1394− },
1395− {
1396− "name": "UnderLotus",
1397− "id": 84985759,
1398− "comment_id": 4118727062,
1399− "created_at": "2026-03-24T14:25:40Z",
1400− "repoId": 987670088,
1401− "pullRequestNo": 2475
1402− },
1403− {
1404− "name": "malikwirin",
1405− "id": 117918464,
1406− "comment_id": 4119816035,
1407− "created_at": "2026-03-24T16:51:44Z",
1408− "repoId": 987670088,
1409− "pullRequestNo": 2476
1410− },
1411− {
1412− "name": "fuleinist",
1413− "id": 1163738,
1414− "comment_id": 4133146531,
1415− "created_at": "2026-03-26T09:45:48Z",
1416− "repoId": 987670088,
1417− "pullRequestNo": 2492
1418− },
1419− {
1420− "name": "iceymoss",
1421− "id": 114280774,
1422− "comment_id": 4134659508,
1423− "created_at": "2026-03-26T13:13:25Z",
1424− "repoId": 987670088,
1425− "pullRequestNo": 2493
1426− },
1427− {
1428− "name": "srivilliamsai",
1429− "id": 191893106,
1430− "comment_id": 4144200398,
1431− "created_at": "2026-03-27T17:37:29Z",
1432− "repoId": 987670088,
1433− "pullRequestNo": 2511
1434− },
1435− {
1436− "name": "Dexterity104",
1437− "id": 173429049,
1438− "comment_id": 4153067126,
1439− "created_at": "2026-03-30T08:05:56Z",
1440− "repoId": 987670088,
1441− "pullRequestNo": 2525
1442− },
1443− {
1444− "name": "majiayu000",
1445− "id": 19658300,
1446− "comment_id": 4160074332,
1447− "created_at": "2026-03-31T05:44:38Z",
1448− "repoId": 987670088,
1449− "pullRequestNo": 2534
1450− },
1451− {
1452− "name": "afsuyadi",
1453− "id": 104284194,
1454− "comment_id": 4160431726,
1455− "created_at": "2026-03-31T07:10:20Z",
1456− "repoId": 987670088,
1457− "pullRequestNo": 2532
1458− },
1459− {
1460− "name": "owldev127",
1461− "id": 175169034,
1462− "comment_id": 4161299761,
1463− "created_at": "2026-03-31T09:44:52Z",
1464− "repoId": 987670088,
1465− "pullRequestNo": 2538
1466− },
1467− {
1468− "name": "MrRolie",
1469− "id": 80284543,
1470− "comment_id": 4168509138,
1471− "created_at": "2026-04-01T08:44:22Z",
1472− "repoId": 987670088,
1473− "pullRequestNo": 2544
1474− },
1475− {
1476− "name": "Kartik33",
1477− "id": 8198703,
1478− "comment_id": 4181386196,
1479− "created_at": "2026-04-03T02:02:31Z",
1480− "repoId": 987670088,
1481− "pullRequestNo": 2554
1482− },
1483− {
1484− "name": "talha7k",
1485− "id": 51679353,
1486− "comment_id": 4182808517,
1487− "created_at": "2026-04-03T09:56:29Z",
1488− "repoId": 987670088,
1489− "pullRequestNo": 2555
1490− },
1491− {
1492− "name": "avianion",
1493− "id": 37309215,
1494− "comment_id": 4186934644,
1495− "created_at": "2026-04-04T10:54:16Z",
1496− "repoId": 987670088,
1497− "pullRequestNo": 2557
1498− },
1499− {
1500− "name": "shahidshabbir-se",
1501− "id": 140221016,
1502− "comment_id": 4191066791,
1503− "created_at": "2026-04-06T08:11:08Z",
1504− "repoId": 987670088,
1505− "pullRequestNo": 2563
1506− },
1507− {
1508− "name": "smlx",
1509− "id": 861778,
1510− "comment_id": 4200126763,
1511− "created_at": "2026-04-07T15:22:15Z",
1512− "repoId": 987670088,
1513− "pullRequestNo": 2575
1514− },
1515− {
1516− "name": "gurnben",
1517− "id": 14117802,
1518− "comment_id": 4216941498,
1519− "created_at": "2026-04-09T19:22:39Z",
1520− "repoId": 987670088,
1521− "pullRequestNo": 2593
1522− },
1523− {
1524− "name": "dshumphr",
1525− "id": 9056521,
1526− "comment_id": 4229412078,
1527− "created_at": "2026-04-11T12:20:44Z",
1528− "repoId": 987670088,
1529− "pullRequestNo": 2601
1530− },
1531− {
1532− "name": "bensantora",
1533− "id": 274462811,
1534− "comment_id": 4229507403,
1535− "created_at": "2026-04-11T13:31:32Z",
1536− "repoId": 987670088,
1537− "pullRequestNo": 2602
1538− },
1539− {
1540− "name": "ahostbr",
1541− "id": 7461677,
1542− "comment_id": 4231674482,
1543− "created_at": "2026-04-12T14:14:41Z",
1544− "repoId": 987670088,
1545− "pullRequestNo": 2606
1546− },
1547− {
1548− "name": "KimBioInfoStudio",
1549− "id": 22641519,
1550− "comment_id": 4244355652,
1551− "created_at": "2026-04-14T13:43:55Z",
1552− "repoId": 987670088,
1553− "pullRequestNo": 2622
1554− },
1555− {
1556− "name": "taigong12",
1557− "id": 276221439,
1558− "comment_id": 4259818851,
1559− "created_at": "2026-04-16T11:50:25Z",
1560− "repoId": 987670088,
1561− "pullRequestNo": 2634
1562− },
1563− {
1564− "name": "pi128",
1565− "id": 77074839,
1566− "comment_id": 4271523344,
1567− "created_at": "2026-04-17T21:52:43Z",
1568− "repoId": 987670088,
1569− "pullRequestNo": 2643
1570− },
1571− {
1572− "name": "enrell",
1573− "id": 60587839,
1574− "comment_id": 4272340887,
1575− "created_at": "2026-04-18T01:47:04Z",
1576− "repoId": 987670088,
1577− "pullRequestNo": 2646
1578− },
1579− {
1580− "name": "gavmor",
1581− "id": 606529,
1582− "comment_id": 4285449550,
1583− "created_at": "2026-04-21T02:02:06Z",
1584− "repoId": 987670088,
1585− "pullRequestNo": 2612
1586− },
1587− {
1588− "name": "axeprpr",
1589− "id": 8937600,
1590− "comment_id": 4293455788,
1591− "created_at": "2026-04-22T04:15:18Z",
1592− "repoId": 987670088,
1593− "pullRequestNo": 2674
1594− },
1595− {
1596− "name": "iuga",
1597− "id": 1430179,
1598− "comment_id": 4298985284,
1599− "created_at": "2026-04-22T18:33:08Z",
1600− "repoId": 987670088,
1601− "pullRequestNo": 2681
1602− },
1603− {
1604− "name": "ne275",
1605− "id": 174412782,
1606− "comment_id": 4303280163,
1607− "created_at": "2026-04-23T09:29:30Z",
1608− "repoId": 987670088,
1609− "pullRequestNo": 2686
1610− },
1611− {
1612− "name": "flynn-eye",
1613− "id": 23251324,
1614− "comment_id": 4304378619,
1615− "created_at": "2026-04-23T12:33:57Z",
1616− "repoId": 987670088,
1617− "pullRequestNo": 2688
1618− },
1619− {
1620− "name": "georgeglarson",
1621− "id": 744063,
1622− "comment_id": 4341592963,
1623− "created_at": "2026-04-29T07:08:48Z",
1624− "repoId": 987670088,
1625− "pullRequestNo": 2749
1626− },
1627− {
1628− "name": "vorticalbox",
1629− "id": 10886065,
1630− "comment_id": 4344669740,
1631− "created_at": "2026-04-29T14:29:35Z",
1632− "repoId": 987670088,
1633− "pullRequestNo": 2751
1634− },
1635− {
1636− "name": "lloydzhou",
1637− "id": 1826685,
1638− "comment_id": 4346011097,
1639− "created_at": "2026-04-29T17:27:37Z",
1640− "repoId": 987670088,
1641− "pullRequestNo": 2752
1642− },
1643− {
1644− "name": "carlosgrillet",
1645− "id": 13719979,
1646− "comment_id": 4351020450,
1647− "created_at": "2026-04-30T08:48:52Z",
1648− "repoId": 987670088,
1649− "pullRequestNo": 2759
1650− },
1651− {
1652− "name": "SAY-5",
1653− "id": 240962040,
1654− "comment_id": 4357189565,
1655− "created_at": "2026-05-01T01:00:00Z",
1656− "repoId": 987670088,
1657− "pullRequestNo": 2691
1658− },
1659− {
1660− "name": "mkaaad",
1661− "id": 119158371,
1662− "comment_id": 4358493210,
1663− "created_at": "2026-05-01T08:25:06Z",
1664− "repoId": 987670088,
1665− "pullRequestNo": 2772
1666− },
1667− {
1668− "name": "pragneshbagary",
1669− "id": 41118746,
1670− "comment_id": 4359152162,
1671− "created_at": "2026-05-01T11:54:16Z",
1672− "repoId": 987670088,
1673− "pullRequestNo": 2773
1674− },
1675− {
1676− "name": "somjik-api",
1677− "id": 47082582,
1678− "comment_id": 4364741275,
1679− "created_at": "2026-05-02T21:17:55Z",
1680− "repoId": 987670088,
1681− "pullRequestNo": 2783
1682− },
1683− {
1684− "name": "ilgax",
1685− "id": 79969769,
1686− "comment_id": 4367211073,
1687− "created_at": "2026-05-03T21:25:46Z",
1688− "repoId": 987670088,
1689− "pullRequestNo": 2790
1690− },
1691− {
1692− "name": "ardevd",
1693− "id": 366855,
1694− "comment_id": 4377260996,
1695− "created_at": "2026-05-05T07:22:31Z",
1696− "repoId": 987670088,
1697− "pullRequestNo": 2801
1698− },
1699− {
1700− "name": "yeonuk-hwang",
1701− "id": 54208214,
1702− "comment_id": 4407666773,
1703− "created_at": "2026-05-08T15:33:03Z",
1704− "repoId": 987670088,
1705− "pullRequestNo": 2836
1706− },
1707− {
1708− "name": "sven2718",
1709− "id": 4741888,
1710− "comment_id": 4410098922,
1711− "created_at": "2026-05-08T21:47:18Z",
1712− "repoId": 987670088,
1713− "pullRequestNo": 2840
1714− },
1715− {
1716− "name": "acheong08",
1717− "id": 36258159,
1718− "comment_id": 4410600427,
1719− "created_at": "2026-05-08T23:37:33Z",
1720− "repoId": 987670088,
1721− "pullRequestNo": 2842
1722− },
1723− {
1724− "name": "smeinecke",
1725− "id": 7316652,
1726− "comment_id": 4411012852,
1727− "created_at": "2026-05-09T01:47:08Z",
1728− "repoId": 987670088,
1729− "pullRequestNo": 2844
1730− },
1731− {
1732− "name": "jan-xyz",
1733− "id": 5249233,
1734− "comment_id": 4432309551,
1735− "created_at": "2026-05-12T15:48:38Z",
1736− "repoId": 987670088,
1737− "pullRequestNo": 2886
1738− },
1739− {
1740− "name": "johnjansen",
1741− "id": 105938,
1742− "comment_id": 4434007350,
1743− "created_at": "2026-05-12T19:28:01Z",
1744− "repoId": 987670088,
1745− "pullRequestNo": 2887
1746− },
1747− {
1748− "name": "pablodz",
1749− "id": 28235457,
1750− "comment_id": 4435307961,
1751− "created_at": "2026-05-12T22:25:09Z",
1752− "repoId": 987670088,
1753− "pullRequestNo": 2892
1754− },
1755− {
1756− "name": "akhenakh",
1757− "id": 218430,
1758− "comment_id": 4446905473,
1759− "created_at": "2026-05-14T02:28:13Z",
1760− "repoId": 987670088,
1761− "pullRequestNo": 2912
1762− },
1763− {
1764− "name": "leonardoaraujosantos",
1765− "id": 898383,
1766− "comment_id": 3166308642,
1767− "created_at": "2025-08-08T01:40:17Z",
1768− "repoId": 987670088,
1769− "pullRequestNo": 644
1770− },
1771− {
1772− "name": "yookibooki",
1773− "id": 61198899,
1774− "comment_id": 4459665029,
1775− "created_at": "2026-05-15T12:16:26Z",
1776− "repoId": 987670088,
1777− "pullRequestNo": 2922
1778− },
1779− {
1780− "name": "CatMe0w",
1781− "id": 7774491,
1782− "comment_id": 4461676513,
1783− "created_at": "2026-05-15T16:58:04Z",
1784− "repoId": 987670088,
1785− "pullRequestNo": 2925
1786− },
1787− {
1788− "name": "Broderick-Westrope",
1789− "id": 55474351,
1790− "comment_id": 4469173328,
1791− "created_at": "2026-05-17T03:35:13Z",
1792− "repoId": 987670088,
1793− "pullRequestNo": 2937
1794− },
1795− {
1796− "name": "processtrader",
1797− "id": 232431073,
1798− "comment_id": 4480941961,
1799− "created_at": "2026-05-18T18:58:31Z",
1800− "repoId": 987670088,
1801− "pullRequestNo": 2950
1802− },
1803− {
1804− "name": "dcu",
1805− "id": 73729,
1806− "comment_id": 4484181213,
1807− "created_at": "2026-05-19T03:37:32Z",
1808− "repoId": 987670088,
1809− "pullRequestNo": 2954
1810− },
1811− {
1812− "name": "mei2jun1",
1813− "id": 285962643,
1814− "comment_id": 4495440988,
1815− "created_at": "2026-05-20T06:53:43Z",
1816− "repoId": 987670088,
1817− "pullRequestNo": 2964
1818− },
1819− {
1820− "name": "g2mt",
1821− "id": 166577174,
1822− "comment_id": 4513096006,
1823− "created_at": "2026-05-21T21:56:14Z",
1824− "repoId": 987670088,
1825− "pullRequestNo": 2979
1826− },
1827− {
1828− "name": "Ricardo-M-L",
1829− "id": 69202550,
1830− "comment_id": 4514494248,
1831− "created_at": "2026-05-22T02:37:08Z",
1832− "repoId": 987670088,
1833− "pullRequestNo": 2847
1834− },
1835− {
1836− "name": "Muttaqin86",
1837− "id": 69788027,
1838− "comment_id": 4520181780,
1839− "created_at": "2026-05-22T15:46:32Z",
1840− "repoId": 987670088,
1841− "pullRequestNo": 2984
1842− },
1843− {
1844− "name": "officialasishkumar",
1845− "id": 87874775,
1846− "comment_id": 4527874300,
1847− "created_at": "2026-05-24T08:44:14Z",
1848− "repoId": 987670088,
1849− "pullRequestNo": 2995
1850− },
1851− {
1852− "name": "yhyu13",
1853− "id": 19365678,
1854− "comment_id": 4528076561,
1855− "created_at": "2026-05-24T10:19:27Z",
1856− "repoId": 987670088,
1857− "pullRequestNo": 2996
1858− },
1859− {
1860− "name": "xulongzhe",
1861− "id": 10559793,
1862− "comment_id": 4569454380,
1863− "created_at": "2026-05-29T00:39:36Z",
1864− "repoId": 987670088,
1865− "pullRequestNo": 3036
1866− },
1867− {
1868− "name": "ardi1s",
1869− "id": 200318875,
1870− "comment_id": 4589172224,
1871− "created_at": "2026-06-01T02:48:53Z",
1872− "repoId": 987670088,
1873− "pullRequestNo": 3049
1874− },
1875− {
1876− "name": "cak3ninja",
1877− "id": 4338875,
1878− "comment_id": 4596570813,
1879− "created_at": "2026-06-01T21:14:16Z",
1880− "repoId": 987670088,
1881− "pullRequestNo": 3059
1882− },
1883− {
1884− "name": "GroovyCarrot",
1885− "id": 5589906,
1886− "comment_id": 4623915928,
1887− "created_at": "2026-06-04T16:01:30Z",
1888− "repoId": 987670088,
1889− "pullRequestNo": 3076
1890− },
1891− {
1892− "name": "CnsMaple",
1893− "id": 92523839,
1894− "comment_id": 4628808493,
1895− "created_at": "2026-06-05T06:24:00Z",
1896− "repoId": 987670088,
1897− "pullRequestNo": 3080
1898− },
1899− {
1900− "name": "yuseferi",
1901− "id": 1736832,
1902− "comment_id": 4548802420,
1903− "created_at": "2026-05-26T21:00:36Z",
1904− "repoId": 987670088,
1905− "pullRequestNo": 3019
1906− },
1907− {
1908− "name": "gmit3",
1909− "id": 26192089,
1910− "comment_id": 4651029942,
1911− "created_at": "2026-06-08T16:18:06Z",
1912− "repoId": 987670088,
1913− "pullRequestNo": 3096
1914− },
1915− {
1916− "name": "brianjlandau",
1917− "id": 3122,
1918− "comment_id": 4654867087,
1919− "created_at": "2026-06-09T00:37:02Z",
1920− "repoId": 987670088,
1921− "pullRequestNo": 3098
1922− },
1923− {
1924− "name": "kypkk",
1925− "id": 68454243,
1926− "comment_id": 4687904764,
1927− "created_at": "2026-06-12T05:55:06Z",
1928− "repoId": 987670088,
1929− "pullRequestNo": 3111
1930− },
1931− {
1932− "name": "warmjademe",
1933− "id": 257661268,
1934− "comment_id": 4720070206,
1935− "created_at": "2026-06-16T14:48:33Z",
1936− "repoId": 987670088,
1937− "pullRequestNo": 3131
1938− },
1939− {
1940− "name": "warmjademe",
1941− "id": 257661268,
1942− "comment_id": 4720177856,
1943− "created_at": "2026-06-16T14:58:33Z",
1944− "repoId": 987670088,
1945− "pullRequestNo": 3131
1946− },
1947− {
1948− "name": "jialudev",
1949− "id": 39230796,
1950− "comment_id": 4725593255,
1951− "created_at": "2026-06-17T03:26:00Z",
1952− "repoId": 987670088,
1953− "pullRequestNo": 3137
1954− },
1955− {
1956− "name": "knight110001",
1957− "id": 21118983,
1958− "comment_id": 4741392218,
1959− "created_at": "2026-06-18T11:16:02Z",
1960− "repoId": 987670088,
1961− "pullRequestNo": 3140
1962− },
1963− {
1964− "name": "ken-jo",
1965− "id": 42824840,
1966− "comment_id": 4755333253,
1967− "created_at": "2026-06-19T22:56:55Z",
1968− "repoId": 987670088,
1969− "pullRequestNo": 3158
1970− },
1971− {
1972− "name": "xorangekiller",
1973− "id": 5561926,
1974− "comment_id": 4758885426,
1975− "created_at": "2026-06-20T16:00:01Z",
1976− "repoId": 987670088,
1977− "pullRequestNo": 3163
1978− },
1979− {
1980− "name": "sithglan",
1981− "id": 1595655,
1982− "comment_id": 4761251782,
1983− "created_at": "2026-06-21T07:28:19Z",
1984− "repoId": 987670088,
1985− "pullRequestNo": 3168
1986− },
1987− {
1988− "name": "macro-ss",
1989− "id": 59944291,
1990− "comment_id": 4729268228,
1991− "created_at": "2026-06-17T11:09:03Z",
1992− "repoId": 987670088,
1993− "pullRequestNo": 3140
1994− },
1995− {
1996− "name": "andrinoff",
1997− "id": 175145001,
1998− "comment_id": 4772633817,
1999− "created_at": "2026-06-22T20:13:54Z",
2000− "repoId": 987670088,
2001− "pullRequestNo": 3184
2002− },
2003− {
2004− "name": "calyptobai",
2005− "id": 111788964,
2006− "comment_id": 4774213287,
2007− "created_at": "2026-06-22T23:56:09Z",
2008− "repoId": 987670088,
2009− "pullRequestNo": 3189
2010− },
2011− {
2012− "name": "truffle-dev",
2013− "id": 260125384,
2014− "comment_id": 4783906418,
2015− "created_at": "2026-06-23T22:07:28Z",
2016− "repoId": 987670088,
2017− "pullRequestNo": 3195
2018− },
2019− {
2020− "name": "chardoncs",
2021− "id": 44740171,
2022− "comment_id": 4786221902,
2023− "created_at": "2026-06-24T05:36:39Z",
2024− "repoId": 987670088,
2025− "pullRequestNo": 3197
2026− },
2027− {
2028− "name": "notno",
2029− "id": 3149184,
2030− "comment_id": 4793889316,
2031− "created_at": "2026-06-24T21:37:51Z",
2032− "repoId": 987670088,
2033− "pullRequestNo": 3202
2034− },
2035− {
2036− "name": "vismaytiwari",
2037− "id": 89745751,
2038− "comment_id": 4797847556,
2039− "created_at": "2026-06-25T09:38:55Z",
2040− "repoId": 987670088,
2041− "pullRequestNo": 3205
2042− },
2043− {
2044− "name": "feizhuzheng",
2045− "id": 130743669,
2046− "comment_id": 4809880810,
2047− "created_at": "2026-06-26T13:09:43Z",
2048− "repoId": 987670088,
2049− "pullRequestNo": 3211
2050− },
2051− {
2052− "name": "syf2211",
2053− "id": 132282304,
2054− "comment_id": 4817246953,
2055− "created_at": "2026-06-27T11:44:54Z",
2056− "repoId": 987670088,
2057− "pullRequestNo": 3221
2058− },
2059− {
2060− "name": "EduardF1",
2061− "id": 50618110,
2062− "comment_id": 4818319813,
2063− "created_at": "2026-06-27T14:15:50Z",
2064− "repoId": 987670088,
2065− "pullRequestNo": 3133
2066− },
2067− {
2068− "name": "sablea",
2069− "id": 52388727,
2070− "comment_id": 4851979164,
2071− "created_at": "2026-07-01T08:13:03Z",
2072− "repoId": 987670088,
2073− "pullRequestNo": 3235
2074− },
2075− {
2076− "name": "Osamaali313",
2077− "id": 86572800,
2078− "comment_id": 4870561813,
2079− "created_at": "2026-07-02T21:19:15Z",
2080− "repoId": 987670088,
2081− "pullRequestNo": 3244
2082− },
2083− {
2084− "name": "lockp111",
2085− "id": 28383475,
2086− "comment_id": 4878248994,
2087− "created_at": "2026-07-03T17:12:26Z",
2088− "repoId": 987670088,
2089− "pullRequestNo": 3247
2090− },
2091− {
2092− "name": "TheRAWagent",
2093− "id": 77039476,
2094− "comment_id": 4879276761,
2095− "created_at": "2026-07-03T20:52:00Z",
2096− "repoId": 987670088,
2097− "pullRequestNo": 3251
2098978 }
2099979 ]
2100980}
.github/dependabot.yml−1
@@ -24,7 +24,6 @@ updates:
2424 - dependency-name: github.com/charmbracelet/lipgloss/v2
2525 versions:
2626 - v2.0.0-beta1
27− - dependency-name: mvdan.cc/sh/moreinterp
2827
2928 - package-ecosystem: "github-actions"
3029 directory: "/"
.github/labeler.yml−12
@@ -3,10 +3,6 @@
33
44"area: ci":
55 - "/^ci: /i"
6−"area: crush run":
7− - "/crush run/i"
8− - "/headless/i"
9− - "/non-interactive/i"
106"area: diff":
117 - "/diff/i"
128"area: docs":
@@ -45,8 +41,6 @@
4541 - "/(panic|crash|segfault)/i"
4642"provider: anthropic claude":
4743 - "/(anthropic|claude)/i"
48−"provider: avian":
49− - "/avian/i"
5044"provider: aws bedrock":
5145 - "/(aws|bedrock)/i"
5246"provider: azure":
@@ -57,12 +51,8 @@
5751 - "/gemini/i"
5852"provider: google vertex":
5953 - "/vertex/i"
60−"provider: hyper":
61− - "/hyper/i"
6254"provider: kimi":
6355 - "/kimi/i"
64−"provider: minimax":
65− - "/minimax/i"
6656"provider: ollama":
6757 - "/llama/i"
6858"provider: openai chatgpt":
@@ -71,8 +61,6 @@
7161 - "/openrouter/i"
7262"provider: qwen":
7363 - "/qwen/i"
74−"provider: vercel":
75− - "/vercel/i"
7664"provider: xai grok":
7765 - "/(xai|x\\.ai|grok)/i"
7866"security":
.github/workflows/build.yml+7−26
@@ -1,30 +1,11 @@
11name: build
2−on:
3− push:
4− branches: [main]
5− pull_request:
6−
7−permissions:
8− contents: read
9−
10−concurrency:
11− group: build-${{ github.event.pull_request.number || github.ref }}
12− cancel-in-progress: true
2+on: [push, pull_request]
133
144jobs:
155 build:
16− strategy:
17− matrix:
18− os: [ubuntu-latest, macos-latest, windows-latest]
19− runs-on: ${{ matrix.os }}
20− steps:
21− - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
22− with:
23− persist-credentials: false
24− - uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
25− with:
26− go-version-file: go.mod
27− - run: go mod tidy
28− - run: git diff --exit-code
29− - run: go build -race ./...
30− - run: go test -race -failfast ./...
6+ uses: charmbracelet/meta/.github/workflows/build.yml@main
7+ with:
8+ go-version: ""
9+ go-version-file: ./go.mod
10+ secrets:
11+ gh_pat: "${{ secrets.PERSONAL_ACCESS_TOKEN }}"
.github/workflows/cla.yml+2−2
@@ -22,14 +22,14 @@ jobs:
2222 github.event.comment.body == 'recheck' ||
2323 github.event.comment.body == 'I have read the Contributor License Agreement (CLA) and hereby sign the CLA.' ||
2424 github.event_name == 'pull_request_target'
25− uses: contributor-assistant/github-action@58daaf842ac3e26d08c2bdf26770d6e9c5b965a9
25+ uses: contributor-assistant/github-action@ca4a40a7d1004f18d9960b404b97e5f30a505a08 # v2.6.1
2626 env:
2727 GITHUB_TOKEN: ${{ secrets.PERSONAL_ACCESS_TOKEN }}
2828 with:
2929 path-to-signatures: ".github/cla-signatures.json"
3030 path-to-document: "https://github.com/charmbracelet/crush/blob/main/CLA.md"
3131 branch: "main"
32− allowlist: charmcli,charmcrush,dependabot[bot],Copilot
32+ allowlist: charmcli,charmcrush,dependabot[bot]
3333 custom-pr-sign-comment: "I have read the Contributor License Agreement (CLA) and hereby sign the CLA."
3434 custom-notsigned-prcomment: "Thank you for your submission. We really appreciate it! Like many open-source projects, we ask that you sign our [Contributor License Agreement](https://github.com/charmbracelet/crush/blob/main/CLA.md) before we can accept your contribution. You can sign the CLA by just posting a Pull Request comment same as the below format."
3535 lock-pullrequest-aftermerge: false
.github/workflows/labeler.yml+1−1
@@ -14,7 +14,6 @@ on:
1414
1515permissions:
1616 issues: write
17− pull-requests: write
1817 contents: read
1918
2019jobs:
@@ -27,4 +26,5 @@ jobs:
2726 enable-versioned-regex: 0
2827 include-title: 1
2928 include-body: 0
29+ repo-token: ${{ secrets.PERSONAL_ACCESS_TOKEN }}
3030 issue-number: ${{ github.event.inputs.issue-number || github.event.issue.number || github.event.pull_request.number }}
.github/workflows/lint.yml+1−2
@@ -1,7 +1,6 @@
11name: lint
22on:
33 push:
4− branches: [main]
54 pull_request:
65
76jobs:
@@ -9,5 +8,5 @@ jobs:
98 uses: charmbracelet/meta/.github/workflows/lint.yml@main
109 with:
1110 golangci_path: .golangci.yml
12− golangci_version: v2.11
11+ golangci_version: v2.4
1312 timeout: 10m
.github/workflows/nightly.yml+1−1
@@ -11,7 +11,7 @@ jobs:
1111 outputs:
1212 should_run: ${{ steps.check.outputs.should_run }}
1313 steps:
14− - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
14+ - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
1515 with:
1616 fetch-depth: 1
1717 - id: check
.github/workflows/release.yml+3−1
@@ -15,7 +15,7 @@ jobs:
1515 goreleaser:
1616 uses: charmbracelet/meta/.github/workflows/goreleaser.yml@main
1717 with:
18− go_version: "1.26"
18+ go_version: "1.25"
1919 macos_sign_entitlements: "./.github/entitlements.plist"
2020 secrets:
2121 docker_username: ${{ secrets.DOCKERHUB_USERNAME }}
@@ -25,6 +25,8 @@ jobs:
2525 fury_token: ${{ secrets.FURY_TOKEN }}
2626 nfpm_gpg_key: ${{ secrets.NFPM_GPG_KEY }}
2727 nfpm_passphrase: ${{ secrets.NFPM_PASSPHRASE }}
28+ npm_token: ${{ secrets.NPM_TOKEN }}
29+ snapcraft_token: ${{ secrets.SNAPCRAFT_TOKEN }}
2830 aur_key: ${{ secrets.AUR_KEY }}
2931 macos_sign_p12: ${{ secrets.MACOS_SIGN_P12 }}
3032 macos_sign_password: ${{ secrets.MACOS_SIGN_PASSWORD }}
.github/workflows/schema-update.yml+3−4
@@ -6,21 +6,20 @@ on:
66 paths:
77 - "internal/config/**"
88 - "internal/agent/hyper/**"
9− workflow_dispatch:
109
1110jobs:
1211 update-schema:
1312 runs-on: ubuntu-latest
1413 steps:
15− - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
14+ - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
1615 with:
1716 token: ${{ secrets.PERSONAL_ACCESS_TOKEN }}
18− - uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
17+ - uses: actions/setup-go@4dc6199c7b1a012772edbd06daecab0f50c9053c # v6.1.0
1918 with:
2019 go-version-file: go.mod
2120 - run: go run . schema > ./schema.json
2221 - run: go generate ./internal/agent/hyper/...
23− - uses: stefanzweifel/git-auto-commit-action@4a55954c782fc1ea30b9056cd3e7a2b40ca8887d # v5
22+ - uses: stefanzweifel/git-auto-commit-action@04702edda442b2e678b25b537cec683a1493fcb9 # v5
2423 with:
2524 commit_message: "chore: auto-update files"
2625 branch: main
.github/workflows/security.ymldeleted−92
@@ -1,92 +0,0 @@
1−name: "security"
2−
3−on:
4− pull_request:
5− push:
6− branches: [main]
7− schedule:
8− - cron: "0 2 * * *"
9−
10−permissions:
11− contents: read
12−
13−concurrency:
14− group: security-${{ github.event.pull_request.number || github.ref }}
15− cancel-in-progress: true
16−
17−jobs:
18− codeql:
19− runs-on: ubuntu-latest
20− strategy:
21− fail-fast: false
22− matrix:
23− language: ["go", "actions"]
24− permissions:
25− actions: read
26− contents: read
27− pull-requests: read
28− security-events: write
29− steps:
30− - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
31− with:
32− persist-credentials: false
33− - uses: github/codeql-action/init@54f647b7e1bb85c95cddabcd46b0c578ec92bc1a # v4.36.3
34− with:
35− languages: ${{ matrix.language }}
36− - uses: github/codeql-action/autobuild@54f647b7e1bb85c95cddabcd46b0c578ec92bc1a # v4.36.3
37− - uses: github/codeql-action/analyze@54f647b7e1bb85c95cddabcd46b0c578ec92bc1a # v4.36.3
38−
39− grype:
40− runs-on: ubuntu-latest
41− permissions:
42− security-events: write
43− actions: read
44− contents: read
45− steps:
46− - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
47− with:
48− persist-credentials: false
49− - uses: anchore/scan-action@e1165082ffb1fe366ebaf02d8526e7c4989ea9d2 # v7.4.0
50− id: scan
51− with:
52− path: "."
53− fail-build: true
54− severity-cutoff: critical
55− - uses: github/codeql-action/upload-sarif@54f647b7e1bb85c95cddabcd46b0c578ec92bc1a # v4.36.3
56− with:
57− sarif_file: ${{ steps.scan.outputs.sarif }}
58−
59− govulncheck:
60− runs-on: ubuntu-latest
61− permissions:
62− security-events: write
63− contents: read
64− steps:
65− - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
66− with:
67− persist-credentials: false
68− - uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
69− with:
70− go-version: stable
71− - name: Install govulncheck
72− run: go install golang.org/x/vuln/cmd/govulncheck@latest
73− - name: Run govulncheck
74− run: |
75− govulncheck -C . -format sarif ./... > results.sarif
76− - uses: github/codeql-action/upload-sarif@54f647b7e1bb85c95cddabcd46b0c578ec92bc1a # v4.36.3
77− with:
78− sarif_file: results.sarif
79−
80− dependency-review:
81− runs-on: ubuntu-latest
82− if: github.event_name == 'pull_request'
83− permissions:
84− contents: read
85− steps:
86− - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
87− with:
88− persist-credentials: false
89− - uses: actions/dependency-review-action@a1d282b36b6f3519aa1f3fc636f609c47dddb294 # v5.0.0
90− with:
91− fail-on-severity: critical
92− allow-licenses: BSD-2-Clause, BSD-3-Clause, MIT, MIT-0, Apache-2.0, MPL-2.0, ISC, LicenseRef-scancode-google-patent-license-golang, Unlicense
.github/workflows/snapshot.ymldeleted−34
@@ -1,34 +0,0 @@
1−name: snapshot
2−
3−on:
4− push:
5− branches:
6− - main
7−
8−permissions:
9− contents: read
10−
11−concurrency:
12− group: snapshot-${{ github.ref }}
13− cancel-in-progress: true
14−
15−jobs:
16− snapshot:
17− runs-on:
18− # Use our own large runners with more CPU and RAM for faster builds
19− group: releasers
20− steps:
21− - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
22− with:
23− fetch-depth: 0
24− persist-credentials: false
25− - uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
26− with:
27− go-version-file: go.mod
28− - uses: goreleaser/goreleaser-action@f06c13b6b1a9625abc9e6e439d9c05a8f2190e94 # v7.2.3
29− with:
30− version: "nightly"
31− distribution: goreleaser-pro
32− args: build --snapshot --clean
33− env:
34− GORELEASER_KEY: ${{ secrets.GORELEASER_KEY }}
.gitignore+2−6
@@ -42,16 +42,12 @@ Thumbs.db
4242.env
4343.env.local
4444
45−# Nix/direnv
46−.direnv/
47−/result
48−
4945**/.crush/**
5046
5147/crush
5248/tmp/
5349
5450manpages/
55−completions/crush.*sh
51+completions/
52+!internal/tui/components/completions/
5653.prettierignore
57−.task
.golangci.yml+4−16
@@ -2,7 +2,6 @@ version: "2"
22linters:
33 enable:
44 - bodyclose
5− - errcheck
65 # - exhaustive
76 # - goconst
87 # - godot
@@ -10,7 +9,6 @@ linters:
109 # - gomoddirectives
1110 - goprintffuncname
1211 # - gosec
13− - ineffassign
1412 - misspell
1513 # - nakedret
1614 # - nestif
@@ -25,30 +23,20 @@ linters:
2523 - tparallel
2624 # - unconvert
2725 # - unparam
28− - unused
2926 - whitespace
3027 # - wrapcheck
28+ disable:
29+ - errcheck
30+ - ineffassign
31+ - unused
3132 exclusions:
3233 generated: lax
3334 presets:
3435 - common-false-positives
35− # Ignores the idiomatic-to-drop error family (*Close, *Flush,
36− # Fprint*, os.Remove/RemoveAll, os.Setenv, stdout/stderr writes) so
37− # errcheck only flags genuinely meaningful dropped errors.
38− - std-error-handling
3936 rules:
40− # Dropped errors in tests (setup writes, httptest encoders) are
41− # low-signal — test failures surface them anyway.
42− - path: _test\.go
43− linters:
44− - errcheck
4537 - text: '(slog|log)\.\w+'
4638 linters:
4739 - noctx
48− - path: internal/shell/run.go
49− text: "SA1019.*interp.ExecHandler"
50− linters:
51− - staticcheck
5240issues:
5341 max-issues-per-linter: 0
5442 max-same-issues: 0
.goreleaser.yml+2−12
@@ -116,7 +116,7 @@ aur_sources:
116116 export CGO_CXXFLAGS="${CXXFLAGS}"
117117 export CGO_LDFLAGS="${LDFLAGS}"
118118 export GOFLAGS="-buildmode=pie -trimpath -mod=readonly -modcacherw"
119− go build -ldflags="-w -s -buildid='' -linkmode=external -X github.com/charmbracelet/crush/internal/version.Version=v${pkgver}" .
119+ go build -ldflags="-w -s -buildid='' -linkmode=external -X main.version=v${pkgver}" .
120120 ./crush completion bash >./completions/crush.bash
121121 ./crush completion zsh >./completions/crush.zsh
122122 ./crush completion fish >./completions/crush.fish
@@ -152,14 +152,7 @@ aurs:
152152 conflicts:
153153 - crush
154154 package: |-
155− case "$CARCH" in
156− aarch64)
157− cd "${srcdir}/crush_${pkgver}_Linux_arm64"
158− ;;
159− *)
160− cd "${srcdir}/crush_${pkgver}_Linux_${CARCH}"
161− ;;
162− esac
155+ cd "${srcdir}/crush_${pkgver}_Linux_${CARCH}"
163156 # bin
164157 install -Dm755 "./crush" "${pkgdir}/usr/bin/crush"
165158 # license
@@ -268,7 +261,6 @@ nix:
268261 name: "Charm"
269262 email: "charmcli@users.noreply.github.com"
270263 license: fsl11Mit
271− formatter: nixfmt
272264 skip_upload: "{{ with .Prerelease }}true{{ end }}"
273265 extra_install: |-
274266 installManPage ./manpages/crush.1.gz
@@ -297,8 +289,6 @@ winget:
297289 owner: microsoft
298290 name: winget-pkgs
299291 branch: master
300− body: |
301− /cc @andreynering
302292
303293changelog:
304294 sort: asc
AGENTS.mddeleted−223
@@ -1,223 +0,0 @@
1−# Crush Development Guide
2−
3−## Project Overview
4−
5−Crush is a terminal-based AI coding assistant built in Go by
6−[Charm](https://charm.land). It connects to LLMs and gives them tools to read,
7−write, and execute code. It supports multiple providers (Anthropic, OpenAI,
8−Gemini, Bedrock, Copilot, Hyper, MiniMax, Vercel, and more), integrates with
9−LSPs for code intelligence, and supports extensibility via MCP servers and
10−agent skills.
11−
12−The module path is `github.com/charmbracelet/crush`.
13−
14−## Architecture
15−
16−```
17−main.go CLI entry point (cobra via internal/cmd)
18−internal/
19− app/app.go Top-level wiring: DB, config, agents, LSP, MCP, events
20− cmd/ CLI commands (root, run, login, models, stats, sessions)
21− config/
22− config.go Config struct, context file paths, agent definitions
23− load.go crush.json loading and validation
24− provider.go Provider configuration and model resolution
25− agent/
26− agent.go SessionAgent: runs LLM conversations per session
27− coordinator.go Coordinator: manages named agents ("coder", "task")
28− hooked_tool.go Decorator that runs PreToolUse hooks before tool execution
29− prompts.go Loads Go-template system prompts
30− templates/ System prompt templates (coder.md.tpl, task.md.tpl, etc.)
31− tools/ All built-in tools (bash, edit, view, grep, glob, etc.)
32− mcp/ MCP client integration
33− hooks/ Hook engine: runs user shell commands on hook events
34− hooks.go Decision types, aggregation logic, event constants
35− runner.go Parallel hook execution, timeout, dedup
36− input.go Stdin payload builder, env vars, stdout parsing (Crush + Claude Code compat)
37− session/session.go Session CRUD backed by SQLite
38− message/ Message model and content types
39− db/ SQLite via sqlc, with migrations
40− sql/ Raw SQL queries (consumed by sqlc)
41− migrations/ Schema migrations
42− lsp/ LSP client manager, auto-discovery, on-demand startup
43− ui/ Bubble Tea v2 TUI (see internal/ui/AGENTS.md)
44− permission/ Tool permission checking and allow-lists
45− skills/ Skill file discovery and loading
46− shell/ Bash command execution with background job support
47− event/ Telemetry (PostHog)
48− pubsub/ Internal pub/sub for cross-component messaging
49− filetracker/ Tracks files touched per session
50− history/ Prompt history
51−```
52−
53−### Key Dependency Roles
54−
55−- **`charm.land/fantasy`**: LLM provider abstraction layer. Handles protocol
56− differences between Anthropic, OpenAI, Gemini, etc. Used in `internal/app`
57− and `internal/agent`.
58−- **`charm.land/bubbletea/v2`**: TUI framework powering the interactive UI.
59−- **`charm.land/lipgloss/v2`**: Terminal styling.
60−- **`charm.land/glamour/v2`**: Markdown rendering in the terminal.
61−- **`charm.land/catwalk`**: Snapshot/golden-file testing for TUI components.
62−- **`sqlc`**: Generates Go code from SQL queries in `internal/db/sql/`.
63−
64−### Key Patterns
65−
66−- **Config is a Service**: accessed via `config.Service`, not global state.
67−- **Tools are self-documenting**: each tool has a `.go` implementation and a
68− `.md` description file in `internal/agent/tools/`.
69−- **System prompts are Go templates**: `internal/agent/templates/*.md.tpl`
70− with runtime data injected.
71−- **Context files**: Crush reads AGENTS.md, CRUSH.md, CLAUDE.md, GEMINI.md
72− (and `.local` variants) from the working directory for project-specific
73− instructions.
74−- **Persistence**: SQLite + sqlc. All queries live in `internal/db/sql/`,
75− generated code in `internal/db/`. Migrations in `internal/db/migrations/`.
76−- **Pub/sub**: `internal/pubsub` for decoupled communication between agent,
77− UI, and services.
78−- **Hooks**: User-defined shell commands in `crush.json` that fire before
79− tool execution. The engine (`internal/hooks/`) is independent of fantasy
80− and agent — it takes inputs, runs commands, returns decisions. The
81− `hookedTool` decorator in `internal/agent/hooked_tool.go` wraps tools at
82− the coordinator level. Hooks run before permission checks. See
83− `HOOKS.md` for the user-facing protocol.
84−- **CGO disabled**: builds with `CGO_ENABLED=0` and
85− `GOEXPERIMENT=greenteagc`.
86−
87−## Build/Test/Lint Commands
88−
89−- **Build**: `go build .` or `go run .`
90−- **Test**: `task test` or `go test ./...` (run single test:
91− `go test ./internal/llm/prompt -run TestGetContextFromPaths`)
92−- **Update Golden Files**: `go test ./... -update` (regenerates `.golden`
93− files when test output changes)
94− - Update specific package:
95− `go test ./internal/tui/components/core -update` (in this case,
96− we're updating "core")
97−- **Lint**: `task lint:fix`
98−- **Format**: `task fmt` (`gofumpt -w .`)
99−- **Modernize**: `task modernize` (runs `modernize` which makes code
100− simplifications)
101−- **Dev**: `task dev` (runs with profiling enabled)
102−
103−## Code Style Guidelines
104−
105−- **Imports**: Use `goimports` formatting, group stdlib, external, internal
106− packages.
107−- **Formatting**: Use gofumpt (stricter than gofmt), enabled in
108− golangci-lint.
109−- **Naming**: Standard Go conventions — PascalCase for exported, camelCase
110− for unexported.
111−- **Types**: Prefer explicit types, use type aliases for clarity (e.g.,
112− `type AgentName string`).
113−- **Error handling**: Return errors explicitly, use `fmt.Errorf` for
114− wrapping.
115−- **Context**: Always pass `context.Context` as first parameter for
116− operations.
117−- **Interfaces**: Define interfaces in consuming packages, keep them small
118− and focused.
119−- **Structs**: Use struct embedding for composition, group related fields.
120−- **Constants**: Use typed constants with iota for enums, group in const
121− blocks.
122−- **Testing**: Use testify's `require` package, parallel tests with
123− `t.Parallel()`, `t.SetEnv()` to set environment variables. Always use
124− `t.Tempdir()` when in need of a temporary directory. This directory does
125− not need to be removed.
126−- **JSON tags**: Use snake_case for JSON field names.
127−- **File permissions**: Use octal notation (0o755, 0o644) for file
128− permissions.
129−- **Log messages**: Log messages must start with a capital letter (e.g.,
130− "Failed to save session" not "failed to save session").
131− - This is enforced by `task lint:log` which runs as part of `task lint`.
132−- **Comments**: End comments in periods unless comments are at the end of the
133− line.
134−
135−## Testing with Mock Providers
136−
137−When writing tests that involve provider configurations, use the mock
138−providers to avoid API calls:
139−
140−```go
141−func TestYourFunction(t *testing.T) {
142− // Enable mock providers for testing
143− originalUseMock := config.UseMockProviders
144− config.UseMockProviders = true
145− defer func() {
146− config.UseMockProviders = originalUseMock
147− config.ResetProviders()
148− }()
149−
150− // Reset providers to ensure fresh mock data
151− config.ResetProviders()
152−
153− // Your test code here - providers will now return mock data
154− providers := config.Providers()
155− // ... test logic
156−}
157−```
158−
159−## Formatting
160−
161−- ALWAYS format any Go code you write.
162− - First, try `gofumpt -w .`.
163− - If `gofumpt` is not available, use `goimports`.
164− - If `goimports` is not available, use `gofmt`.
165− - You can also use `task fmt` to run `gofumpt -w .` on the entire project,
166− as long as `gofumpt` is on the `PATH`.
167−
168−## Comments
169−
170−- Comments that live on their own lines should start with capital letters and
171− end with periods. Wrap comments at 78 columns.
172−
173−## Committing
174−
175−- ALWAYS use semantic commits (`fix:`, `feat:`, `chore:`, `refactor:`,
176− `docs:`, `sec:`, etc).
177−- Try to keep commits to one line, not including your attribution. Only use
178− multi-line commits when additional context is truly necessary.
179−
180−## Working on the TUI (UI)
181−
182−Anytime you need to work on the TUI, read `internal/ui/AGENTS.md` before
183−starting work.
184−
185−## Styling System
186−
187−The styling system lives in `internal/ui/styles/` and is organized into
188−three layers:
189−
190−- **`quickstyle.go`**: The stable base theme builder. `quickStyle(opts)`
191− constructs a `Styles` struct from `quickStyleOpts` — a palette of
192− design tokens (primary, secondary, fgBase, bgBase, success, error, etc.).
193− `quickStyle` must be fully token-driven: never hardcode specific
194− `charmtone.*` colors here (except Chroma syntax highlighting, which is
195− pending tokenization). This lets any theme reuse the base without
196− inheriting Charmtone-specific colors.
197−- **`themes.go`**: Defines concrete themes. Each theme function (e.g.
198− `CharmtonePantera`) calls `quickStyle` with its palette, then applies
199− theme-specific overrides as needed.
200−- **`styles.go`**: Defines the `Styles` struct and its documentation —
201− the shape of what `quickStyle` produces.
202−
203−**Adding theme-specific overrides**: When a style genuinely needs a
204−color that doesn't fit the token model (e.g. the bang prompt uses
205−Salt/Hazy/Larple), keep `quickStyle` on the closest semantic token and
206−override only the differing colors in the theme function:
207−
208−```go
209−func CharmtonePantera() Styles {
210− s := quickStyle(quickStyleOpts{ /* palette */ })
211−
212− // Override only the colors that differ from the token defaults.
213− s.Editor.PromptBangIconFocused = s.Editor.PromptBangIconFocused.
214− Foreground(charmtone.Salt).
215− Background(charmtone.Hazy)
216−
217− return s
218−}
219−```
220−
221−**Adding a new theme**: Add a function in `themes.go` that returns the
222−result of `quickStyle` with a `quickStyleOpts` palette (plus any needed
223−overrides), then wire it into `ThemeForProvider`.
CRUSH.mdnew file+72
@@ -0,0 +1,72 @@
1+# Crush Development Guide
2+
3+## Build/Test/Lint Commands
4+
5+- **Build**: `go build .` or `go run .`
6+- **Test**: `task test` or `go test ./...` (run single test: `go test ./internal/llm/prompt -run TestGetContextFromPaths`)
7+- **Update Golden Files**: `go test ./... -update` (regenerates .golden files when test output changes)
8+ - Update specific package: `go test ./internal/tui/components/core -update` (in this case, we're updating "core")
9+- **Lint**: `task lint:fix`
10+- **Format**: `task fmt` (gofumpt -w .)
11+- **Dev**: `task dev` (runs with profiling enabled)
12+
13+## Code Style Guidelines
14+
15+- **Imports**: Use goimports formatting, group stdlib, external, internal packages
16+- **Formatting**: Use gofumpt (stricter than gofmt), enabled in golangci-lint
17+- **Naming**: Standard Go conventions - PascalCase for exported, camelCase for unexported
18+- **Types**: Prefer explicit types, use type aliases for clarity (e.g., `type AgentName string`)
19+- **Error handling**: Return errors explicitly, use `fmt.Errorf` for wrapping
20+- **Context**: Always pass context.Context as first parameter for operations
21+- **Interfaces**: Define interfaces in consuming packages, keep them small and focused
22+- **Structs**: Use struct embedding for composition, group related fields
23+- **Constants**: Use typed constants with iota for enums, group in const blocks
24+- **Testing**: Use testify's `require` package, parallel tests with `t.Parallel()`,
25+ `t.SetEnv()` to set environment variables. Always use `t.Tempdir()` when in
26+ need of a temporary directory. This directory does not need to be removed.
27+- **JSON tags**: Use snake_case for JSON field names
28+- **File permissions**: Use octal notation (0o755, 0o644) for file permissions
29+- **Comments**: End comments in periods unless comments are at the end of the line.
30+
31+## Testing with Mock Providers
32+
33+When writing tests that involve provider configurations, use the mock providers to avoid API calls:
34+
35+```go
36+func TestYourFunction(t *testing.T) {
37+ // Enable mock providers for testing
38+ originalUseMock := config.UseMockProviders
39+ config.UseMockProviders = true
40+ defer func() {
41+ config.UseMockProviders = originalUseMock
42+ config.ResetProviders()
43+ }()
44+
45+ // Reset providers to ensure fresh mock data
46+ config.ResetProviders()
47+
48+ // Your test code here - providers will now return mock data
49+ providers := config.Providers()
50+ // ... test logic
51+}
52+```
53+
54+## Formatting
55+
56+- ALWAYS format any Go code you write.
57+ - First, try `gofumpt -w .`.
58+ - If `gofumpt` is not available, use `goimports`.
59+ - If `goimports` is not available, use `gofmt`.
60+ - You can also use `task fmt` to run `gofumpt -w .` on the entire project,
61+ as long as `gofumpt` is on the `PATH`.
62+
63+## Comments
64+
65+- Comments that live on their own lines should start with capital letters and
66+ end with periods. Wrap comments at 78 columns.
67+
68+## Committing
69+
70+- ALWAYS use semantic commits (`fix:`, `feat:`, `chore:`, `refactor:`, `docs:`, `sec:`, etc).
71+- Try to keep commits to one line, not including your attribution. Only use
72+ multi-line commits when additional context is truly necessary.
LICENSE.md+1−1
@@ -6,7 +6,7 @@ FSL-1.1-MIT
66
77## Notice
88
9−Copyright 2025-2026 Charmbracelet, Inc.
9+Copyright 2025 Charmbracelet, Inc
1010
1111## Terms and Conditions
1212
README.md+55−328
@@ -1,16 +1,13 @@
11# Crush
22
3−> [!NOTE]
4−> This is a personal fork of [charmbracelet/crush](https://github.com/charmbracelet/crush) with UI/UX tweaks and performance improvements.
5−
63<p align="center">
7− <a href="https://stuff.charm.sh/crush/charm-crush.png"><img width="450" alt="Charm Crush Logo" src="https://github.com/user-attachments/assets/cf8ca3ce-8b02-43f0-9d0f-5a331488da4b" /></a><br />
4+ <a href="https://stuff.charm.sh/crush/charm-crush.png"><img width="450" alt="Charm Crush Logo" src="https://github.com/user-attachments/assets/adc1a6f4-b284-4603-836c-59038caa2e8b" /></a><br />
85 <a href="https://github.com/charmbracelet/crush/releases"><img src="https://img.shields.io/github/release/charmbracelet/crush" alt="Latest Release"></a>
96 <a href="https://github.com/charmbracelet/crush/actions"><img src="https://github.com/charmbracelet/crush/actions/workflows/build.yml/badge.svg" alt="Build Status"></a>
107</p>
118
129<p align="center">Your new coding bestie, now available in your favourite terminal.<br />Your tools, your code, and your workflows, wired into your LLM of choice.</p>
13−<p align="center">终端里的编程新搭档，<br />无缝接入你的工具、代码与工作流，全面兼容主流 LLM 模型。</p>
10+<p align="center">你的新编程伙伴，现在就在你最爱的终端中。<br />你的工具、代码和工作流，都与您选择的 LLM 模型紧密相连。</p>
1411
1512<p align="center"><img width="800" alt="Crush Demo" src="https://github.com/user-attachments/assets/58280caf-851b-470a-b6f7-d5c4ea8a1968" /></p>
1613
@@ -21,8 +18,7 @@
2118- **Session-Based:** maintain multiple work sessions and contexts per project
2219- **LSP-Enhanced:** Crush uses LSPs for additional context, just like you do
2320- **Extensible:** add capabilities via MCPs (`http`, `stdio`, and `sse`)
24−- **Works Everywhere:** first-class support in every terminal on macOS, Linux, Windows (PowerShell and WSL), Android, FreeBSD, OpenBSD, and NetBSD
25−- **Industrial Grade:** built on the Charm ecosystem, powering 25k+ applications, from leading open source projects to business-critical infrastructure
21+- **Works Everywhere:** first-class support in every terminal on macOS, Linux, Windows (PowerShell and WSL), FreeBSD, OpenBSD, and NetBSD
2622
2723## Installation
2824
@@ -40,9 +36,6 @@ yay -S crush-bin
4036
4137# Nix
4238nix run github:numtide/nix-ai-tools#crush
43−
44−# FreeBSD
45−pkg install crush
4639```
4740
4841Windows users:
@@ -59,9 +52,9 @@ scoop install crush
5952<details>
6053<summary><strong>Nix (NUR)</strong></summary>
6154
62−Crush is available via the official Charm [NUR](https://github.com/nix-community/NUR) in `nur.repos.charmbracelet.crush`, which is the most up-to-date way to get Crush in Nix.
55+Crush is available via [NUR](https://github.com/nix-community/NUR) in `nur.repos.charmbracelet.crush`.
6356
64−You can also try out Crush via the NUR with `nix-shell`:
57+You can also try out Crush via `nix-shell`:
6558
6659```bash
6760# Add the NUR channel.
@@ -172,56 +165,35 @@ go install github.com/charmbracelet/crush@latest
172165> [!WARNING]
173166> Productivity may increase when using Crush and you may find yourself nerd
174167> sniped when first using the application. If the symptoms persist, join the
175−> [Slack][slack] or [Discord][discord] and nerd snipe the rest of us.
168+> [Discord][discord] and nerd snipe the rest of us.
176169
177170## Getting Started
178171
179172The quickest way to get started is to grab an API key for your preferred
180−provider such as Anthropic, OpenAI, Groq, OpenRouter, or Vercel AI Gateway and just start
173+provider such as Anthropic, OpenAI, Groq, or OpenRouter and just start
181174Crush. You'll be prompted to enter your API key.
182175
183176That said, you can also set environment variables for preferred providers.
184177
185178| Environment Variable | Provider |
186179| --------------------------- | -------------------------------------------------- |
187−| `HYPER_API_KEY` | Charm Hyper |
188180| `ANTHROPIC_API_KEY` | Anthropic |
189181| `OPENAI_API_KEY` | OpenAI |
190−| `VERCEL_API_KEY` | Vercel AI Gateway |
182+| `OPENROUTER_API_KEY` | OpenRouter |
191183| `GEMINI_API_KEY` | Google Gemini |
192−| `SYNTHETIC_API_KEY` | Synthetic |
193−| `ZAI_API_KEY` | Z.ai |
194−| `MINIMAX_API_KEY` | MiniMax |
195−| `HF_TOKEN` | Hugging Face Inference |
196184| `CEREBRAS_API_KEY` | Cerebras |
197−| `OPENROUTER_API_KEY` | OpenRouter |
198−| `IONET_API_KEY` | io.net |
199−| `ALIBABA_SINGAPORE_API_KEY` | Alibaba (Singapore) |
200−| `ALIBABA_US_API_KEY` | Alibaba (United States) |
201−| `GROQ_API_KEY` | Groq |
202−| `AVIAN_API_KEY` | Avian |
203−| `OPENCODE_API_KEY` | OpenCode Zen & Go |
185+| `HF_TOKEN` | Huggingface Inference |
204186| `VERTEXAI_PROJECT` | Google Cloud VertexAI (Gemini) |
205187| `VERTEXAI_LOCATION` | Google Cloud VertexAI (Gemini) |
206−| `AWS_ACCESS_KEY_ID` | Amazon Bedrock (Claude) |
207−| `AWS_SECRET_ACCESS_KEY` | Amazon Bedrock (Claude) |
208−| `AWS_REGION` | Amazon Bedrock (Claude) |
209−| `AWS_PROFILE` | Amazon Bedrock (Custom Profile) |
210−| `AWS_BEARER_TOKEN_BEDROCK` | Amazon Bedrock |
188+| `GROQ_API_KEY` | Groq |
189+| `AWS_ACCESS_KEY_ID` | Amazon Bedrock (Claude) |
190+| `AWS_SECRET_ACCESS_KEY` | Amazon Bedrock (Claude) |
191+| `AWS_REGION` | Amazon Bedrock (Claude) |
192+| `AWS_PROFILE` | Amazon Bedrock (Custom Profile) |
193+| `AWS_BEARER_TOKEN_BEDROCK` | Amazon Bedrock |
211194| `AZURE_OPENAI_API_ENDPOINT` | Azure OpenAI models |
212195| `AZURE_OPENAI_API_KEY` | Azure OpenAI models (optional when using Entra ID) |
213196| `AZURE_OPENAI_API_VERSION` | Azure OpenAI models |
214−| `MOONSHOT_API_KEY` | Moonshot |
215−
216−### Subscriptions
217−
218−If you prefer subscription-based usage, here are some plans that work well in
219−Crush:
220−
221−- [Synthetic](https://synthetic.new/pricing)
222−- [GLM Coding Plan](https://z.ai/subscribe)
223−- [Kimi Code](https://www.kimi.com/membership/pricing)
224−- [MiniMax Coding Plan](https://platform.minimax.io/subscribe/coding-plan)
225197
226198### By the Way
227199
@@ -233,10 +205,6 @@ Crush’s default model listing is managed in [Catwalk](https://github.com/charm
233205
234206## Configuration
235207
236−> [!TIP]
237−> Crush ships with a builtin `crush-config` skill for configuring itself. In
238−> many cases you can simply ask Crush to configure itself.
239−
240208Crush runs great with no configuration. That said, if you do need or want to
241209customize Crush, configuration can be added either local to the project itself,
242210or globally, with the following priority:
@@ -254,8 +222,7 @@ Configuration itself is stored as a JSON object:
254222}
255223```
256224
257−As an additional note, Crush also stores ephemeral data, such as application
258−state, in one additional location:
225+As an additional note, Crush also stores ephemeral data, such as application state, in one additional location:
259226
260227```bash
261228# Unix
@@ -267,9 +234,8 @@ $HOME/.local/share/crush/crush.json
267234
268235> [!TIP]
269236> You can override the user and data config locations by setting:
270−>
271−> - `CRUSH_GLOBAL_CONFIG`
272−> - `CRUSH_GLOBAL_DATA`
237+> * `CRUSH_GLOBAL_CONFIG`
238+> * `CRUSH_GLOBAL_DATA`
273239
274240### LSPs
275241
@@ -299,36 +265,10 @@ like you would. LSPs can be added manually like so:
299265
300266### MCPs
301267
302−Crush also supports Model Context Protocol (MCP) servers through three transport
303−types: `stdio` for command-line servers, `http` for HTTP endpoints, and `sse`
304−for Server-Sent Events.
305−
306−Shell-style value expansion (`$VAR`, `${VAR:-default}`, `$(command)`, quoting,
307−nesting) works in `command`, `args`, `env`, `headers`, and `url`, so
308−file-based secrets work out of the box. You can use values like `"$TOKEN"`
309−or `"$(cat /path/to/secret/token)"`. Expansion runs through Crush's embedded
310−shell, so the same syntax works on every supported system, Windows included.
311−
312−Unset variables expand to the empty string by default, matching bash. For
313−required credentials, use `${VAR:?message}` so an unset variable fails loudly
314−at load time with `message` instead of silently resolving to empty:
315−
316−```json
317−{ "api_key": "${CODEBERG_TOKEN:?set CODEBERG_TOKEN}" }
318−```
319−
320−Headers (both MCP `headers` and provider `extra_headers`) whose value
321−resolves to the empty string are dropped from the outgoing request rather
322−than sent as `Header:`. That keeps optional env-gated headers like
323−`"OpenAI-Organization": "$OPENAI_ORG_ID"` clean when the variable is unset.
324−
325−Provider `extra_body` is a non-expanding JSON passthrough; put env-driven
326−values in `extra_headers` or the provider's `api_key` / `base_url`, all of
327−which do expand.
328−
329−> **Security note:** `crush.json` is trusted code. Any `$(...)` in it runs at
330−> load time with your shell's privileges, before the UI appears. Don't launch
331−> Crush in a directory whose `crush.json` you haven't reviewed.
268+Crush also supports Model Context Protocol (MCP) servers through three
269+transport types: `stdio` for command-line servers, `http` for HTTP endpoints,
270+and `sse` for Server-Sent Events. Environment variable expansion is supported
271+using `$(echo $VAR)` syntax.
332272
333273```json
334274{
@@ -368,72 +308,6 @@ which do expand.
368308}
369309```
370310
371−### Hooks
372−
373−Crush has preliminary support for hooks. For details, see
374−[the hook guide](./docs/hooks/).
375−
376−### Sharing a workspace across clients
377−
378−When Crush is run against a shared backend (for example two TUIs talking to
379−the same `crush serve`), clients are grouped into **workspaces** keyed by
380−their resolved `--cwd`. Two clients with the same `--cwd` join the same
381−underlying workspace, so they share the session list, message history,
382−permission queue, LSP, and MCP state.
383−
384−Joining is implicit: pointing a second client at the same working directory
385−attaches it to the existing workspace. Each new invocation, however, starts
386−in its own fresh session by default. To pick up the conversation another
387−client already has open, use the session manager (the session picker) and
388−select it. Sessions surface two signals there:
389−
390−- `IsBusy` is set while an agent turn is in flight for that session.
391−- `AttachedClients` reports how many clients are currently viewing it.
392−
393−A non-zero `AttachedClients` (often combined with `IsBusy`) is the cue that a
394−session is "in progress" on another client and joining it will mirror that
395−view live.
396−
397−The first client to create a workspace fixes its process-wide flags. In
398−particular, `--yolo` and `--debug` follow a **first-wins** rule: later
399−clients that arrive at the same `--cwd` with different values for those
400−flags do not change the running workspace. A debug log line is emitted
401−recording the mismatch, and the workspace keeps the flags it was created
402−with.
403−
404−A workspace lives as long as at least one client has an SSE event stream
405−open against it. When the last stream disconnects, the workspace is torn
406−down. There is a short grace window right after `POST /v1/workspaces` so a
407−client that has created the workspace but not yet opened its event stream
408−does not get reaped before it can attach.
409−
410−### Global context files
411−
412−Crush automatically includes two files for cross-project instructions.
413−
414−- `~/.config/crush/CRUSH.md`: Crush-specific rules that would confuse other
415− agentic coding tools. If you only use Crush, this is the only one you need to
416− edit.
417−- `~/.config/AGENTS.md`: generic instructions that other coding tools might
418− read. Avoid referring to Crush-specific features or workflows here. You
419− probably only care about this if you use multiple agentic coding tools and
420− want to share instructions between them.
421−
422−You can customize these paths using the `global_context_paths` option in your
423−configuration:
424−
425−```jsonc
426−{
427− "$schema": "https://charm.land/crush.json",
428− "options": {
429− "global_context_paths": [
430− "~/path/to/custom/context/file.md",
431− "/full/path/to/folder/of/files/" // recursively load all .md files in folder
432− ]
433− }
434−}
435−```
436−
437311### Ignoring Files
438312
439313Crush respects `.gitignore` files by default, but you can also create a
@@ -478,135 +352,16 @@ completely hidden from the agent.
478352{
479353 "$schema": "https://charm.land/crush.json",
480354 "options": {
481− "disabled_tools": ["bash", "sourcegraph"]
355+ "disabled_tools": [
356+ "bash",
357+ "sourcegraph"
358+ ]
482359 }
483360}
484361```
485362
486363To disable tools from MCP servers, see the [MCP config section](#mcps).
487364
488−### Disabling Skills
489−
490−If you'd like to prevent Crush from using certain skills entirely, you can
491−disable them via the `options.disabled_skills` list. Disabled skills are hidden
492−from the agent, including builtin skills and skills discovered from disk.
493−
494−```json
495−{
496− "$schema": "https://charm.land/crush.json",
497− "options": {
498− "disabled_skills": ["crush-config"]
499− }
500−}
501−```
502−
503−### Agent Skills
504−
505−Crush supports the [Agent Skills](https://agentskills.io) open standard for
506−extending agent capabilities with reusable skill packages. Skills are folders
507−containing a `SKILL.md` file with instructions that Crush can discover and
508−activate on demand.
509−
510−The global paths we looks for skills are:
511−
512−* `$CRUSH_SKILLS_DIR`
513−* `$XDG_CONFIG_HOME/agents/skills` or `~/.config/agents/skills/`
514−* `$XDG_CONFIG_HOME/crush/skills` or `~/.config/crush/skills/`
515−* `~/.agents/skills/`
516−* `~/.claude/skills/`
517−* On Windows, we _also_ look at
518− * `%LOCALAPPDATA%\agents\skills\` or `%USERPROFILE%\AppData\Local\agents\skills\`
519− * `%LOCALAPPDATA%\crush\skills\` or `%USERPROFILE%\AppData\Local\crush\skills\`
520−* Additional paths configured via `options.skills_paths`
521−
522−On top of that, we _also_ load skills in your project from the following
523−relative paths:
524−
525−* `.agents/skills`
526−* `.crush/skills`
527−* `.claude/skills`
528−* `.cursor/skills`
529−
530−```jsonc
531−{
532− "$schema": "https://charm.land/crush.json",
533− "options": {
534− "skills_paths": [
535− "~/.config/crush/skills", // Windows: "%LOCALAPPDATA%\\crush\\skills",
536− "./project-skills",
537− ],
538− },
539−}
540−```
541−
542−You can get started with example skills from [anthropics/skills](https://github.com/anthropics/skills):
543−
544−```bash
545−# Unix
546−mkdir -p ~/.config/crush/skills
547−cd ~/.config/crush/skills
548−git clone https://github.com/anthropics/skills.git _temp
549−mv _temp/skills/* . && rm -rf _temp
550−```
551−
552−```powershell
553−# Windows (PowerShell)
554−mkdir -Force "$env:LOCALAPPDATA\crush\skills"
555−cd "$env:LOCALAPPDATA\crush\skills"
556−git clone https://github.com/anthropics/skills.git _temp
557−mv _temp/skills/* . ; rm -r -force _temp
558−```
559−
560−#### User-Invocable Skills
561−
562−Skills can be made invocable as commands from the commands palette (Ctrl+P). Add `user-invocable: true` to the skill's YAML frontmatter:
563−
564−```yaml
565−---
566−name: my-skill
567−description: A skill that can be invoked as a command.
568−user-invocable: true
569−---
570−```
571−
572−User-invocable skills appear in the commands palette with a `user:` or `project:` prefix:
573−- Skills from global directories show as `user:skill-name`
574−- Skills from project directories show as `project:skill-name`
575−
576−When invoked, the skill's instructions are loaded into the conversation context.
577−
578−To prevent the model from auto-triggering a skill (while still allowing user invocation), add `disable-model-invocation: true`:
579−
580−```yaml
581−---
582−name: my-skill
583−description: Only invocable by users, not the model.
584−user-invocable: true
585−disable-model-invocation: true
586−---
587−```
588−
589−Skills with `disable-model-invocation` won't appear in the model's available skills list but can still be invoked manually by users.
590−
591−### Desktop notifications
592−
593−Crush sends desktop notifications when a tool call requires permission and when
594−the agent finishes its turn. They're only sent when the terminal window isn't
595−focused _and_ your terminal supports reporting the focus state.
596−
597−```jsonc
598−{
599− "$schema": "https://charm.land/crush.json",
600− "options": {
601− "disable_notifications": false, // default
602− },
603−}
604−```
605−
606−To disable desktop notifications, set `disable_notifications` to `true` in your
607−configuration. On macOS, notifications currently lack icons due to platform
608−limitations.
609−
610365### Initialization
611366
612367When you initialize a project, Crush analyzes your codebase and creates
@@ -648,9 +403,10 @@ it creates. You can customize this behavior with the `attribution` option:
648403
649404- `trailer_style`: Controls the attribution trailer added to commit messages
650405 (default: `assisted-by`)
651− - `assisted-by`: Adds `Assisted-by: Crush:[ModelID]` as specified in [the convention](https://docs.kernel.org/process/coding-assistants.html#attribution)
652− - `co-authored-by`: Adds `Co-Authored-By: Crush <crush@charm.land>`
653− - `none`: No attribution trailer
406+ - `assisted-by`: Adds `Assisted-by: [Model Name] via Crush <crush@charm.land>`
407+ (includes the model name)
408+ - `co-authored-by`: Adds `Co-Authored-By: Crush <crush@charm.land>`
409+ - `none`: No attribution trailer
654410- `generated_with`: When true (default), adds `💘 Generated with Crush` line to
655411 commit messages and PR descriptions
656412
@@ -662,9 +418,8 @@ Anthropic-compatible APIs.
662418> [!NOTE]
663419> Note that we support two "types" for OpenAI. Make sure to choose the right one
664420> to ensure the best experience!
665−>
666−> - `openai` should be used when proxying or routing requests through OpenAI.
667−> - `openai-compat` should be used when using non-OpenAI providers that have OpenAI-compatible APIs.
421+> * `openai` should be used when proxying or routing requests through OpenAI.
422+> * `openai-compat` should be used when using non-OpenAI providers that have OpenAI-compatible APIs.
668423
669424#### OpenAI-Compatible APIs
670425
@@ -775,10 +530,9 @@ To add specific models to the configuration, configure as such:
775530
776531### Local Models
777532
778−Crush can auto-discovers models from local providers. Add a custom provider
779−with `type` set to `llamacpp`, `omlx`, `lmstudio`, `litellm`, or `ollama`
780−and leave out the models list. Crush will populate the model list
781−automatically.
533+Local models can also be configured via OpenAI-compatible API. Here are two common examples:
534+
535+#### Ollama
782536
783537```json
784538{
@@ -786,50 +540,37 @@ automatically.
786540 "ollama": {
787541 "name": "Ollama",
788542 "base_url": "http://localhost:11434/v1/",
789− "type": "ollama"
790− }
791− }
792−}
793−```
794−
795−For llama.cpp (`llama-server`), point at the server's base URL:
796−
797−```json
798−{
799− "providers": {
800− "llamacpp": {
801− "name": "llama.cpp",
802− "base_url": "http://localhost:2222",
803− "type": "llamacpp"
543+ "type": "openai-compat",
544+ "models": [
545+ {
546+ "name": "Qwen 3 30B",
547+ "id": "qwen3:30b",
548+ "context_window": 256000,
549+ "default_max_tokens": 20000
550+ }
551+ ]
804552 }
805553 }
806554}
807555```
808556
809−#### Manual Model Configuration
810−
811−You can still list models explicitly. User-defined models always take
812−precedence over discovered ones, and any fields you set won't be overwritten
813−by auto-discovery. Auto discovery will run if the model list is empty for any
814−`openai-compat` provider or if you pass `"discover_models": true` it will merge
815− the found models with your hand configured ones.
557+#### LM Studio
816558
817559```json
818560{
819561 "providers": {
820− "ollama": {
821− "name": "Ollama",
822− "base_url": "http://localhost:11434/v1/",
823− "type": "ollama",
562+ "lmstudio": {
563+ "name": "LM Studio",
564+ "base_url": "http://localhost:1234/v1/",
565+ "type": "openai-compat",
824566 "models": [
825567 {
826568 "name": "Qwen 3 30B",
827− "id": "qwen3:30b",
569+ "id": "qwen/qwen3-30b-a3b-2507",
828570 "context_window": 256000,
829571 "default_max_tokens": 20000
830572 }
831− ],
832− "discover_models": true
573+ ]
833574 }
834575 }
835576}
@@ -947,21 +688,8 @@ Or by setting the following in your config:
947688}
948689```
949690
950−Crush also respects the [`DO_NOT_TRACK`](https://donottrack.sh/) convention
951−which can be enabled via `export DO_NOT_TRACK=1`.
952−
953−## Q&A
954−
955−### Why is clipboard copy and paste not working?
956−
957−Installing an extra tool might be needed on Unix-like environments.
958−
959−| Environment | Tool |
960−| ------------------- | ------------------------ |
961−| Windows | Native support |
962−| macOS | Native support |
963−| Linux/BSD + Wayland | `wl-copy` and `wl-paste` |
964−| Linux/BSD + X11 | `xclip` or `xsel` |
691+Crush also respects the [`DO_NOT_TRACK`](https://consoledonottrack.com)
692+convention which can be enabled via `export DO_NOT_TRACK=1`.
965693
966694## Contributing
967695
@@ -972,12 +700,11 @@ See the [contributing guide](https://github.com/charmbracelet/crush?tab=contribu
972700We’d love to hear your thoughts on this project. Need help? We gotchu. You can find us on:
973701
974702- [Twitter](https://twitter.com/charmcli)
975−- [Slack][slack]
703+- [Slack](https://charm.land/slack)
976704- [Discord][discord]
977705- [The Fediverse](https://mastodon.social/@charmcli)
978706- [Bluesky](https://bsky.app/profile/charm.land)
979707
980−[slack]: https://charm.land/slack
981708[discord]: https://charm.land/discord
982709
983710## License
@@ -988,7 +715,7 @@ We’d love to hear your thoughts on this project. Need help? We gotchu. You can
988715
989716Part of [Charm](https://charm.land).
990717
991−<a href="https://charm.land/"><img alt="The Charm logo" width="400" src="https://stuff.charm.sh/charm-banner-softy.jpg" /></a>
718+<a href="https://charm.land/"><img alt="The Charm logo" width="400" src="https://stuff.charm.sh/charm-banner-next.jpg" /></a>
992719
993720<!--prettier-ignore-->
994721Charm热爱开源 • Charm loves open source
Taskfile.yaml+6−82
@@ -5,8 +5,6 @@ version: "3"
55vars:
66 VERSION:
77 sh: git describe --long 2>/dev/null || echo ""
8− RACE:
9− sh: test -f race.log && echo "1" || echo ""
108
119env:
1210 CGO_ENABLED: 0
@@ -23,16 +21,10 @@ tasks:
2321 lint:
2422 desc: Run base linters
2523 cmds:
26− - task: lint:log
2724 - golangci-lint run --path-mode=abs --config=".golangci.yml" --timeout=5m
2825 env:
2926 GOEXPERIMENT: null
3027
31− lint:log:
32− desc: Check that log messages start with capital letters
33− cmds:
34− - ./scripts/check_log_capitalization.sh
35−
3628 lint:fix:
3729 desc: Run base linters and fix issues
3830 cmds:
@@ -45,44 +37,19 @@ tasks:
4537 vars:
4638 LDFLAGS: '{{if .VERSION}}-ldflags="-X github.com/charmbracelet/crush/internal/version.Version={{.VERSION}}"{{end}}'
4739 cmds:
48− - "go build -v {{if .RACE}}-race{{end}} {{.LDFLAGS}} ."
49− sources:
50− - ./**/*.go
51− - go.mod
52− - internal/agent/**/*.md
53− - internal/agent/**/*.md.tpl
54− - internal/agent/hyper/provider.json
40+ - go build {{.LDFLAGS}} .
5541 generates:
56− - crush{{exeExt}}
42+ - crush
5743
5844 run:
5945 desc: Run build
6046 cmds:
61− - task: build
62− - "./crush{{exeExt}} {{.CLI_ARGS}} {{if .RACE}}2>race.log{{end}}"
63−
64− run:catwalk:
65− desc: Run build with local Catwalk
66− env:
67− CATWALK_URL: http://localhost:8080
68− cmds:
69− - task: build
70− - ./crush{{exeExt}} {{.CLI_ARGS}}
71−
72− run:onboarding:
73− desc: Run build with custom config to test onboarding
74− env:
75− CRUSH_GLOBAL_DATA: tmp/onboarding/data
76− CRUSH_GLOBAL_CONFIG: tmp/onboarding/config
77− cmds:
78− - task: build
79− - rm -rf tmp/onboarding
80− - ./crush{{exeExt}} {{.CLI_ARGS}}
47+ - go run . {{.CLI_ARGS}}
8148
8249 test:
8350 desc: Run tests
8451 cmds:
85− - go test -race -failfast ./... {{.CLI_ARGS}}
52+ - go test ./... {{.CLI_ARGS}}
8653
8754 test:record:
8855 desc: Run tests and record all VCR cassettes again
@@ -96,16 +63,6 @@ tasks:
9663 cmds:
9764 - gofumpt -w .
9865
99− fmt:html:
100− desc: Run prettier on HTML/CSS/JS files
101− cmds:
102− - prettier --write internal/cmd/stats/index.html internal/cmd/stats/index.css internal/cmd/stats/index.js
103−
104− modernize:
105− desc: Run modernize
106− cmds:
107− - go run golang.org/x/tools/go/analysis/passes/modernize/cmd/modernize@latest -fix -test ./...
108−
10966 dev:
11067 desc: Run with profiling enabled
11168 env:
@@ -120,12 +77,6 @@ tasks:
12077 cmds:
12178 - task: fetch-tags
12279 - go install {{.LDFLAGS}} -v .
123− sources:
124− - ./**/*.go
125− - go.mod
126− - internal/agent/**/*.md
127− - internal/agent/**/*.md.tpl
128− - internal/agent/hyper/provider.json
12980
13081 profile:cpu:
13182 desc: 10s CPU profile
@@ -168,10 +119,6 @@ tasks:
168119 msg: Not on main branch
169120 - sh: "[ $(git status --porcelain=2 | wc -l) = 0 ]"
170121 msg: "Git is dirty"
171− - sh: 'gh run list --workflow build.yml --commit $(git rev-parse HEAD) --status success --json conclusion -q ".[0].conclusion" | grep -q success'
172− msg: "Test build for this commit failed or not present"
173− - sh: 'gh run list --workflow snapshot.yml --commit $(git rev-parse HEAD) --status success --json conclusion -q ".[0].conclusion" | grep -q success'
174− msg: "Snapshot build for this commit failed or not present"
175122 cmds:
176123 - task: fetch-tags
177124 - git commit --allow-empty -m "{{.NEXT}}"
@@ -186,30 +133,7 @@ tasks:
186133
187134 deps:
188135 desc: Update Fantasy and Catwalk
189− env:
190− # The Go proxy takes a bit of time to see the latest release. Setting
191− # these bypass it to ensure we can update to a release from a minute ago.
192− GOPROXY: direct
193− GONOSUMDB: charm.land/*
194136 cmds:
195− - go get charm.land/fantasy@latest
196− - go get charm.land/catwalk@latest
137+ - go get charm.land/fantasy
138+ - go get github.com/charmbracelet/catwalk
197139 - go mod tidy
198−
199− swag:
200− desc: Generate OpenAPI spec from swag annotations
201− cmds:
202− - go run github.com/swaggo/swag/cmd/swag@v1.16.6 init --generalInfo main.go --dir . --output internal/swagger --packageName swagger --parseDependency --parseInternal --parseDepth 5
203− sources:
204− - internal/server/*.go
205− - internal/proto/*.go
206− - main.go
207− generates:
208− - internal/swagger/docs.go
209− - internal/swagger/swagger.json
210− - internal/swagger/swagger.yaml
211−
212− sqlc:
213− desc: Generate code using SQLC
214− cmds:
215− - sqlc generate
docs/hooks/FUTURE.mddeleted−260
@@ -1,260 +0,0 @@
1−# Hooks: Future Work
2−
3−This document tracks planned features and design notes for hooks that are not
4−yet implemented. Nothing here is part of the current contract. Treat it as a
5−scratchpad for what's next, not as documentation of current behavior.
6−
7−> [!NOTE]
8−> This document was largely LLM-generated.
9−
10−## `context_files`
11−
12−**Status:** planned, not implemented.
13−
14−### Motivation
15−
16−Today, a hook that wants to inject reference material into the agent's context
17−has exactly one knob: `context` (string or array of strings). Whatever the hook
18−puts there is concatenated into what the model sees. That's fine for short notes
19−("current branch: main", "scrubbed secrets") but it scales badly:
20−
21−- Dumping a whole `README.md` or `package.json` into `context` burns tokens on
22− every tool call where the hook fires.
23−- The model sees the file contents even if it doesn't need them.
24−- Large files can push the turn past the context window.
25−
26−`context_files` is the lazy alternative: the hook returns **paths**, not
27−contents. Crush tells the agent the files exist and are relevant, and the agent
28−decides whether to open them with its existing `view` tool.
29−
30−### Proposed shape
31−
32−Additive envelope field. Accepts a list of strings:
33−
34−```jsonc
35−{
36− "decision": "allow",
37− "context": "Scrubbed one secret",
38− "context_files": ["README.md", "docs/ARCHITECTURE.md"],
39−}
40−```
41−
42−Paths are resolved relative to `CRUSH_CWD`. Non-existent paths are dropped with
43−a debug log (don't fail the hook over a missing file).
44−
45−### How the agent sees it
46−
47−Crush appends a short note to the turn's context along the lines of:
48−
49−```
50−## Referenced files
51−- README.md
52−- docs/ARCHITECTURE.md
53−```
54−
55−No file contents are inlined. The agent opens them with `view` if it decides
56−they're relevant. This keeps cost proportional to need.
57−
58−### Aggregation
59−
60−Matches the existing rules for lists:
61−
62−- Concatenates across matching hooks in config order.
63−- Deduplicates paths (same file referenced by two hooks → listed once).
64−- Dropped entirely if the final decision is `deny` or `halt`.
65−
66−### Backwards compatibility
67−
68−Purely additive. Hooks that don't emit `context_files` are unaffected. Existing
69−envelopes keep working unchanged. No version bump required.
70−
71−### Open questions
72−
73−- Should `context_files` paths be constrained to `CRUSH_PROJECT_DIR`? Probably
74− yes, to avoid hooks smuggling in arbitrary filesystem reads.
75−- Do we want a per-file line range (`"README.md:1-40"`) or keep it dead simple
76− (whole-file references only)? Start simple; add ranges only if asked for.
77−- Should we annotate "why this file is relevant" per entry? An object form
78− (`{"path": "...", "reason": "..."}`) would allow that but complicates the
79− schema. Defer until there's a real user need.
80−
81−## Sub-agent opt-in
82−
83−**Status:** not implemented.
84−
85−### Background
86−
87−Today hooks fire **only** on the top-level agent's tool calls. Sub-agents
88−(`agent` task tool, `agentic_fetch`, future delegated loops) run without hook
89−interception so a single delegated turn doesn't trigger the user's hook N times.
90−
91−The outer sub-agent tool call itself is hooked, so blanket policy like "never
92−spawn sub-agents" or "rewrite prompts sent to the task agent" still works from
93−the coder's side. The sub-agent's inner loop is the part that's exempt.
94−
95−### Why users might want the escape hatch
96−
97−- Audit logging of every tool call, including delegated ones.
98−- Redaction hooks that want to apply uniformly regardless of who called the
99− tool.
100−- Policy that cares about the _tool_ not the _caller_: "never fetch from this
101− domain, even in `agentic_fetch`."
102−
103−Until someone actually asks, don't ship this. YAGNI.
104−
105−### Proposed shape
106−
107−Additive, per-hook. Zero-value matches current default (skip sub-agents):
108−
109−```jsonc
110−{
111− "hooks": {
112− "PreToolUse": [
113− {
114− "matcher": "^bash$",
115− "command": "./hooks/audit.sh",
116− "include_sub_agents": true, // default false
117− },
118− ],
119− },
120−}
121−```
122−
123−Implementation changes where `wrapToolsWithHooks` decides to skip. Instead of a
124−single `isSubAgent` bailout, the runner filters per-hook matches by the hook's
125−`include_sub_agents` flag. Hooks that opt in get wrapped into sub-agent tool
126−slices too; everything else stays skipped.
127−
128−### Backwards Compatibility
129−
130−Purely additive. Hooks that don't set `include_sub_agents` get the default
131−(`false` = skip sub-agents). No wire format change, no version bump. The initial
132−transition from "hooks fire everywhere" to "hooks skip sub-agents by default"
133−was a one-time behavior change; adding the opt-in is pure addition.
134−
135−### Side benefit: payload awareness
136−
137−Extend the stdin payload with `"is_sub_agent": true|false` so hook scripts that
138−opt in can branch on caller type ("audit top-level and sub-agent calls
139−differently"). Also purely additive — hooks that don't read the field are
140−unaffected.
141−
142−### Open questions
143−
144−- Per-hook flag (above) vs a global `hooks.include_sub_agents` default? A global
145− toggle is simpler but coarse-grained; per-hook is more flexible and
146− composable. Start per-hook; a global default can be layered on later with
147− explicit precedence ("per-hook overrides global").
148−- Does an opt-in hook see hooks from _nested_ sub-agents too (a sub-agent that
149− itself calls a sub-agent)? Probably yes — once you've opted in you want the
150− full tree. But call it out explicitly in docs so users aren't surprised by N²
151− explosions on pathological configs.
152−
153−## `UserPromptSubmit` event
154−
155−**Status:** not implemented.
156−
157−### Motivation
158−
159−Today Crush supports exactly one hook event, `PreToolUse`. That's enough to gate
160−and rewrite tool calls but nothing else. The next-most-useful event is
161−`UserPromptSubmit`: fires after the user hits Enter but before the turn hits the
162−LLM. Lets hooks inject context, rewrite prompts, or gate on content without the
163−mutation complexity of `PostToolUse` (output scrubbing, error coercion, size
164−limits — all rabbit holes).
165−
166−### Use cases
167−
168−- Prepend project context the user didn't think to include ("current branch:
169− `feat/x`; last commit: `<sha> <title>`").
170−- Point at reference files via `context_files` (when that lands) so the agent
171− knows where to look without being force-fed contents.
172−- Redact secrets out of the prompt before it leaves the machine.
173−- Refuse prompts matching a policy ("don't send anything mentioning
174− `production.env`") — with `deny` and a reason the user sees.
175−- Expand shorthand (`@TODO` → "please address the TODO in …").
176−
177−### Proposed shape
178−
179−Stdin payload extends the common envelope with the prompt:
180−
181−```jsonc
182−{
183− "event": "UserPromptSubmit",
184− "session_id": "…",
185− "cwd": "/home/user/project",
186− "prompt": "fix the login flow",
187− "attachments": ["screenshot.png"],
188−}
189−```
190−
191−Output envelope reuses common fields plus one new per-event field,
192−`updated_prompt`:
193−
194−```jsonc
195−{
196− "decision": "allow", // optional; deny blocks the submission entirely
197− "reason": "includes a production secret", // shown to the user when denying
198− "context": "Current branch: feat/login",
199− "updated_prompt": "fix the login flow\n\n(from @TODO on line 42)",
200−}
201−```
202−
203−`updated_prompt` is a **full replacement** — not a merge patch — because a
204−prompt is a single string with no natural key structure. If multiple hooks emit
205−`updated_prompt`, later hooks in config order win.
206−
207−### Aggregation
208−
209−Reuses the universal rules:
210−
211−- `halt` is sticky. Halts the whole turn before the LLM is called.
212−- `context` concatenates in config order.
213−- `updated_prompt`: last writer wins.
214−- `decision: "deny"` blocks the submission. The user sees `reason`; the turn
215− never reaches the LLM.
216−
217−### Differences from `PreToolUse`
218−
219−- No `updated_input`: there are no tool inputs at this point.
220−- No permission-prompt bypass: there's no permission prompt for a user prompt.
221−- `decision: "allow"` is functionally identical to silence. It exists only for
222− symmetry with `PreToolUse` and to give hook authors a consistent vocabulary.
223− (Could be argued both ways — consider dropping it here.)
224−- Fires on every user submission, including follow-ups in the same session.
225− Hooks should be fast; no subprocess-per-keystroke scenarios but the per-turn
226− overhead is real.
227−
228−### Implementation sketch
229−
230−- New event constant `EventUserPromptSubmit` in `internal/hooks/hooks.go`.
231−- `Runner.Run` already takes an event name; no interface change.
232−- A new call site in `sessionAgent.Run` (or the coordinator's Run path) that
233− fires hooks after creating the user message but before the first LLM call. If
234− the aggregate decision is `deny` or `halt`, abort the turn and surface
235− `reason` to the user.
236−- If hooks return `context`, prepend it to the prompt seen by the LLM (or attach
237− as a system-message-level note — decide based on how the prompt is threaded
238− through fantasy).
239−- If hooks return `updated_prompt`, replace the prompt body before the first LLM
240− call. The message row in the DB should still store the _original_ prompt so
241− the user sees what they typed; only the outbound version is rewritten. (Or:
242− store both, show the original, send the rewritten — mirror how `updated_input`
243− is handled today.)
244−
245−### Open questions
246−
247−- Store original vs rewritten prompt? Probably both, with UI showing original
248− and a subtle indicator that a hook modified it.
249−- Do hooks fire on queued prompts too, or only when actually dispatched? If the
250− user queues three prompts and the hook blocks the second, what happens to the
251− third? Simplest rule: fire when dispatched; denial skips to the next queued
252− prompt with a visible note.
253−- What about the `/commands` prefix? Does `UserPromptSubmit` fire for slash
254− commands, or are those intercepted earlier? Probably earlier — hooks see only
255− freeform prompts that would actually reach the LLM.
256−
257−## Cross-platform shell (Windows support)
258−
259−**Status:** implemented. See the [Execution model](README.md#execution-model)
260−section in `README.md` for the current behavior and contract.
docs/hooks/README.mddeleted−759
@@ -1,759 +0,0 @@
1−# Hooks
2−
3−> [!NOTE]
4−> This document was designed for both humans and agents.
5−
6−Hooks are user-defined shell scripts that run when various events happen during
7−the agent lifecycle, allowing you to both build on top of Crush, customize
8−its behavior, and exert deterministic control over an agent's wily behavior.
9−
10−Hooks are just shell commands, and were designed to be both simple and future
11−forward.
12−
13−### Hot Hook Facts
14−
15−- Hooks are just shell commands
16−- Hooks can be written in any language because they’re just executables: Bash, Python, Node, Rust, Haskell, whatever
17−- Hooks are Claude Code-compatible
18−- Crush ships with a builtin `crush-hook` skill write, edit, and configure
19− hooks; just tell Crush how to configure Crush
20−- Crush currently supports just one hook, `PreToolUse`, with plans to support
21− the full gamut; please let us know which hooks you'd like to see next
22−- Hooks run in parallel for speed, but their results compose in config order
23− for determinism
24−
25−### Some things you can do with hooks:
26−
27−- Block "dangerous" commands: no more `git push -f` or `cabal init`
28−- Rewrite tool input: turn `node` calls info `deno`, scrub secrets from
29− commands, rewrite all mentions of "Haskell" into "Haskell, The Best
30− Language", and so on
31−- Inject context: add notes to the model's context whenever certain tools are
32− called. For example: "remember to run gofumpt after editing Go files"
33−- Auto-approve tools: skip the permission prompt for bash commands that
34− you know are safe
35−- Log certain tool calls
36−
37−…And lots more. Show us what you're building!
38−
39−## Baby's First Hook
40−
41−Let's just dive into it and make a simple hook. This particular hook will
42−disallow the use of Haskell (but we love you, Simon Peyton Jones).
43−
44−### Config
45−
46−The first thing we need to do is hook up our hook. Let's add the following to
47−our **project-level** `crush.json`. Relative paths like `./no-haskell.sh` work
48−here because the project root is your working directory. If you're configuring
49−a global hook (`~/.config/crush/crush.json`), use an absolute path instead.
50−
51−```jsonc
52−{
53− // As expected, hooks go in a "hooks" object.
54− "hooks": {
55− // PreToolUse is an event that fires before a tool is used.
56− "PreToolUse": [
57− {
58− // What tool do we want to hook into? In this case, Bash, because it
59− // runs the stuff we wanna block.
60− "matcher": "^bash$",
61−
62− // The path to our actual hook script.
63− "command": "./no-haskell.sh",
64− },
65− ],
66− },
67−}
68−```
69−
70−Now, let's make our `no-haskell.sh` hook script.
71−
72−```bash
73−#!/usr/bin/env bash
74−
75−# Disallow ghc, cabal, and stack. Pipe the bash command output
76−# ($CRUSH_TOOL_INPUT_COMMAND) to grep and match on a regexp.
77−if echo "$CRUSH_TOOL_INPUT_COMMAND" | grep -qE '(^| )((ghc|cabal|stack)(\.exe)?)( |$)'; then
78−
79− # Someone is trying to use Haskell. Let's send a message back to the model
80− # and user explaining why we're blocking this. Note that we send all feedback
81− # like this to stderr.
82− echo "No Haskell allowed, kiddo." >&2
83−
84− # Now, block the tool call by exiting with code 2.
85− exit 2
86−fi
87−```
88−
89−That's basically it. For the full guide on how hooks work, however, read on.
90−
91−---
92−
93−## Execution model
94−
95−Hooks run through Crush's embedded POSIX shell (`mvdan.cc/sh`) — the same
96−interpreter the `bash` tool uses. Inline commands and shebang-less scripts
97−execute in-process; scripts with a `#!` shebang dispatch to the named
98−interpreter via `os/exec`. This contract is identical on macOS, Linux, and
99−Windows.
100−
101−What this means in practice:
102−
103−- **Windows without Unix tooling**: inline shell (`echo`, pipelines, `jq`,
104− `grep`), shebang-less `.sh` scripts, inline PowerShell
105− (`powershell -Command …`), and `.exe` invocations all work out of the box
106− with no WSL, Git Bash, Cygwin, or MSYS required.
107−- **PowerShell scripts** (`.ps1`) are not auto-dispatched by extension.
108− Invoke them explicitly: `powershell -File ./audit.ps1` (or
109− `pwsh -File ./audit.ps1`).
110−- **Shebang'd scripts** require the named interpreter on `PATH`. Git for
111− Windows ships `bash.exe`, which makes `#!/bin/bash` and
112− `#!/usr/bin/env bash` scripts work on Windows the same way they do on
113− Unix. CRLF line endings in the shebang line are tolerated.
114−- **Permissive shebang fallback**: if the absolute path in a shebang
115− doesn't exist (e.g. `#!/bin/bash` on Windows), Crush falls back to a
116− `PATH` lookup of the base name (`bash`) before giving up. A debug-level
117− log records the fallback. If the interpreter isn't on `PATH` either, the
118− hook fails cleanly as a non-blocking warning and the agent proceeds as
119− "no opinion".
120−- **Environment**: every hook sees `CRUSH=1`, `AGENT=crush`, and
121− `AI_AGENT=crush` on top of the `CRUSH_*` hook-specific variables. These
122− three markers are guaranteed and match what the `bash` tool sets, so
123− scripts that detect "am I being run by an AI agent?" behave the same in
124− both contexts.
125−- **Timeout behavior**: when a hook exceeds its timeout, Crush cancels the
126− context and waits a short grace period (~1s) for the interpreter to
127− yield. If the hook still hasn't returned, Crush abandons it, logs a
128− warning, and treats the result as "no opinion" so the agent can proceed.
129− Long-running work should honor context cancellation or run in a
130− subprocess via a shebang.
131−
132−## Configuration
133−
134−Hooks can be added to your `crush.json` (or `.crush.json`) at both the global
135−and project-level, with project level hooks taking precedence.
136−
137−```jsonc
138−{
139− "hooks": {
140− "PreToolUse": [
141− {
142− "name": "no-rm-rf", // friendly name shown in the TUI
143− "matcher": "bash", // regex tested against the tool name
144− "command": "./hooks/my-hot-hook.sh", // the path to the hook
145− "timeout": 10, // in seconds; default 30
146− },
147− ],
148− },
149−}
150−```
151−
152−> [!IMPORTANT]
153−> The `command` is resolved relative to your **current working directory** —
154−> not relative to the config file. Relative paths like `./hooks/whatever.sh`
155−> work fine in project-level `crush.json` because the project root is also
156−> your working directory. For **global** config (`~/.config/crush/`),
157−> however, you must use either an absolute path or an inline command:
158−>
159−> ```jsonc
160−> // Global ~/.config/crush/crush.json
161−> {
162−> "hooks": {
163−> "PreToolUse": [
164−> {
165−> "command": "/home/you/.config/crush/hooks/no-haskell.sh"
166−> // or use an inline command:
167−> // "command": "echo '{\"decision\":\"allow\"}'"
168−> }
169−> ]
170−> }
171−> }
172−> ```
173−
174−Remember, hooks will run in parallel but resolve in config order. Last hook
175−wins when rewriting input, but first deny wins when blocking.
176−
177−## Events
178−
179−Here are the events you can hook into (spoiler: there's currently just one):
180−
181−### PreToolUse
182−
183−This hook fires before every tool call. Use it to block dangerous commands,
184−enforce policies, rewrite tool input, inject context the model should see, log
185−stuff, and so on.
186−
187−**Matched against**: the tool name (e.g. `bash`, `edit`, `write`,
188−`mcp_github_create_pull_request`).
189−
190−> [!NOTE]
191−> Event names are case insensitive and snake-caseable, so `PreToolUse`,
192−> `pretooluse`, `PRETOOLUSE`, `pre_tool_use`, and `PRE_TOOL_USE` all work.
193−
194−**Scope**: `PreToolUse` only fires on the **top-level agent's** tool calls.
195−Sub-agents (the `agent` task tool, `agentic_fetch`, etc.) run without hook
196−interception so a single delegated turn doesn't trigger your hook N times. The
197−outer sub-agent tool call itself _is_ hooked, so policy like "never let the
198−agent spawn sub-agents" still works.
199−
200−Hooks are keyed by event name. Only `command` is required, and you can omit
201−`matcher` to match all tools.
202−
203−## Building Hooks
204−
205−When a hook fires, Crush:
206−
207−1. Filters hooks whose `matcher` regex matches the tool name (no matcher = match
208− all).
209−2. Deduplicates by `command` (identical commands run once).
210−3. Runs all matching hooks **in parallel** through Crush's embedded POSIX
211− shell (see [Execution model](#execution-model)).
212−4. Waits for all to finish (or time out), then aggregates results **in config
213− order**: deny wins over allow, allow wins over none; `updated_input` patches
214− shallow-merge in order.
215−5. Applies the result **before** permission checks. If the aggregated decision
216− is `deny`, the tool call is blocked and you never see a permission prompt
217− for it. If it's `allow`, Crush treats that as affirmative pre-approval and
218− also skips the prompt. Silence (no decision) falls through to the normal
219− permission flow.
220−
221−Note that you can omit `matcher` and match in your shell script instead,
222−however you'll incur some additional overhead as Crush will still parse and
223−run each hook.
224−
225−### Input
226−
227−Each hook receives data two ways: environment variables and stdin (as JSON).
228−Environment variables are typically easier to work with, with JSON being
229−available when input is more complex.
230−
231−#### Environment Variables
232−
233−The available environment variables are:
234−
235−| Variable | Description |
236−| ---------------------------- | ---------------------------------------------- |
237−| `CRUSH` | Always `1` when running under Crush. |
238−| `AGENT` | Always `crush`. |
239−| `AI_AGENT` | Always `crush`. |
240−| `CRUSH_EVENT` | The hook event name (e.g. `PreToolUse`). |
241−| `CRUSH_TOOL_NAME` | The tool being called (e.g. `bash`). |
242−| `CRUSH_SESSION_ID` | Current session ID. |
243−| `CRUSH_CWD` | Working directory. |
244−| `CRUSH_PROJECT_DIR` | Project root directory. |
245−| `CRUSH_TOOL_INPUT_COMMAND` | For `bash` calls: the shell command being run. |
246−| `CRUSH_TOOL_INPUT_FILE_PATH` | For file tools: the target file path. |
247−
248−The `CRUSH`, `AGENT`, and `AI_AGENT` markers are also set by the `bash`
249−tool, so a script can detect "am I running under Crush?" the same way in
250−either context.
251−
252−#### JSON
253−
254−Standard input provides the full context as JSON:
255−
256−```jsonc
257−{
258− "event": "PreToolUse", // Hook event name
259− "session_id": "313909e", // Current session ID
260− "cwd": "/home/user/project", // Working directory
261− "tool_name": "bash", // The tool being called
262− "tool_input": { "command": "rm -rf /" }, // The tool's input
263−}
264−```
265−
266−Note that `tool_input` field contains the raw JSON the model sent to the tool.
267−
268−To parse the stdin JSON in your hook script, read from stdin and use a tool like
269−`jq`:
270−
271−```bash
272−#!/usr/bin/env bash
273−read -r input
274−tool_name=$(echo "$input" | jq -r '.tool_name')
275−command=$(echo "$input" | jq -r '.tool_input.command // empty')
276−```
277−
278−You can also use tools like Python:
279−
280−```python
281−#!/usr/bin/env python3
282−import json, sys
283−
284−data = json.load(sys.stdin)
285−tool_name = data.get("tool_name", "")
286−command = data.get("tool_input", {}).get("command", "")
287−```
288−
289−### Output
290−
291−Hooks communicate back to Crush via **exit code** and `stdout`/`stderr`. The
292−simplest way to do this is to return an error code and print additional context
293−to stderr. For example:
294−
295−```bash
296−# Here, error code 2 blocks the tool, using stderr as the reason:
297−if some_bad_condition; then
298− echo "Blocked: reason here" >&2
299− exit 2
300−fi
301−```
302−
303−| Exit Code | Meaning |
304−| --------- | ---------------------------------------------------------------- |
305−| 0 | Success. Stdout is parsed as JSON (see fields below). |
306−| 2 | **Block the tool.** Stderr is used as the deny reason (no JSON). |
307−| 49 | **Halt the turn.** Stderr is used as the halt reason (no JSON). |
308−| Other | Non-blocking error. Logged and ignored — the tool call proceeds. |
309−
310−The difference between exit 2 and exit 49:
311−
312−- **Exit 2** blocks the current tool call. The agent sees the error and can try
313− something else.
314−- **Exit 49** halts the whole turn. The agent doesn't get to respond further;
315− the user takes over. Use this when something is wrong enough that the agent
316− shouldn't keep trying. 49 sits in an empty slice of the exit-code space —
317− between the generic-error range (1-30), the BSD `sysexits.h` range (64-78),
318− and the killed-by-signal range (128+) — so it can't be hit by accident.
319−
320−That said, if you need more control, or if you need to rewrite input, you can
321−use JSON on stdout. Exit 0 and print a JSON object to provide context, update
322−the input, or still deny/halt with a reason:
323−
324−```jsonc
325−{
326− "version": 1, // Output envelope version. Optional; defaults to 1.
327− "decision": "allow", // "allow", "deny", or null. Omit for no opinion.
328− "halt": false, // If true, halts the turn entirely.
329− "reason": "LGTM", // Shown when denying or halting.
330− "context": "Scrubbed secrets", // String or array of strings. Appended to what the model sees.
331− "updated_input": { "command": "…" }, // Shallow-merged into the tool's input before execution.
332−}
333−```
334−
335−`version` is an optional integer at the top of the envelope. It defaults to `1`
336−if omitted. Unknown higher versions are still parsed; the field exists so the
337−envelope can evolve without a compatibility shim.
338−
339−`decision: "allow"` is **affirmative**: it pre-approves the tool call and
340−bypasses the permission prompt entirely. Silence (no `decision`, or
341−`decision: null`) means "no opinion" — the tool still goes through the
342−normal permission flow. Use `"allow"` when you want to auto-approve; omit it
343−when you only want to inject context or rewrite input without also vouching
344−for the call.
345−
346−`updated_input` is a shallow-merge patch. Keys you include overwrite matching
347−keys in `tool_input`; keys you don't include are preserved. If the model called
348−`bash` with `{"command": "npm test", "timeout": 60000}` and your hook returns
349−`{"updated_input": {"command": "bun test"}}`, the tool runs with
350−`{"command": "bun test", "timeout": 60000}` — the timeout isn't dropped. The
351−merge is shallow: nested objects are replaced wholesale, not deep-merged.
352−
353−`halt: true` stops the turn entirely. The agent doesn't get to respond further;
354−the user takes over. The exit-code shorthand is `exit 49` with stderr as the
355−reason.
356−
357−`context` accepts either a string or an array of strings. Use the string form
358−for a single observation; use the array form when a hook produces multiple
359−distinct notes and you'd rather not concatenate them by hand. Empty strings and
360−empty array entries are dropped.
361−
362−Here's a full shell script that produces this JSON:
363−
364−```bash
365−#!/usr/bin/env bash
366−# Example: rewrite a bash command using RTK
367−
368−read -r input
369−original_cmd=$(echo "$input" | jq -r '.tool_input.command')
370−rewritten=$(secret-scrubber rewrite "$original_cmd")
371−
372−cat <<EOF
373−{
374− "decision": "allow",
375− "context": "Scrubbed secrets",
376− "updated_input": {"command": "$rewritten"}
377−}
378−EOF
379−```
380−
381−### Multiple Hooks
382−
383−Hooks run in parallel, but their results compose in config order. Whichever hook
384−finishes first doesn't get to "win" by virtue of timing; composition is
385−deterministic based on the order hooks appear in `crush.json`.
386−
387−When multiple hooks match the same tool call:
388−
389−- If **any** hook denies, the tool call is blocked. `reason` values are
390− concatenated in config order (newline-separated).
391−- If **any** hook halts, the turn ends after the tool call is blocked.
392−- If no hook denies or halts but at least one allows, the tool call proceeds
393− **and the permission prompt is skipped**.
394−- `context` values are concatenated in config order. Strings and arrays compose
395− uniformly — each string becomes one entry, and array entries are flattened in.
396−- `updated_input` patches shallow-merge in config order against the original
397− tool input. Later hooks override earlier ones on colliding keys. If denied or
398− halted, `updated_input` patches are ignored.
399−
400−### Timeouts
401−
402−If a hook exceeds its timeout, Crush cancels its context and treats the
403−result as a non-blocking error so the tool call proceeds. The default
404−timeout is 30 seconds. Shebang-dispatched subprocesses are killed through
405−`exec.CommandContext`; in-process hooks get a short grace period to yield
406−and are then abandoned (the agent moves on regardless). Long-running work
407−should honor context cancellation or run out-of-process via a shebang.
408−
409−## Examples
410−
411−### Block destructive commands
412−
413−Prevent the agent from running `rm -rf` in bash:
414−
415−```json
416−{
417− "hooks": {
418− "PreToolUse": [
419− {
420− "matcher": "^bash$",
421− "command": "./hooks/no-rm-rf.sh"
422− }
423− ]
424− }
425−}
426−```
427−
428−`hooks/no-rm-rf.sh`:
429−
430−```bash
431−#!/usr/bin/env bash
432−# Block rm -rf commands in the bash tool. Otherwise stay silent so the
433−# normal permission flow runs.
434−
435−if echo "$CRUSH_TOOL_INPUT_COMMAND" | grep -qE 'rm\s+-(rf|fr)\s+/'; then
436− echo "Refusing to run rm -rf against root" >&2
437− exit 2
438−fi
439−
440−exit 0
441−```
442−
443−### Auto-approve read-only tools
444−
445−Skip the permission prompt for tools that can't change anything. The hook
446−returns `decision: "allow"`, which tells Crush to pre-approve the call:
447−
448−```jsonc
449−{
450− "hooks": {
451− "PreToolUse": [
452− {
453− "matcher": "^(view|ls|grep|glob)$",
454− "command": "echo '{\"decision\":\"allow\"}'",
455− },
456− ],
457− },
458−}
459−```
460−
461−No script file needed — the command is inline. Every `view`/`ls`/`grep`/`glob`
462−call now runs without prompting. Add the `bash` tool to this list at your own
463−risk; consider a more targeted allowlist instead:
464−
465−```bash
466−#!/usr/bin/env bash
467−# hooks/safe-bash.sh — auto-approve read-only bash commands.
468−
469−case "$CRUSH_TOOL_INPUT_COMMAND" in
470− ls*|cat*|grep*|rg*|echo*|pwd*)
471− echo '{"decision":"allow"}'
472− ;;
473− *)
474− # Silent — fall through to the normal permission prompt.
475− exit 0
476− ;;
477−esac
478−```
479−
480−### Inject context into file writes
481−
482−Add a reminder to the model whenever it writes a Go file:
483−
484−```json
485−{
486− "hooks": {
487− "PreToolUse": [
488− {
489− "matcher": "^(edit|write|multiedit)$",
490− "command": "./hooks/go-context.sh"
491− }
492− ]
493− }
494−}
495−```
496−
497−`hooks/go-context.sh`:
498−
499−```bash
500−#!/usr/bin/env bash
501−# Remind the model about Go formatting when editing .go files.
502−# Emit context only; stay silent on `decision` so the normal permission
503−# prompt still runs for edits/writes.
504−
505−if [[ "$CRUSH_TOOL_INPUT_FILE_PATH" == *.go ]]; then
506− echo '{"context": "Remember: run gofumpt after editing Go files."}'
507−else
508− echo '{}'
509−fi
510−```
511−
512−### Block all MCP tools
513−
514−The `command` can be inline. This one-liner matches all MCP tools and blocks
515−them:
516−
517−```jsonc
518−{ "matcher": "^mcp_", "command": "echo 'MCP tools are disabled' >&2; exit 2" }
519−```
520−
521−### Log every tool call
522−
523−With no `matcher` this fires for every tool. It exits 0 with no stdout so the
524−tool call always proceeds.
525−
526−```jsonc
527−{ "command": "echo \"$(date -Iseconds) $CRUSH_TOOL_NAME\" >> ./tools.log" }
528−```
529−
530−### A real-world Example:
531−
532−For a more practical example, see [`rtk-rewrite.sh`](./examples/rtk-rewrite.sh),
533−which demonstrates how to rewrite tool input using
534−[RTK](https://github.com/rtk-ai/rtk) to save tokens.
535−
536−### Using other languages
537−
538−Hooks aren't limited to shell scripts: any executable works. Here's the same
539−"block rm -rf" example in some other languages.
540−
541−#### Lua
542−
543−`{"matcher": "^bash$", "command": "lua ./hooks/no-rm-rf.lua"}`
544−
545−```lua
546−local input = io.read("*a")
547−local tool_input = input:match('"command":"(.-)"') or ""
548−
549−if tool_input:match("rm%s+%-[rf][rf]%s+/") then
550− io.stderr:write("Refusing to run rm -rf against root\n")
551− os.exit(2)
552−end
553−```
554−
555−#### JavaScript
556−
557−`{"matcher": "^bash$", "command": "node ./hooks/no-rm-rf.js"}`
558−
559−```js
560−let input = "";
561−process.stdin.on("data", (chunk) => (input += chunk));
562−process.stdin.on("end", () => {
563− const { tool_input: toolInput } = JSON.parse(input);
564−
565− if (/rm\s+-[rf]{2}\s+\//.test(toolInput.command)) {
566− process.stderr.write("Refusing to run rm -rf against root\n");
567− process.exit(2);
568− }
569−});
570−```
571−
572−---
573−
574−## Claude Code compatibility
575−
576−Crush hooks are broadly compatible with [Claude Code
577−hooks](https://docs.claude.com/en/docs/claude-code/hooks): the config shape,
578−stdin payload, output envelope, and exit codes line up so most Claude Code
579−hooks run under Crush unchanged. This document covers the Crush-specific API
580−only — anything not documented here isn't guaranteed to work.
581−
582−One intentional divergence: Crush treats `updated_input` as a shallow-merge
583−patch against the original `tool_input` rather than a full replacement. Keys
584−you omit are preserved. See [Output](#output) for details.
585−
586−---
587−
588−## Reference
589−
590−This is the official reference of the narrative above. If prose and this section
591−disagree, the prose should be presumed canonical for intent, while this section
592−is canonical for shape.
593−
594−Both the stdin payload and the output envelope have **common fields** that apply
595−to every event and **per-event fields** that only some events recognize. When an
596−event doesn't understand a field, it's ignored.
597−
598−### Hook config
599−
600−Each entry under a `hooks.<EventName>` array:
601−
602−```jsonc
603−{
604− // string. Optional. Friendly display name shown in the TUI. Falls back to
605− // command when omitted.
606− "name": "no-rm-rf",
607−
608− // string. Optional. Regex tested against the tool name. Omit to match all.
609− "matcher": "^bash$",
610−
611− // string. Required. Shell command to run.
612− "command": "./hooks/my-hook.sh",
613−
614− // number. Optional. Seconds before the hook is killed. Defaults to 30.
615− "timeout": 10,
616−}
617−```
618−
619−### Stdin payload (common)
620−
621−Present in every hook event:
622−
623−```jsonc
624−{
625− // string. Hook event name.
626− "event": "PreToolUse",
627−
628− // string. Current session ID.
629− "session_id": "313909e",
630−
631− // string. Working directory when invoked.
632− "cwd": "/home/user/project",
633−}
634−```
635−
636−### Stdin payload — PreToolUse
637−
638−Extends the common payload:
639−
640−```jsonc
641−{
642− // ...common fields...
643−
644− // string. The tool being called.
645− "tool_name": "bash",
646−
647− // object. Raw JSON input the model sent to the tool. Shape is per-tool.
648− "tool_input": {
649− "command": "npm test",
650− },
651−}
652−```
653−
654−### Output envelope (common)
655−
656−Fields a hook may print to stdout on exit 0. All are optional and apply to every
657−event:
658−
659−```jsonc
660−{
661− // number. Defaults to 1. Unknown higher values still parse; exists for
662− // forward-compat.
663− "version": 1,
664−
665− // boolean. If true, ends the turn entirely. User takes over.
666− "halt": false,
667−
668− // string. Shown when denying (to the model) or halting (to the model and
669− // user).
670− "reason": "not allowed",
671−
672− // string | string[]. Appended to what the model sees. Empty entries are
673− // dropped.
674− "context": "Rewrote with RTK",
675−}
676−```
677−
678−### Output envelope — PreToolUse
679−
680−Extends the common envelope:
681−
682−```jsonc
683−{
684− // ...common fields...
685−
686− // "allow" | "deny" | null. null/omitted = no opinion, the tool still goes
687− // through the normal permission prompt. "allow" is affirmative: pre-approves
688− // the tool call and bypasses the prompt. "deny" blocks the call; the model
689− // sees the error and may try something else.
690− "decision": "allow",
691−
692− // object. Shallow-merge patch against tool_input. Nested objects are
693− // replaced wholesale, not deep-merged.
694− "updated_input": {
695− "command": "bun test",
696− },
697−}
698−```
699−
700−### Exit codes
701−
702−| Code | Meaning |
703−| ----- | ------------------------------------------------------------------------ |
704−| `0` | Success. Stdout is parsed as the output envelope. |
705−| `2` | Block this tool call. Stderr becomes the deny reason. Stdout is ignored. |
706−| `49` | Halt the whole turn. Stderr becomes the halt reason. Stdout is ignored. |
707−| other | Non-blocking error. Logged and ignored; the tool call proceeds. |
708−
709−Exit `2` only applies to events that can block something. On events where
710−there's nothing to block, it's treated as a non-blocking error.
711−
712−### Aggregation
713−
714−When multiple hooks match the same event, results compose in **config order**.
715−
716−Universal rules:
717−
718−1. `halt` is sticky: if any hook halts, the turn ends.
719−2. `reason` values concatenate with `\n` in config order. Halt-only hooks
720− without a deny still contribute their reason.
721−3. `context` values concatenate with `\n` in config order. String entries and
722− array entries flatten uniformly.
723−
724−PreToolUse-specific rules:
725−
726−4. `decision` precedence: `deny` > `allow` > `null`. First deny determines the
727− outcome; subsequent allows don't override. If the final aggregated decision
728− is `allow`, Crush pre-approves the tool call and skips the permission
729− prompt. If it's `null` (no hook allowed), the tool goes through the normal
730− permission flow.
731−5. `updated_input` patches shallow-merge sequentially against the original
732− `tool_input`. Later patches override earlier ones on colliding keys. Patches
733− are **ignored** if the final decision is deny or halt.
734−
735−### Environment variables
736−
737−See [Environment Variables](#environment-variables) above for the full list.
738−
739−---
740−
741−## Whatcha think?
742−
743−We'd love to hear your thoughts on this project. Need help? We gotchu. You can
744−find us on:
745−
746−- [Twitter](https://twitter.com/charmcli)
747−- [Slack](https://charm.land/slack)
748−- [Discord](https://charm.land/discord)
749−- [The Fediverse](https://mastodon.social/@charmcli)
750−- [Bluesky](https://bsky.app/profile/charm.land)
751−
752−---
753−
754−Part of [Charm](https://charm.land).
755−
756−<a href="https://charm.land/"><img alt="The Charm logo" width="400" src="https://stuff.charm.sh/charm-banner-softy.jpg" /></a>
757−
758−<!--prettier-ignore-->
759−Charm热爱开源 • Charm loves open source
docs/hooks/examples/rtk-rewrite.shdeleted−60
@@ -1,60 +0,0 @@
1−#!/usr/bin/env bash
2−
3−# RTK hook for Crush
4−# This hook rewrites bash commands to use rtk for token savings.
5−#
6−# https://github.com/rtk-ai/rtk
7−#
8−# Requires: rtk >= 0.23.0, jq
9−#
10−# All rewrite logic lives in `rtk rewrite`, which is the single source of
11−# truth. To add or change rewrite rules, edit the Rust registry, not this
12−# file.
13−#
14−# Exit code protocol for `rtk rewrite`:
15−# 0 + stdout Rewrite found → allow with updated input
16−# 1 No RTK equivalent → pass through unchanged
17−# 2 Deny rule matched → pass through
18−
19−set -euo pipefail
20−
21−if ! command -v jq &>/dev/null; then
22− echo "[rtk] WARNING: jq is not installed. Install: https://jqlang.github.io/jq/download/" >&2
23− exit 0
24−fi
25−
26−if ! command -v rtk &>/dev/null; then
27− echo "[rtk] WARNING: rtk is not installed. Install: https://github.com/rtk-ai/rtk#installation" >&2
28− exit 0
29−fi
30−
31−# Version guard: rtk rewrite requires >= 0.23.0.
32−RTK_VERSION=$(rtk --version 2>/dev/null | grep -oE '[0-9]+\.[0-9]+\.[0-9]+' | head -1)
33−if [ -n "$RTK_VERSION" ]; then
34− MAJOR=$(echo "$RTK_VERSION" | cut -d. -f1)
35− MINOR=$(echo "$RTK_VERSION" | cut -d. -f2)
36− if [ "$MAJOR" -eq 0 ] && [ "$MINOR" -lt 23 ]; then
37− echo "[rtk] WARNING: rtk $RTK_VERSION is too old (need >= 0.23.0). Upgrade: cargo install rtk" >&2
38− exit 0
39− fi
40−fi
41−
42−CMD="${CRUSH_TOOL_INPUT_COMMAND:-}"
43−if [ -z "$CMD" ]; then
44− exit 0
45−fi
46−
47−REWRITTEN=$(rtk rewrite "$CMD" 2>/dev/null) && EXIT_CODE=0 || EXIT_CODE=$?
48−
49−case $EXIT_CODE in
50−0 | 3)
51− # Rewrite found. If identical, the command already uses rtk.
52− [ "$CMD" = "$REWRITTEN" ] && exit 0
53− jq -n --arg cmd "$REWRITTEN" \
54− '{decision: "allow", updated_input: ({command: $cmd} | tostring)}'
55− ;;
56−*)
57− # No rewrite (1), deny (2), or unexpected — pass through.
58− exit 0
59− ;;
60−esac
flake.lockdeleted−60
@@ -1,60 +0,0 @@
1−{
2− "nodes": {
3− "flake-utils": {
4− "inputs": {
5− "systems": "systems"
6− },
7− "locked": {
8− "lastModified": 1731533236,
9− "narHash": "sha256-l0KFg5HjrsfsO/JpG+r7fRrqm12kzFHyUHqHCVpMMbI=",
10− "owner": "numtide",
11− "repo": "flake-utils",
12− "rev": "11707dc2f618dd54ca8739b309ec4fc024de578b",
13− "type": "github"
14− },
15− "original": {
16− "owner": "numtide",
17− "repo": "flake-utils",
18− "type": "github"
19− }
20− },
21− "nixpkgs": {
22− "locked": {
23− "lastModified": 1782964654,
24− "narHash": "sha256-oqyac50OyRdni5ZK9H7ZuAJoR3LzgsOdUcbBlUsk9lg=",
25− "owner": "NixOS",
26− "repo": "nixpkgs",
27− "rev": "3130a1cf8f7c794ea5a4760c3fa4c745d64ec269",
28− "type": "github"
29− },
30− "original": {
31− "owner": "NixOS",
32− "repo": "nixpkgs",
33− "type": "github"
34− }
35− },
36− "root": {
37− "inputs": {
38− "flake-utils": "flake-utils",
39− "nixpkgs": "nixpkgs"
40− }
41− },
42− "systems": {
43− "locked": {
44− "lastModified": 1681028828,
45− "narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
46− "owner": "nix-systems",
47− "repo": "default",
48− "rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
49− "type": "github"
50− },
51− "original": {
52− "owner": "nix-systems",
53− "repo": "default",
54− "type": "github"
55− }
56− }
57− },
58− "root": "root",
59− "version": 7
60−}
flake.nixdeleted−75
@@ -1,75 +0,0 @@
1−{
2− description = "Crush development environment";
3−
4− inputs = {
5− nixpkgs.url = "github:NixOS/nixpkgs";
6− flake-utils.url = "github:numtide/flake-utils";
7− };
8−
9− outputs = {
10− self,
11− nixpkgs,
12− flake-utils,
13− }:
14− flake-utils.lib.eachDefaultSystem (
15− system: let
16− pkgs = nixpkgs.legacyPackages.${system};
17− version = "devel";
18− in {
19− packages.default = pkgs.buildGoModule {
20− pname = "crush";
21− inherit version;
22−
23− src = ./.;
24−
25− vendorHash = null;
26−
27− # Match the Go toolchain used in the dev shell.
28− go = pkgs.go_1_26;
29−
30− env.CGO_ENABLED = 0;
31−
32− ldflags = [
33− "-s"
34− "-w"
35− "-X github.com/charmbracelet/crush/internal/version.Version=${version}"
36− ];
37−
38− # The test suite requires network access and external tools.
39− doCheck = false;
40−
41− meta = {
42− description = "Terminal-based AI coding assistant";
43− homepage = "https://github.com/charmbracelet/crush";
44− license = pkgs.lib.licenses.mit;
45− mainProgram = "crush";
46− };
47− };
48−
49− devShells.default = pkgs.mkShell {
50− buildInputs = with pkgs; [
51− # Go toolchain
52− go_1_26
53−
54− # Development tools
55− gopls # Go language server
56− golangci-lint # Linter
57− gofumpt # Formatter (stricter than gofmt)
58− go-task # Task runner
59− delve # Go debugger
60−
61− # Additional tools
62− git # Version control
63− gh # GitHub CLI
64− svu # Semantic version utility
65− sqlc # SQL code generator
66− ];
67−
68− shellHook = ''
69− # Set Go environment variables
70− export CGO_ENABLED=0
71− '';
72− };
73− }
74− );
75−}
go.mod+111−151
@@ -1,159 +1,135 @@
11module github.com/charmbracelet/crush
22
3−go 1.26.4
3+go 1.25.5
44
55require (
6− charm.land/bubbles/v2 v2.1.1
7− charm.land/bubbletea/v2 v2.0.8
8− charm.land/catwalk v0.49.0
9− charm.land/fang/v2 v2.0.1
10− charm.land/fantasy v0.35.0
11− charm.land/glamour/v2 v2.0.1
12− charm.land/lipgloss/v2 v2.0.5
13− charm.land/log/v2 v2.0.0
6+ charm.land/bubbles/v2 v2.0.0-rc.1
7+ charm.land/bubbletea/v2 v2.0.0-rc.2.0.20251216153312-819e2e89c62e
8+ charm.land/fantasy v0.5.5
9+ charm.land/glamour/v2 v2.0.0-20251110203732-69649f93d3b1
10+ charm.land/lipgloss/v2 v2.0.0-beta.3.0.20251205162909-7869489d8971
11+ charm.land/log/v2 v2.0.0-20251110204020-529bb77f35da
1412 charm.land/x/vcr v0.1.1
1513 github.com/JohannesKaufmann/html-to-markdown v1.6.0
1614 github.com/MakeNowJust/heredoc v1.0.0
17− github.com/Microsoft/go-winio v0.6.2
18− github.com/PuerkitoBio/goquery v1.12.0
19− github.com/alecthomas/chroma/v2 v2.27.0
20− github.com/aymanbagabas/go-udiff v0.4.1
21− github.com/bmatcuk/doublestar/v4 v4.10.0
15+ github.com/PuerkitoBio/goquery v1.11.0
16+ github.com/alecthomas/chroma/v2 v2.20.0
17+ github.com/atotto/clipboard v0.1.4
18+ github.com/aymanbagabas/go-udiff v0.3.1
19+ github.com/bmatcuk/doublestar/v4 v4.9.1
2220 github.com/charlievieth/fastwalk v1.0.14
23− github.com/charmbracelet/colorprofile v0.4.3
24− github.com/charmbracelet/openai-go v0.0.0-20260617131321-5e4b9c18c4be
25− github.com/charmbracelet/ultraviolet v0.0.0-20260703014108-f5a850f9c2b7
26− github.com/charmbracelet/x/ansi v0.11.7
27− github.com/charmbracelet/x/editor v0.2.0
21+ github.com/charmbracelet/catwalk v0.11.2
22+ github.com/charmbracelet/colorprofile v0.4.1
23+ github.com/charmbracelet/fang v0.4.4
24+ github.com/charmbracelet/ultraviolet v0.0.0-20251212194010-b927aa605560
25+ github.com/charmbracelet/x/ansi v0.11.3
2826 github.com/charmbracelet/x/etag v0.2.0
29− github.com/charmbracelet/x/exp/charmtone v0.0.0-20260527151214-009e6338d40d
27+ github.com/charmbracelet/x/exp/charmtone v0.0.0-20250708181618-a60a724ba6c3
3028 github.com/charmbracelet/x/exp/golden v0.0.0-20250806222409-83e3a29d542f
3129 github.com/charmbracelet/x/exp/ordered v0.1.0
32− github.com/charmbracelet/x/exp/slice v0.0.0-20260622092256-25656177ba8e
33− github.com/charmbracelet/x/exp/strings v0.1.0
34− github.com/charmbracelet/x/powernap v0.1.6
30+ github.com/charmbracelet/x/exp/slice v0.0.0-20251201173703-9f73bfd934ff
31+ github.com/charmbracelet/x/powernap v0.0.0-20251015113943-25f979b54ad4
3532 github.com/charmbracelet/x/term v0.2.2
36− github.com/clipperhouse/displaywidth v0.11.0
37− github.com/clipperhouse/uax29/v2 v2.7.0
3833 github.com/denisbrodbeck/machineid v1.0.1
39− github.com/disintegration/imaging v1.6.2
40− github.com/dustin/go-humanize v1.0.1
41− github.com/gen2brain/beeep v0.11.2
42− github.com/go-git/go-git/v5 v5.19.1
34+ github.com/disintegration/imageorient v0.0.0-20180920195336-8147d86e83ec
4335 github.com/google/uuid v1.6.0
44− github.com/invopop/jsonschema v0.14.0
45− github.com/itchyny/gojq v0.12.19
36+ github.com/invopop/jsonschema v0.13.0
4637 github.com/joho/godotenv v1.5.1
47− github.com/jordanella/go-ansi-paintbrush v0.0.0-20240728195301-b7ad996ecf3d
48− github.com/lucasb-eyer/go-colorful v1.4.0
49− github.com/mattn/go-isatty v0.0.22
50− github.com/modelcontextprotocol/go-sdk v1.6.1
51− github.com/ncruces/go-sqlite3 v0.35.1
38+ github.com/lucasb-eyer/go-colorful v1.3.0
39+ github.com/modelcontextprotocol/go-sdk v1.1.0
40+ github.com/muesli/termenv v0.16.0
41+ github.com/ncruces/go-sqlite3 v0.30.3
42+ github.com/nfnt/resize v0.0.0-20180221191011-83c6a9932646
5243 github.com/nxadm/tail v1.4.11
44+ github.com/openai/openai-go/v2 v2.7.1
5345 github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c
54− github.com/posthog/posthog-go v1.17.5
55− github.com/pressly/goose/v3 v3.27.2
56− github.com/qjebbs/go-jsons v1.0.0-alpha.6
46+ github.com/posthog/posthog-go v1.6.13
47+ github.com/pressly/goose/v3 v3.26.0
48+ github.com/qjebbs/go-jsons v1.0.0-alpha.4
5749 github.com/rivo/uniseg v0.4.7
58− github.com/sahilm/fuzzy v0.1.3
59− github.com/sourcegraph/jsonrpc2 v0.2.1
50+ github.com/sabhiram/go-gitignore v0.0.0-20210923224102-525f6e181f06
51+ github.com/sahilm/fuzzy v0.1.1
6052 github.com/spf13/cobra v1.10.2
53+ github.com/srwiley/oksvg v0.0.0-20221011165216-be6e8873101c
54+ github.com/srwiley/rasterx v0.0.0-20220730225603-2ab79fcdd4ef
6155 github.com/stretchr/testify v1.11.1
62− github.com/swaggo/http-swagger/v2 v2.0.2
63− github.com/swaggo/swag v1.16.6
64− github.com/tidwall/gjson v1.19.0
56+ github.com/tidwall/gjson v1.18.0
6557 github.com/tidwall/sjson v1.2.5
66− github.com/zeebo/xxh3 v1.1.0
67− go.uber.org/goleak v1.3.0
68− golang.design/x/clipboard v0.8.0
69− golang.org/x/net v0.56.0
70− golang.org/x/sync v0.21.0
71− golang.org/x/sys v0.46.0
72− golang.org/x/text v0.38.0
58+ github.com/zeebo/xxh3 v1.0.2
59+ golang.org/x/mod v0.31.0
60+ golang.org/x/net v0.48.0
61+ golang.org/x/sync v0.19.0
62+ golang.org/x/text v0.32.0
7363 gopkg.in/natefinch/lumberjack.v2 v2.2.1
74− gopkg.in/yaml.v3 v3.0.1
75− modernc.org/sqlite v1.53.0
7664 mvdan.cc/sh/moreinterp v0.0.0-20250902163504-3cf4fd5717a5
77− mvdan.cc/sh/v3 v3.13.1
65+ mvdan.cc/sh/v3 v3.12.1-0.20250902163504-3cf4fd5717a5
7866)
7967
8068require (
81− cloud.google.com/go v0.123.0 // indirect
82− cloud.google.com/go/auth v0.20.0 // indirect
69+ cloud.google.com/go v0.116.0 // indirect
70+ cloud.google.com/go/auth v0.17.0 // indirect
8371 cloud.google.com/go/auth/oauth2adapt v0.2.8 // indirect
84− cloud.google.com/go/compute/metadata v0.9.0 // indirect
85− git.sr.ht/~jackmordaunt/go-toast v1.1.2 // indirect
72+ cloud.google.com/go/compute/metadata v0.8.0 // indirect
8673 github.com/Azure/azure-sdk-for-go/sdk/azcore v1.17.0 // indirect
8774 github.com/Azure/azure-sdk-for-go/sdk/internal v1.10.0 // indirect
88− github.com/KyleBanks/depth v1.2.1 // indirect
89− github.com/andybalholm/brotli v1.2.1 // indirect
75+ github.com/RealAlexandreAI/json-repair v0.0.14 // indirect
9076 github.com/andybalholm/cascadia v1.3.3 // indirect
91− github.com/atotto/clipboard v0.1.4 // indirect
92− github.com/aws/aws-sdk-go-v2 v1.42.0 // indirect
93− github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.13 // indirect
94− github.com/aws/aws-sdk-go-v2/config v1.32.25 // indirect
95− github.com/aws/aws-sdk-go-v2/credentials v1.19.24 // indirect
96− github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.29 // indirect
97− github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.29 // indirect
98− github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.29 // indirect
99− github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.30 // indirect
100− github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.12 // indirect
101− github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.29 // indirect
102− github.com/aws/aws-sdk-go-v2/service/signin v1.2.0 // indirect
103− github.com/aws/aws-sdk-go-v2/service/sso v1.31.3 // indirect
104− github.com/aws/aws-sdk-go-v2/service/ssooidc v1.36.6 // indirect
105− github.com/aws/aws-sdk-go-v2/service/sts v1.43.3 // indirect
106− github.com/aws/smithy-go v1.27.3 // indirect
77+ github.com/aws/aws-sdk-go-v2 v1.41.0 // indirect
78+ github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.6.3 // indirect
79+ github.com/aws/aws-sdk-go-v2/config v1.27.27 // indirect
80+ github.com/aws/aws-sdk-go-v2/credentials v1.17.27 // indirect
81+ github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.16.11 // indirect
82+ github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.15 // indirect
83+ github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.15 // indirect
84+ github.com/aws/aws-sdk-go-v2/internal/ini v1.8.0 // indirect
85+ github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.11.3 // indirect
86+ github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.11.17 // indirect
87+ github.com/aws/aws-sdk-go-v2/service/sso v1.22.4 // indirect
88+ github.com/aws/aws-sdk-go-v2/service/ssooidc v1.26.4 // indirect
89+ github.com/aws/aws-sdk-go-v2/service/sts v1.30.3 // indirect
90+ github.com/aws/smithy-go v1.24.0 // indirect
91+ github.com/aymanbagabas/go-osc52/v2 v2.0.1 // indirect
10792 github.com/aymerick/douceur v0.2.0 // indirect
10893 github.com/bahlo/generic-list-go v0.2.0 // indirect
109− github.com/buger/jsonparser v1.1.2 // indirect
110− github.com/cespare/xxhash/v2 v2.3.0 // indirect
111− github.com/charmbracelet/anthropic-sdk-go v0.0.0-20260223140439-63879b0b8dab // indirect
94+ github.com/buger/jsonparser v1.1.1 // indirect
95+ github.com/charmbracelet/anthropic-sdk-go v0.0.0-20251024181547-21d6f3d9a904 // indirect
96+ github.com/charmbracelet/x/json v0.2.0 // indirect
11297 github.com/charmbracelet/x/termios v0.1.1 // indirect
11398 github.com/charmbracelet/x/windows v0.2.2 // indirect
114− github.com/cyphar/filepath-securejoin v0.6.1 // indirect
115− github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect
116− github.com/dlclark/regexp2/v2 v2.2.1 // indirect
117− github.com/ebitengine/purego v0.10.1 // indirect
118− github.com/esiqveland/notify v0.13.3 // indirect
119− github.com/felixge/httpsnoop v1.1.0 // indirect
99+ github.com/clipperhouse/displaywidth v0.6.1 // indirect
100+ github.com/clipperhouse/stringish v0.1.1 // indirect
101+ github.com/clipperhouse/uax29/v2 v2.3.0 // indirect
102+ github.com/davecgh/go-spew v1.1.1 // indirect
103+ github.com/disintegration/gift v1.1.2 // indirect
104+ github.com/dlclark/regexp2 v1.11.5 // indirect
105+ github.com/dustin/go-humanize v1.0.1 // indirect
106+ github.com/felixge/httpsnoop v1.0.4 // indirect
120107 github.com/fsnotify/fsnotify v1.9.0 // indirect
121− github.com/go-git/gcfg v1.5.1-0.20230307220236-3a3c6141e376 // indirect
122− github.com/go-git/go-billy/v5 v5.9.0 // indirect
123− github.com/go-json-experiment/json v0.0.0-20260623181947-01eb4420fa68 // indirect
108+ github.com/go-json-experiment/json v0.0.0-20251027170946-4849db3c2f7e // indirect
124109 github.com/go-logfmt/logfmt v0.6.0 // indirect
125110 github.com/go-logr/logr v1.4.3 // indirect
126111 github.com/go-logr/stdr v1.2.2 // indirect
127− github.com/go-ole/go-ole v1.3.0 // indirect
128− github.com/go-openapi/jsonpointer v0.19.5 // indirect
129− github.com/go-openapi/jsonreference v0.20.0 // indirect
130− github.com/go-openapi/spec v0.20.6 // indirect
131− github.com/go-openapi/swag v0.19.15 // indirect
132− github.com/go-viper/mapstructure/v2 v2.5.0 // indirect
133− github.com/goccy/go-json v0.10.5 // indirect
134− github.com/goccy/go-yaml v1.19.2 // indirect
135− github.com/godbus/dbus/v5 v5.2.2 // indirect
136− github.com/golang/freetype v0.0.0-20170609003504-e2365dfdc4a0 // indirect
112+ github.com/go-viper/mapstructure/v2 v2.4.0 // indirect
113+ github.com/goccy/go-yaml v1.19.0 // indirect
137114 github.com/google/go-cmp v0.7.0 // indirect
138− github.com/google/jsonschema-go v0.4.3 // indirect
115+ github.com/google/jsonschema-go v0.3.0 // indirect
139116 github.com/google/s2a-go v0.1.9 // indirect
140− github.com/googleapis/enterprise-certificate-proxy v0.3.17 // indirect
141− github.com/googleapis/gax-go/v2 v2.22.0 // indirect
117+ github.com/googleapis/enterprise-certificate-proxy v0.3.6 // indirect
118+ github.com/googleapis/gax-go/v2 v2.15.0 // indirect
142119 github.com/gorilla/css v1.0.1 // indirect
143120 github.com/gorilla/websocket v1.5.3 // indirect
144121 github.com/hashicorp/golang-lru/v2 v2.0.7 // indirect
145122 github.com/inconshreveable/mousetrap v1.1.0 // indirect
146− github.com/itchyny/timefmt-go v0.1.8 // indirect
147− github.com/jackmordaunt/icns/v3 v3.0.1 // indirect
148− github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99 // indirect
149− github.com/josharian/intern v1.0.0 // indirect
150− github.com/kaptinlin/jsonpointer v0.4.26 // indirect
151− github.com/kaptinlin/jsonschema v0.9.2 // indirect
152− github.com/klauspost/compress v1.18.6 // indirect
153− github.com/klauspost/cpuid/v2 v2.3.0 // indirect
123+ github.com/kaptinlin/go-i18n v0.2.2 // indirect
124+ github.com/kaptinlin/jsonpointer v0.4.8 // indirect
125+ github.com/kaptinlin/jsonschema v0.6.5 // indirect
126+ github.com/kaptinlin/messageformat-go v0.4.7 // indirect
127+ github.com/klauspost/compress v1.18.0 // indirect
128+ github.com/klauspost/cpuid/v2 v2.0.9 // indirect
154129 github.com/klauspost/pgzip v1.2.6 // indirect
155130 github.com/mailru/easyjson v0.7.7 // indirect
156− github.com/mattn/go-runewidth v0.0.24 // indirect
131+ github.com/mattn/go-isatty v0.0.20 // indirect
132+ github.com/mattn/go-runewidth v0.0.19 // indirect
157133 github.com/mfridman/interpolate v0.0.2 // indirect
158134 github.com/microcosm-cc/bluemonday v1.0.27 // indirect
159135 github.com/mitchellh/mapstructure v1.5.0 // indirect
@@ -162,60 +138,44 @@ require (
162138 github.com/muesli/mango-cobra v1.2.0 // indirect
163139 github.com/muesli/mango-pflag v0.1.0 // indirect
164140 github.com/muesli/roff v0.1.0 // indirect
165− github.com/ncruces/go-sqlite3-wasm/v3 v3.1.35302 // indirect
166− github.com/ncruces/go-strftime v1.0.0 // indirect
167141 github.com/ncruces/julianday v1.0.0 // indirect
168− github.com/nfnt/resize v0.0.0-20180221191011-83c6a9932646 // indirect
169− github.com/pb33f/ordered-map/v2 v2.3.1 // indirect
170− github.com/pierrec/lz4/v4 v4.1.26 // indirect
171− github.com/pjbgf/sha1cd v0.6.0 // indirect
172− github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
173− github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec // indirect
174− github.com/segmentio/asm v1.2.1 // indirect
175− github.com/segmentio/encoding v0.5.4 // indirect
176− github.com/sergeymakinen/go-bmp v1.0.0 // indirect
177− github.com/sergeymakinen/go-ico v1.0.0-beta.0 // indirect
142+ github.com/pierrec/lz4/v4 v4.1.22 // indirect
143+ github.com/pmezard/go-difflib v1.0.0 // indirect
144+ github.com/sergi/go-diff v1.3.2-0.20230802210424-5b0b94c5c0d3 // indirect
178145 github.com/sethvargo/go-retry v0.3.0 // indirect
146+ github.com/sourcegraph/jsonrpc2 v0.2.1 // indirect
179147 github.com/spf13/pflag v1.0.9 // indirect
180− github.com/swaggo/files/v2 v2.0.0 // indirect
181− github.com/tadvi/systray v0.0.0-20190226123456-11a2b8fa57af // indirect
148+ github.com/tetratelabs/wazero v1.10.1 // indirect
182149 github.com/tidwall/match v1.1.1 // indirect
183150 github.com/tidwall/pretty v1.2.1 // indirect
184151 github.com/u-root/u-root v0.14.1-0.20250807200646-5e7721023dc7 // indirect
185152 github.com/u-root/uio v0.0.0-20240224005618-d2acac8f3701 // indirect
153+ github.com/wk8/go-ordered-map/v2 v2.1.8 // indirect
186154 github.com/xo/terminfo v0.0.0-20220910002029-abceb7e1c41e // indirect
187155 github.com/yosida95/uritemplate/v3 v3.0.2 // indirect
188156 github.com/yuin/goldmark v1.7.8 // indirect
189157 github.com/yuin/goldmark-emoji v1.0.5 // indirect
190− go.opentelemetry.io/auto/sdk v1.2.1 // indirect
191− go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.69.0 // indirect
192− go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.69.0 // indirect
193− go.opentelemetry.io/otel v1.44.0 // indirect
194− go.opentelemetry.io/otel/metric v1.44.0 // indirect
195− go.opentelemetry.io/otel/trace v1.44.0 // indirect
158+ go.opentelemetry.io/auto/sdk v1.1.0 // indirect
159+ go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.61.0 // indirect
160+ go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.61.0 // indirect
161+ go.opentelemetry.io/otel v1.37.0 // indirect
162+ go.opentelemetry.io/otel/metric v1.37.0 // indirect
163+ go.opentelemetry.io/otel/trace v1.37.0 // indirect
196164 go.uber.org/multierr v1.11.0 // indirect
197165 go.yaml.in/yaml/v4 v4.0.0-rc.3 // indirect
198− golang.design/x/x11 v0.2.0 // indirect
199− golang.org/x/crypto v0.53.0 // indirect
200− golang.org/x/exp v0.0.0-20260410095643-746e56fc9e2f // indirect
201− golang.org/x/exp/shiny v0.0.0-20250606033433-dcc06ee1d476 // indirect
202− golang.org/x/image v0.43.0 // indirect
203− golang.org/x/mobile v0.0.0-20250606033058-a2a15c67f36f // indirect
204− golang.org/x/mod v0.36.0 // indirect
205− golang.org/x/oauth2 v0.36.0 // indirect
206− golang.org/x/term v0.44.0 // indirect
207− golang.org/x/time v0.15.0 // indirect
208− golang.org/x/tools v0.45.0 // indirect
209− google.golang.org/api v0.286.0 // indirect
210− google.golang.org/genai v1.62.0 // indirect
211− google.golang.org/genproto/googleapis/rpc v0.0.0-20260622175928-b703f567277d // indirect
212− google.golang.org/grpc v1.81.1 // indirect
213− google.golang.org/protobuf v1.36.11 // indirect
166+ golang.org/x/crypto v0.46.0 // indirect
167+ golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b // indirect
168+ golang.org/x/image v0.27.0 // indirect
169+ golang.org/x/oauth2 v0.34.0 // indirect
170+ golang.org/x/sys v0.39.0 // indirect
171+ golang.org/x/term v0.38.0 // indirect
172+ golang.org/x/time v0.12.0 // indirect
173+ google.golang.org/api v0.239.0 // indirect
174+ google.golang.org/genai v1.39.0 // indirect
175+ google.golang.org/genproto/googleapis/rpc v0.0.0-20250603155806-513f23925822 // indirect
176+ google.golang.org/grpc v1.74.2 // indirect
177+ google.golang.org/protobuf v1.36.10 // indirect
214178 gopkg.in/dnaeon/go-vcr.v4 v4.0.6-0.20251110073552-01de4eb40290 // indirect
215179 gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7 // indirect
216− gopkg.in/warnings.v0 v0.1.2 // indirect
217− gopkg.in/yaml.v2 v2.4.0 // indirect
218− modernc.org/libc v1.73.4 // indirect
219− modernc.org/mathutil v1.7.1 // indirect
220− modernc.org/memory v1.11.0 // indirect
180+ gopkg.in/yaml.v3 v3.0.1 // indirect
221181)
go.sum+225−351
@@ -1,31 +1,25 @@
1−charm.land/bubbles/v2 v2.1.1 h1:7r55WzBxpo/R3z98hGmY7KKPd3ET6vsf0Fb9sDHOV60=
2−charm.land/bubbles/v2 v2.1.1/go.mod h1:GE6M31gaWZVXzGw73OeuTTgy4lX+OtkH0E5ymnNsHxo=
3−charm.land/bubbletea/v2 v2.0.8 h1:SxTJMhCAI3lbPmy4SgX5LWZ24AdINr4I6UEqzZvYJuY=
4−charm.land/bubbletea/v2 v2.0.8/go.mod h1:2SkdgoTXluXJHOUwAoRlRXF/28vklb1rFl6GcgV1/ss=
5−charm.land/catwalk v0.49.0 h1:pXcHh9H76VvwGqPYMZhJe5vRqMLpzGsv0anJArKw70g=
6−charm.land/catwalk v0.49.0/go.mod h1:bw6/oiChsa9Fkr8LgYn84KrbbJY2z1+m7Jmlmmv3B2A=
7−charm.land/fang/v2 v2.0.1 h1:zQCM8JQJ1JnQX/66B5jlCYBUxL2as5JXQZ2KJ6EL0mY=
8−charm.land/fang/v2 v2.0.1/go.mod h1:S1GmkpcvK+OB5w9caywUnJcsMew45Ot8FXqoz8ALrII=
9−charm.land/fantasy v0.35.0 h1:iFES7cnt3/o20T01+y2PDkHj5dHEWRFQH0vSXYzV8xo=
10−charm.land/fantasy v0.35.0/go.mod h1:rUqUhunz+c6k66L0hHd51CrXB3SSzPNKkwBrzIe6XnY=
11−charm.land/glamour/v2 v2.0.1 h1:xl+r00A4aJWU0z8fgwKd9fQQ4rsphqGUzuEiXZP5n+c=
12−charm.land/glamour/v2 v2.0.1/go.mod h1:jo9z8XqVKPeEFMVdvCRLGk++RyJ3CdUwgNr7EvXLw3k=
13−charm.land/lipgloss/v2 v2.0.5 h1:kbNxgeeUOYv5J0YdpxFjfvf3dFvqH8Aci4zB6xqFtrY=
14−charm.land/lipgloss/v2 v2.0.5/go.mod h1:9oqhxt4yxIMe6q5A4kHr44DremZk7J9UNh74GlWa5nc=
15−charm.land/log/v2 v2.0.0 h1:SY3Cey7ipx86/MBXQHwsguOT6X1exT94mmJRdzTNs+s=
16−charm.land/log/v2 v2.0.0/go.mod h1:c3cZSRqm20qUVVAR1WmS/7ab8bgha3C6G7DjPcaVZz0=
1+charm.land/bubbles/v2 v2.0.0-rc.1 h1:EiIFVAc3Zi/yY86td+79mPhHR7AqZ1OxF+6ztpOCRaM=
2+charm.land/bubbles/v2 v2.0.0-rc.1/go.mod h1:5AbN6cEd/47gkEf8TgiQ2O3RZ5QxMS14l9W+7F9fPC4=
3+charm.land/bubbletea/v2 v2.0.0-rc.2.0.20251216153312-819e2e89c62e h1:tXwTmgGpwZT7ParKF5xbEQBVjM2e1uKhKi/GpfU3mYQ=
4+charm.land/bubbletea/v2 v2.0.0-rc.2.0.20251216153312-819e2e89c62e/go.mod h1:pDM18flq3Z4njKZPA3zCvyVSSIJbMcoqlE82BdGUtL8=
5+charm.land/fantasy v0.5.5 h1:Dw/NBLH9HLX/ouCz604RXGD7BYzr0lT56/B4ylMGZjg=
6+charm.land/fantasy v0.5.5/go.mod h1:QyJLJGissYdBifvitgAxFcYhNACSr0G1faC75CIESUk=
7+charm.land/glamour/v2 v2.0.0-20251110203732-69649f93d3b1 h1:9q4+yyU7105T3OrOx0csMyKnw89yMSijJ+rVld/Z2ek=
8+charm.land/glamour/v2 v2.0.0-20251110203732-69649f93d3b1/go.mod h1:J3kVhY6oHXZq5f+8vC3hmDO95fEvbqj3z7xDwxrfzU8=
9+charm.land/lipgloss/v2 v2.0.0-beta.3.0.20251205162909-7869489d8971 h1:xZFcNsJMiIDbFtWRyDmkKNk1sjojfaom4Zoe0cyH/8c=
10+charm.land/lipgloss/v2 v2.0.0-beta.3.0.20251205162909-7869489d8971/go.mod h1:i61Y3FmdbcBNSKa+pKB3DaE4uVQmBLMs/xlvRyHcXAE=
11+charm.land/log/v2 v2.0.0-20251110204020-529bb77f35da h1:vZa/Ow0uLclpfaDY0ubjzE+B0eLQqi2zanmpeALanow=
12+charm.land/log/v2 v2.0.0-20251110204020-529bb77f35da/go.mod h1:Tj12StbPc4GwksDF6XwhC9wdXouinIVxRGKKmmmzdSU=
1713charm.land/x/vcr v0.1.1 h1:PXCFMUG0rPtyk35rhfzYCJEduOzWXCIbrXTFq4OF/9Q=
1814charm.land/x/vcr v0.1.1/go.mod h1:eByq2gqzWvcct/8XE2XO5KznoWEBiXH56+y2gphbltM=
19−cloud.google.com/go v0.123.0 h1:2NAUJwPR47q+E35uaJeYoNhuNEM9kM8SjgRgdeOJUSE=
20−cloud.google.com/go v0.123.0/go.mod h1:xBoMV08QcqUGuPW65Qfm1o9Y4zKZBpGS+7bImXLTAZU=
21−cloud.google.com/go/auth v0.20.0 h1:kXTssoVb4azsVDoUiF8KvxAqrsQcQtB53DcSgta74CA=
22−cloud.google.com/go/auth v0.20.0/go.mod h1:942/yi/itH1SsmpyrbnTMDgGfdy2BUqIKyd0cyYLc5Q=
15+cloud.google.com/go v0.116.0 h1:B3fRrSDkLRt5qSHWe40ERJvhvnQwdZiHu0bJOpldweE=
16+cloud.google.com/go v0.116.0/go.mod h1:cEPSRWPzZEswwdr9BxE6ChEn01dWlTaF05LiC2Xs70U=
17+cloud.google.com/go/auth v0.17.0 h1:74yCm7hCj2rUyyAocqnFzsAYXgJhrG26XCFimrc/Kz4=
18+cloud.google.com/go/auth v0.17.0/go.mod h1:6wv/t5/6rOPAX4fJiRjKkJCvswLwdet7G8+UGXt7nCQ=
2319cloud.google.com/go/auth/oauth2adapt v0.2.8 h1:keo8NaayQZ6wimpNSmW5OPc283g65QNIiLpZnkHRbnc=
2420cloud.google.com/go/auth/oauth2adapt v0.2.8/go.mod h1:XQ9y31RkqZCcwJWNSx2Xvric3RrU88hAYYbjDWYDL+c=
25−cloud.google.com/go/compute/metadata v0.9.0 h1:pDUj4QMoPejqq20dK0Pg2N4yG9zIkYGdBtwLoEkH9Zs=
26−cloud.google.com/go/compute/metadata v0.9.0/go.mod h1:E0bWwX5wTnLPedCKqk3pJmVgCBSM6qQI1yTBdEb3C10=
27−git.sr.ht/~jackmordaunt/go-toast v1.1.2 h1:/yrfI55LRt1M7H1vkaw+NaH1+L1CDxrqDltwm5euVuE=
28−git.sr.ht/~jackmordaunt/go-toast v1.1.2/go.mod h1:jA4OqHKTQ4AFBdwrSnwnskUIIS3HYzlJSgdzCKqfavo=
21+cloud.google.com/go/compute/metadata v0.8.0 h1:HxMRIbao8w17ZX6wBnjhcDkW6lTFpgcaobyVfZWqRLA=
22+cloud.google.com/go/compute/metadata v0.8.0/go.mod h1:sYOGTp851OV9bOFJ9CH7elVvyzopvWQFNNghtDQ/Biw=
2923github.com/Azure/azure-sdk-for-go/sdk/azcore v1.17.0 h1:g0EZJwz7xkXQiZAI5xi9f3WWFYBlX1CPTrR+NDToRkQ=
3024github.com/Azure/azure-sdk-for-go/sdk/azcore v1.17.0/go.mod h1:XCW7KnZet0Opnr7HccfUw1PLc4CjHqpcaxW8DHklNkQ=
3125github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.7.0 h1:tfLQ34V6F7tVSwoTf/4lH5sE0o6eCJuNDTmH09nDpbc=
@@ -36,154 +30,127 @@ github.com/AzureAD/microsoft-authentication-library-for-go v1.2.2 h1:XHOnouVk1mx
3630github.com/AzureAD/microsoft-authentication-library-for-go v1.2.2/go.mod h1:wP83P5OoQ5p6ip3ScPr0BAq0BvuPAvacpEuSzyouqAI=
3731github.com/JohannesKaufmann/html-to-markdown v1.6.0 h1:04VXMiE50YYfCfLboJCLcgqF5x+rHJnb1ssNmqpLH/k=
3832github.com/JohannesKaufmann/html-to-markdown v1.6.0/go.mod h1:NUI78lGg/a7vpEJTz/0uOcYMaibytE4BUOQS8k78yPQ=
39−github.com/KyleBanks/depth v1.2.1 h1:5h8fQADFrWtarTdtDudMmGsC7GPbOAu6RVB3ffsVFHc=
40−github.com/KyleBanks/depth v1.2.1/go.mod h1:jzSb9d0L43HxTQfT+oSA1EEp2q+ne2uh6XgeJcm8brE=
4133github.com/MakeNowJust/heredoc v1.0.0 h1:cXCdzVdstXyiTqTvfqk9SDHpKNjxuom+DOlyEeQ4pzQ=
4234github.com/MakeNowJust/heredoc v1.0.0/go.mod h1:mG5amYoWBHf8vpLOuehzbGGw0EHxpZZ6lCpQ4fNJ8LE=
43−github.com/Microsoft/go-winio v0.6.2 h1:F2VQgta7ecxGYO8k3ZZz3RS8fVIXVxONVUPlNERoyfY=
44−github.com/Microsoft/go-winio v0.6.2/go.mod h1:yd8OoFMLzJbo9gZq8j5qaps8bJ9aShtEA8Ipt1oGCvU=
4535github.com/PuerkitoBio/goquery v1.9.2/go.mod h1:GHPCaP0ODyyxqcNoFGYlAprUFH81NuRPd0GX3Zu2Mvk=
46−github.com/PuerkitoBio/goquery v1.12.0 h1:pAcL4g3WRXekcB9AU/y1mbKez2dbY2AajVhtkO8RIBo=
47−github.com/PuerkitoBio/goquery v1.12.0/go.mod h1:802ej+gV2y7bbIhOIoPY5sT183ZW0YFofScC4q/hIpQ=
36+github.com/PuerkitoBio/goquery v1.11.0 h1:jZ7pwMQXIITcUXNH83LLk+txlaEy6NVOfTuP43xxfqw=
37+github.com/PuerkitoBio/goquery v1.11.0/go.mod h1:wQHgxUOU3JGuj3oD/QFfxUdlzW6xPHfqyHre6VMY4DQ=
38+github.com/RealAlexandreAI/json-repair v0.0.14 h1:4kTqotVonDVTio5n2yweRUELVcNe2x518wl0bCsw0t0=
39+github.com/RealAlexandreAI/json-repair v0.0.14/go.mod h1:GKJi5borR78O8c7HCVbgqjhoiVibZ6hJldxbc6dGrAI=
4840github.com/alecthomas/assert/v2 v2.11.0 h1:2Q9r3ki8+JYXvGsDyBXwH3LcJ+WK5D0gc5E8vS6K3D0=
4941github.com/alecthomas/assert/v2 v2.11.0/go.mod h1:Bze95FyfUr7x34QZrjL+XP+0qgp/zg8yS+TtBj1WA3k=
50−github.com/alecthomas/chroma/v2 v2.27.0 h1:FodwmyOBgJULFYmDqibcp9pvfDLWdtPRh9v/r5BXYZs=
51−github.com/alecthomas/chroma/v2 v2.27.0/go.mod h1:NjJ3ciIgrqBNeIkWZ4e46nseoLDslxU1LmfCoL+wcY8=
52−github.com/alecthomas/repr v0.5.2 h1:SU73FTI9D1P5UNtvseffFSGmdNci/O6RsqzeXJtP0Qs=
53−github.com/alecthomas/repr v0.5.2/go.mod h1:Fr0507jx4eOXV7AlPV6AVZLYrLIuIeSOWtW57eE/O/4=
54−github.com/andybalholm/brotli v1.2.1 h1:R+f5xP285VArJDRgowrfb9DqL18yVK0gKAW/F+eTWro=
55−github.com/andybalholm/brotli v1.2.1/go.mod h1:rzTDkvFWvIrjDXZHkuS16NPggd91W3kUSvPlQ1pLaKY=
42+github.com/alecthomas/chroma/v2 v2.20.0 h1:sfIHpxPyR07/Oylvmcai3X/exDlE8+FA820NTz+9sGw=
43+github.com/alecthomas/chroma/v2 v2.20.0/go.mod h1:e7tViK0xh/Nf4BYHl00ycY6rV7b8iXBksI9E359yNmA=
44+github.com/alecthomas/repr v0.5.1 h1:E3G4t2QbHTSNpPKBgMTln5KLkZHLOcU7r37J4pXBuIg=
45+github.com/alecthomas/repr v0.5.1/go.mod h1:Fr0507jx4eOXV7AlPV6AVZLYrLIuIeSOWtW57eE/O/4=
5646github.com/andybalholm/cascadia v1.3.2/go.mod h1:7gtRlve5FxPPgIgX36uWBX58OdBsSS6lUvCFb+h7KvU=
5747github.com/andybalholm/cascadia v1.3.3 h1:AG2YHrzJIm4BZ19iwJ/DAua6Btl3IwJX+VI4kktS1LM=
5848github.com/andybalholm/cascadia v1.3.3/go.mod h1:xNd9bqTn98Ln4DwST8/nG+H0yuB8Hmgu1YHNnWw0GeA=
5949github.com/atotto/clipboard v0.1.4 h1:EH0zSVneZPSuFR11BlR9YppQTVDbh5+16AmcJi4g1z4=
6050github.com/atotto/clipboard v0.1.4/go.mod h1:ZY9tmq7sm5xIbd9bOK4onWV4S6X0u6GY7Vn0Yu86PYI=
61−github.com/aws/aws-sdk-go-v2 v1.42.0 h1:XvXMJTkFQtpBKIWZnmr9ZEOc2InWM2yldjXEJ/bymhA=
62−github.com/aws/aws-sdk-go-v2 v1.42.0/go.mod h1:27+ACypSLljLAEKsCYOmrjKh83vuTRkuAe9Uv/3A4bg=
63−github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.13 h1:p1BBrg/Hhp6uK7zpejeI8QFXHJeC/mynzi04Sl03k9g=
64−github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.13/go.mod h1:8cIfkE9MDhkRZGpQ22aV6/lkYeYSozpz16Smrs5x4Ls=
65−github.com/aws/aws-sdk-go-v2/config v1.32.25 h1:ACCejvStYoilgwrfegSt5ZntCbPrk52qfwyNcnl3omM=
66−github.com/aws/aws-sdk-go-v2/config v1.32.25/go.mod h1:LJyU8sDRbXUxFn8xMJIGP+v9QYYwveNLI8a/giAOiAs=
67−github.com/aws/aws-sdk-go-v2/credentials v1.19.24 h1:2hQqYCV9yqyePQ9o6dCrZc/zO8U3TwPr9mIKlZnPu/I=
68−github.com/aws/aws-sdk-go-v2/credentials v1.19.24/go.mod h1:IDwpACtwqHLISdzfwUUNq4P9DsB/h5BLg4FwJPNfqFY=
69−github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.29 h1:r6qZHbT+wxgWO/e9vYNUEtg7lv5+UN3pRqKhLXvnArg=
70−github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.29/go.mod h1:QRnaRcTVGKPGRy8w78HMQtKUGRYcnMZAANATkeVA6Mo=
71−github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.29 h1:f3vKqSo13fhTYb+JEcXwXefZQE26I1FB5eTSniU67ko=
72−github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.29/go.mod h1:MzoLFUArKGpGD+ukmPiTPG1X5x4o6M2kq4v2dr1FiEc=
73−github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.29 h1:RdwIf/CuUsvJX3RgJagbOyotl/cxoLY4xviKuE7p2GY=
74−github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.29/go.mod h1:71wt8W2EgswdZy9Mf9KNnzxZ3TiZlv4caKghPktDOkA=
75−github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.30 h1:VTGy885W5DKBxWRUJbym9hytNaYzsyaPkCHGRRMAOhU=
76−github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.30/go.mod h1:AS0HycUvJRFvTt613AYDOgO2jzw+00cVSMny8XB3yMY=
77−github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.12 h1:ZD2+BSw9vFsNlKYIasSNt3uDbjqqXIBcM13UJv/Lx2k=
78−github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.12/go.mod h1:Ms4zlcVBbXbiP7EVLhl+lgjvA/a7YphqQ3Ih3174EmI=
79−github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.29 h1:DRebniUGZ2MqiiIVmQJ04vIXr918hubdHMnarSLEWyU=
80−github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.29/go.mod h1:LfRkPCD8YHDM2E5eTkos2UpwYeZnBcVarTa8L59bJHA=
81−github.com/aws/aws-sdk-go-v2/service/signin v1.2.0 h1:3nXpRcFwRCW8n7HgO2QGy0Dc20eQNfBuUemGQhpF8m8=
82−github.com/aws/aws-sdk-go-v2/service/signin v1.2.0/go.mod h1:LxYujSTLPRlp2vTtcUO/+1ilrew8ytt6SvQyOgejzFQ=
83−github.com/aws/aws-sdk-go-v2/service/sso v1.31.3 h1:ey1XLTYXb9PcLt4535632o5kCGXNXEhNb620Dqwuylo=
84−github.com/aws/aws-sdk-go-v2/service/sso v1.31.3/go.mod h1:Lk7PlmoTYryQmyBG0EXqj5BcUbj3whXdU2s3yGI3EAc=
85−github.com/aws/aws-sdk-go-v2/service/ssooidc v1.36.6 h1:yLr03zQE/5Eu5l3QU0Si+xMbLMbSDF2YXsigqXngs6g=
86−github.com/aws/aws-sdk-go-v2/service/ssooidc v1.36.6/go.mod h1:Q5N6icH+KJZDLh+ESNwzdv6cZ6vLFF/egy3IOxWhmz4=
87−github.com/aws/aws-sdk-go-v2/service/sts v1.43.3 h1:VrIhKRCSK1umelSgB9RghvA9RTUYeQffyAS5ApXehNI=
88−github.com/aws/aws-sdk-go-v2/service/sts v1.43.3/go.mod h1:r8wkDOuLaaMFqFiYAb8dGY2A3gJCOujMc6CFOVC4Zhc=
89−github.com/aws/smithy-go v1.27.3 h1:F3Zb497UhhskkfpJmfkXswyo+t0sh9OTBnIHjogWbVY=
90−github.com/aws/smithy-go v1.27.3/go.mod h1:YE2RhdIuDbA5E5bTdciG9KrW3+TiEONeUWCqxX9i1Fc=
91−github.com/aymanbagabas/go-udiff v0.4.1 h1:OEIrQ8maEeDBXQDoGCbbTTXYJMYRCRO1fnodZ12Gv5o=
92−github.com/aymanbagabas/go-udiff v0.4.1/go.mod h1:0L9PGwj20lrtmEMeyw4WKJ/TMyDtvAoK9bf2u/mNo3w=
51+github.com/aws/aws-sdk-go-v2 v1.41.0 h1:tNvqh1s+v0vFYdA1xq0aOJH+Y5cRyZ5upu6roPgPKd4=
52+github.com/aws/aws-sdk-go-v2 v1.41.0/go.mod h1:MayyLB8y+buD9hZqkCW3kX1AKq07Y5pXxtgB+rRFhz0=
53+github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.6.3 h1:tW1/Rkad38LA15X4UQtjXZXNKsCgkshC3EbmcUmghTg=
54+github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.6.3/go.mod h1:UbnqO+zjqk3uIt9yCACHJ9IVNhyhOCnYk8yA19SAWrM=
55+github.com/aws/aws-sdk-go-v2/config v1.27.27 h1:HdqgGt1OAP0HkEDDShEl0oSYa9ZZBSOmKpdpsDMdO90=
56+github.com/aws/aws-sdk-go-v2/config v1.27.27/go.mod h1:MVYamCg76dFNINkZFu4n4RjDixhVr51HLj4ErWzrVwg=
57+github.com/aws/aws-sdk-go-v2/credentials v1.17.27 h1:2raNba6gr2IfA0eqqiP2XiQ0UVOpGPgDSi0I9iAP+UI=
58+github.com/aws/aws-sdk-go-v2/credentials v1.17.27/go.mod h1:gniiwbGahQByxan6YjQUMcW4Aov6bLC3m+evgcoN4r4=
59+github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.16.11 h1:KreluoV8FZDEtI6Co2xuNk/UqI9iwMrOx/87PBNIKqw=
60+github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.16.11/go.mod h1:SeSUYBLsMYFoRvHE0Tjvn7kbxaUhl75CJi1sbfhMxkU=
61+github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.15 h1:SoNJ4RlFEQEbtDcCEt+QG56MY4fm4W8rYirAmq+/DdU=
62+github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.15/go.mod h1:U9ke74k1n2bf+RIgoX1SXFed1HLs51OgUSs+Ph0KJP8=
63+github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.15 h1:C6WHdGnTDIYETAm5iErQUiVNsclNx9qbJVPIt03B6bI=
64+github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.15/go.mod h1:ZQLZqhcu+JhSrA9/NXRm8SkDvsycE+JkV3WGY41e+IM=
65+github.com/aws/aws-sdk-go-v2/internal/ini v1.8.0 h1:hT8rVHwugYE2lEfdFE0QWVo81lF7jMrYJVDWI+f+VxU=
66+github.com/aws/aws-sdk-go-v2/internal/ini v1.8.0/go.mod h1:8tu/lYfQfFe6IGnaOdrpVgEL2IrrDOf6/m9RQum4NkY=
67+github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.11.3 h1:dT3MqvGhSoaIhRseqw2I0yH81l7wiR2vjs57O51EAm8=
68+github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.11.3/go.mod h1:GlAeCkHwugxdHaueRr4nhPuY+WW+gR8UjlcqzPr1SPI=
69+github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.11.17 h1:HGErhhrxZlQ044RiM+WdoZxp0p+EGM62y3L6pwA4olE=
70+github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.11.17/go.mod h1:RkZEx4l0EHYDJpWppMJ3nD9wZJAa8/0lq9aVC+r2UII=
71+github.com/aws/aws-sdk-go-v2/service/sso v1.22.4 h1:BXx0ZIxvrJdSgSvKTZ+yRBeSqqgPM89VPlulEcl37tM=
72+github.com/aws/aws-sdk-go-v2/service/sso v1.22.4/go.mod h1:ooyCOXjvJEsUw7x+ZDHeISPMhtwI3ZCB7ggFMcFfWLU=
73+github.com/aws/aws-sdk-go-v2/service/ssooidc v1.26.4 h1:yiwVzJW2ZxZTurVbYWA7QOrAaCYQR72t0wrSBfoesUE=
74+github.com/aws/aws-sdk-go-v2/service/ssooidc v1.26.4/go.mod h1:0oxfLkpz3rQ/CHlx5hB7H69YUpFiI1tql6Q6Ne+1bCw=
75+github.com/aws/aws-sdk-go-v2/service/sts v1.30.3 h1:ZsDKRLXGWHk8WdtyYMoGNO7bTudrvuKpDKgMVRlepGE=
76+github.com/aws/aws-sdk-go-v2/service/sts v1.30.3/go.mod h1:zwySh8fpFyXp9yOr/KVzxOl8SRqgf/IDw5aUt9UKFcQ=
77+github.com/aws/smithy-go v1.24.0 h1:LpilSUItNPFr1eY85RYgTIg5eIEPtvFbskaFcmmIUnk=
78+github.com/aws/smithy-go v1.24.0/go.mod h1:LEj2LM3rBRQJxPZTB4KuzZkaZYnZPnvgIhb4pu07mx0=
79+github.com/aymanbagabas/go-osc52/v2 v2.0.1 h1:HwpRHbFMcZLEVr42D4p7XBqjyuxQH5SMiErDT4WkJ2k=
80+github.com/aymanbagabas/go-osc52/v2 v2.0.1/go.mod h1:uYgXzlJ7ZpABp8OJ+exZzJJhRNQ2ASbcXHWsFqH8hp8=
81+github.com/aymanbagabas/go-udiff v0.3.1 h1:LV+qyBQ2pqe0u42ZsUEtPiCaUoqgA9gYRDs3vj1nolY=
82+github.com/aymanbagabas/go-udiff v0.3.1/go.mod h1:G0fsKmG+P6ylD0r6N/KgQD/nWzgfnl8ZBcNLgcbrw8E=
9383github.com/aymerick/douceur v0.2.0 h1:Mv+mAeH1Q+n9Fr+oyamOlAkUNPWPlA8PPGR0QAaYuPk=
9484github.com/aymerick/douceur v0.2.0/go.mod h1:wlT5vV2O3h55X9m7iVYN0TBM0NH/MmbLnd30/FjWUq4=
9585github.com/bahlo/generic-list-go v0.2.0 h1:5sz/EEAK+ls5wF+NeqDpk5+iNdMDXrh3z3nPnH1Wvgk=
9686github.com/bahlo/generic-list-go v0.2.0/go.mod h1:2KvAjgMlE5NNynlg/5iLrrCCZ2+5xWbdbCW3pNTGyYg=
97−github.com/bmatcuk/doublestar/v4 v4.10.0 h1:zU9WiOla1YA122oLM6i4EXvGW62DvKZVxIe6TYWexEs=
98−github.com/bmatcuk/doublestar/v4 v4.10.0/go.mod h1:xBQ8jztBU6kakFMg+8WGxn0c6z1fTSPVIjEY1Wr7jzc=
99−github.com/buger/jsonparser v1.1.2 h1:frqHqw7otoVbk5M8LlE/L7HTnIq2v9RX6EJ48i9AxJk=
100−github.com/buger/jsonparser v1.1.2/go.mod h1:6RYKKt7H4d4+iWqouImQ9R2FZql3VbhNgx27UK13J/0=
101−github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
102−github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
87+github.com/bmatcuk/doublestar/v4 v4.9.1 h1:X8jg9rRZmJd4yRy7ZeNDRnM+T3ZfHv15JiBJ/avrEXE=
88+github.com/bmatcuk/doublestar/v4 v4.9.1/go.mod h1:xBQ8jztBU6kakFMg+8WGxn0c6z1fTSPVIjEY1Wr7jzc=
89+github.com/buger/jsonparser v1.1.1 h1:2PnMjfWD7wBILjqQbt530v576A/cAbQvEW9gGIpYMUs=
90+github.com/buger/jsonparser v1.1.1/go.mod h1:6RYKKt7H4d4+iWqouImQ9R2FZql3VbhNgx27UK13J/0=
10391github.com/charlievieth/fastwalk v1.0.14 h1:3Eh5uaFGwHZd8EGwTjJnSpBkfwfsak9h6ICgnWlhAyg=
10492github.com/charlievieth/fastwalk v1.0.14/go.mod h1:diVcUreiU1aQ4/Wu3NbxxH4/KYdKpLDojrQ1Bb2KgNY=
105−github.com/charmbracelet/anthropic-sdk-go v0.0.0-20260223140439-63879b0b8dab h1:J7XQLgl9sefgTnTGrmX3xqvp5o6MCiBzEjGv5igAlc4=
106−github.com/charmbracelet/anthropic-sdk-go v0.0.0-20260223140439-63879b0b8dab/go.mod h1:hqlYqR7uPKOKfnNeicUbZp0Ps0GeYFlKYtwh5HGDCx8=
107−github.com/charmbracelet/colorprofile v0.4.3 h1:QPa1IWkYI+AOB+fE+mg/5/4HRMZcaXex9t5KX76i20Q=
108−github.com/charmbracelet/colorprofile v0.4.3/go.mod h1:/zT4BhpD5aGFpqQQqw7a+VtHCzu+zrQtt1zhMt9mR4Q=
109−github.com/charmbracelet/openai-go v0.0.0-20260617131321-5e4b9c18c4be h1:pg+OWlIkk9HOe/8P5J95aKe2wGDzFUiiyFOUpwR30B4=
110−github.com/charmbracelet/openai-go v0.0.0-20260617131321-5e4b9c18c4be/go.mod h1:1DahUaExbUZx/jD+FNT2PKP4L9rLE5+ZBRuI8mZjd/E=
111−github.com/charmbracelet/ultraviolet v0.0.0-20260703014108-f5a850f9c2b7 h1:3FmWoGNWK4STvqg0O0Aeav2T7rodWJAPeF0QpH+8gFw=
112−github.com/charmbracelet/ultraviolet v0.0.0-20260703014108-f5a850f9c2b7/go.mod h1:f/jRa757WUmaOZrbPspXymbg/GnbF+rwe4OLsG7aXYo=
113−github.com/charmbracelet/x/ansi v0.11.7 h1:kzv1kJvjg2S3r9KHo8hDdHFQLEqn4RBCb39dAYC84jI=
114−github.com/charmbracelet/x/ansi v0.11.7/go.mod h1:9qGpnAVYz+8ACONkZBUWPtL7lulP9No6p1epAihUZwQ=
115−github.com/charmbracelet/x/editor v0.2.0 h1:7XLUKtaRaB8jN7bWU2p2UChiySyaAuIfYiIRg8gGWwk=
116−github.com/charmbracelet/x/editor v0.2.0/go.mod h1:p3oQ28TSL3YPd+GKJ1fHWcp+7bVGpedHpXmo0D6t1dY=
93+github.com/charmbracelet/anthropic-sdk-go v0.0.0-20251024181547-21d6f3d9a904 h1:rwLdEpG9wE6kL69KkEKDiWprO8pQOZHZXeod6+9K+mw=
94+github.com/charmbracelet/anthropic-sdk-go v0.0.0-20251024181547-21d6f3d9a904/go.mod h1:8TIYxZxsuCqqeJ0lga/b91tBwrbjoHDC66Sq5t8N2R4=
95+github.com/charmbracelet/catwalk v0.11.2 h1:m+eE7yv/uIrKW95FpFeGDMFrAugotylX89XzpkZwlLk=
96+github.com/charmbracelet/catwalk v0.11.2/go.mod h1:qg+Yl9oaZTkTvRscqbxfttzOFQ4v0pOT5XwC7b5O0NQ=
97+github.com/charmbracelet/colorprofile v0.4.1 h1:a1lO03qTrSIRaK8c3JRxJDZOvhvIeSco3ej+ngLk1kk=
98+github.com/charmbracelet/colorprofile v0.4.1/go.mod h1:U1d9Dljmdf9DLegaJ0nGZNJvoXAhayhmidOdcBwAvKk=
99+github.com/charmbracelet/fang v0.4.4 h1:G4qKxF6or/eTPgmAolwPuRNyuci3hTUGGX1rj1YkHJY=
100+github.com/charmbracelet/fang v0.4.4/go.mod h1:P5/DNb9DddQ0Z0dbc0P3ol4/ix5Po7Ofr2KMBfAqoCo=
101+github.com/charmbracelet/ultraviolet v0.0.0-20251212194010-b927aa605560 h1:j3PW2hypGoPKBy3ooKzW0TFxaxhyHK3NbkLLn4KeRFc=
102+github.com/charmbracelet/ultraviolet v0.0.0-20251212194010-b927aa605560/go.mod h1:VWATWLRwYP06VYCEur7FsNR2B1xAo7Y+xl1PTbd1ePc=
103+github.com/charmbracelet/x/ansi v0.11.3 h1:6DcVaqWI82BBVM/atTyq6yBoRLZFBsnoDoX9GCu2YOI=
104+github.com/charmbracelet/x/ansi v0.11.3/go.mod h1:yI7Zslym9tCJcedxz5+WBq+eUGMJT0bM06Fqy1/Y4dI=
117105github.com/charmbracelet/x/etag v0.2.0 h1:Euj1VkheoHfTYA9y+TCwkeXF/hN8Fb9l4LqZl79pt04=
118106github.com/charmbracelet/x/etag v0.2.0/go.mod h1:C1B7/bsgvzzxpfu0Rabbd+rTHJa5TmC/qgTseCf6DF0=
119−github.com/charmbracelet/x/exp/charmtone v0.0.0-20260527151214-009e6338d40d h1:sMilwx1YIYTrQva6jsB522AoRYAerNaDIKP4ZPtUq0A=
120−github.com/charmbracelet/x/exp/charmtone v0.0.0-20260527151214-009e6338d40d/go.mod h1:nsExn0DGyX0lh9LwLHTn2Gg+hafdzfSXnC+QmEJTZFY=
107+github.com/charmbracelet/x/exp/charmtone v0.0.0-20250708181618-a60a724ba6c3 h1:1xwHZg6eMZ9Wv5TE1UGub6ARubyOd1Lo5kPUI/6VL50=
108+github.com/charmbracelet/x/exp/charmtone v0.0.0-20250708181618-a60a724ba6c3/go.mod h1:T9jr8CzFpjhFVHjNjKwbAD7KwBNyFnj2pntAO7F2zw0=
121109github.com/charmbracelet/x/exp/golden v0.0.0-20250806222409-83e3a29d542f h1:pk6gmGpCE7F3FcjaOEKYriCvpmIN4+6OS/RD0vm4uIA=
122110github.com/charmbracelet/x/exp/golden v0.0.0-20250806222409-83e3a29d542f/go.mod h1:IfZAMTHB6XkZSeXUqriemErjAWCCzT0LwjKFYCZyw0I=
123111github.com/charmbracelet/x/exp/ordered v0.1.0 h1:55/qLwjIh0gL0Vni+QAWk7T/qRVP6sBf+2agPBgnOFE=
124112github.com/charmbracelet/x/exp/ordered v0.1.0/go.mod h1:5UHwmG+is5THxMyCJHNPCn2/ecI07aKNrW+LcResjJ8=
125−github.com/charmbracelet/x/exp/slice v0.0.0-20260622092256-25656177ba8e h1:TerxTCW/3BrnpqKxeouW0cWSjZb7PsVAmtNftRAAFRE=
126−github.com/charmbracelet/x/exp/slice v0.0.0-20260622092256-25656177ba8e/go.mod h1:vqEfX6xzqW1pKKZUUiFOKg0OQ7bCh54Q2vR/tserrRA=
127−github.com/charmbracelet/x/exp/strings v0.1.0 h1:i69S2XI7uG1u4NLGeJPSYU++Nmjvpo9nwd6aoEm7gkA=
128−github.com/charmbracelet/x/exp/strings v0.1.0/go.mod h1:/ehtMPNh9K4odGFkqYJKpIYyePhdp1hLBRvyY4bWkH8=
129−github.com/charmbracelet/x/powernap v0.1.6 h1:tsnQWQVl9arYm5S/tQVXuMJcvnkUNNkXhBWlEBDRNqM=
130−github.com/charmbracelet/x/powernap v0.1.6/go.mod h1:cmdl5zlP5mR8TF2Y68UKc7hdGUDiSJ2+4hk0h04Hsx4=
113+github.com/charmbracelet/x/exp/slice v0.0.0-20251201173703-9f73bfd934ff h1:Uwr+/JS+qnRcO/++xjYEDtW7x+P5E4+4cBiOHTt2Xfk=
114+github.com/charmbracelet/x/exp/slice v0.0.0-20251201173703-9f73bfd934ff/go.mod h1:vqEfX6xzqW1pKKZUUiFOKg0OQ7bCh54Q2vR/tserrRA=
115+github.com/charmbracelet/x/json v0.2.0 h1:DqB+ZGx2h+Z+1s98HOuOyli+i97wsFQIxP2ZQANTPrQ=
116+github.com/charmbracelet/x/json v0.2.0/go.mod h1:opFIflx2YgXgi49xVUu8gEQ21teFAxyMwvOiZhIvWNM=
117+github.com/charmbracelet/x/powernap v0.0.0-20251015113943-25f979b54ad4 h1:i/XilBPYK4L1Yo/mc9FPx0SyJzIsN0y4sj1MWq9Sscc=
118+github.com/charmbracelet/x/powernap v0.0.0-20251015113943-25f979b54ad4/go.mod h1:cmdl5zlP5mR8TF2Y68UKc7hdGUDiSJ2+4hk0h04Hsx4=
131119github.com/charmbracelet/x/term v0.2.2 h1:xVRT/S2ZcKdhhOuSP4t5cLi5o+JxklsoEObBSgfgZRk=
132120github.com/charmbracelet/x/term v0.2.2/go.mod h1:kF8CY5RddLWrsgVwpw4kAa6TESp6EB5y3uxGLeCqzAI=
133121github.com/charmbracelet/x/termios v0.1.1 h1:o3Q2bT8eqzGnGPOYheoYS8eEleT5ZVNYNy8JawjaNZY=
134122github.com/charmbracelet/x/termios v0.1.1/go.mod h1:rB7fnv1TgOPOyyKRJ9o+AsTU/vK5WHJ2ivHeut/Pcwo=
135123github.com/charmbracelet/x/windows v0.2.2 h1:IofanmuvaxnKHuV04sC0eBy/smG6kIKrWG2/jYn2GuM=
136124github.com/charmbracelet/x/windows v0.2.2/go.mod h1:/8XtdKZzedat74NQFn0NGlGL4soHB0YQZrETF96h75k=
137−github.com/clipperhouse/displaywidth v0.11.0 h1:lBc6kY44VFw+TDx4I8opi/EtL9m20WSEFgwIwO+UVM8=
138−github.com/clipperhouse/displaywidth v0.11.0/go.mod h1:bkrFNkf81G8HyVqmKGxsPufD3JhNl3dSqnGhOoSD/o0=
139−github.com/clipperhouse/uax29/v2 v2.7.0 h1:+gs4oBZ2gPfVrKPthwbMzWZDaAFPGYK72F0NJv2v7Vk=
140−github.com/clipperhouse/uax29/v2 v2.7.0/go.mod h1:EFJ2TJMRUaplDxHKj1qAEhCtQPW2tJSwu5BF98AuoVM=
141−github.com/cncf/xds/go v0.0.0-20260202195803-dba9d589def2 h1:aBangftG7EVZoUb69Os8IaYg++6uMOdKK83QtkkvJik=
142−github.com/cncf/xds/go v0.0.0-20260202195803-dba9d589def2/go.mod h1:qwXFYgsP6T7XnJtbKlf1HP8AjxZZyzxMmc+Lq5GjlU4=
125+github.com/clipperhouse/displaywidth v0.6.1 h1:/zMlAezfDzT2xy6acHBzwIfyu2ic0hgkT83UX5EY2gY=
126+github.com/clipperhouse/displaywidth v0.6.1/go.mod h1:R+kHuzaYWFkTm7xoMmK1lFydbci4X2CicfbGstSGg0o=
127+github.com/clipperhouse/stringish v0.1.1 h1:+NSqMOr3GR6k1FdRhhnXrLfztGzuG+VuFDfatpWHKCs=
128+github.com/clipperhouse/stringish v0.1.1/go.mod h1:v/WhFtE1q0ovMta2+m+UbpZ+2/HEXNWYXQgCt4hdOzA=
129+github.com/clipperhouse/uax29/v2 v2.3.0 h1:SNdx9DVUqMoBuBoW3iLOj4FQv3dN5mDtuqwuhIGpJy4=
130+github.com/clipperhouse/uax29/v2 v2.3.0/go.mod h1:Wn1g7MK6OoeDT0vL+Q0SQLDz/KpfsVRgg6W7ihQeh4g=
143131github.com/cpuguy83/go-md2man/v2 v2.0.6/go.mod h1:oOW0eioCTA6cOiMLiUPZOpcVxMig6NIQQ7OS05n1F4g=
144−github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
145132github.com/creack/pty v1.1.24 h1:bJrF4RRfyJnbTJqzRLHzcGaZK1NeM5kTC9jGgovnR1s=
146133github.com/creack/pty v1.1.24/go.mod h1:08sCNb52WyoAwi2QDyzUCTgcvVFhUzewun7wtTfvcwE=
147−github.com/cyphar/filepath-securejoin v0.6.1 h1:5CeZ1jPXEiYt3+Z6zqprSAgSWiggmpVyciv8syjIpVE=
148−github.com/cyphar/filepath-securejoin v0.6.1/go.mod h1:A8hd4EnAeyujCJRrICiOWqjS1AX0a9kM5XL+NwKoYSc=
149134github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
135+github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
150136github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
151−github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc h1:U9qPSI2PIWSS1VwoXQT9A3Wy9MM3WgvqSxFWenqJduM=
152−github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
153137github.com/denisbrodbeck/machineid v1.0.1 h1:geKr9qtkB876mXguW2X6TU4ZynleN6ezuMSRhl4D7AQ=
154138github.com/denisbrodbeck/machineid v1.0.1/go.mod h1:dJUwb7PTidGDeYyUBmXZ2GphQBbjJCrnectwCyxcUSI=
155−github.com/disintegration/imaging v1.6.2 h1:w1LecBlG2Lnp8B3jk5zSuNqd7b4DXhcjwek1ei82L+c=
156−github.com/disintegration/imaging v1.6.2/go.mod h1:44/5580QXChDfwIclfc/PCwrr44amcmDAg8hxG0Ewe4=
157−github.com/dlclark/regexp2/v2 v2.2.1 h1:mf4KkFUj0gJuarK8P+LgiS+Lit7m9N1yAwEfPbee7R0=
158−github.com/dlclark/regexp2/v2 v2.2.1/go.mod h1:avUrQvPaLz2DrFNHJF0taWAFFX2C1GMSSoeiqFjcBmU=
159−github.com/dnaeon/go-vcr v1.2.0 h1:zHCHvJYTMh1N7xnV7zf1m1GPBF9Ad0Jk/whtQ1663qI=
160−github.com/dnaeon/go-vcr v1.2.0/go.mod h1:R4UdLID7HZT3taECzJs4YgbbH6PIGXB6W/sc5OLb6RQ=
139+github.com/disintegration/gift v1.1.2 h1:9ZyHJr+kPamiH10FX3Pynt1AxFUob812bU9Wt4GMzhs=
140+github.com/disintegration/gift v1.1.2/go.mod h1:Jh2i7f7Q2BM7Ezno3PhfezbR1xpUg9dUg3/RlKGr4HI=
141+github.com/disintegration/imageorient v0.0.0-20180920195336-8147d86e83ec h1:YrB6aVr9touOt75I9O1SiancmR2GMg45U9UYf0gtgWg=
142+github.com/disintegration/imageorient v0.0.0-20180920195336-8147d86e83ec/go.mod h1:K0KBFIr1gWu/C1Gp10nFAcAE4hsB7JxE6OgLijrJ8Sk=
143+github.com/dlclark/regexp2 v1.11.5 h1:Q/sSnsKerHeCkc/jSTNq1oCm7KiVgUMZRDUoRu0JQZQ=
144+github.com/dlclark/regexp2 v1.11.5/go.mod h1:DHkYz0B9wPfa6wondMfaivmHpzrQ3v9q8cnmRbL6yW8=
161145github.com/dustin/go-humanize v1.0.1 h1:GzkhY7T5VNhEkwH0PVJgjz+fX1rhBrR7pRT3mDkpeCY=
162146github.com/dustin/go-humanize v1.0.1/go.mod h1:Mu1zIs6XwVuF/gI1OepvI0qD18qycQx+mFykh5fBlto=
163−github.com/ebitengine/purego v0.10.1 h1:dewVBCBT2GaMu1SrNTYxQhgQBethzfhiwvZiLGP/qyY=
164−github.com/ebitengine/purego v0.10.1/go.mod h1:iIjxzd6CiRiOG0UyXP+V1+jWqUXVjPKLAI0mRfJZTmQ=
165−github.com/envoyproxy/go-control-plane v0.14.0 h1:hbG2kr4RuFj222B6+7T83thSPqLjwBIfQawTkC++2HA=
166−github.com/envoyproxy/go-control-plane/envoy v1.37.0 h1:u3riX6BoYRfF4Dr7dwSOroNfdSbEPe9Yyl09/B6wBrQ=
167−github.com/envoyproxy/go-control-plane/envoy v1.37.0/go.mod h1:DReE9MMrmecPy+YvQOAOHNYMALuowAnbjjEMkkWOi6A=
168−github.com/envoyproxy/protoc-gen-validate v1.3.3 h1:MVQghNeW+LZcmXe7SY1V36Z+WFMDjpqGAGacLe2T0ds=
169−github.com/envoyproxy/protoc-gen-validate v1.3.3/go.mod h1:TsndJ/ngyIdQRhMcVVGDDHINPLWB7C82oDArY51KfB0=
170−github.com/esiqveland/notify v0.13.3 h1:QCMw6o1n+6rl+oLUfg8P1IIDSFsDEb2WlXvVvIJbI/o=
171−github.com/esiqveland/notify v0.13.3/go.mod h1:hesw/IRYTO0x99u1JPweAl4+5mwXJibQVUcP0Iu5ORE=
172−github.com/felixge/httpsnoop v1.1.0 h1:3YtUj32ZZkqZtt3sZZsClsymw/QDuVfpNhoA31zeORc=
173−github.com/felixge/httpsnoop v1.1.0/go.mod h1:Zqxgdd+1Rkcz8euOqdr7lqgCRJztwr5hp9vDSi5UZCE=
147+github.com/felixge/httpsnoop v1.0.4 h1:NFTV2Zj1bL4mc9sqWACXbQFVBBg2W3GPvqp8/ESS2Wg=
148+github.com/felixge/httpsnoop v1.0.4/go.mod h1:m8KPJKqk1gH5J9DgRY2ASl2lWCfGKXixSwevea8zH2U=
174149github.com/fsnotify/fsnotify v1.6.0/go.mod h1:sl3t1tCWJFWoRz9R8WJCbQihKKwmorjAbSClcnxKAGw=
175150github.com/fsnotify/fsnotify v1.9.0 h1:2Ml+OJNzbYCTzsxtv8vKSFD9PbJjmhYF14k/jKC7S9k=
176151github.com/fsnotify/fsnotify v1.9.0/go.mod h1:8jBTzvmWwFyi3Pb8djgCCO5IBqzKJ/Jwo8TRcHyHii0=
177−github.com/gen2brain/beeep v0.11.2 h1:+KfiKQBbQCuhfJFPANZuJ+oxsSKAYNe88hIpJuyKWDA=
178−github.com/gen2brain/beeep v0.11.2/go.mod h1:jQVvuwnLuwOcdctHn/uyh8horSBNJ8uGb9Cn2W4tvoc=
179−github.com/go-git/gcfg v1.5.1-0.20230307220236-3a3c6141e376 h1:+zs/tPmkDkHx3U66DAb0lQFJrpS6731Oaa12ikc+DiI=
180−github.com/go-git/gcfg v1.5.1-0.20230307220236-3a3c6141e376/go.mod h1:an3vInlBmSxCcxctByoQdvwPiA7DTK7jaaFDBTtu0ic=
181−github.com/go-git/go-billy/v5 v5.9.0 h1:jItGXszUDRtR/AlferWPTMN4j38BQ88XnXKbilmmBPA=
182−github.com/go-git/go-billy/v5 v5.9.0/go.mod h1:jCnQMLj9eUgGU7+ludSTYoZL/GGmii14RxKFj7ROgHw=
183−github.com/go-git/go-git/v5 v5.19.1 h1:nX27AnaU43/K5bKktKwgBmR9lawoYVe1Ckg0rgzzN00=
184−github.com/go-git/go-git/v5 v5.19.1/go.mod h1:Pb1v0c7/g8aGQJwx9Us09W85yGoyvSwuhEGMH7zjDKQ=
185−github.com/go-json-experiment/json v0.0.0-20260623181947-01eb4420fa68 h1:KZaTBSyshWX3MP5jukJcNSuXDQTO+rNpt0J564dX/eg=
186−github.com/go-json-experiment/json v0.0.0-20260623181947-01eb4420fa68/go.mod h1:tphK2c80bpPhMOI4v6bIc2xWywPfbqi1Z06+RcrMkDg=
152+github.com/go-json-experiment/json v0.0.0-20251027170946-4849db3c2f7e h1:Lf/gRkoycfOBPa42vU2bbgPurFong6zXeFtPoxholzU=
153+github.com/go-json-experiment/json v0.0.0-20251027170946-4849db3c2f7e/go.mod h1:uNVvRXArCGbZ508SxYYTC5v1JWoz2voff5pm25jU1Ok=
187154github.com/go-logfmt/logfmt v0.6.0 h1:wGYYu3uicYdqXVgoYbvnkrPVXkuLM1p1ifugDMEdRi4=
188155github.com/go-logfmt/logfmt v0.6.0/go.mod h1:WYhtIu8zTZfxdn5+rREduYbwxfcBr/Vr6KEVveWlfTs=
189156github.com/go-logr/logr v1.2.2/go.mod h1:jdQByPbusPIv2/zmleS9BjJVeZ6kBagPoEUsqbVz/1A=
@@ -191,50 +158,29 @@ github.com/go-logr/logr v1.4.3 h1:CjnDlHq8ikf6E492q6eKboGOC0T8CDaOvkHCIg8idEI=
191158github.com/go-logr/logr v1.4.3/go.mod h1:9T104GzyrTigFIr8wt5mBrctHMim0Nb2HLGrmQ40KvY=
192159github.com/go-logr/stdr v1.2.2 h1:hSWxHoqTgW2S2qGc0LTAI563KZ5YKYRhT3MFKZMbjag=
193160github.com/go-logr/stdr v1.2.2/go.mod h1:mMo/vtBO5dYbehREoey6XUKy/eSumjCCveDpRre4VKE=
194−github.com/go-ole/go-ole v1.3.0 h1:Dt6ye7+vXGIKZ7Xtk4s6/xVdGDQynvom7xCFEdWr6uE=
195−github.com/go-ole/go-ole v1.3.0/go.mod h1:5LS6F96DhAwUc7C+1HLexzMXY1xGRSryjyPPKW6zv78=
196−github.com/go-openapi/jsonpointer v0.19.3/go.mod h1:Pl9vOtqEWErmShwVjC8pYs9cog34VGT37dQOVbmoatg=
197−github.com/go-openapi/jsonpointer v0.19.5 h1:gZr+CIYByUqjcgeLXnQu2gHYQC9o73G2XUeOFYEICuY=
198−github.com/go-openapi/jsonpointer v0.19.5/go.mod h1:Pl9vOtqEWErmShwVjC8pYs9cog34VGT37dQOVbmoatg=
199−github.com/go-openapi/jsonreference v0.20.0 h1:MYlu0sBgChmCfJxxUKZ8g1cPWFOB37YSZqewK7OKeyA=
200−github.com/go-openapi/jsonreference v0.20.0/go.mod h1:Ag74Ico3lPc+zR+qjn4XBUmXymS4zJbYVCZmcgkasdo=
201−github.com/go-openapi/spec v0.20.6 h1:ich1RQ3WDbfoeTqTAb+5EIxNmpKVJZWBNah9RAT0jIQ=
202−github.com/go-openapi/spec v0.20.6/go.mod h1:2OpW+JddWPrpXSCIX8eOx7lZ5iyuWj3RYR6VaaBKcWA=
203−github.com/go-openapi/swag v0.19.5/go.mod h1:POnQmlKehdgb5mhVOsnJFsivZCEZ/vjK9gh66Z9tfKk=
204−github.com/go-openapi/swag v0.19.15 h1:D2NRCBzS9/pEY3gP9Nl8aDqGUcPFrwG2p+CNFrLyrCM=
205−github.com/go-openapi/swag v0.19.15/go.mod h1:QYRuS/SOXUCsnplDa677K7+DxSOj6IPNl/eQntq43wQ=
206161github.com/go-quicktest/qt v1.101.0 h1:O1K29Txy5P2OK0dGo59b7b0LR6wKfIhttaAhHUyn7eI=
207162github.com/go-quicktest/qt v1.101.0/go.mod h1:14Bz/f7NwaXPtdYEgzsx46kqSxVwTbzVZsDC26tQJow=
208−github.com/go-viper/mapstructure/v2 v2.5.0 h1:vM5IJoUAy3d7zRSVtIwQgBj7BiWtMPfmPEgAXnvj1Ro=
209−github.com/go-viper/mapstructure/v2 v2.5.0/go.mod h1:oJDH3BJKyqBA2TXFhDsKDGDTlndYOZ6rGS0BRZIxGhM=
210−github.com/goccy/go-json v0.10.5 h1:Fq85nIqj+gXn/S5ahsiTlK3TmC85qgirsdTP/+DeaC4=
211−github.com/goccy/go-json v0.10.5/go.mod h1:oq7eo15ShAhp70Anwd5lgX2pLfOS3QCiwU/PULtXL6M=
212−github.com/goccy/go-yaml v1.19.2 h1:PmFC1S6h8ljIz6gMRBopkjP1TVT7xuwrButHID66PoM=
213−github.com/goccy/go-yaml v1.19.2/go.mod h1:XBurs7gK8ATbW4ZPGKgcbrY1Br56PdM69F7LkFRi1kA=
214−github.com/godbus/dbus/v5 v5.1.0/go.mod h1:xhWf0FNVPg57R7Z0UbKHbJfkEywrmjJnf7w5xrFpKfA=
215−github.com/godbus/dbus/v5 v5.2.2 h1:TUR3TgtSVDmjiXOgAAyaZbYmIeP3DPkld3jgKGV8mXQ=
216−github.com/godbus/dbus/v5 v5.2.2/go.mod h1:3AAv2+hPq5rdnr5txxxRwiGjPXamgoIHgz9FPBfOp3c=
217−github.com/golang-jwt/jwt/v5 v5.3.1 h1:kYf81DTWFe7t+1VvL7eS+jKFVWaUnK9cB1qbwn63YCY=
218−github.com/golang-jwt/jwt/v5 v5.3.1/go.mod h1:fxCRLWMO43lRc8nhHWY6LGqRcf+1gQWArsqaEUEa5bE=
219−github.com/golang/freetype v0.0.0-20170609003504-e2365dfdc4a0 h1:DACJavvAHhabrF08vX0COfcOBJRhZ8lUbR+ZWIs0Y5g=
220−github.com/golang/freetype v0.0.0-20170609003504-e2365dfdc4a0/go.mod h1:E/TSTwGwJL78qG/PmXZO1EjYhfJinVAhrmmHX6Z8B9k=
163+github.com/go-viper/mapstructure/v2 v2.4.0 h1:EBsztssimR/CONLSZZ04E8qAkxNYq4Qp9LvH92wZUgs=
164+github.com/go-viper/mapstructure/v2 v2.4.0/go.mod h1:oJDH3BJKyqBA2TXFhDsKDGDTlndYOZ6rGS0BRZIxGhM=
165+github.com/goccy/go-yaml v1.19.0 h1:EmkZ9RIsX+Uq4DYFowegAuJo8+xdX3T/2dwNPXbxEYE=
166+github.com/goccy/go-yaml v1.19.0/go.mod h1:XBurs7gK8ATbW4ZPGKgcbrY1Br56PdM69F7LkFRi1kA=
167+github.com/golang-jwt/jwt/v5 v5.2.2 h1:Rl4B7itRWVtYIHFrSNd7vhTiz9UpLdi6gZhZ3wEeDy8=
168+github.com/golang-jwt/jwt/v5 v5.2.2/go.mod h1:pqrtFR0X4osieyHYxtmOUWsAWrfe1Q5UVIyoH402zdk=
221169github.com/golang/protobuf v1.5.4 h1:i7eJL8qZTpSEXOPTxNKhASYpMn+8e5Q6AdndVa1dWek=
222170github.com/golang/protobuf v1.5.4/go.mod h1:lnTiLA8Wa4RWRcIUkrtSVa5nRhsEGBg48fD6rSs7xps=
223171github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
224172github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=
225173github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=
226−github.com/google/jsonschema-go v0.4.3 h1:/DBOLZTfDow7pe2GmaJNhltueGTtDKICi8V8p+DQPd0=
227−github.com/google/jsonschema-go v0.4.3/go.mod h1:r5quNTdLOYEz95Ru18zA0ydNbBuYoo9tgaYcxEYhJVE=
228−github.com/google/pprof v0.0.0-20250317173921-a4b03ec1a45e h1:ijClszYn+mADRFY17kjQEVQ1XRhq2/JR1M3sGqeJoxs=
229−github.com/google/pprof v0.0.0-20250317173921-a4b03ec1a45e/go.mod h1:boTsfXsheKC2y+lKOCMpSfarhxDeIzfZG1jqGcPl3cA=
174+github.com/google/jsonschema-go v0.3.0 h1:6AH2TxVNtk3IlvkkhjrtbUc4S8AvO0Xii0DxIygDg+Q=
175+github.com/google/jsonschema-go v0.3.0/go.mod h1:r5quNTdLOYEz95Ru18zA0ydNbBuYoo9tgaYcxEYhJVE=
230176github.com/google/s2a-go v0.1.9 h1:LGD7gtMgezd8a/Xak7mEWL0PjoTQFvpRudN895yqKW0=
231177github.com/google/s2a-go v0.1.9/go.mod h1:YA0Ei2ZQL3acow2O62kdp9UlnvMmU7kA6Eutn0dXayM=
232178github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
233179github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
234−github.com/googleapis/enterprise-certificate-proxy v0.3.17 h1:73NfMHdiqo9JFU9+7a5ExpVa10/R29pXfZIaW559nrg=
235−github.com/googleapis/enterprise-certificate-proxy v0.3.17/go.mod h1:rSEsBUemEBZEexP2y6jPp16LUmUbjmSbcPMQizR0o4k=
236−github.com/googleapis/gax-go/v2 v2.22.0 h1:PjIWBpgGIVKGoCXuiCoP64altEJCj3/Ei+kSU5vlZD4=
237−github.com/googleapis/gax-go/v2 v2.22.0/go.mod h1:irWBbALSr0Sk3qlqb9SyJ1h68WjgeFuiOzI4Rqw5+aY=
180+github.com/googleapis/enterprise-certificate-proxy v0.3.6 h1:GW/XbdyBFQ8Qe+YAmFU9uHLo7OnF5tL52HFAgMmyrf4=
181+github.com/googleapis/enterprise-certificate-proxy v0.3.6/go.mod h1:MkHOF77EYAE7qfSuSS9PU6g4Nt4e11cnsDUowfwewLA=
182+github.com/googleapis/gax-go/v2 v2.15.0 h1:SyjDc1mGgZU5LncH8gimWo9lW1DtIfPibOG81vgd/bo=
183+github.com/googleapis/gax-go/v2 v2.15.0/go.mod h1:zVVkkxAQHa1RQpg9z2AUCMnKhi0Qld9rcmyfL1OZhoc=
238184github.com/gorilla/css v1.0.1 h1:ntNaBIghp6JmvWnxbZKANoLyuXTPZ4cAMlo6RyhlbO8=
239185github.com/gorilla/css v1.0.1/go.mod h1:BvnYkspnSzMmwRK+b8/xgNPLiIuNZr6vbZBTPQ2A3b0=
240186github.com/gorilla/websocket v1.4.1/go.mod h1:YR8l580nyteQvAITg2hZ9XVh4b55+EU/adAjf1fMHhE=
@@ -246,30 +192,23 @@ github.com/hexops/gotextdiff v1.0.3 h1:gitA9+qJrrTCsiCl7+kh75nPqQt1cx4ZkudSTLoUq
246192github.com/hexops/gotextdiff v1.0.3/go.mod h1:pSWU5MAI3yDq+fZBTazCSJysOMbxWL1BSow5/V2vxeg=
247193github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8=
248194github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw=
249−github.com/invopop/jsonschema v0.14.0 h1:MHQqLhvpNUZfw+hM3AZDYK7jxO8FZoQeQM77g8iyZjg=
250−github.com/invopop/jsonschema v0.14.0/go.mod h1:ygm6C2EaVNMBDPpaPlnOA2pFAxBnxGjFlMZABxm9n2I=
251−github.com/itchyny/gojq v0.12.19 h1:ttXA0XCLEMoaLOz5lSeFOZ6u6Q3QxmG46vfgI4O0DEs=
252−github.com/itchyny/gojq v0.12.19/go.mod h1:5galtVPDywX8SPSOrqjGxkBeDhSxEW1gSxoy7tn1iZY=
253−github.com/itchyny/timefmt-go v0.1.8 h1:1YEo1JvfXeAHKdjelbYr/uCuhkybaHCeTkH8Bo791OI=
254−github.com/itchyny/timefmt-go v0.1.8/go.mod h1:5E46Q+zj7vbTgWY8o5YkMeYb4I6GeWLFnetPy5oBrAI=
255−github.com/jackmordaunt/icns/v3 v3.0.1 h1:xxot6aNuGrU+lNgxz5I5H0qSeCjNKp8uTXB1j8D4S3o=
256−github.com/jackmordaunt/icns/v3 v3.0.1/go.mod h1:5sHL59nqTd2ynTnowxB/MDQFhKNqkK8X687uKNygaSQ=
257−github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99 h1:BQSFePA1RWJOlocH6Fxy8MmwDt+yVQYULKfN0RoTN8A=
258−github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99/go.mod h1:1lJo3i6rXxKeerYnT8Nvf0QmHCRC1n8sfWVwXF2Frvo=
195+github.com/invopop/jsonschema v0.13.0 h1:KvpoAJWEjR3uD9Kbm2HWJmqsEaHt8lBUpd0qHcIi21E=
196+github.com/invopop/jsonschema v0.13.0/go.mod h1:ffZ5Km5SWWRAIN6wbDXItl95euhFz2uON45H2qjYt+0=
259197github.com/joho/godotenv v1.5.1 h1:7eLL/+HRGLY0ldzfGMeQkb7vMd0as4CfYvUVzLqw0N0=
260198github.com/joho/godotenv v1.5.1/go.mod h1:f4LDr5Voq0i2e/R5DDNOoa2zzDfwtkZa6DnEwAbqwq4=
261−github.com/jordanella/go-ansi-paintbrush v0.0.0-20240728195301-b7ad996ecf3d h1:on25kP+Sx7sxUMRQiA8gdcToAGet4DK/EIA30mXre+4=
262−github.com/jordanella/go-ansi-paintbrush v0.0.0-20240728195301-b7ad996ecf3d/go.mod h1:SV0W0APWP9MZ1/gfDQ/NzzTlWdIgYZ/ZbpN4d/UXRYw=
263−github.com/josharian/intern v1.0.0 h1:vlS4z54oSdjm0bgjRigI+G1HpF+tI+9rE5LLzOg8HmY=
264199github.com/josharian/intern v1.0.0/go.mod h1:5DoeVV0s6jJacbCEi61lwdGj/aVlrQvzHFFd8Hwg//Y=
265−github.com/kaptinlin/jsonpointer v0.4.26 h1:tw616yszHek+B3/GtDSia+uzBa3sLXGpmo4tYeMhBZw=
266−github.com/kaptinlin/jsonpointer v0.4.26/go.mod h1:wVOBaXGGnP42YsMb6zev/3W5POTvspdNfh8DXzf8XS8=
267−github.com/kaptinlin/jsonschema v0.9.2 h1:zqowDnBkpg80OeIt4Bl1bOyfKY1/KVVzst1m3MCsxd4=
268−github.com/kaptinlin/jsonschema v0.9.2/go.mod h1:mCH2W5lXd29tdDjvoFfY32nedPORnlk7pCVrrcs/NkQ=
269−github.com/klauspost/compress v1.18.6 h1:2jupLlAwFm95+YDR+NwD2MEfFO9d4z4Prjl1XXDjuao=
270−github.com/klauspost/compress v1.18.6/go.mod h1:cwPg85FWrGar70rWktvGQj8/hthj3wpl0PGDogxkrSQ=
271−github.com/klauspost/cpuid/v2 v2.3.0 h1:S4CRMLnYUhGeDFDqkGriYKdfoFlDnMtqTiI/sFzhA9Y=
272−github.com/klauspost/cpuid/v2 v2.3.0/go.mod h1:hqwkgyIinND0mEev00jJYCxPNVRVXFQeu1XKlok6oO0=
200+github.com/kaptinlin/go-i18n v0.2.2 h1:kebVCZme/BrCTqonh/J+VYCl1+Of5C18bvyn3DRPl5M=
201+github.com/kaptinlin/go-i18n v0.2.2/go.mod h1:MiwkeHryBopAhC/M3zEwIM/2IN8TvTqJQswPw6kceqM=
202+github.com/kaptinlin/jsonpointer v0.4.8 h1:HocHcXrOBfP/nUJw0YYjed/TlQvuCAY6uRs3Qok7F6g=
203+github.com/kaptinlin/jsonpointer v0.4.8/go.mod h1:9y0LgXavlmVE5FSHShY5LRlURJJVhbyVJSRWkilrTqA=
204+github.com/kaptinlin/jsonschema v0.6.5 h1:hC7upwWlvamWqeTVQ3ab20F4w0XKNKR1drY9apoqGOU=
205+github.com/kaptinlin/jsonschema v0.6.5/go.mod h1:EbhSbdxZ4QjzIORdMWOrRXJeCHrLTJqXDA8JzNaeFc8=
206+github.com/kaptinlin/messageformat-go v0.4.7 h1:HQ/OvFUSU7+fAHWkZnP2ug9y+A/ZyTE8j33jfWr8O3Q=
207+github.com/kaptinlin/messageformat-go v0.4.7/go.mod h1:DusKpv8CIybczGvwIVn3j13hbR3psr5mOwhFudkiq1c=
208+github.com/klauspost/compress v1.18.0 h1:c/Cqfb0r+Yi+JtIEq73FWXVkRonBlf0CRNYc8Zttxdo=
209+github.com/klauspost/compress v1.18.0/go.mod h1:2Pp+KzxcywXVXMr50+X0Q/Lsb43OQHYWRCY2AiWywWQ=
210+github.com/klauspost/cpuid/v2 v2.0.9 h1:lgaqFMSdTdQYdZ04uHyN2d/eKdOMyi2YLSvlQIBFYa4=
211+github.com/klauspost/cpuid/v2 v2.0.9/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg=
273212github.com/klauspost/pgzip v1.2.6 h1:8RXeL5crjEUFnR2/Sn6GJNWtSQ3Dk8pq4CL3jvdDyjU=
274213github.com/klauspost/pgzip v1.2.6/go.mod h1:Ch1tH69qFZu15pkjo5kYi6mth2Zzwzt50oCQKQE9RUs=
275214github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
@@ -281,25 +220,22 @@ github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
281220github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
282221github.com/kylelemons/godebug v1.1.0 h1:RPNrshWIDI6G2gRW9EHilWtl7Z6Sb1BR0xunSBf0SNc=
283222github.com/kylelemons/godebug v1.1.0/go.mod h1:9/0rRGxNHcop5bhtWyNeEfOS8JIWk580+fNqagV/RAw=
284−github.com/lucasb-eyer/go-colorful v1.4.0 h1:UtrWVfLdarDgc44HcS7pYloGHJUjHV/4FwW4TvVgFr4=
285−github.com/lucasb-eyer/go-colorful v1.4.0/go.mod h1:R4dSotOR9KMtayYi1e77YzuveK+i7ruzyGqttikkLy0=
286−github.com/mailru/easyjson v0.0.0-20190614124828-94de47d64c63/go.mod h1:C1wdFJiN94OJF2b5HbByQZoLdCWB1Yqtg26g4irojpc=
287−github.com/mailru/easyjson v0.0.0-20190626092158-b2ccc519800e/go.mod h1:C1wdFJiN94OJF2b5HbByQZoLdCWB1Yqtg26g4irojpc=
288−github.com/mailru/easyjson v0.7.6/go.mod h1:xzfreul335JAWq5oZzymOObrkdz5UnU4kGfJJLY9Nlc=
223+github.com/lucasb-eyer/go-colorful v1.3.0 h1:2/yBRLdWBZKrf7gB40FoiKfAWYQ0lqNcbuQwVHXptag=
224+github.com/lucasb-eyer/go-colorful v1.3.0/go.mod h1:R4dSotOR9KMtayYi1e77YzuveK+i7ruzyGqttikkLy0=
289225github.com/mailru/easyjson v0.7.7 h1:UGYAvKxe3sBsEDzO8ZeWOSlIQfWFlxbzLZe7hwFURr0=
290226github.com/mailru/easyjson v0.7.7/go.mod h1:xzfreul335JAWq5oZzymOObrkdz5UnU4kGfJJLY9Nlc=
291−github.com/mattn/go-isatty v0.0.22 h1:j8l17JJ9i6VGPUFUYoTUKPSgKe/83EYU2zBC7YNKMw4=
292−github.com/mattn/go-isatty v0.0.22/go.mod h1:ZXfXG4SQHsB/w3ZeOYbR0PrPwLy+n6xiMrJlRFqopa4=
293−github.com/mattn/go-runewidth v0.0.24 h1:cpokDiIn0MGnhdHwuWnJBITySJ20QyNGnY2kR/ay2DU=
294−github.com/mattn/go-runewidth v0.0.24/go.mod h1:XBkDxAl56ILZc9knddidhrOlY5R/pDhgLpndooCuJAs=
227+github.com/mattn/go-isatty v0.0.20 h1:xfD0iDuEKnDkl03q4limB+vH+GxLEtL/jb4xVJSWWEY=
228+github.com/mattn/go-isatty v0.0.20/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
229+github.com/mattn/go-runewidth v0.0.19 h1:v++JhqYnZuu5jSKrk9RbgF5v4CGUjqRfBm05byFGLdw=
230+github.com/mattn/go-runewidth v0.0.19/go.mod h1:XBkDxAl56ILZc9knddidhrOlY5R/pDhgLpndooCuJAs=
295231github.com/mfridman/interpolate v0.0.2 h1:pnuTK7MQIxxFz1Gr+rjSIx9u7qVjf5VOoM/u6BbAxPY=
296232github.com/mfridman/interpolate v0.0.2/go.mod h1:p+7uk6oE07mpE/Ik1b8EckO0O4ZXiGAfshKBWLUM9Xg=
297233github.com/microcosm-cc/bluemonday v1.0.27 h1:MpEUotklkwCSLeH+Qdx1VJgNqLlpY2KXwXFM08ygZfk=
298234github.com/microcosm-cc/bluemonday v1.0.27/go.mod h1:jFi9vgW+H7c3V0lb6nR74Ib/DIB5OBs92Dimizgw2cA=
299235github.com/mitchellh/mapstructure v1.5.0 h1:jeMsZIYE/09sWLaz43PL7Gy6RuMjD2eJVyuac5Z2hdY=
300236github.com/mitchellh/mapstructure v1.5.0/go.mod h1:bFUtVrKA4DC2yAKiSyO/QUcy7e+RRV2QTWOzhPopBRo=
301−github.com/modelcontextprotocol/go-sdk v1.6.1 h1:0zOSupjKUxPKSocPT1Wtago+mUHU2/uZ4xSOY0FGReU=
302−github.com/modelcontextprotocol/go-sdk v1.6.1/go.mod h1:kzm3kzFL1/+AziGOE0nUs3gvPoNxMCvkxokMkuFapXQ=
237+github.com/modelcontextprotocol/go-sdk v1.1.0 h1:Qjayg53dnKC4UZ+792W21e4BpwEZBzwgRW6LrjLWSwA=
238+github.com/modelcontextprotocol/go-sdk v1.1.0/go.mod h1:6fM3LCm3yV7pAs8isnKLn07oKtB0MP9LHd3DfAcKw10=
303239github.com/muesli/cancelreader v0.2.2 h1:3I4Kt4BQjOR54NavqnDogx/MIoWBFa0StPA8ELUXHmA=
304240github.com/muesli/cancelreader v0.2.2/go.mod h1:3XuTXfFS2VjM+HTLZY9Ak0l6eUKfijIfMUZ4EgX0QYo=
305241github.com/muesli/mango v0.1.0 h1:DZQK45d2gGbql1arsYA4vfg4d7I9Hfx5rX/GCmzsAvI=
@@ -310,43 +246,35 @@ github.com/muesli/mango-pflag v0.1.0 h1:UADqbYgpUyRoBja3g6LUL+3LErjpsOwaC9ywvBWe
310246github.com/muesli/mango-pflag v0.1.0/go.mod h1:YEQomTxaCUp8PrbhFh10UfbhbQrM/xJ4i2PB8VTLLW0=
311247github.com/muesli/roff v0.1.0 h1:YD0lalCotmYuF5HhZliKWlIx7IEhiXeSfq7hNjFqGF8=
312248github.com/muesli/roff v0.1.0/go.mod h1:pjAHQM9hdUUwm/krAfrLGgJkXJ+YuhtsfZ42kieB2Ig=
313−github.com/ncruces/go-sqlite3 v0.35.1 h1:h/LaVyQwIvBBT0+2JmVe2tbYyWjUQ093/pYhpBqdxJo=
314−github.com/ncruces/go-sqlite3 v0.35.1/go.mod h1:fXOSIkWwN5NXgbJk+7Zls8QIW4xOflmgh11OFvcY+J0=
315−github.com/ncruces/go-sqlite3-wasm/v3 v3.1.35302 h1:Cew7/eNAMd1zhpXYBjofBua/63pFvbvB2h4PM/p6gKU=
316−github.com/ncruces/go-sqlite3-wasm/v3 v3.1.35302/go.mod h1:xe0CfafDUxfh+fSVKjHHMiAxoG9KALt5nFtbGNb/jRs=
317−github.com/ncruces/go-strftime v1.0.0 h1:HMFp8mLCTPp341M/ZnA4qaf7ZlsbTc+miZjCLOFAw7w=
318−github.com/ncruces/go-strftime v1.0.0/go.mod h1:Fwc5htZGVVkseilnfgOVb9mKy6w1naJmn9CehxcKcls=
249+github.com/muesli/termenv v0.16.0 h1:S5AlUN9dENB57rsbnkPyfdGuWIlkmzJjbFf0Tf5FWUc=
250+github.com/muesli/termenv v0.16.0/go.mod h1:ZRfOIKPFDYQoDFF4Olj7/QJbW60Ol/kL1pU3VfY/Cnk=
251+github.com/ncruces/go-sqlite3 v0.30.3 h1:X/CgWW9GzmIAkEPrifhKqf0cC15DuOVxAJaHFTTAURQ=
252+github.com/ncruces/go-sqlite3 v0.30.3/go.mod h1:AxKu9sRxkludimFocbktlY6LiYSkxiI5gTA8r+os/Nw=
253+github.com/ncruces/go-strftime v0.1.9 h1:bY0MQC28UADQmHmaF5dgpLmImcShSi2kHU9XLdhx/f4=
254+github.com/ncruces/go-strftime v0.1.9/go.mod h1:Fwc5htZGVVkseilnfgOVb9mKy6w1naJmn9CehxcKcls=
319255github.com/ncruces/julianday v1.0.0 h1:fH0OKwa7NWvniGQtxdJRxAgkBMolni2BjDHaWTxqt7M=
320256github.com/ncruces/julianday v1.0.0/go.mod h1:Dusn2KvZrrovOMJuOt0TNXL6tB7U2E8kvza5fFc9G7g=
321257github.com/nfnt/resize v0.0.0-20180221191011-83c6a9932646 h1:zYyBkD/k9seD2A7fsi6Oo2LfFZAehjjQMERAvZLEDnQ=
322258github.com/nfnt/resize v0.0.0-20180221191011-83c6a9932646/go.mod h1:jpp1/29i3P1S/RLdc7JQKbRpFeM1dOBd8T9ki5s+AY8=
323−github.com/niemeyer/pretty v0.0.0-20200227124842-a10e7caefd8e/go.mod h1:zD1mROLANZcx1PVRCS0qkT7pwLkGfwJo4zjcN/Tysno=
324259github.com/nxadm/tail v1.4.11 h1:8feyoE3OzPrcshW5/MJ4sGESc5cqmGkGCWlco4l0bqY=
325260github.com/nxadm/tail v1.4.11/go.mod h1:OTaG3NK980DZzxbRq6lEuzgU+mug70nY11sMd4JXXHc=
326−github.com/onsi/gomega v1.34.1 h1:EUMJIKUjM8sKjYbtxQI9A4z2o+rruxnzNvpknOXie6k=
327−github.com/onsi/gomega v1.34.1/go.mod h1:kU1QgUvBDLXBJq618Xvm2LUX6rSAfRaFRTcdOeDLwwY=
328−github.com/pb33f/ordered-map/v2 v2.3.1 h1:5319HDO0aw4DA4gzi+zv4FXU9UlSs3xGZ40wcP1nBjY=
329−github.com/pb33f/ordered-map/v2 v2.3.1/go.mod h1:qxFQgd0PkVUtOMCkTapqotNgzRhMPL7VvaHKbd1HnmQ=
330−github.com/pierrec/lz4/v4 v4.1.26 h1:GrpZw1gZttORinvzBdXPUXATeqlJjqUG/D87TKMnhjY=
331−github.com/pierrec/lz4/v4 v4.1.26/go.mod h1:EoQMVJgeeEOMsCqCzqFm2O0cJvljX2nGZjcRIPL34O4=
332−github.com/pjbgf/sha1cd v0.6.0 h1:3WJ8Wz8gvDz29quX1OcEmkAlUg9diU4GxJHqs0/XiwU=
333−github.com/pjbgf/sha1cd v0.6.0/go.mod h1:lhpGlyHLpQZoxMv8HcgXvZEhcGs0PG/vsZnEJ7H0iCM=
261+github.com/openai/openai-go/v2 v2.7.1 h1:/tfvTJhfv7hTSL8mWwc5VL4WLLSDL5yn9VqVykdu9r8=
262+github.com/openai/openai-go/v2 v2.7.1/go.mod h1:jrJs23apqJKKbT+pqtFgNKpRju/KP9zpUTZhz3GElQE=
263+github.com/pelletier/go-toml/v2 v2.2.4 h1:mye9XuhQ6gvn5h28+VilKrrPoQVanw5PMw/TB0t5Ec4=
264+github.com/pelletier/go-toml/v2 v2.2.4/go.mod h1:2gIqNv+qfxSVS7cM2xJQKtLSTLUE9V8t9Stt+h56mCY=
265+github.com/pierrec/lz4/v4 v4.1.22 h1:cKFw6uJDK+/gfw5BcDL0JL5aBsAFdsIT18eRtLj7VIU=
266+github.com/pierrec/lz4/v4 v4.1.22/go.mod h1:gZWDp/Ze/IJXGXf23ltt2EXimqmTUXEy0GFuRQyBid4=
334267github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c h1:+mdjkGKdHQG3305AYmdv1U2eRNDiU2ErMBj1gwrq8eQ=
335268github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c/go.mod h1:7rwL4CYBLnjLxUqIJNnCWiEdr3bn6IUYi15bNlnbCCU=
336269github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
337−github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
338−github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
339−github.com/planetscale/vtprotobuf v0.6.1-0.20240319094008-0393e58bdf10 h1:GFCKgmp0tecUJ0sJuv4pzYCqS9+RGSn52M3FUwPs+uo=
340−github.com/planetscale/vtprotobuf v0.6.1-0.20240319094008-0393e58bdf10/go.mod h1:t/avpk3KcrXxUnYOhZhMXJlSEyie6gQbtLq5NM3loB8=
270+github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
341271github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
342−github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 h1:Jamvg5psRIccs7FGNTlIRMkT8wgtp5eCXdBlqhYGL6U=
343−github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
344−github.com/posthog/posthog-go v1.17.5 h1:mrLiAdyiQpl8Yeyg23iShyAztJMaUrYzsBjKeH52Aak=
345−github.com/posthog/posthog-go v1.17.5/go.mod h1://M430hNH3e8CDv4i8SJesb26816Mpa6GIZaiP4pNQU=
346−github.com/pressly/goose/v3 v3.27.2 h1:FjKNzcmMdGrQlSIu5alMSmakQtJFBgtw+A0bb1p/LC8=
347−github.com/pressly/goose/v3 v3.27.2/go.mod h1:qWW+/8dkVtJYjJrbIpwD5xxnEJTUKvxkQ9JKQp9LaIM=
348−github.com/qjebbs/go-jsons v1.0.0-alpha.6 h1:9pMjdrCT7rj9CDIM0FXf9Ilie8PEy9g1b4qMkCnedjQ=
349−github.com/qjebbs/go-jsons v1.0.0-alpha.6/go.mod h1:wNJrtinHyC3YSf6giEh4FJN8+yZV7nXBjvmfjhBIcw4=
272+github.com/posthog/posthog-go v1.6.13 h1:4t9j0VOIJBgITm4v5rLsLy3IKUkU9dn2VusMNzZXScw=
273+github.com/posthog/posthog-go v1.6.13/go.mod h1:LcC1Nu4AgvV22EndTtrMXTy+7RGVC0MhChSw7Qk5XkY=
274+github.com/pressly/goose/v3 v3.26.0 h1:KJakav68jdH0WDvoAcj8+n61WqOIaPGgH0bJWS6jpmM=
275+github.com/pressly/goose/v3 v3.26.0/go.mod h1:4hC1KrritdCxtuFsqgs1R4AU5bWtTAf+cnWvfhf2DNY=
276+github.com/qjebbs/go-jsons v1.0.0-alpha.4 h1:Qsb4ohRUHQODIUAsJKdKJ/SIDbsO7oGOzsfy+h1yQZs=
277+github.com/qjebbs/go-jsons v1.0.0-alpha.4/go.mod h1:wNJrtinHyC3YSf6giEh4FJN8+yZV7nXBjvmfjhBIcw4=
350278github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec h1:W09IVJc94icq4NjY3clb7Lk8O1qJ8BdBEF8z0ibU0rE=
351279github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo=
352280github.com/rivo/uniseg v0.4.7 h1:WUdvkW8uEhrYfLC4ZzdpI2ztxP1I582+49Oc5Mq64VQ=
@@ -354,18 +282,12 @@ github.com/rivo/uniseg v0.4.7/go.mod h1:FN3SvrM+Zdj16jyLfmOkMNblXMcoc8DfTHruCPUc
354282github.com/rogpeppe/go-internal v1.14.1 h1:UQB4HGPB6osV0SQTLymcB4TgvyWu6ZyliaW0tI/otEQ=
355283github.com/rogpeppe/go-internal v1.14.1/go.mod h1:MaRKkUm5W0goXpeCfT7UZI6fk/L7L7so1lCWt35ZSgc=
356284github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
357−github.com/sahilm/fuzzy v0.1.3 h1:juByESSS32nVD81vr6tHmKmA/8zde7gE+x5CLxrzXPU=
358−github.com/sahilm/fuzzy v0.1.3/go.mod h1:au6//VbVSqu6DFrkL2CfjlJ5iURpNCPeE+1GwY3XsT8=
285+github.com/sabhiram/go-gitignore v0.0.0-20210923224102-525f6e181f06 h1:OkMGxebDjyw0ULyrTYWeN0UNCCkmCWfjPnIA2W6oviI=
286+github.com/sabhiram/go-gitignore v0.0.0-20210923224102-525f6e181f06/go.mod h1:+ePHsJ1keEjQtpvf9HHw0f4ZeJ0TLRsxhunSI2hYJSs=
287+github.com/sahilm/fuzzy v0.1.1 h1:ceu5RHF8DGgoi+/dR5PsECjCDH1BE3Fnmpo7aVXOdRA=
288+github.com/sahilm/fuzzy v0.1.1/go.mod h1:VFvziUEIMCrT6A6tw2RFIXPXXmzXbOsSHF0DOI8ZK9Y=
359289github.com/sebdah/goldie/v2 v2.5.3 h1:9ES/mNN+HNUbNWpVAlrzuZ7jE+Nrczbj8uFRjM7624Y=
360290github.com/sebdah/goldie/v2 v2.5.3/go.mod h1:oZ9fp0+se1eapSRjfYbsV/0Hqhbuu3bJVvKI/NNtssI=
361−github.com/segmentio/asm v1.2.1 h1:DTNbBqs57ioxAD4PrArqftgypG4/qNpXoJx8TVXxPR0=
362−github.com/segmentio/asm v1.2.1/go.mod h1:BqMnlJP91P8d+4ibuonYZw9mfnzI9HfxselHZr5aAcs=
363−github.com/segmentio/encoding v0.5.4 h1:OW1VRern8Nw6ITAtwSZ7Idrl3MXCFwXHPgqESYfvNt0=
364−github.com/segmentio/encoding v0.5.4/go.mod h1:HS1ZKa3kSN32ZHVZ7ZLPLXWvOVIiZtyJnO1gPH1sKt0=
365−github.com/sergeymakinen/go-bmp v1.0.0 h1:SdGTzp9WvCV0A1V0mBeaS7kQAwNLdVJbmHlqNWq0R+M=
366−github.com/sergeymakinen/go-bmp v1.0.0/go.mod h1:/mxlAQZRLxSvJFNIEGGLBE/m40f3ZnUifpgVDlcUIEY=
367−github.com/sergeymakinen/go-ico v1.0.0-beta.0 h1:m5qKH7uPKLdrygMWxbamVn+tl2HfiA3K6MFJw4GfZvQ=
368−github.com/sergeymakinen/go-ico v1.0.0-beta.0/go.mod h1:wQ47mTczswBO5F0NoDt7O0IXgnV4Xy3ojrroMQzyhUk=
369291github.com/sergi/go-diff v1.0.0/go.mod h1:0CfEIISq7TuYL3j771MWULgwwjU+GofnZX9QAmXWZgo=
370292github.com/sergi/go-diff v1.3.1/go.mod h1:aMJSSKb2lpPvRNec0+w3fl7LP9IOFzdc9Pa4NFbPK1I=
371293github.com/sergi/go-diff v1.3.2-0.20230802210424-5b0b94c5c0d3 h1:n661drycOFuPLCN3Uc8sB6B/s6Z4t2xvBgU1htSHuq8=
@@ -378,28 +300,21 @@ github.com/spf13/cobra v1.10.2 h1:DMTTonx5m65Ic0GOoRY2c16WCbHxOOw6xxezuLaBpcU=
378300github.com/spf13/cobra v1.10.2/go.mod h1:7C1pvHqHw5A4vrJfjNwvOdzYu0Gml16OCs2GRiTUUS4=
379301github.com/spf13/pflag v1.0.9 h1:9exaQaMOCwffKiiiYk6/BndUBv+iRViNW+4lEMi0PvY=
380302github.com/spf13/pflag v1.0.9/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
303+github.com/srwiley/oksvg v0.0.0-20221011165216-be6e8873101c h1:km8GpoQut05eY3GiYWEedbTT0qnSxrCjsVbb7yKY1KE=
304+github.com/srwiley/oksvg v0.0.0-20221011165216-be6e8873101c/go.mod h1:cNQ3dwVJtS5Hmnjxy6AgTPd0Inb3pW05ftPSX7NZO7Q=
305+github.com/srwiley/rasterx v0.0.0-20220730225603-2ab79fcdd4ef h1:Ch6Q+AZUxDBCVqdkI8FSpFyZDtCVBc2VmejdNrm5rRQ=
306+github.com/srwiley/rasterx v0.0.0-20220730225603-2ab79fcdd4ef/go.mod h1:nXTWP6+gD5+LUJ8krVhhoeHjvHTutPxMYl5SvkcnJNE=
381307github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
382−github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
383−github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo=
384308github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
385309github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
386310github.com/stretchr/testify v1.6.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
387−github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
388−github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
389−github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
390311github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U=
391312github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=
392−github.com/swaggo/files/v2 v2.0.0 h1:hmAt8Dkynw7Ssz46F6pn8ok6YmGZqHSVLZ+HQM7i0kw=
393−github.com/swaggo/files/v2 v2.0.0/go.mod h1:24kk2Y9NYEJ5lHuCra6iVwkMjIekMCaFq/0JQj66kyM=
394−github.com/swaggo/http-swagger/v2 v2.0.2 h1:FKCdLsl+sFCx60KFsyM0rDarwiUSZ8DqbfSyIKC9OBg=
395−github.com/swaggo/http-swagger/v2 v2.0.2/go.mod h1:r7/GBkAWIfK6E/OLnE8fXnviHiDeAHmgIyooa4xm3AQ=
396−github.com/swaggo/swag v1.16.6 h1:qBNcx53ZaX+M5dxVyTrgQ0PJ/ACK+NzhwcbieTt+9yI=
397−github.com/swaggo/swag v1.16.6/go.mod h1:ngP2etMK5a0P3QBizic5MEwpRmluJZPHjXcMoj4Xesg=
398−github.com/tadvi/systray v0.0.0-20190226123456-11a2b8fa57af h1:6yITBqGTE2lEeTPG04SN9W+iWHCRyHqlVYILiSXziwk=
399−github.com/tadvi/systray v0.0.0-20190226123456-11a2b8fa57af/go.mod h1:4F09kP5F+am0jAwlQLddpoMDM+iewkxxt6nxUQ5nq5o=
313+github.com/tetratelabs/wazero v1.10.1 h1:2DugeJf6VVk58KTPszlNfeeN8AhhpwcZqkJj2wwFuH8=
314+github.com/tetratelabs/wazero v1.10.1/go.mod h1:DRm5twOQ5Gr1AoEdSi0CLjDQF1J9ZAuyqFIjl1KKfQU=
400315github.com/tidwall/gjson v1.14.2/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk=
401−github.com/tidwall/gjson v1.19.0 h1:xwxm7n691Uf3u5OFjzngavjGTh55KX5q/9w9xHW88JU=
402−github.com/tidwall/gjson v1.19.0/go.mod h1:V37/opeE/JbLUOfH0QTXiNez2l0RUjYUhpT4szFQAfc=
316+github.com/tidwall/gjson v1.18.0 h1:FIDeeyB800efLX89e5a8Y0BNH+LOngJyGrIWxG2FKQY=
317+github.com/tidwall/gjson v1.18.0/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk=
403318github.com/tidwall/match v1.1.1 h1:+Ho715JplO36QYgwN9PGYNhgZvoUSc9X2c80KVTi+GA=
404319github.com/tidwall/match v1.1.1/go.mod h1:eRSPERbgtNPcGhD8UCthc6PmLEQXEWd3PRB5JTxsfmM=
405320github.com/tidwall/pretty v1.2.0/go.mod h1:ITEVvHYasfjBbM0u2Pg8T2nJnzm8xPwvNhhsoaGGjNU=
@@ -411,10 +326,10 @@ github.com/u-root/u-root v0.14.1-0.20250807200646-5e7721023dc7 h1:ax+jBy7xFhh+Ka
411326github.com/u-root/u-root v0.14.1-0.20250807200646-5e7721023dc7/go.mod h1:/0Qr7qJeDwWxoKku2xKQ4Szc+SwBE3g9VE8jNiamsmc=
412327github.com/u-root/uio v0.0.0-20240224005618-d2acac8f3701 h1:pyC9PaHYZFgEKFdlp3G8RaCKgVpHZnecvArXvPXcFkM=
413328github.com/u-root/uio v0.0.0-20240224005618-d2acac8f3701/go.mod h1:P3a5rG4X7tI17Nn3aOIAYr5HbIMukwXG0urG0WuL8OA=
329+github.com/wk8/go-ordered-map/v2 v2.1.8 h1:5h/BUHu93oj4gIdvHHHGsScSTMijfx5PeYkE/fJgbpc=
330+github.com/wk8/go-ordered-map/v2 v2.1.8/go.mod h1:5nJHM5DyteebpVlHnWMV0rPz6Zp7+xBAnxjb1X5vnTw=
414331github.com/xo/terminfo v0.0.0-20220910002029-abceb7e1c41e h1:JVG44RsyaB9T2KIHavMF/ppJZNG9ZpyihvCd0w101no=
415332github.com/xo/terminfo v0.0.0-20220910002029-abceb7e1c41e/go.mod h1:RbqR21r5mrJuqunuUZ/Dhy/avygyECGrLceyNeo4LiM=
416−github.com/xyproto/randomstring v1.0.5 h1:YtlWPoRdgMu3NZtP45drfy1GKoojuR7hmRcnhZqKjWU=
417−github.com/xyproto/randomstring v1.0.5/go.mod h1:rgmS5DeNXLivK7YprL0pY+lTuhNQW3iGxZ18UQApw/E=
418333github.com/yosida95/uritemplate/v3 v3.0.2 h1:Ed3Oyj9yrmi9087+NczuL5BwkIc4wvTb5zIM+UJPGz4=
419334github.com/yosida95/uritemplate/v3 v3.0.2/go.mod h1:ILOh0sOhIJR3+L/8afwt/kE++YT040gmv5BQTMR2HP4=
420335github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
@@ -425,35 +340,29 @@ github.com/yuin/goldmark-emoji v1.0.5 h1:EMVWyCGPlXJfUXBXpuMu+ii3TIaxbVBnEX9uaDC
425340github.com/yuin/goldmark-emoji v1.0.5/go.mod h1:tTkZEbwu5wkPmgTcitqddVxY9osFZiavD+r4AzQrh1U=
426341github.com/zeebo/assert v1.3.0 h1:g7C04CbJuIDKNPFHmsk4hwZDO5O+kntRxzaUoNXj+IQ=
427342github.com/zeebo/assert v1.3.0/go.mod h1:Pq9JiuJQpG8JLJdtkwrJESF0Foym2/D9XMU5ciN/wJ0=
428−github.com/zeebo/xxh3 v1.1.0 h1:s7DLGDK45Dyfg7++yxI0khrfwq9661w9EN78eP/UZVs=
429−github.com/zeebo/xxh3 v1.1.0/go.mod h1:IisAie1LELR4xhVinxWS5+zf1lA4p0MW4T+w+W07F5s=
430−go.opentelemetry.io/auto/sdk v1.2.1 h1:jXsnJ4Lmnqd11kwkBV2LgLoFMZKizbCi5fNZ/ipaZ64=
431−go.opentelemetry.io/auto/sdk v1.2.1/go.mod h1:KRTj+aOaElaLi+wW1kO/DZRXwkF4C5xPbEe3ZiIhN7Y=
432−go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.69.0 h1:2yEATaop1/a1I4psnSLgWVPLWwCzkqWakgJy7xTDVy0=
433−go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.69.0/go.mod h1:D7J12YRapIekYyPWgGPlA/23pRmpSEZC5xJC/TTLI9U=
434−go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.69.0 h1:8tvICD4vSTOOsNrsI4Ljf6C+6UKvpTEH5XY3JMoyPoo=
435−go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.69.0/go.mod h1:z9+yiacE0IHRqM4qFfkbt/JYlmYXgss8GY/jXoNuPJI=
436−go.opentelemetry.io/otel v1.44.0 h1:JjwHmHpA4iZ3wBxluu2fbbE7j4kqlE8jXyAyPXH7HqU=
437−go.opentelemetry.io/otel v1.44.0/go.mod h1:BMgjTHL9WPRlRjL2oZCBTL4whCGtXch2H4BhOPIAyYc=
438−go.opentelemetry.io/otel/metric v1.44.0 h1:1w0gILTcHdr3YI+ixLyjemwrVnsMURbTZFrSYCdDdmc=
439−go.opentelemetry.io/otel/metric v1.44.0/go.mod h1:8O7hanEPBNgEMmybD3s2VBKcgWOCsA6tzHBPODAiquo=
440−go.opentelemetry.io/otel/sdk v1.44.0 h1:nHYwb9lK+fJPU/dnT6s7W7Z8itMWyqrnVfbheVYrZ58=
441−go.opentelemetry.io/otel/sdk v1.44.0/go.mod h1:Osuydd3Se74nqjAKxid74N5eC+jfEqfTegHRnq58oK0=
442−go.opentelemetry.io/otel/sdk/metric v1.44.0 h1:3LlKgI+VjbVsjNRFZJZAJ30WjXC5VkNRks6si09iEfI=
443−go.opentelemetry.io/otel/sdk/metric v1.44.0/go.mod h1:5B5pMARnXxKhltooO4xUuCBorl65a4EpnTalObqOigA=
444−go.opentelemetry.io/otel/trace v1.44.0 h1:jxF5CsGYCe74MCRx2X4g7WsY/VBKRqqpNvXlX/6gtIk=
445−go.opentelemetry.io/otel/trace v1.44.0/go.mod h1:oLl1jrMQAVo6v3GAggN+1VH9VIz9iUSvW53sW1Q8PIE=
446−go.uber.org/goleak v1.3.0 h1:2K3zAYmnTNqV73imy9J1T3WC+gmCePx2hEGkimedGto=
447−go.uber.org/goleak v1.3.0/go.mod h1:CoHD4mav9JJNrW/WLlf7HGZPjdw8EucARQHekz1X6bE=
343+github.com/zeebo/xxh3 v1.0.2 h1:xZmwmqxHZA8AI603jOQ0tMqmBr9lPeFwGg6d+xy9DC0=
344+github.com/zeebo/xxh3 v1.0.2/go.mod h1:5NWz9Sef7zIDm2JHfFlcQvNekmcEl9ekUZQQKCYaDcA=
345+go.opentelemetry.io/auto/sdk v1.1.0 h1:cH53jehLUN6UFLY71z+NDOiNJqDdPRaXzTel0sJySYA=
346+go.opentelemetry.io/auto/sdk v1.1.0/go.mod h1:3wSPjt5PWp2RhlCcmmOial7AvC4DQqZb7a7wCow3W8A=
347+go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.61.0 h1:q4XOmH/0opmeuJtPsbFNivyl7bCt7yRBbeEm2sC/XtQ=
348+go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.61.0/go.mod h1:snMWehoOh2wsEwnvvwtDyFCxVeDAODenXHtn5vzrKjo=
349+go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.61.0 h1:F7Jx+6hwnZ41NSFTO5q4LYDtJRXBf2PD0rNBkeB/lus=
350+go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.61.0/go.mod h1:UHB22Z8QsdRDrnAtX4PntOl36ajSxcdUMt1sF7Y6E7Q=
351+go.opentelemetry.io/otel v1.37.0 h1:9zhNfelUvx0KBfu/gb+ZgeAfAgtWrfHJZcAqFC228wQ=
352+go.opentelemetry.io/otel v1.37.0/go.mod h1:ehE/umFRLnuLa/vSccNq9oS1ErUlkkK71gMcN34UG8I=
353+go.opentelemetry.io/otel/metric v1.37.0 h1:mvwbQS5m0tbmqML4NqK+e3aDiO02vsf/WgbsdpcPoZE=
354+go.opentelemetry.io/otel/metric v1.37.0/go.mod h1:04wGrZurHYKOc+RKeye86GwKiTb9FKm1WHtO+4EVr2E=
355+go.opentelemetry.io/otel/sdk v1.36.0 h1:b6SYIuLRs88ztox4EyrvRti80uXIFy+Sqzoh9kFULbs=
356+go.opentelemetry.io/otel/sdk v1.36.0/go.mod h1:+lC+mTgD+MUWfjJubi2vvXWcVxyr9rmlshZni72pXeY=
357+go.opentelemetry.io/otel/sdk/metric v1.36.0 h1:r0ntwwGosWGaa0CrSt8cuNuTcccMXERFwHX4dThiPis=
358+go.opentelemetry.io/otel/sdk/metric v1.36.0/go.mod h1:qTNOhFDfKRwX0yXOqJYegL5WRaW376QbB7P4Pb0qva4=
359+go.opentelemetry.io/otel/trace v1.37.0 h1:HLdcFNbRQBE2imdSEgm/kwqmQj1Or1l/7bW6mxVK7z4=
360+go.opentelemetry.io/otel/trace v1.37.0/go.mod h1:TlgrlQ+PtQO5XFerSPUYG0JSgGyryXewPGyayAWSBS0=
448361go.uber.org/multierr v1.11.0 h1:blXXJkSxSSfBVBlC76pxqeO+LN3aDfLQo+309xJstO0=
449362go.uber.org/multierr v1.11.0/go.mod h1:20+QtiLqy0Nd6FdQB9TLXag12DsQkrbs3htMFfDN80Y=
450363go.yaml.in/yaml/v3 v3.0.4/go.mod h1:DhzuOOF2ATzADvBadXxruRBLzYTpT36CKvDb3+aBEFg=
451364go.yaml.in/yaml/v4 v4.0.0-rc.3 h1:3h1fjsh1CTAPjW7q/EMe+C8shx5d8ctzZTrLcs/j8Go=
452365go.yaml.in/yaml/v4 v4.0.0-rc.3/go.mod h1:aZqd9kCMsGL7AuUv/m/PvWLdg5sjJsZ4oHDEnfPPfY0=
453−golang.design/x/clipboard v0.8.0 h1:6VEcH28wwcSgKc+vnxHHDWiRjrakTQIAJnPUrt3aOgg=
454−golang.design/x/clipboard v0.8.0/go.mod h1:s0pwrtA3Q9fgnVtGDmP5ZK/pp55cQKB23esKsjwWhWM=
455−golang.design/x/x11 v0.2.0 h1:Uiwu2guGihsJX/ZCzpoDPFz5gR/Qntm08mvoBCmRydo=
456−golang.design/x/x11 v0.2.0/go.mod h1:/5q1mFkdc1rL8mvB7DsQFi6as4tIkBv4FXjcP07mrkE=
457366golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
458367golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
459368golang.org/x/crypto v0.13.0/go.mod h1:y6Z2r+Rw4iayiXXAIxJIDAJ1zMW4yaTpebo8fPOliYc=
@@ -461,24 +370,19 @@ golang.org/x/crypto v0.19.0/go.mod h1:Iy9bg/ha4yyC70EfRS8jz+B6ybOBKMaSxLj6P6oBDf
461370golang.org/x/crypto v0.22.0/go.mod h1:vr6Su+7cTlO45qkww3VDJlzDn0ctJvRgYbC2NvXHt+M=
462371golang.org/x/crypto v0.23.0/go.mod h1:CKFgDieR+mRhux2Lsu27y0fO304Db0wZe70UKqHu0v8=
463372golang.org/x/crypto v0.31.0/go.mod h1:kDsLvtWBEx7MV9tJOj9bnXsPbxwJQ6csT/x4KIN4Ssk=
464−golang.org/x/crypto v0.53.0 h1:QZ4Muo8THX6CizN2vPPd5fBGHyogrdK9fG4wLPFUsto=
465−golang.org/x/crypto v0.53.0/go.mod h1:DNLU434OwVakk9PzuwV8w62mAJpRJL3vsgcfp4Qnsio=
466−golang.org/x/exp v0.0.0-20260410095643-746e56fc9e2f h1:W3F4c+6OLc6H2lb//N1q4WpJkhzJCK5J6kUi1NTVXfM=
467−golang.org/x/exp v0.0.0-20260410095643-746e56fc9e2f/go.mod h1:J1xhfL/vlindoeF/aINzNzt2Bket5bjo9sdOYzOsU80=
468−golang.org/x/exp/shiny v0.0.0-20250606033433-dcc06ee1d476 h1:Wdx0vgH5Wgsw+lF//LJKmWOJBLWX6nprsMqnf99rYDE=
469−golang.org/x/exp/shiny v0.0.0-20250606033433-dcc06ee1d476/go.mod h1:ygj7T6vSGhhm/9yTpOQQNvuAUFziTH7RUiH74EoE2C8=
470−golang.org/x/image v0.0.0-20191009234506-e7c1f5e7dbb8/go.mod h1:FeLwcggjj3mMvU+oOTbSwawSJRM1uh48EjtB4UJZlP0=
471−golang.org/x/image v0.43.0 h1:FLxcP4ec2350nTfOC8ysKtqYSIFbk/QGjw1ZHNP4tsY=
472−golang.org/x/image v0.43.0/go.mod h1:rrpelvGFt+kLPAjPM4HeWPgrl0FtafueU//e5N0qk/Q=
473−golang.org/x/mobile v0.0.0-20250606033058-a2a15c67f36f h1:/n+PL2HlfqeSiDCuhdBbRNlGS/g2fM4OHufalHaTVG8=
474−golang.org/x/mobile v0.0.0-20250606033058-a2a15c67f36f/go.mod h1:ESkJ836Z6LpG6mTVAhA48LpfW/8fNR0ifStlH2axyfg=
373+golang.org/x/crypto v0.46.0 h1:cKRW/pmt1pKAfetfu+RCEvjvZkA9RimPbh7bhFjGVBU=
374+golang.org/x/crypto v0.46.0/go.mod h1:Evb/oLKmMraqjZ2iQTwDwvCtJkczlDuTmdJXoZVzqU0=
375+golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b h1:M2rDM6z3Fhozi9O7NWsxAkg/yqS/lQJ6PmkyIV3YP+o=
376+golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b/go.mod h1:3//PLf8L/X+8b4vuAfHzxeRUl04Adcb341+IGKfnqS8=
377+golang.org/x/image v0.27.0 h1:C8gA4oWU/tKkdCfYT6T2u4faJu3MeNS5O8UPWlPF61w=
378+golang.org/x/image v0.27.0/go.mod h1:xbdrClrAUway1MUTEZDq9mz/UpRwYAkFFNUslZtcB+g=
475379golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
476380golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
477381golang.org/x/mod v0.12.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
478382golang.org/x/mod v0.15.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
479383golang.org/x/mod v0.17.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
480−golang.org/x/mod v0.36.0 h1:JJjpVx6myfUsUdAzZuOSTTmRE0PfZeNWzzvKrP7amb4=
481−golang.org/x/mod v0.36.0/go.mod h1:moc6ELqsWcOw5Ef3xVprK5ul/MvtVvkIXLziUOICjUQ=
384+golang.org/x/mod v0.31.0 h1:HaW9xtz0+kOcWKwli0ZXy79Ix+UW/vOfmWI5QVd2tgI=
385+golang.org/x/mod v0.31.0/go.mod h1:43JraMp9cGx1Rx3AqioxrbrhNsLl2l/iNAvuBkrezpg=
482386golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
483387golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
484388golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
@@ -490,10 +394,10 @@ golang.org/x/net v0.21.0/go.mod h1:bIjVDfnllIU7BJ2DNgfnXvpSvtn8VRwhlsaeUTyUS44=
490394golang.org/x/net v0.24.0/go.mod h1:2Q7sJY5mzlzWjKtYUEXSlBWCdyaioyXzRB2RtU8KVE8=
491395golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM=
492396golang.org/x/net v0.33.0/go.mod h1:HXLR5J+9DxmrqMwG9qjGCxZ+zKXxBru04zlTvWlWuN4=
493−golang.org/x/net v0.56.0 h1:Rw8j/hFzGvJUZwNBXnAtf5sVDVt+65SK2C7IxCxZt5o=
494−golang.org/x/net v0.56.0/go.mod h1:D3Ku6r+V6JROoZK144D2XfMHFcMq/0zSfLelVTCFKec=
495−golang.org/x/oauth2 v0.36.0 h1:peZ/1z27fi9hUOFCAZaHyrpWG5lwe0RJEEEeH0ThlIs=
496−golang.org/x/oauth2 v0.36.0/go.mod h1:YDBUJMTkDnJS+A4BP4eZBjCqtokkg1hODuPjwiGPO7Q=
397+golang.org/x/net v0.48.0 h1:zyQRTTrjc33Lhh0fBgT/H3oZq9WuvRR5gPC70xpDiQU=
398+golang.org/x/net v0.48.0/go.mod h1:+ndRgGjkh8FGtu1w1FGbEC31if4VrNVMuKTgcAAnQRY=
399+golang.org/x/oauth2 v0.34.0 h1:hqK/t4AKgbqWkdkcAeI8XLmbK+4m4G5YeQRrmiotGlw=
400+golang.org/x/oauth2 v0.34.0/go.mod h1:lzm5WQJQwKZ3nwavOZ3IS5Aulzxi68dUSgRHujetwEA=
497401golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
498402golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
499403golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
@@ -501,8 +405,8 @@ golang.org/x/sync v0.3.0/go.mod h1:FU7BRWz2tNW+3quACPkgCx/L+uEAv1htQ0V83Z9Rj+Y=
501405golang.org/x/sync v0.6.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
502406golang.org/x/sync v0.7.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
503407golang.org/x/sync v0.10.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
504−golang.org/x/sync v0.21.0 h1:HLII4xRRTtCRkxYp4HNFF0Js/Og6q2i++KXbg0gHCwM=
505−golang.org/x/sync v0.21.0/go.mod h1:9xrNwdLfx4jkKbNva9FpL6vEN7evnE43NNNJQ2LF3+0=
408+golang.org/x/sync v0.19.0 h1:vV+1eWNmZ5geRlYjzm2adRgW2/mcpevXNg50YZtPCE4=
409+golang.org/x/sync v0.19.0/go.mod h1:9KTHXmSnoGruLpwFjVSX0lNNA75CykiMECbovNTZqGI=
506410golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
507411golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
508412golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
@@ -511,6 +415,7 @@ golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBc
511415golang.org/x/sys v0.0.0-20220908164124-27713097b956/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
512416golang.org/x/sys v0.1.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
513417golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
418+golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
514419golang.org/x/sys v0.7.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
515420golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
516421golang.org/x/sys v0.12.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
@@ -518,8 +423,8 @@ golang.org/x/sys v0.17.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
518423golang.org/x/sys v0.19.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
519424golang.org/x/sys v0.20.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
520425golang.org/x/sys v0.28.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
521−golang.org/x/sys v0.46.0 h1:noSf2Fq6F8DBgS+LysIkx7rIExoNHJsxOAtPp4rthXw=
522−golang.org/x/sys v0.46.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
426+golang.org/x/sys v0.39.0 h1:CvCKL8MeisomCi6qNZ+wbb0DN9E5AATixKsvNtMoMFk=
427+golang.org/x/sys v0.39.0/go.mod h1:OgkHotnGiDImocRcuBABYBEXf8A9a87e/uXjp9XT3ks=
523428golang.org/x/telemetry v0.0.0-20240228155512-f48c80bd79b2/go.mod h1:TeRTkGYfJXctD9OcfyVLyj2J3IxLnKwHJR8f4D8a3YE=
524429golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
525430golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
@@ -531,8 +436,8 @@ golang.org/x/term v0.17.0/go.mod h1:lLRBjIVuehSbZlaOtGMbcMncT+aqLLLmKrsjNrUguwk=
531436golang.org/x/term v0.19.0/go.mod h1:2CuTdWZ7KHSQwUzKva0cbMg6q2DMI3Mmxp+gKJbskEk=
532437golang.org/x/term v0.20.0/go.mod h1:8UkIAJTvZgivsXaD6/pH6U9ecQzZ45awqEOzuCvwpFY=
533438golang.org/x/term v0.27.0/go.mod h1:iMsnZpn0cago0GOrHO2+Y7u7JPn5AylBrcoWkElMTSM=
534−golang.org/x/term v0.44.0 h1:0rLvDRCtNj0gZkyIXhCyOb2OAzEhLVqc4B+hrsBhrmc=
535−golang.org/x/term v0.44.0/go.mod h1:7ze4MdzUzLXpSAoFP1H0bOI9aXDqveSvatT5vKcFh2Y=
439+golang.org/x/term v0.38.0 h1:PQ5pkm/rLO6HnxFR7N2lJHOZX6Kez5Y1gDSJla6jo7Q=
440+golang.org/x/term v0.38.0/go.mod h1:bSEAKrOT1W+VSu9TSCMtoGEOUcKxOKgl3LE5QEF/xVg=
536441golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
537442golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
538443golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
@@ -542,39 +447,31 @@ golang.org/x/text v0.13.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE=
542447golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
543448golang.org/x/text v0.15.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
544449golang.org/x/text v0.21.0/go.mod h1:4IBbMaMmOPCJ8SecivzSH54+73PCFmPWxNTLm+vZkEQ=
545−golang.org/x/text v0.38.0 h1:sXmwo9DwP3OK9EZ7PqAdaooSGozfl/3a6/xJcbzPRhE=
546−golang.org/x/text v0.38.0/go.mod h1:YXZt3QhHUKYT53r2lLKFIVi6Ao1jdzrTR/KQ09qyxF4=
547−golang.org/x/time v0.15.0 h1:bbrp8t3bGUeFOx08pvsMYRTCVSMk89u4tKbNOZbp88U=
548−golang.org/x/time v0.15.0/go.mod h1:Y4YMaQmXwGQZoFaVFk4YpCt4FLQMYKZe9oeV/f4MSno=
450+golang.org/x/text v0.32.0 h1:ZD01bjUt1FQ9WJ0ClOL5vxgxOI/sVCNgX1YtKwcY0mU=
451+golang.org/x/text v0.32.0/go.mod h1:o/rUWzghvpD5TXrTIBuJU77MTaN0ljMWE47kxGJQ7jY=
452+golang.org/x/time v0.12.0 h1:ScB/8o8olJvc+CQPWrK3fPZNfh7qgwCrY0zJmoEQLSE=
453+golang.org/x/time v0.12.0/go.mod h1:CDIdPxbZBQxdj6cxyCIdrNogrJKMJ7pr37NYpMcMDSg=
549454golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
550455golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
551456golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=
552457golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU=
553458golang.org/x/tools v0.13.0/go.mod h1:HvlwmtVNQAhOuCjW7xxvovg8wbNq7LwfXh/k7wXUl58=
554459golang.org/x/tools v0.21.1-0.20240508182429-e35e4ccd0d2d/go.mod h1:aiJjzUbINMkxbQROHiO6hDPo2LHcIPhhQsa9DLh0yGk=
555−golang.org/x/tools v0.45.0 h1:18qN3FAooORvApf5XjCXgsuayZOEtXf6JK18I3+ONa8=
556−golang.org/x/tools v0.45.0/go.mod h1:LuUGqqaXcXMEFEruIVJVm5mgDD8vww/z/SR1gQ4uE/0=
460+golang.org/x/tools v0.39.0 h1:ik4ho21kwuQln40uelmciQPp9SipgNDdrafrYA4TmQQ=
461+golang.org/x/tools v0.39.0/go.mod h1:JnefbkDPyD8UU2kI5fuf8ZX4/yUeh9W877ZeBONxUqQ=
557462golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
558−gonum.org/v1/gonum v0.17.0 h1:VbpOemQlsSMrYmn7T2OUvQ4dqxQXU+ouZFQsZOx50z4=
559−gonum.org/v1/gonum v0.17.0/go.mod h1:El3tOrEuMpv2UdMrbNlKEh9vd86bmQ6vqIcDwxEOc1E=
560−google.golang.org/api v0.286.0 h1:TdTXMvzYKnWV1/lPbCdbXRqBrkDqjPto22H2xeZZ8LI=
561−google.golang.org/api v0.286.0/go.mod h1:NlOlUIr8MPoIhT9Bb/oUnRuHbJOLwxb6JSYJM8Yz+jQ=
562−google.golang.org/genai v1.62.0 h1:PaBju84orf4Vbcc6OfHe4vxhxhjwulKTgOpEc3iIc00=
563−google.golang.org/genai v1.62.0/go.mod h1:mDdPDFXo1Ats7f1WXVyZgWb/CkMzFWTWJruIMy7hGIU=
564−google.golang.org/genproto v0.0.0-20260622175928-b703f567277d h1:CP5omUq8AJTiWMrPKM1WRLJ7zZeXd9OPcQD3TbBNAyY=
565−google.golang.org/genproto v0.0.0-20260622175928-b703f567277d/go.mod h1:DrwuGJgFSEVNpv3S5Q5VxhRTvdnjauw9GtvwVOEARfA=
566−google.golang.org/genproto/googleapis/api v0.0.0-20260622175928-b703f567277d h1:xr2lwHI91bn3UiXcnyzRMQjp2LRiM8wEHzwUaE0YhTs=
567−google.golang.org/genproto/googleapis/api v0.0.0-20260622175928-b703f567277d/go.mod h1:O0ZOWSrfWfJ+Z5HbwZ+wNtHsg/vk1k2C/w67eww8PfQ=
568−google.golang.org/genproto/googleapis/rpc v0.0.0-20260622175928-b703f567277d h1:mpAgMyM9vQHxycBlDq50y1VHpfSfVwzXvrQKtYbXuUY=
569−google.golang.org/genproto/googleapis/rpc v0.0.0-20260622175928-b703f567277d/go.mod h1:4Hqkh8ycfw05ld/3BWL7rJOSfebL2Q+DVDeRgYgxUU8=
570−google.golang.org/grpc v1.81.1 h1:VnnIIZ88UzOOKLukQi+ImGz8O1Wdp8nAGGnvOfEIWQQ=
571−google.golang.org/grpc v1.81.1/go.mod h1:xGH9GfzOyMTGIOXBJmXt+BX/V0kcdQbdcuwQ/zNw42I=
572−google.golang.org/protobuf v1.36.11 h1:fV6ZwhNocDyBLK0dj+fg8ektcVegBBuEolpbTQyBNVE=
573−google.golang.org/protobuf v1.36.11/go.mod h1:HTf+CrKn2C3g5S8VImy6tdcUvCska2kB7j23XfzDpco=
463+google.golang.org/api v0.239.0 h1:2hZKUnFZEy81eugPs4e2XzIJ5SOwQg0G82bpXD65Puo=
464+google.golang.org/api v0.239.0/go.mod h1:cOVEm2TpdAGHL2z+UwyS+kmlGr3bVWQQ6sYEqkKje50=
465+google.golang.org/genai v1.39.0 h1:80I1sYFGROliWNxEgPWDklNYVO8xq/bNvw70BFh6XmA=
466+google.golang.org/genai v1.39.0/go.mod h1:A3kkl0nyBjyFlNjgxIwKq70julKbIxpSxqKO5gw/gmk=
467+google.golang.org/genproto/googleapis/rpc v0.0.0-20250603155806-513f23925822 h1:fc6jSaCT0vBduLYZHYrBBNY4dsWuvgyff9noRNDdBeE=
468+google.golang.org/genproto/googleapis/rpc v0.0.0-20250603155806-513f23925822/go.mod h1:qQ0YXyHHx3XkvlzUtpXDkS29lDSafHMZBAZDc03LQ3A=
469+google.golang.org/grpc v1.74.2 h1:WoosgB65DlWVC9FqI82dGsZhWFNBSLjQ84bjROOpMu4=
470+google.golang.org/grpc v1.74.2/go.mod h1:CtQ+BGjaAIXHs/5YS3i473GqwBBa1zGQNevxdeBEXrM=
471+google.golang.org/protobuf v1.36.10 h1:AYd7cD/uASjIL6Q9LiTjz8JLcrh/88q5UObnmY3aOOE=
472+google.golang.org/protobuf v1.36.10/go.mod h1:HTf+CrKn2C3g5S8VImy6tdcUvCska2kB7j23XfzDpco=
574473gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
575−gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
576474gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
577−gopkg.in/check.v1 v1.0.0-20200227125254-8fa46927fb4f/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
578475gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
579476gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
580477gopkg.in/dnaeon/go-vcr.v4 v4.0.6-0.20251110073552-01de4eb40290 h1:g3ah7zaWmw41EtOgBNXpx8zk4HYuH3OMwB+qh1Dt834=
@@ -583,44 +480,21 @@ gopkg.in/natefinch/lumberjack.v2 v2.2.1 h1:bBRl1b0OH9s/DuPhuXpNl+VtCaJXFZ5/uEFST
583480gopkg.in/natefinch/lumberjack.v2 v2.2.1/go.mod h1:YD8tP3GAjkrDg1eZH7EGmyESg/lsYskCTPBJVb9jqSc=
584481gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7 h1:uRGJdciOHaEIrze2W8Q3AKkepLTh2hOroT7a+7czfdQ=
585482gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7/go.mod h1:dt/ZhP58zS4L8KSrWDmTeBkI65Dw0HsyUHuEVlX15mw=
586−gopkg.in/warnings.v0 v0.1.2 h1:wFXVbFY8DY5/xOe1ECiWdKCzZlxgshcYVNkBHstARME=
587−gopkg.in/warnings.v0 v0.1.2/go.mod h1:jksf8JmL6Qr/oQM2OXTHunEvvTAsrWBLb6OOjuVWRNI=
588483gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
589484gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY=
590485gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ=
591486gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
592−gopkg.in/yaml.v3 v3.0.0-20200615113413-eeeca48fe776/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
593487gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
594488gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
595−modernc.org/cc/v4 v4.28.4 h1:Hd/4Es+MBj+/7hSdZaisNyu6bv3V0Dp2MdllyfqaH+c=
596−modernc.org/cc/v4 v4.28.4/go.mod h1:OnovgIhbbMXMu1aISnJ0wvVD1KnW+cAUJkIrAWh+kVI=
597−modernc.org/ccgo/v4 v4.34.4 h1:OVnSOWQjVKOYkFxoHYB+qQmSHK5gqMqARM+K9DpR/Ws=
598−modernc.org/ccgo/v4 v4.34.4/go.mod h1:qdKqE8FNIYyysougB1RX9MxCzp5oJOcQXSobANJ4TuE=
599−modernc.org/fileutil v1.4.0 h1:j6ZzNTftVS054gi281TyLjHPp6CPHr2KCxEXjEbD6SM=
600−modernc.org/fileutil v1.4.0/go.mod h1:EqdKFDxiByqxLk8ozOxObDSfcVOv/54xDs/DUHdvCUU=
601−modernc.org/gc/v2 v2.6.5 h1:nyqdV8q46KvTpZlsw66kWqwXRHdjIlJOhG6kxiV/9xI=
602−modernc.org/gc/v2 v2.6.5/go.mod h1:YgIahr1ypgfe7chRuJi2gD7DBQiKSLMPgBQe9oIiito=
603−modernc.org/gc/v3 v3.1.3 h1:6QAplYyVO+KdPW3pGnqmJDUxtkec8ooEWvks/hhU3lc=
604−modernc.org/gc/v3 v3.1.3/go.mod h1:HFK/6AGESC7Ex+EZJhJ2Gni6cTaYpSMmU/cT9RmlfYY=
605−modernc.org/goabi0 v0.2.0 h1:HvEowk7LxcPd0eq6mVOAEMai46V+i7Jrj13t4AzuNks=
606−modernc.org/goabi0 v0.2.0/go.mod h1:CEFRnnJhKvWT1c1JTI3Avm+tgOWbkOu5oPA8eH8LnMI=
607−modernc.org/libc v1.73.4 h1:+ra4Ui8ngyt8HDcO1FTDPWlkAh6yOdaO2yAoh8MddQA=
608−modernc.org/libc v1.73.4/go.mod h1:DXZ3eO8qMCNn2SnmTNCiC71nJ9Rcq3PsnpU6Vc4rWK8=
489+modernc.org/libc v1.66.3 h1:cfCbjTUcdsKyyZZfEUKfoHcP3S0Wkvz3jgSzByEWVCQ=
490+modernc.org/libc v1.66.3/go.mod h1:XD9zO8kt59cANKvHPXpx7yS2ELPheAey0vjIuZOhOU8=
609491modernc.org/mathutil v1.7.1 h1:GCZVGXdaN8gTqB1Mf/usp1Y/hSqgI2vAGGP4jZMCxOU=
610492modernc.org/mathutil v1.7.1/go.mod h1:4p5IwJITfppl0G4sUEDtCr4DthTaT47/N3aT6MhfgJg=
611493modernc.org/memory v1.11.0 h1:o4QC8aMQzmcwCK3t3Ux/ZHmwFPzE6hf2Y5LbkRs+hbI=
612494modernc.org/memory v1.11.0/go.mod h1:/JP4VbVC+K5sU2wZi9bHoq2MAkCnrt2r98UGeSK7Mjw=
613−modernc.org/opt v0.2.0 h1:tGyef5ApycA7FSEOMraay9SaTk5zmbx7Tu+cJs4QKZg=
614−modernc.org/opt v0.2.0/go.mod h1:03fq9lsNfvkYSfxrfUhZCWPk1lm4cq4N+Bh//bEtgns=
615−modernc.org/sortutil v1.2.1 h1:+xyoGf15mM3NMlPDnFqrteY07klSFxLElE2PVuWIJ7w=
616−modernc.org/sortutil v1.2.1/go.mod h1:7ZI3a3REbai7gzCLcotuw9AC4VZVpYMjDzETGsSMqJE=
617−modernc.org/sqlite v1.53.0 h1:20WG8N9q4ji/dEqGk4uiI0c6OPjSeLTNYGFCc3+7c1M=
618−modernc.org/sqlite v1.53.0/go.mod h1:xoEpOIpGrgT48H5iiyt/YXPCZPEzlfmfFwtk8Lklw8s=
619−modernc.org/strutil v1.2.1 h1:UneZBkQA+DX2Rp35KcM69cSsNES9ly8mQWD71HKlOA0=
620−modernc.org/strutil v1.2.1/go.mod h1:EHkiggD70koQxjVdSBM3JKM7k6L0FbGE5eymy9i3B9A=
621−modernc.org/token v1.1.0 h1:Xl7Ap9dKaEs5kLoOQeQmPWevfnk/DM5qcLcYlA8ys6Y=
622−modernc.org/token v1.1.0/go.mod h1:UGzOrNV1mAFSEB63lOFHIpNRUVMvYTc6yu1SMY/XTDM=
495+modernc.org/sqlite v1.38.2 h1:Aclu7+tgjgcQVShZqim41Bbw9Cho0y/7WzYptXqkEek=
496+modernc.org/sqlite v1.38.2/go.mod h1:cPTJYSlgg3Sfg046yBShXENNtPrWrDX8bsbAQBzgQ5E=
623497mvdan.cc/sh/moreinterp v0.0.0-20250902163504-3cf4fd5717a5 h1:mO2lyKtGwu4mGQ+Qqjx0+fd5UU5BXhX/rslFmxd5aco=
624498mvdan.cc/sh/moreinterp v0.0.0-20250902163504-3cf4fd5717a5/go.mod h1:Of9PCedbLDYT8b3EyiYG64rNnx5nOp27OLCVdDrjJyo=
625−mvdan.cc/sh/v3 v3.13.1 h1:DP3TfgZhDkT7lerUdnp6PTGKyxxzz6T+cOlY/xEvfWk=
626−mvdan.cc/sh/v3 v3.13.1/go.mod h1:lXJ8SexMvEVcHCoDvAGLZgFJ9Wsm2sulmoNEXGhYZD0=
499+mvdan.cc/sh/v3 v3.12.1-0.20250902163504-3cf4fd5717a5 h1:e7Z/Lgw/zMijvQBVrfh/vUDZ+9FpuSLrJDVGBuoJtuo=
500+mvdan.cc/sh/v3 v3.12.1-0.20250902163504-3cf4fd5717a5/go.mod h1:P21wo2gLLe3426sP+CmANLBaixSEbRtPl35w3YlM6dg=
internal/agent/.env.sample−1
@@ -1,5 +1,4 @@
11CRUSH_ANTHROPIC_API_KEY=
2−CRUSH_HYPER_API_KEY=
32CRUSH_OPENAI_API_KEY=
43CRUSH_OPENROUTER_API_KEY=
54CRUSH_ZAI_API_KEY=
internal/agent/accepted_run_test.godeleted−231
@@ -1,231 +0,0 @@
1−package agent
2−
3−import (
4− "context"
5− "testing"
6−
7− "github.com/charmbracelet/crush/internal/message"
8− "github.com/stretchr/testify/assert"
9− "github.com/stretchr/testify/require"
10−)
11−
12−// newCancelTestAgent builds a DB-backed sessionAgent with no model. The
13−// tests here exercise the dispatch/cancel/persist paths, none of which
14−// reach agent.Stream, so a model is unnecessary.
15−func newCancelTestAgent(t *testing.T) (*sessionAgent, fakeEnv) {
16− t.Helper()
17− env := testEnv(t)
18− sa := NewSessionAgent(SessionAgentOptions{
19− Sessions: env.sessions,
20− Messages: env.messages,
21− }).(*sessionAgent)
22− return sa, env
23−}
24−
25−func (a *sessionAgent) acceptedCount(sessionID string) int {
26− c, _ := a.acceptedRuns.Get(sessionID)
27− return c
28−}
29−
30−func (a *sessionAgent) hasPendingCancel(sessionID string) bool {
31− mark, ok := a.cancelMark.Get(sessionID)
32− return ok && mark > 0
33−}
34−
35−func (a *sessionAgent) pendingCancelMark(sessionID string) uint64 {
36− mark, _ := a.cancelMark.Get(sessionID)
37− return mark
38−}
39−
40−func TestAcceptedRun_CloseIsIdempotent(t *testing.T) {
41− t.Parallel()
42− sa, _ := newCancelTestAgent(t)
43−
44− accept := sa.BeginAccepted("sid")
45− require.Equal(t, "sid", accept.SessionID())
46− require.Equal(t, 1, sa.acceptedCount("sid"))
47−
48− accept.Close()
49− require.Equal(t, 0, sa.acceptedCount("sid"))
50−
51− // Repeated Close must not underflow the counter.
52− accept.Close()
53− accept.Close()
54− require.Equal(t, 0, sa.acceptedCount("sid"))
55−}
56−
57−func TestAcceptedRun_MultipleReservations(t *testing.T) {
58− t.Parallel()
59− sa, _ := newCancelTestAgent(t)
60−
61− a1 := sa.BeginAccepted("sid")
62− a2 := sa.BeginAccepted("sid")
63− require.Equal(t, 2, sa.acceptedCount("sid"))
64−
65− a1.Close()
66− require.Equal(t, 1, sa.acceptedCount("sid"))
67−
68− a2.Close()
69− require.Equal(t, 0, sa.acceptedCount("sid"))
70−}
71−
72−func TestAcceptedRun_NilSafe(t *testing.T) {
73− t.Parallel()
74− var accept *AcceptedRun
75− require.Equal(t, "", accept.SessionID())
76− // Must not panic.
77− accept.Close()
78−}
79−
80−func TestCancel_IdleDoesNotRecordPendingCancel(t *testing.T) {
81− t.Parallel()
82− sa, _ := newCancelTestAgent(t)
83−
84− // No accepted run, no active request: a true no-op.
85− sa.Cancel("sid")
86− require.False(t, sa.hasPendingCancel("sid"))
87−}
88−
89−func TestCancel_AcceptedRecordsPendingCancel(t *testing.T) {
90− t.Parallel()
91− sa, _ := newCancelTestAgent(t)
92−
93− accept := sa.BeginAccepted("sid")
94− defer accept.Close()
95−
96− sa.Cancel("sid")
97− require.True(t, sa.hasPendingCancel("sid"))
98−}
99−
100−func TestCancel_SecondCancelWhilePendingIsNoOp(t *testing.T) {
101− t.Parallel()
102− sa, _ := newCancelTestAgent(t)
103−
104− accept := sa.BeginAccepted("sid")
105− defer accept.Close()
106−
107− sa.Cancel("sid")
108− require.True(t, sa.hasPendingCancel("sid"))
109−
110− // A second cancel while a pending cancel is already recorded must
111− // remain a single pending cancel; one Run consumes exactly one.
112− sa.Cancel("sid")
113− require.True(t, sa.hasPendingCancel("sid"))
114−}
115−
116−func TestRun_CancelOnEntryPersistsCanceledTurn(t *testing.T) {
117− t.Parallel()
118− sa, env := newCancelTestAgent(t)
119−
120− sess, err := env.sessions.Create(t.Context(), "session")
121− require.NoError(t, err)
122−
123− accept := sa.BeginAccepted(sess.ID)
124− // A cancel arrives in the accepted-but-not-yet-active window.
125− sa.Cancel(sess.ID)
126− require.True(t, sa.hasPendingCancel(sess.ID))
127−
128− result, err := sa.Run(t.Context(), SessionAgentCall{
129− SessionID: sess.ID,
130− Prompt: "hello",
131− Accepted: accept,
132− })
133− require.NoError(t, err)
134− require.Nil(t, result)
135−
136− // The pending cancel was consumed and the accept released.
137− require.False(t, sa.hasPendingCancel(sess.ID))
138− require.Equal(t, 0, sa.acceptedCount(sess.ID))
139−
140− msgs, err := env.messages.List(t.Context(), sess.ID)
141− require.NoError(t, err)
142− require.Len(t, msgs, 2)
143− assert.Equal(t, message.User, msgs[0].Role)
144− assert.Equal(t, message.Assistant, msgs[1].Role)
145− assert.Equal(t, message.FinishReasonCanceled, msgs[1].FinishReason())
146−}
147−
148−func TestPersistCanceledTurn_WritesBothWhenUserMissing(t *testing.T) {
149− t.Parallel()
150− sa, env := newCancelTestAgent(t)
151−
152− sess, err := env.sessions.Create(t.Context(), "session")
153− require.NoError(t, err)
154−
155− err = sa.persistCanceledTurn(t.Context(), SessionAgentCall{
156− SessionID: sess.ID,
157− Prompt: "hello",
158− }, false)
159− require.NoError(t, err)
160−
161− msgs, err := env.messages.List(t.Context(), sess.ID)
162− require.NoError(t, err)
163− require.Len(t, msgs, 2)
164− assert.Equal(t, message.User, msgs[0].Role)
165− assert.Equal(t, message.Assistant, msgs[1].Role)
166− assert.Equal(t, message.FinishReasonCanceled, msgs[1].FinishReason())
167−}
168−
169−func TestPersistCanceledTurn_WritesAssistantOnlyWhenUserCreated(t *testing.T) {
170− t.Parallel()
171− sa, env := newCancelTestAgent(t)
172−
173− sess, err := env.sessions.Create(t.Context(), "session")
174− require.NoError(t, err)
175−
176− // Simulate PrepareStep having already created the user message.
177− _, err = sa.createUserMessage(t.Context(), SessionAgentCall{
178− SessionID: sess.ID,
179− Prompt: "hello",
180− })
181− require.NoError(t, err)
182−
183− err = sa.persistCanceledTurn(t.Context(), SessionAgentCall{
184− SessionID: sess.ID,
185− Prompt: "hello",
186− }, true)
187− require.NoError(t, err)
188−
189− msgs, err := env.messages.List(t.Context(), sess.ID)
190− require.NoError(t, err)
191− require.Len(t, msgs, 2)
192− assert.Equal(t, message.User, msgs[0].Role)
193− assert.Equal(t, message.Assistant, msgs[1].Role)
194− assert.Equal(t, message.FinishReasonCanceled, msgs[1].FinishReason())
195−}
196−
197−func TestPersistCanceledTurn_SucceedsWithCanceledContext(t *testing.T) {
198− t.Parallel()
199− sa, env := newCancelTestAgent(t)
200−
201− sess, err := env.sessions.Create(t.Context(), "session")
202− require.NoError(t, err)
203−
204− // Simulate workspace shutdown having already canceled the run
205− // context. WithoutCancel must let the writes through.
206− ctx, cancel := context.WithCancel(t.Context())
207− cancel()
208−
209− err = sa.persistCanceledTurn(ctx, SessionAgentCall{
210− SessionID: sess.ID,
211− Prompt: "hello",
212− }, false)
213− require.NoError(t, err)
214−
215− msgs, err := env.messages.List(t.Context(), sess.ID)
216− require.NoError(t, err)
217− require.Len(t, msgs, 2)
218−}
219−
220−func TestClearPendingCancel(t *testing.T) {
221− t.Parallel()
222− sa, _ := newCancelTestAgent(t)
223−
224− accept := sa.BeginAccepted("sid")
225− defer accept.Close()
226− sa.Cancel("sid")
227− require.True(t, sa.hasPendingCancel("sid"))
228−
229− sa.clearPendingCancel("sid")
230− require.False(t, sa.hasPendingCancel("sid"))
231−}
internal/agent/agent.go+208−1380
@@ -12,78 +12,41 @@ import (
1212 "context"
1313 _ "embed"
1414 "encoding/base64"
15− "encoding/json"
1615 "errors"
1716 "fmt"
1817 "log/slog"
19− "math"
20− "net/http"
2118 "os"
22− "regexp"
2319 "strconv"
2420 "strings"
2521 "sync"
26− "sync/atomic"
2722 "time"
2823
29− "charm.land/catwalk/pkg/catwalk"
3024 "charm.land/fantasy"
3125 "charm.land/fantasy/providers/anthropic"
3226 "charm.land/fantasy/providers/bedrock"
3327 "charm.land/fantasy/providers/google"
3428 "charm.land/fantasy/providers/openai"
3529 "charm.land/fantasy/providers/openrouter"
36− "charm.land/fantasy/providers/vercel"
3730 "charm.land/lipgloss/v2"
31+ "github.com/charmbracelet/catwalk/pkg/catwalk"
3832 "github.com/charmbracelet/crush/internal/agent/hyper"
39− "github.com/charmbracelet/crush/internal/agent/notify"
4033 "github.com/charmbracelet/crush/internal/agent/tools"
41− "github.com/charmbracelet/crush/internal/agent/tools/mcp"
4234 "github.com/charmbracelet/crush/internal/config"
4335 "github.com/charmbracelet/crush/internal/csync"
4436 "github.com/charmbracelet/crush/internal/message"
45− "github.com/charmbracelet/crush/internal/pubsub"
37+ "github.com/charmbracelet/crush/internal/permission"
4638 "github.com/charmbracelet/crush/internal/session"
4739 "github.com/charmbracelet/crush/internal/stringext"
48− "github.com/charmbracelet/crush/internal/version"
49− "github.com/charmbracelet/x/ansi"
50− "github.com/charmbracelet/x/exp/charmtone"
5140)
5241
53−const (
54− DefaultSessionName = "Untitled Session"
55−
56− // Constants for auto-summarization thresholds
57− largeContextWindowThreshold = 200_000
58− largeContextWindowBuffer = 20_000
59− smallContextWindowRatio = 0.2
60−)
61−
62−var userAgent = fmt.Sprintf("Charm-Crush/%s (https://charm.land/crush)", version.Version)
63−
6442//go:embed templates/title.md
6543var titlePrompt []byte
6644
6745//go:embed templates/summary.md
6846var summaryPrompt []byte
6947
70−// Used to remove <think> tags from generated titles.
71−var (
72− thinkTagRegex = regexp.MustCompile(`(?s)<think>.*?</think>`)
73− orphanThinkTagRegex = regexp.MustCompile(`</?think>`)
74−)
75−
7648type SessionAgentCall struct {
77− SessionID string
78− // RunID, when non-empty, is the caller-supplied correlator that
79− // gets echoed back on the notify.RunComplete event emitted for
80− // this turn. It is preserved when the call is enqueued behind a
81− // busy session so the queued turn's terminal event is still
82− // recognisable to the original caller. Callers that need a
83− // reliable completion contract (e.g. `crush run` against a
84− // session that may be busy) MUST set it; SessionID alone is
85− // ambiguous when concurrent turns share the same session.
86− RunID string
49+ SessionID string
8750 Prompt string
8851 ProviderOptions fantasy.ProviderOptions
8952 Attachments []message.Attachment
@@ -93,45 +56,12 @@ type SessionAgentCall struct {
9356 TopK *int64
9457 FrequencyPenalty *float64
9558 PresencePenalty *float64
96− NonInteractive bool
97− // OnComplete, when non-nil, replaces the default RunComplete
98− // publish path: the inner Run hands the terminal payload to this
99− // callback instead of emitting it on the RunComplete broker. The
100− // coordinator uses this hook to coalesce the unauthorized →
101− // re-auth → retry chain into a single user-visible terminal
102− // event, so non-interactive clients (e.g. `crush run`) don't
103− // exit on a stale failed-attempt RunComplete before the
104− // successful retry. It is intentionally stripped when queueing
105− // a busy-session call (see Run): the originating
106− // coordinator.Run has long returned by the time the queued
107− // recursion drains, so falling back to the default broker
108− // publish keeps the event visible to subscribers.
109− OnComplete func(notify.RunComplete)
110− // Accepted, when non-nil, is the accept reservation taken by
111− // BeginAccepted before the call was dispatched onto a goroutine
112− // (the client/server fire-and-forget path). Run consumes it under
113− // dispatchMu[SessionID] once the accepted -> (cancel-on-entry |
114− // queued | active) transition has been chosen. When nil
115− // (in-process / local callers like AppWorkspace), behavior is
116− // unchanged and no accept tracking applies.
117− Accepted *AcceptedRun
118− // acceptSeq carries the accept sequence of the handle that produced
119− // this call after it has been enqueued and its Accepted handle
120− // stripped. The queue-drain paths compare it against a session's
121− // cancel mark so a follow-up queued before a cancel is dropped while
122− // one queued after the cancel survives. 0 means untracked (an
123− // in-process enqueue with no accept reservation), which the drain
124− // paths treat as covered by any present mark, preserving the
125− // pre-sequence behavior.
126− acceptSeq uint64
12759}
12860
12961type SessionAgent interface {
13062 Run(context.Context, SessionAgentCall) (*fantasy.AgentResult, error)
131− BeginAccepted(sessionID string) *AcceptedRun
13263 SetModels(large Model, small Model)
13364 SetTools(tools []fantasy.AgentTool)
134− SetSystemPrompt(systemPrompt string)
13565 Cancel(sessionID string)
13666 CancelAll()
13767 IsSessionBusy(sessionID string) bool
@@ -141,71 +71,28 @@ type SessionAgent interface {
14171 ClearQueue(sessionID string)
14272 Summarize(context.Context, string, fantasy.ProviderOptions) error
14373 Model() Model
144− GenerateTitle(ctx context.Context, sessionID, userPrompt string)
14574}
14675
14776type Model struct {
14877 Model fantasy.LanguageModel
14978 CatwalkCfg catwalk.Model
15079 ModelCfg config.SelectedModel
151− FlatRate bool
15280}
15381
15482type sessionAgent struct {
155− largeModel *csync.Value[Model]
156− smallModel *csync.Value[Model]
157− systemPromptPrefix *csync.Value[string]
158− systemPrompt *csync.Value[string]
159− tools *csync.Slice[fantasy.AgentTool]
160− toolsGen atomic.Uint64 // bumped by SetTools; lets PrepareStep skip re-copying unchanged tools
161−
83+ largeModel Model
84+ smallModel Model
85+ systemPromptPrefix string
86+ systemPrompt string
16287 isSubAgent bool
88+ tools []fantasy.AgentTool
16389 sessions session.Service
16490 messages message.Service
16591 disableAutoSummarize bool
16692 isYolo bool
167− notify pubsub.Publisher[notify.Notification]
168− runComplete pubsub.Publisher[notify.RunComplete]
16993
17094 messageQueue *csync.Map[string, []SessionAgentCall]
17195 activeRequests *csync.Map[string, context.CancelFunc]
172−
173− // dispatchMu holds a per-session mutex that serializes the
174− // accepted -> (cancel-on-entry | queued | active) transition in
175− // Run against a concurrent Cancel. The lock is held only during
176− // the brief handoff (no DB or LLM I/O under the lock).
177− dispatchMu *csync.Map[string, *sync.Mutex]
178− // acceptedRuns counts dispatched-but-not-yet-active runs per
179− // session. A counter > 0 means a dispatched prompt is in flight
180− // and has not yet completed the dispatch handoff in Run. Only
181− // BeginAccepted increments it; only AcceptedRun.Close decrements
182− // it.
183− acceptedRuns *csync.Map[string, int]
184− // cancelMark records, per session, a high-water accept sequence: an
185− // accepted handle is canceled by it iff the handle's sequence is at
186− // or below the mark. Cancel raises the mark to the latest sequence
187− // assigned at cancel time, so a single Cancel covers every prompt
188− // accepted-but-not-yet-active then, while a prompt accepted later
189− // (higher sequence) is never poisoned. Absent or 0 means no pending
190− // cancel. It is only raised by Cancel when acceptedRuns > 0, so an
191− // idle Escape never records a mark.
192− cancelMark *csync.Map[string, uint64]
193− // dispatchMuCreate guards lazy creation of per-session entries in
194− // dispatchMu so two goroutines can't race to lock different mutex
195− // instances for the same session.
196− dispatchMuCreate sync.Mutex
197− // acceptedMu serializes increments/decrements of acceptedRuns and
198− // the assignment of accept sequence numbers from acceptSeqGen. It
199− // is separate from dispatchMu so AcceptedRun.Close (which may run
200− // while Run holds dispatchMu for the same session) does not
201− // deadlock by re-entering the dispatch lock.
202− acceptedMu sync.Mutex
203− // acceptSeqGen is the monotonic source of accept sequence numbers.
204− // Each BeginAccepted increments it under acceptedMu and stamps the
205− // returned handle, so sequences strictly increase in accept order
206− // across the agent. Cancel uses its current value as the per-session
207− // high-water mark.
208− acceptSeqGen uint64
20996}
21097
21198type SessionAgentOptions struct {
@@ -219,466 +106,55 @@ type SessionAgentOptions struct {
219106 Sessions session.Service
220107 Messages message.Service
221108 Tools []fantasy.AgentTool
222− Notify pubsub.Publisher[notify.Notification]
223− RunComplete pubsub.Publisher[notify.RunComplete]
224109}
225110
226111func NewSessionAgent(
227112 opts SessionAgentOptions,
228113) SessionAgent {
229114 return &sessionAgent{
230− largeModel: csync.NewValue(opts.LargeModel),
231− smallModel: csync.NewValue(opts.SmallModel),
232− systemPromptPrefix: csync.NewValue(opts.SystemPromptPrefix),
233− systemPrompt: csync.NewValue(opts.SystemPrompt),
115+ largeModel: opts.LargeModel,
116+ smallModel: opts.SmallModel,
117+ systemPromptPrefix: opts.SystemPromptPrefix,
118+ systemPrompt: opts.SystemPrompt,
234119 isSubAgent: opts.IsSubAgent,
235120 sessions: opts.Sessions,
236121 messages: opts.Messages,
237122 disableAutoSummarize: opts.DisableAutoSummarize,
238− tools: csync.NewSliceFrom(opts.Tools),
123+ tools: opts.Tools,
239124 isYolo: opts.IsYolo,
240− notify: opts.Notify,
241− runComplete: opts.RunComplete,
242125 messageQueue: csync.NewMap[string, []SessionAgentCall](),
243126 activeRequests: csync.NewMap[string, context.CancelFunc](),
244− dispatchMu: csync.NewMap[string, *sync.Mutex](),
245− acceptedRuns: csync.NewMap[string, int](),
246− cancelMark: csync.NewMap[string, uint64](),
247− }
248−}
249−
250−// AcceptedRun owns exactly one accept reservation taken by
251−// BeginAccepted. It is the only carrier of accept-state across the
252−// backend.runAgent / Coordinator.Run / sessionAgent.Run layers: a
253−// counter > 0 means a dispatched prompt is in flight and has not yet
254−// completed the dispatch handoff in Run. Close is the only way to
255−// release the reservation and is idempotent.
256−type AcceptedRun struct {
257− agent *sessionAgent
258− sessionID string
259− // seq is the monotonic accept sequence stamped by BeginAccepted. A
260− // cancel covers this handle iff seq is at or below the session's
261− // cancel mark, so a handle accepted after a cancel (higher seq) is
262− // never poisoned by it.
263− seq uint64
264− done atomic.Bool
265−}
266−
267−// Close decrements the accept counter for this reservation. It is safe
268−// to call multiple times; only the first call has effect.
269−func (r *AcceptedRun) Close() {
270− if r == nil {
271− return
272− }
273− if !r.done.CompareAndSwap(false, true) {
274− return
275− }
276− r.agent.endAccepted(r.sessionID)
277−}
278−
279−// SessionID exposes the session this reservation is for so the run path
280−// can use it without an extra parameter.
281−func (r *AcceptedRun) SessionID() string {
282− if r == nil {
283− return ""
284− }
285− return r.sessionID
286−}
287−
288−// BeginAccepted increments the accept counter for sessionID and returns
289−// a handle whose Close is the only way to decrement it. It is the only
290−// entry point that mutates acceptedRuns.
291−func (a *sessionAgent) BeginAccepted(sessionID string) *AcceptedRun {
292− a.acceptedMu.Lock()
293− defer a.acceptedMu.Unlock()
294− count, _ := a.acceptedRuns.Get(sessionID)
295− a.acceptedRuns.Set(sessionID, count+1)
296− a.acceptSeqGen++
297− return &AcceptedRun{agent: a, sessionID: sessionID, seq: a.acceptSeqGen}
298−}
299−
300−// endAccepted decrements the accept counter for sessionID. It is only
301−// called via AcceptedRun.Close. It uses a dedicated lock (not the
302−// per-session dispatch mutex) so it can run while Run holds dispatchMu
303−// for the same session without deadlocking.
304−//
305−// When the count reaches zero the session's cancel mark is dropped: no
306−// accepted handle remains for it to cover, and any handle accepted later
307−// gets a strictly higher sequence that the mark would not match anyway.
308−// Handles canceled on entry never reach RunComplete, so this is the only
309−// place that clears the mark for an all-canceled batch. Sibling handles
310−// covered by the same mark are serialized on the per-session dispatch
311−// mutex and read the mark before they Close, so this never clears it out
312−// from under a covered handle still waiting to enter Run.
313−func (a *sessionAgent) endAccepted(sessionID string) {
314− a.acceptedMu.Lock()
315− defer a.acceptedMu.Unlock()
316− count, ok := a.acceptedRuns.Get(sessionID)
317− if !ok || count <= 1 {
318− a.acceptedRuns.Del(sessionID)
319− a.cancelMark.Del(sessionID)
320− return
321− }
322− a.acceptedRuns.Set(sessionID, count-1)
323−}
324−
325−// sessionMu returns the per-session dispatch mutex, creating it on first
326−// use. Creation is guarded so concurrent callers always observe the same
327−// mutex instance for a given session.
328−func (a *sessionAgent) sessionMu(sessionID string) *sync.Mutex {
329− if mu, ok := a.dispatchMu.Get(sessionID); ok {
330− return mu
331− }
332− a.dispatchMuCreate.Lock()
333− defer a.dispatchMuCreate.Unlock()
334− if mu, ok := a.dispatchMu.Get(sessionID); ok {
335− return mu
336− }
337− mu := &sync.Mutex{}
338− a.dispatchMu.Set(sessionID, mu)
339− return mu
340−}
341−
342−// enqueueCall appends call to the session's message queue. The
343−// OnComplete hook is stripped: the caller that supplied it (typically
344−// coordinator.Run) has its own retry/coalesce scope that ends when it
345−// returns, so by the time the queue drains nobody is left to consume the
346−// buffered terminal event. The recursive Run falls back to the default
347−// broker publish, which is what existing subscribers expect for queued
348−// turns.
349−func (a *sessionAgent) enqueueCall(call SessionAgentCall) {
350− existing, ok := a.messageQueue.Get(call.SessionID)
351− if !ok {
352− existing = make([]SessionAgentCall, 0, 4)
353− }
354− queued := call
355− if call.Accepted != nil {
356− // Preserve the accept sequence after the handle is stripped so
357− // the queue-drain paths can tell a follow-up queued before a
358− // cancel (covered by the mark) from one queued after it.
359− queued.acceptSeq = call.Accepted.seq
360− }
361− queued.OnComplete = nil
362− queued.Accepted = nil
363− existing = append(existing, queued)
364− a.messageQueue.Set(call.SessionID, existing)
365−}
366−
367−// drainQueueForStep partitions the session's queued calls for the current
368−// streaming step under the per-session dispatch mutex so the filtering is
369−// atomic against a concurrent Cancel: canceledBySeq requires the caller to
370−// hold that mutex, and evaluating it here (rather than after unlocking)
371−// prevents a cancel recorded between the drain and the check from being
372−// observed inconsistently.
373−//
374−// Calls covered by a pending cancel are dropped; the dropped ones that
375−// carry a RunID are returned in canceledWithRunID so the caller can
376−// publish their terminal cancelled RunComplete (a caller waiting on that
377−// RunID, e.g. `crush run`, would otherwise hang). Uncanceled calls without
378−// a RunID are returned in fold to be folded into the active turn,
379−// preserving the existing follow-up behavior. Uncanceled calls that carry
380−// a RunID are left in the queue so each runs as its own turn via the
381−// recursive run path and publishes its own RunComplete, giving every
382−// RunID-bearing prompt an explicit lifecycle instead of being silently
383−// absorbed into another turn. fold is processed by the caller without the
384−// lock held.
385−func (a *sessionAgent) drainQueueForStep(sessionID string) (fold, canceledWithRunID []SessionAgentCall) {
386− dispatchLock := a.sessionMu(sessionID)
387− dispatchLock.Lock()
388− defer dispatchLock.Unlock()
389− queuedCalls, _ := a.messageQueue.Get(sessionID)
390− var keep []SessionAgentCall
391− for _, queued := range queuedCalls {
392− if a.canceledBySeq(sessionID, queued.acceptSeq) {
393− if queued.RunID != "" {
394− canceledWithRunID = append(canceledWithRunID, queued)
395− }
396− continue
397− }
398− if queued.RunID != "" {
399− keep = append(keep, queued)
400− continue
401− }
402− fold = append(fold, queued)
403− }
404− if len(keep) == 0 {
405− a.messageQueue.Del(sessionID)
406− } else {
407− a.messageQueue.Set(sessionID, keep)
408− }
409− return fold, canceledWithRunID
410−}
411−
412−// publishCanceledQueueDrops emits a terminal cancelled RunComplete for
413−// every dropped queued call that carries a RunID. A queued prompt removed
414−// from the queue without ever running — covered by a pending cancel, or
415−// cleared by Cancel/ClearQueue — would otherwise leave a caller blocked on
416−// that RunID: `crush run` ignores live message events and exits only on a
417−// RunComplete whose RunID matches. Calls without a RunID had no such waiter
418−// and are dropped silently as before. A detached, bounded context keeps the
419−// must-deliver publish alive even when the run context that triggered the
420−// drop is already canceled.
421−func (a *sessionAgent) publishCanceledQueueDrops(drops []SessionAgentCall) {
422− var hasRunID bool
423− for _, d := range drops {
424− if d.RunID != "" {
425− hasRunID = true
426− break
427− }
428− }
429− if !hasRunID {
430− return
431− }
432− ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
433− defer cancel()
434− for _, d := range drops {
435− if d.RunID == "" {
436− continue
437− }
438− a.publishRunComplete(ctx, d, notify.RunComplete{
439− SessionID: d.SessionID,
440− RunID: d.RunID,
441− Cancelled: true,
442− })
443− }
444−}
445−
446−// clearQueueAndNotify removes all queued prompts for the session and
447−// publishes a terminal cancelled RunComplete for any that carried a RunID,
448−// so callers waiting on those RunIDs (e.g. `crush run`) are not left
449−// hanging when their queued prompt is discarded without running.
450−func (a *sessionAgent) clearQueueAndNotify(sessionID string) {
451− queued, ok := a.messageQueue.Get(sessionID)
452− a.messageQueue.Del(sessionID)
453− if !ok {
454− return
455− }
456− a.publishCanceledQueueDrops(queued)
457−}
458−
459−// clearPendingCancel removes any pending-cancel mark for sessionID. It
460−// takes the per-session dispatch lock so it is ordered against Cancel
461−// and the dispatch handoff.
462−func (a *sessionAgent) clearPendingCancel(sessionID string) {
463− mu := a.sessionMu(sessionID)
464− mu.Lock()
465− defer mu.Unlock()
466− a.cancelMark.Del(sessionID)
467−}
468−
469−// canceledBySeq reports whether an accepted handle or queued call with
470−// the given accept sequence is covered by a pending cancel for the
471−// session. Callers must hold the session's dispatch mutex. A tracked
472−// sequence (seq > 0) is covered only when it is at or below the cancel
473−// high-water mark, so a prompt accepted after the cancel (higher seq) is
474−// never poisoned. An untracked sequence (seq == 0, an in-process enqueue
475−// with no accept reservation) is covered whenever any mark is present,
476−// preserving the pre-sequence behavior. The mark is not consumed: it
477−// stays so every sibling handle it covers observes the same cancel, and
478−// a later handle (higher seq) ignores it regardless.
479−func (a *sessionAgent) canceledBySeq(sessionID string, seq uint64) bool {
480− mark, ok := a.cancelMark.Get(sessionID)
481− if !ok || mark == 0 {
482− return false
483− }
484− return seq == 0 || seq <= mark
485−}
486−
487−// persistCanceledTurn writes the user/assistant records for a turn that
488−// was canceled before (or just as) streaming would have produced them.
489−// It creates the user message only when it was not already created by an
490−// earlier createUserMessage call (userMsgCreated), then writes an
491−// assistant message with FinishReasonCanceled. Both writes use
492−// context.WithoutCancel(ctx) so workspace shutdown (which cancels the run
493−// context) can't drop them.
494−func (a *sessionAgent) persistCanceledTurn(ctx context.Context, call SessionAgentCall, userMsgCreated bool) error {
495− writeCtx, cancel := context.WithTimeout(context.WithoutCancel(ctx), 5*time.Second)
496− defer cancel()
497− if !userMsgCreated {
498− if _, err := a.createUserMessage(writeCtx, call); err != nil {
499− return err
500− }
501− }
502− largeModel := a.largeModel.Get()
503− assistant, err := a.messages.Create(writeCtx, call.SessionID, message.CreateMessageParams{
504− Role: message.Assistant,
505− Parts: []message.ContentPart{},
506− Model: largeModel.ModelCfg.Model,
507− Provider: largeModel.ModelCfg.Provider,
508− })
509− if err != nil {
510− return err
511127 }
512− assistant.AddFinish(message.FinishReasonCanceled, "User canceled request", "")
513− return a.messages.Update(writeCtx, assistant)
514128}
515129
516−// publishRunComplete emits the authoritative terminal event for a turn.
517−// It honors the per-call OnComplete hook when set (so the coordinator can
518−// coalesce retries) and otherwise falls back to the RunComplete broker.
519−// ctx is used only for the bounded-blocking must-deliver publish; the
520−// terminal payload is supplied by the caller. This is the single emit path
521−// shared by the streaming defer and the cancel-on-entry early return so a
522−// caller waiting on RunComplete (e.g. `crush run` with a RunID) always
523−// observes exactly one terminal event regardless of which Run branch ends
524−// the turn.
525−func (a *sessionAgent) publishRunComplete(ctx context.Context, call SessionAgentCall, complete notify.RunComplete) {
526− if call.OnComplete != nil {
527− call.OnComplete(complete)
528− return
529− }
530− if a.runComplete == nil {
531− return
532− }
533− a.runComplete.PublishMustDeliver(ctx, pubsub.UpdatedEvent, complete)
534−}
535−
536−// ValidateCall performs the cheap structural validation that
537−// sessionAgent.Run requires before a call can be dispatched: a call must
538−// carry either a non-empty prompt or a text attachment, and it must name a
539−// session. It is exported so callers that accept a run before dispatching it
540−// (e.g. backend.SendMessage) can apply the same checks and keep the error
541−// contract consistent.
542−func ValidateCall(call SessionAgentCall) error {
543− if call.Prompt == "" && !message.ContainsTextAttachment(call.Attachments) {
544− return ErrEmptyPrompt
130+func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (*fantasy.AgentResult, error) {
131+ if call.Prompt == "" {
132+ return nil, ErrEmptyPrompt
545133 }
546134 if call.SessionID == "" {
547− return ErrSessionMissing
548− }
549− return nil
550−}
551−
552−func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (result *fantasy.AgentResult, retErr error) {
553− if err := ValidateCall(call); err != nil {
554− return nil, err
135+ return nil, ErrSessionMissing
555136 }
556137
557− // genCtx/cancel are the run context and its cancel func. For the
558− // accepted (fire-and-forget) dispatch path they are created under
559− // dispatchMu below so a concurrent Cancel can observe the
560− // activeRequests entry before the assistant message exists. For
561− // the in-process path they stay nil here and are created later,
562− // preserving the original ordering.
563− var (
564− genCtx context.Context
565− cancel context.CancelFunc
566− activeRegistered bool
567− userMsgCreated bool
568− )
569−
570− if call.Accepted != nil {
571− // Serialize the accepted -> (cancel-on-entry | queued |
572− // active) transition against a concurrent Cancel. Cancel takes
573− // the same per-session lock, so every cancel observes at least
574− // one of: a cancel mark, an activeRequests entry, or a
575− // messageQueue entry it then clears.
576− mu := a.sessionMu(call.SessionID)
577− mu.Lock()
578−
579− if a.canceledBySeq(call.SessionID, call.Accepted.seq) {
580− // Cancel-on-entry: a cancel arrived while this run was
581− // dispatched but not yet active, and this handle's accept
582− // sequence is at or below the session's cancel mark. The
583− // mark is left in place so sibling handles it also covers
584− // observe the same cancel; release the accept reservation,
585− // drop the lock, and persist a canceled turn without
586− // entering Stream.
587− //
588− // This path returns before the streaming defer that
589− // publishes RunComplete is installed, so emit the terminal
590− // event explicitly. Without it, a caller waiting on
591− // RunComplete for this RunID (e.g. `crush run`, which
592− // ignores message events and blocks on RunComplete) would
593− // hang on an immediately-canceled accepted run.
594− call.Accepted.Close()
595− mu.Unlock()
596− complete := notify.RunComplete{
597− SessionID: call.SessionID,
598− RunID: call.RunID,
599− Cancelled: true,
600− }
601− if err := a.persistCanceledTurn(ctx, call, false); err != nil {
602− complete.Error = err.Error()
603− a.publishRunComplete(ctx, call, complete)
604− return nil, err
605− }
606− a.publishRunComplete(ctx, call, complete)
607− return nil, nil
608− }
609−
610− if a.IsSessionBusy(call.SessionID) {
611− // Busy: an earlier prompt is active. Queue this call and
612− // release the accept reservation. A Cancel arriving after
613− // this point sees the active entry and clears the queue.
614− a.enqueueCall(call)
615− call.Accepted.Close()
616− mu.Unlock()
617− return nil, nil
138+ // Queue the message if busy
139+ if a.IsSessionBusy(call.SessionID) {
140+ existing, ok := a.messageQueue.Get(call.SessionID)
141+ if !ok {
142+ existing = []SessionAgentCall{}
618143 }
619−
620− // Idle: become the active run. Register the cancel func before
621− // dropping the lock so a Cancel that arrives between here and
622− // assistant creation is not lost.
623− runCtx := context.WithValue(ctx, tools.SessionIDContextKey, call.SessionID)
624− genCtx, cancel = context.WithCancel(runCtx)
625− a.activeRequests.Set(call.SessionID, cancel)
626− activeRegistered = true
627− call.Accepted.Close()
628− mu.Unlock()
629−
630− defer cancel()
631− defer a.activeRequests.Del(call.SessionID)
632− } else if a.IsSessionBusy(call.SessionID) {
633− // Queue the message if busy. Strip OnComplete: the caller that
634− // supplied the hook (typically coordinator.Run) has its own
635− // retry/coalesce scope that ends when it returns, so by the time
636− // the queue drains nobody is left to consume the buffered
637− // terminal event. The recursive Run will fall back to the
638− // default broker publish, which is what existing subscribers
639− // expect for queued turns.
640− a.enqueueCall(call)
144+ existing = append(existing, call)
145+ a.messageQueue.Set(call.SessionID, existing)
641146 return nil, nil
642147 }
643148
644− // Copy mutable fields under lock to avoid races with SetTools/SetModels.
645− agentTools := a.tools.Copy()
646− // Per-step tool snapshot reused across PrepareStep calls; only
647− // re-copied when SetTools bumps toolsGen (see PrepareStep below).
648− var (
649− stepTools []fantasy.AgentTool
650− stepToolsGen uint64
651− stepToolsInit bool
652− )
653− largeModel := a.largeModel.Get()
654− systemPrompt := a.systemPrompt.Get()
655− promptPrefix := a.systemPromptPrefix.Get()
656− var instructions strings.Builder
657−
658− for _, server := range mcp.GetStates() {
659− if server.State != mcp.StateConnected {
660− continue
661− }
662− if s := server.Client.InitializeResult().Instructions; s != "" {
663− instructions.WriteString(s)
664− instructions.WriteString("\n\n")
665− }
666− }
667−
668− if s := instructions.String(); s != "" {
669− systemPrompt += "\n\n<mcp-instructions>\n" + s + "\n</mcp-instructions>"
670− }
671−
672− if len(agentTools) > 0 {
149+ if len(a.tools) > 0 {
673150 // Add Anthropic caching to the last tool.
674− agentTools[len(agentTools)-1].SetProviderOptions(a.getCacheControlOptions())
151+ a.tools[len(a.tools)-1].SetProviderOptions(a.getCacheControlOptions())
675152 }
676153
677154 agent := fantasy.NewAgent(
678− largeModel.Model,
679− fantasy.WithSystemPrompt(systemPrompt),
680− fantasy.WithTools(agentTools...),
681− fantasy.WithUserAgent(userAgent),
155+ a.largeModel.Model,
156+ fantasy.WithSystemPrompt(a.systemPrompt),
157+ fantasy.WithTools(a.tools...),
682158 )
683159
684160 sessionLock := sync.Mutex{}
@@ -693,115 +169,42 @@ func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (result *
693169 }
694170
695171 var wg sync.WaitGroup
696− // Generate title from the first real (non-shell) user prompt.
697− if !hasUserTextMessage(msgs) {
172+ // Generate title if first message.
173+ if len(msgs) == 0 {
698174 titleCtx := ctx // Copy to avoid race with ctx reassignment below.
699175 wg.Go(func() {
700− a.GenerateTitle(titleCtx, call.SessionID, call.Prompt)
176+ a.generateTitle(titleCtx, call.SessionID, call.Prompt)
701177 })
702178 }
703− defer wg.Wait()
704179
705180 // Add the user message to the session.
706181 _, err = a.createUserMessage(ctx, call)
707182 if err != nil {
708183 return nil, err
709184 }
710− userMsgCreated = true
711185
712186 // Add the session to the context.
713187 ctx = context.WithValue(ctx, tools.SessionIDContextKey, call.SessionID)
714188
715− // For the accepted dispatch path the run context and cancel func
716− // were already created and registered under dispatchMu above; reuse
717− // them. For the in-process path create them here, preserving the
718− // original ordering.
719− if !activeRegistered {
720− genCtx, cancel = context.WithCancel(ctx)
721− a.activeRequests.Set(call.SessionID, cancel)
189+ genCtx, cancel := context.WithCancel(ctx)
190+ a.activeRequests.Set(call.SessionID, cancel)
722191
723− defer cancel()
724− defer a.activeRequests.Del(call.SessionID)
725− }
726− // skipRunComplete is set just before the queued-recursion path so
727− // the outer Run doesn't publish a RunComplete that would race
728− // with — and be superseded by — the recursive call's own
729− // RunComplete (each queued user prompt is its own turn and
730− // publishes exactly one terminal event).
731− var skipRunComplete bool
732− // currentAssistant is declared here so the deferred RunComplete
733− // publish below can capture the pointer that PrepareStep will
734− // later (re)assign for each streaming step. The final assistant
735− // message of the turn is the value reachable through this
736− // pointer when the defer runs.
737− var currentAssistant *message.Message
738− // Drain any debounced message updates before returning. message.Service
739− // already flushes synchronously on terminal updates, but a defer here
740− // guarantees the contract at every Run exit (success, error, panic
741− // recovery upstream) without callers needing to know.
742− //
743− // After the flush completes — meaning all per-message
744− // Publish(UpdatedEvent) calls have fired and been buffered into
745− // every subscriber's channel — publish the authoritative
746− // RunComplete event for this turn. The flush-then-publish order
747− // gives well-behaved clients the best chance of seeing the final
748− // message event before RunComplete; the embedded Text field
749− // reconciles for clients that observe the events out of order
750− // (the pubsub broker fan-in does not serialize publishes from
751− // different upstream brokers).
752− defer func() {
753− // Use a context detached from the run context: workspace
754− // shutdown cancels ctx before this goroutine returns, but the
755− // buffered streaming deltas must still land before the DB is
756− // closed. A short timeout bounds the flush.
757− flushCtx, flushCancel := context.WithTimeout(context.WithoutCancel(ctx), 5*time.Second)
758− defer flushCancel()
759− if flushErr := a.messages.FlushAll(flushCtx); flushErr != nil {
760− slog.Error("Failed to flush pending message updates after run", "error", flushErr)
761− }
762− if skipRunComplete {
763− return
764− }
765− complete := notify.RunComplete{SessionID: call.SessionID, RunID: call.RunID}
766− if currentAssistant != nil {
767− complete.MessageID = currentAssistant.ID
768− complete.Text = currentAssistant.Content().String()
769− }
770− if retErr != nil {
771− complete.Error = retErr.Error()
772− complete.Cancelled = errors.Is(retErr, context.Canceled)
773− } else if ctx.Err() != nil {
774− complete.Cancelled = true
775− }
776− // Prefer the per-call hook when supplied so the coordinator
777− // can coalesce retries (e.g. unauthorized → re-auth → retry)
778− // into a single user-visible terminal event. The fallback
779− // must-deliver publish applies bounded-blocking semantics to
780− // the authoritative terminal event so a momentarily-full
781− // subscriber channel can't silently drop it and hang
782− // non-interactive clients waiting on RunComplete.
783− a.publishRunComplete(ctx, call, complete)
784− }()
785−
786− history, files := a.preparePrompt(msgs, largeModel.CatwalkCfg.SupportsImages, call.Attachments...)
192+ defer cancel()
193+ defer a.activeRequests.Del(call.SessionID)
194+
195+ history, files := a.preparePrompt(msgs, call.Attachments...)
787196
788197 startTime := time.Now()
789198 a.eventPromptSent(call.SessionID)
790199
791− var stepMessages []fantasy.Message
200+ var currentAssistant *message.Message
792201 var shouldSummarize bool
793− sanitizedToolCalls := make(map[string]bool)
794− // Don't send MaxOutputTokens if 0 — some providers (e.g. LM Studio) reject it
795− var maxOutputTokens *int64
796− if call.MaxOutputTokens > 0 {
797− maxOutputTokens = &call.MaxOutputTokens
798− }
799− result, err = agent.Stream(genCtx, fantasy.AgentStreamCall{
202+ result, err := agent.Stream(genCtx, fantasy.AgentStreamCall{
800203 Prompt: message.PromptWithTextAttachments(call.Prompt, call.Attachments),
801204 Files: files,
802205 Messages: history,
803206 ProviderOptions: call.ProviderOptions,
804− MaxOutputTokens: maxOutputTokens,
207+ MaxOutputTokens: &call.MaxOutputTokens,
805208 TopP: call.TopP,
806209 Temperature: call.Temperature,
807210 PresencePenalty: call.PresencePenalty,
@@ -813,30 +216,9 @@ func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (result *
813216 prepared.Messages[i].ProviderOptions = nil
814217 }
815218
816− // Use latest tools (updated by SetTools when MCP tools change).
817− // Reuse the previous step's copy unless SetTools has bumped the
818− // generation, so an unchanged tool set isn't re-copied every step.
819− if gen := a.toolsGen.Load(); !stepToolsInit || gen != stepToolsGen {
820− stepTools = a.tools.Copy()
821− stepToolsGen = gen
822− stepToolsInit = true
823− }
824− prepared.Tools = stepTools
825−
826− // Drain queued follow-up prompts for this step. Calls covered
827− // by a cancel recorded while they sat in the queue are dropped:
828− // a cancel that arrived after a prompt was queued must not let
829− // it run as part of this step. Coverage is per-call by accept
830− // sequence so a follow-up queued after the cancel (higher seq)
831− // is not dropped. A dropped prompt carrying a RunID still gets
832− // its terminal cancelled RunComplete so a caller waiting on it
833− // does not hang. Uncanceled prompts without a RunID are folded
834− // into this turn; uncanceled prompts with a RunID are left
835− // queued so each runs as its own turn (with its own
836− // RunComplete) via the recursive run path below.
837− fold, canceledRunIDs := a.drainQueueForStep(call.SessionID)
838− a.publishCanceledQueueDrops(canceledRunIDs)
839− for _, queued := range fold {
219+ queuedCalls, _ := a.messageQueue.Get(call.SessionID)
220+ a.messageQueue.Del(call.SessionID)
221+ for _, queued := range queuedCalls {
840222 userMessage, createErr := a.createUserMessage(callContext, queued)
841223 if createErr != nil {
842224 return callContext, prepared, createErr
@@ -844,7 +226,7 @@ func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (result *
844226 prepared.Messages = append(prepared.Messages, userMessage.ToAIMessage()...)
845227 }
846228
847− prepared.Messages = a.workaroundProviderMediaLimitations(prepared.Messages, largeModel)
229+ prepared.Messages = a.workaroundProviderMediaLimitations(prepared.Messages)
848230
849231 lastSystemRoleInx := 0
850232 systemMessageUpdated := false
@@ -862,30 +244,23 @@ func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (result *
862244 }
863245 }
864246
865− if promptPrefix != "" {
247+ if promptPrefix := a.promptPrefix(); promptPrefix != "" {
866248 prepared.Messages = append([]fantasy.Message{fantasy.NewSystemMessage(promptPrefix)}, prepared.Messages...)
867249 }
868250
869− // Save a reference to the prepared messages for token
870− // estimation in OnStepFinish. No clone needed here — the
871− // messages are not modified between PrepareStep and
872− // OnStepFinish (which run sequentially), and the clone is
873− // only needed when the provider returns zero usage.
874− stepMessages = prepared.Messages
875−
876251 var assistantMsg message.Message
877252 assistantMsg, err = a.messages.Create(callContext, call.SessionID, message.CreateMessageParams{
878253 Role: message.Assistant,
879254 Parts: []message.ContentPart{},
880− Model: largeModel.ModelCfg.Model,
881− Provider: largeModel.ModelCfg.Provider,
255+ Model: a.largeModel.ModelCfg.Model,
256+ Provider: a.largeModel.ModelCfg.Provider,
882257 })
883258 if err != nil {
884259 return callContext, prepared, err
885260 }
886261 callContext = context.WithValue(callContext, tools.MessageIDContextKey, assistantMsg.ID)
887− callContext = context.WithValue(callContext, tools.SupportsImagesContextKey, largeModel.CatwalkCfg.SupportsImages)
888− callContext = context.WithValue(callContext, tools.ModelNameContextKey, largeModel.CatwalkCfg.Name)
262+ callContext = context.WithValue(callContext, tools.SupportsImagesContextKey, a.largeModel.CatwalkCfg.SupportsImages)
263+ callContext = context.WithValue(callContext, tools.ModelNameContextKey, a.largeModel.CatwalkCfg.Name)
889264 currentAssistant = &assistantMsg
890265 return callContext, prepared, err
891266 },
@@ -936,39 +311,25 @@ func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (result *
936311 Finished: false,
937312 }
938313 currentAssistant.AddToolCall(toolCall)
939− // Use parent ctx instead of genCtx to ensure the update succeeds
940− // even if the request is canceled mid-stream
941− return a.messages.Update(ctx, *currentAssistant)
314+ return a.messages.Update(genCtx, *currentAssistant)
942315 },
943316 OnRetry: func(err *fantasy.ProviderError, delay time.Duration) {
944− slog.Warn("Provider request failed, retrying", providerRetryLogFields(err, delay)...)
317+ // TODO: implement
945318 },
946319 OnToolCall: func(tc fantasy.ToolCallContent) error {
947− input, wasSanitized := sanitizeToolInput(tc.ToolName, tc.ToolCallID, tc.Input)
948− if wasSanitized {
949− sanitizedToolCalls[tc.ToolCallID] = true
950− }
951320 toolCall := message.ToolCall{
952321 ID: tc.ToolCallID,
953322 Name: tc.ToolName,
954− Input: input,
323+ Input: tc.Input,
955324 ProviderExecuted: false,
956325 Finished: true,
957326 }
958327 currentAssistant.AddToolCall(toolCall)
959− // Use parent ctx instead of genCtx to ensure the update succeeds
960− // even if the request is canceled mid-stream
961− return a.messages.Update(ctx, *currentAssistant)
328+ return a.messages.Update(genCtx, *currentAssistant)
962329 },
963330 OnToolResult: func(result fantasy.ToolResultContent) error {
964331 toolResult := a.convertToToolResult(result)
965− if sanitizedToolCalls[result.ToolCallID] {
966− toolResult.Content = "Tool call failed: arguments were not valid JSON. Please check your tool call format and try again."
967− toolResult.IsError = true
968− }
969− // Use parent ctx instead of genCtx to ensure the message is created
970− // even if the request is canceled mid-stream
971− _, createMsgErr := a.messages.Create(ctx, currentAssistant.SessionID, message.CreateMessageParams{
332+ _, createMsgErr := a.messages.Create(genCtx, currentAssistant.SessionID, message.CreateMessageParams{
972333 Role: message.Tool,
973334 Parts: []message.ContentPart{
974335 toolResult,
@@ -977,9 +338,6 @@ func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (result *
977338 return createMsgErr
978339 },
979340 OnStepFinish: func(stepResult fantasy.StepResult) error {
980− for _, w := range stepResult.Warnings {
981− slog.Warn("Provider warning", "type", w.Type, "message", w.Message)
982− }
983341 finishReason := message.FinishReasonUnknown
984342 switch stepResult.FinishReason {
985343 case fantasy.FinishReasonLength:
@@ -989,51 +347,31 @@ func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (result *
989347 case fantasy.FinishReasonToolCalls:
990348 finishReason = message.FinishReasonToolUse
991349 }
992− // If a tool result halted the turn (e.g. a hook halt or a
993− // permission denial), the step ends on FinishReasonToolCalls but
994− // the model will not be called again. Treat it as the end of the
995− // turn so the UI can render the assistant footer.
996− if finishReason == message.FinishReasonToolUse {
997− for _, tr := range stepResult.Content.ToolResults() {
998− if tr.StopTurn {
999− finishReason = message.FinishReasonEndTurn
1000− break
1001− }
1002− }
1003− }
1004350 currentAssistant.AddFinish(finishReason, "", "")
1005351 sessionLock.Lock()
1006− defer sessionLock.Unlock()
1007−
1008− updatedSession, getSessionErr := a.sessions.Get(ctx, call.SessionID)
352+ updatedSession, getSessionErr := a.sessions.Get(genCtx, call.SessionID)
1009353 if getSessionErr != nil {
354+ sessionLock.Unlock()
1010355 return getSessionErr
1011356 }
1012− usage, estimated := fallbackStepUsage(stepMessages, stepResult)
1013− a.updateSessionUsage(largeModel, &updatedSession, usage, a.openrouterCost(stepResult.ProviderMetadata), estimated)
1014− extractHyperCredits(stepResult.ProviderMetadata)
1015− _, sessionErr := a.sessions.Save(ctx, updatedSession)
357+ a.updateSessionUsage(a.largeModel, &updatedSession, stepResult.Usage, a.openrouterCost(stepResult.ProviderMetadata))
358+ _, sessionErr := a.sessions.Save(genCtx, updatedSession)
359+ sessionLock.Unlock()
1016360 if sessionErr != nil {
1017361 return sessionErr
1018362 }
1019− currentSession = updatedSession
1020363 return a.messages.Update(genCtx, *currentAssistant)
1021364 },
1022365 StopWhen: []fantasy.StopCondition{
1023366 func(_ []fantasy.StepResult) bool {
1024− cw := int64(largeModel.CatwalkCfg.ContextWindow)
1025− // If context window is unknown (0), skip auto-summarize
1026− // to avoid immediately truncating custom/local models.
1027− if cw == 0 {
1028− return false
1029− }
367+ cw := int64(a.largeModel.CatwalkCfg.ContextWindow)
1030368 tokens := currentSession.CompletionTokens + currentSession.PromptTokens
1031369 remaining := cw - tokens
1032370 var threshold int64
1033− if cw > largeContextWindowThreshold {
1034− threshold = largeContextWindowBuffer
371+ if cw > 200_000 {
372+ threshold = 20_000
1035373 } else {
1036− threshold = int64(float64(cw) * smallContextWindowRatio)
374+ threshold = int64(float64(cw) * 0.2)
1037375 }
1038376 if (remaining <= threshold) && !a.disableAutoSummarize {
1039377 shouldSummarize = true
@@ -1041,48 +379,22 @@ func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (result *
1041379 }
1042380 return false
1043381 },
1044− func(steps []fantasy.StepResult) bool {
1045− return hasRepeatedToolCalls(steps, loopDetectionWindowSize, loopDetectionMaxRepeats)
1046− },
1047382 },
1048383 })
1049384
1050385 a.eventPromptResponded(call.SessionID, time.Since(startTime).Truncate(time.Second))
1051386
1052387 if err != nil {
1053− isHyper := largeModel.ModelCfg.Provider == hyper.Name
1054388 isCancelErr := errors.Is(err, context.Canceled)
389+ isPermissionErr := errors.Is(err, permission.ErrorPermissionDenied)
1055390 if currentAssistant == nil {
1056− // Cancel-before-assistant-creation window: the run was
1057− // canceled after activeRequests.Set but before PrepareStep
1058− // created the assistant message. Without this, the turn
1059− // would return with no FinishReasonCanceled marker and no
1060− // user-visible record. The user message was already created
1061− // above, so persistCanceledTurn only writes the assistant
1062− // record.
1063− if isCancelErr {
1064− if persistErr := a.persistCanceledTurn(ctx, call, userMsgCreated); persistErr != nil {
1065− return nil, persistErr
1066− }
1067− }
1068391 return result, err
1069392 }
1070− // Persist final state with a context detached from the run
1071− // context. The run context (ctx) is derived from the
1072− // workspace context, which workspace shutdown cancels before
1073− // agent goroutines finish; using ctx here would drop the
1074− // final assistant state. WithoutCancel keeps the values
1075− // (e.g. session ID) while ignoring cancellation, and a short
1076− // timeout bounds the cleanup writes.
1077− cleanupCtx, cleanupCancel := context.WithTimeout(context.WithoutCancel(ctx), 5*time.Second)
1078− defer cleanupCancel()
1079393 // Ensure we finish thinking on error to close the reasoning state.
1080394 currentAssistant.FinishThinking()
1081395 toolCalls := currentAssistant.ToolCalls()
1082− // INFO: we use the cleanup context here because the genCtx has been cancelled.
1083− // Only load messages from the current assistant message onward — tool
1084− // results for this turn's tool calls can only exist after it.
1085− msgs, createErr := a.messages.ListAfter(cleanupCtx, currentAssistant.SessionID, currentAssistant.ID)
396+ // INFO: we use the parent context here because the genCtx has been cancelled.
397+ msgs, createErr := a.messages.List(ctx, currentAssistant.SessionID)
1086398 if createErr != nil {
1087399 return nil, createErr
1088400 }
@@ -1091,7 +403,7 @@ func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (result *
1091403 tc.Finished = true
1092404 tc.Input = "{}"
1093405 currentAssistant.AddToolCall(tc)
1094− updateErr := a.messages.Update(cleanupCtx, *currentAssistant)
406+ updateErr := a.messages.Update(ctx, *currentAssistant)
1095407 if updateErr != nil {
1096408 return nil, updateErr
1097409 }
@@ -1116,7 +428,9 @@ func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (result *
1116428 }
1117429 content := "There was an error while executing the tool"
1118430 if isCancelErr {
1119− content = "Error: user cancelled assistant tool calling"
431+ content = "Tool execution canceled by user"
432+ } else if isPermissionErr {
433+ content = "User denied permission"
1120434 }
1121435 toolResult := message.ToolResult{
1122436 ToolCallID: tc.ID,
@@ -1124,7 +438,7 @@ func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (result *
1124438 Content: content,
1125439 IsError: true,
1126440 }
1127− _, createErr = a.messages.Create(cleanupCtx, currentAssistant.SessionID, message.CreateMessageParams{
441+ _, createErr = a.messages.Create(context.Background(), currentAssistant.SessionID, message.CreateMessageParams{
1128442 Role: message.Tool,
1129443 Parts: []message.ContentPart{
1130444 toolResult,
@@ -1137,23 +451,22 @@ func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (result *
1137451 var fantasyErr *fantasy.Error
1138452 var providerErr *fantasy.ProviderError
1139453 const defaultTitle = "Provider Error"
1140− linkStyle := lipgloss.NewStyle().Foreground(charmtone.Guac).Underline(true)
1141454 if isCancelErr {
1142455 currentAssistant.AddFinish(message.FinishReasonCanceled, "User canceled request", "")
1143− } else if isHyper && errors.As(err, &providerErr) && providerErr.StatusCode == http.StatusUnauthorized {
1144− currentAssistant.AddFinish(message.FinishReasonError, "Unauthorized", `Please re-authenticate with Hyper. You can also run "crush auth" to re-authenticate.`)
1145− } else if isHyper && errors.As(err, &providerErr) && providerErr.StatusCode == http.StatusPaymentRequired {
456+ } else if isPermissionErr {
457+ currentAssistant.AddFinish(message.FinishReasonPermissionDenied, "User denied permission", "")
458+ } else if errors.Is(err, hyper.ErrNoCredits) {
1146459 url := hyper.BaseURL()
1147− link := linkStyle.Hyperlink(url, "id=hyper").Render(url)
460+ link := lipgloss.NewStyle().Hyperlink(url, "id=hyper").Render(url)
1148461 currentAssistant.AddFinish(message.FinishReasonError, "No credits", "You're out of credits. Add more at "+link)
1149462 } else if errors.As(err, &providerErr) {
1150463 if providerErr.Message == "The requested model is not supported." {
1151464 url := "https://github.com/settings/copilot/features"
1152− link := linkStyle.Hyperlink(url, "id=copilot").Render(url)
465+ link := lipgloss.NewStyle().Hyperlink(url, "id=hyper").Render(url)
1153466 currentAssistant.AddFinish(
1154467 message.FinishReasonError,
1155468 "Copilot model not enabled",
1156− fmt.Sprintf("%q is not enabled in Copilot. Go to the following page to enable it. Then, wait 5 minutes before trying again. %s", largeModel.CatwalkCfg.Name, link),
469+ fmt.Sprintf("%q is not enabled in Copilot. Go to the following page to enable it. Then, wait a minute before trying again. %s", a.largeModel.CatwalkCfg.Name, link),
1157470 )
1158471 } else {
1159472 currentAssistant.AddFinish(message.FinishReasonError, cmp.Or(stringext.Capitalize(providerErr.Title), defaultTitle), providerErr.Message)
@@ -1163,14 +476,15 @@ func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (result *
1163476 } else {
1164477 currentAssistant.AddFinish(message.FinishReasonError, defaultTitle, err.Error())
1165478 }
1166− // Note: we use the cleanup context here because the genCtx has been
479+ // Note: we use the parent context here because the genCtx has been
1167480 // cancelled.
1168− updateErr := a.messages.Update(cleanupCtx, *currentAssistant)
481+ updateErr := a.messages.Update(ctx, *currentAssistant)
1169482 if updateErr != nil {
1170483 return nil, updateErr
1171484 }
1172485 return nil, err
1173486 }
487+ wg.Wait()
1174488
1175489 if shouldSummarize {
1176490 a.activeRequests.Del(call.SessionID)
@@ -1189,123 +503,17 @@ func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (result *
1189503 }
1190504 }
1191505
1192− // Release active request before publishing the notification.
1193− // TUI handlers poll IsSessionBusy() and only re-evaluate when a
1194− // tea.Msg arrives, so the cleanup must precede the notify or
1195− // subscribers see stale busy state at the moment of receipt.
506+ // Release active request before processing queued messages.
1196507 a.activeRequests.Del(call.SessionID)
1197508 cancel()
1198509
1199− // Send notification that agent has finished its turn (skip for
1200− // nested/non-interactive sessions).
1201− if !call.NonInteractive && a.notify != nil {
1202− a.notify.Publish(pubsub.CreatedEvent, notify.Notification{
1203− SessionID: call.SessionID,
1204− SessionTitle: currentSession.Title,
1205− Type: notify.TypeAgentFinished,
1206− })
1207− }
1208−
1209− // Hand off to the next queued prompt (if any) under dispatchMu so
1210− // the transition from this finished run to the queued run is atomic
1211− // against a concurrent Cancel. activeRequests for this session was
1212− // just deleted above, so without the lock there is a window in
1213− // which the session looks idle and a cancel becomes a no-op that
1214− // fails to stop the queued prompt. Holding the lock lets us observe
1215− // a pending cancel recorded against the session and drop the queue
1216− // instead of running it, and (for the recursion) hand a fresh
1217− // accept reservation to the dequeued call so acceptedRuns stays > 0
1218− // across the recursive Run's own dispatch handoff — keeping the
1219− // session observable to Cancel for the entire transition and
1220− // closing the dequeue -> re-register window.
1221− mu := a.sessionMu(call.SessionID)
1222− mu.Lock()
1223− queuedMessages, _ := a.messageQueue.Get(call.SessionID)
1224− if mark, ok := a.cancelMark.Get(call.SessionID); ok && mark > 0 && len(queuedMessages) > 0 {
1225− // A cancel was recorded for this session (e.g. it arrived while
1226− // this run was active and follow-ups had been queued). Drop the
1227− // queued prompts it covers (accept sequence at or below the
1228− // mark, or untracked); keep any queued after the cancel (higher
1229− // sequence) so they still run.
1230− var kept []SessionAgentCall
1231− var canceledRunIDDrops []SessionAgentCall
1232− for _, q := range queuedMessages {
1233− if q.acceptSeq == 0 || q.acceptSeq <= mark {
1234− if q.RunID != "" {
1235− canceledRunIDDrops = append(canceledRunIDDrops, q)
1236− }
1237− continue
1238− }
1239− kept = append(kept, q)
1240− }
1241− queuedMessages = kept
1242− a.messageQueue.Set(call.SessionID, kept)
1243− // A dropped prompt carrying a RunID must still publish its
1244− // terminal cancelled RunComplete so a caller waiting on that
1245− // RunID does not hang.
1246− a.publishCanceledQueueDrops(canceledRunIDDrops)
1247− }
1248− if len(queuedMessages) == 0 {
1249− // No queued work. Clear the cancel mark only when no accepted
1250− // run remains in flight that it might still cover; otherwise a
1251− // sibling prompt (sequence at or below the mark) waiting to
1252− // enter Run would lose its cancellation. When accepted runs are
1253− // gone, this also clears a stale mark so it can't catch a
1254− // future run.
1255− a.messageQueue.Del(call.SessionID)
1256− a.acceptedMu.Lock()
1257− inFlight, _ := a.acceptedRuns.Get(call.SessionID)
1258− a.acceptedMu.Unlock()
1259− if inFlight == 0 {
1260− a.cancelMark.Del(call.SessionID)
1261− }
1262− mu.Unlock()
510+ queuedMessages, ok := a.messageQueue.Get(call.SessionID)
511+ if !ok || len(queuedMessages) == 0 {
1263512 return result, err
1264513 }
1265− // There are queued messages, restart the loop. Suppress the outer
1266− // defer's emit: it would otherwise observe the recursive Run's retErr
1267− // (named-return clobbering through the return below) against this
1268− // turn's MessageID/Text and publish a mixed, racing event.
1269− skipRunComplete = true
1270− // Decide whether this turn still owes its own terminal RunComplete.
1271− // Each submitted prompt with a RunID has its own lifecycle, so a turn
1272− // that is finished and handing off to a *different* queued prompt must
1273− // publish its own RunComplete here — leaving it to the recursive turn
1274− // (which carries a different RunID) would hang a caller waiting on
1275− // this turn's RunID. The exception is the summarize-continuation path,
1276− // which re-queues this same call (same RunID) to resume after a
1277− // summary; in that case the eventual terminal turn for this RunID
1278− // publishes, so publishing now would double-emit.
1279− outerOwesRunComplete := call.RunID != ""
1280− if outerOwesRunComplete {
1281− for _, q := range queuedMessages {
1282− if q.RunID == call.RunID {
1283− outerOwesRunComplete = false
1284− break
1285− }
1286− }
1287− }
514+ // There are queued messages restart the loop.
1288515 firstQueuedMessage := queuedMessages[0]
1289516 a.messageQueue.Set(call.SessionID, queuedMessages[1:])
1290− // Reserve a fresh accept for the dequeued prompt before dropping the
1291− // lock so acceptedRuns > 0 across the handoff into the recursive
1292− // Run. This closes the window between this dequeue and the recursive
1293− // Run registering its activeRequests entry: a cancel arriving in
1294− // that window now records a pending cancel (acceptedRuns > 0) that
1295− // the recursive Run's accepted path observes as cancel-on-entry.
1296− firstQueuedMessage.Accepted = a.BeginAccepted(call.SessionID)
1297− mu.Unlock()
1298− if outerOwesRunComplete {
1299− complete := notify.RunComplete{SessionID: call.SessionID, RunID: call.RunID}
1300− if currentAssistant != nil {
1301− complete.MessageID = currentAssistant.ID
1302− complete.Text = currentAssistant.Content().String()
1303− }
1304− if ctx.Err() != nil {
1305− complete.Cancelled = true
1306− }
1307− a.publishRunComplete(ctx, call, complete)
1308− }
1309517 return a.Run(ctx, firstQueuedMessage)
1310518}
1311519
@@ -1314,10 +522,6 @@ func (a *sessionAgent) Summarize(ctx context.Context, sessionID string, opts fan
1314522 return ErrSessionBusy
1315523 }
1316524
1317− // Copy mutable fields under lock to avoid races with SetModels.
1318− largeModel := a.largeModel.Get()
1319− systemPromptPrefix := a.systemPromptPrefix.Get()
1320−
1321525 currentSession, err := a.sessions.Get(ctx, sessionID)
1322526 if err != nil {
1323527 return fmt.Errorf("failed to get session: %w", err)
@@ -1331,34 +535,35 @@ func (a *sessionAgent) Summarize(ctx context.Context, sessionID string, opts fan
1331535 return nil
1332536 }
1333537
1334− aiMsgs, _ := a.preparePrompt(msgs, largeModel.CatwalkCfg.SupportsImages)
538+ aiMsgs, _ := a.preparePrompt(msgs)
1335539
1336540 genCtx, cancel := context.WithCancel(ctx)
1337541 a.activeRequests.Set(sessionID, cancel)
1338542 defer a.activeRequests.Del(sessionID)
1339543 defer cancel()
1340− defer func() {
1341− if flushErr := a.messages.FlushAll(ctx); flushErr != nil {
1342− slog.Error("Failed to flush pending message updates after summarize", "error", flushErr)
1343− }
1344− }()
1345544
1346− agent := fantasy.NewAgent(
1347− largeModel.Model,
545+ agent := fantasy.NewAgent(a.largeModel.Model,
1348546 fantasy.WithSystemPrompt(string(summaryPrompt)),
1349− fantasy.WithUserAgent(userAgent),
1350547 )
1351548 summaryMessage, err := a.messages.Create(ctx, sessionID, message.CreateMessageParams{
1352549 Role: message.Assistant,
1353− Model: largeModel.ModelCfg.Model,
1354− Provider: largeModel.ModelCfg.Provider,
550+ Model: a.largeModel.Model.Model(),
551+ Provider: a.largeModel.Model.Provider(),
1355552 IsSummaryMessage: true,
1356553 })
1357554 if err != nil {
1358555 return err
1359556 }
1360557
1361− summaryPromptText := buildSummaryPrompt(currentSession.Todos)
558+ summaryPromptText := "Provide a detailed summary of our conversation above."
559+ if len(currentSession.Todos) > 0 {
560+ summaryPromptText += "\n\n## Current Todo List\n\n"
561+ for _, t := range currentSession.Todos {
562+ summaryPromptText += fmt.Sprintf("- [%s] %s\n", t.Status, t.Content)
563+ }
564+ summaryPromptText += "\nInclude these tasks and their statuses in your summary. "
565+ summaryPromptText += "Instruct the resuming assistant to use the `todos` tool to continue tracking progress on these tasks."
566+ }
1362567
1363568 resp, err := agent.Stream(genCtx, fantasy.AgentStreamCall{
1364569 Prompt: summaryPromptText,
@@ -1366,8 +571,8 @@ func (a *sessionAgent) Summarize(ctx context.Context, sessionID string, opts fan
1366571 ProviderOptions: opts,
1367572 PrepareStep: func(callContext context.Context, options fantasy.PrepareStepFunctionOptions) (_ context.Context, prepared fantasy.PrepareStepResult, err error) {
1368573 prepared.Messages = options.Messages
1369− if systemPromptPrefix != "" {
1370− prepared.Messages = append([]fantasy.Message{fantasy.NewSystemMessage(systemPromptPrefix)}, prepared.Messages...)
574+ if a.systemPromptPrefix != "" {
575+ prepared.Messages = append([]fantasy.Message{fantasy.NewSystemMessage(a.systemPromptPrefix)}, prepared.Messages...)
1371576 }
1372577 return callContext, prepared, nil
1373578 },
@@ -1397,12 +602,6 @@ func (a *sessionAgent) Summarize(ctx context.Context, sessionID string, opts fan
1397602 deleteErr := a.messages.Delete(ctx, summaryMessage.ID)
1398603 return deleteErr
1399604 }
1400− // Mark the summary message as finished with an error so the UI
1401− // stops spinning.
1402− summaryMessage.AddFinish(message.FinishReasonError, "Summarization Error", err.Error())
1403− if updateErr := a.messages.Update(ctx, summaryMessage); updateErr != nil {
1404− return updateErr
1405− }
1406605 return err
1407606 }
1408607
@@ -1422,42 +621,20 @@ func (a *sessionAgent) Summarize(ctx context.Context, sessionID string, opts fan
1422621 }
1423622 openrouterCost = &newCost
1424623 }
1425− extractHyperCredits(step.ProviderMetadata)
1426624 }
1427625
1428− a.updateSessionUsage(largeModel, ¤tSession, resp.TotalUsage, openrouterCost, false)
626+ a.updateSessionUsage(a.largeModel, ¤tSession, resp.TotalUsage, openrouterCost)
1429627
1430628 // Just in case, get just the last usage info.
1431629 usage := resp.Response.Usage
1432630 currentSession.SummaryMessageID = summaryMessage.ID
1433− currentSession.CompletionTokens = summaryCompletionTokens(usage, summaryMessage)
631+ currentSession.CompletionTokens = usage.OutputTokens
1434632 currentSession.PromptTokens = 0
1435− currentSession.EstimatedUsage = usageIsZero(usage)
1436633 _, err = a.sessions.Save(genCtx, currentSession)
1437− if err != nil {
1438− return err
1439− }
1440−
1441− // Release the active request before processing queued messages so that
1442− // Run() does not see the session as busy.
1443− a.activeRequests.Del(sessionID)
1444− cancel()
1445−
1446− // Process any messages that were queued while summarizing.
1447− queuedMessages, ok := a.messageQueue.Get(sessionID)
1448− if !ok || len(queuedMessages) == 0 {
1449− return nil
1450− }
1451− firstQueuedMessage := queuedMessages[0]
1452− a.messageQueue.Set(sessionID, queuedMessages[1:])
1453− _, qErr := a.Run(ctx, firstQueuedMessage)
1454− return qErr
634+ return err
1455635}
1456636
1457−// cacheControlOptions is computed once for the process lifetime: the env check
1458−// is constant and callers only read (never mutate) the returned map, so the
1459−// same shared value can be reused across the ~3 calls per step.
1460−var cacheControlOptions = sync.OnceValue(func() fantasy.ProviderOptions {
637+func (a *sessionAgent) getCacheControlOptions() fantasy.ProviderOptions {
1461638 if t, _ := strconv.ParseBool(os.Getenv("CRUSH_DISABLE_ANTHROPIC_CACHE")); t {
1462639 return fantasy.ProviderOptions{}
1463640 }
@@ -1468,14 +645,7 @@ var cacheControlOptions = sync.OnceValue(func() fantasy.ProviderOptions {
1468645 bedrock.Name: &anthropic.ProviderCacheControlOptions{
1469646 CacheControl: anthropic.CacheControl{Type: "ephemeral"},
1470647 },
1471− vercel.Name: &anthropic.ProviderCacheControlOptions{
1472− CacheControl: anthropic.CacheControl{Type: "ephemeral"},
1473− },
1474648 }
1475−})
1476−
1477−func (a *sessionAgent) getCacheControlOptions() fantasy.ProviderOptions {
1478− return cacheControlOptions()
1479649}
1480650
1481651func (a *sessionAgent) createUserMessage(ctx context.Context, call SessionAgentCall) (message.Message, error) {
@@ -1495,66 +665,27 @@ func (a *sessionAgent) createUserMessage(ctx context.Context, call SessionAgentC
1495665 return msg, nil
1496666}
1497667
1498−func (a *sessionAgent) preparePrompt(msgs []message.Message, supportsImages bool, attachments ...message.Attachment) ([]fantasy.Message, []fantasy.FilePart) {
1499− history := make([]fantasy.Message, 0, len(msgs)+1)
668+func (a *sessionAgent) preparePrompt(msgs []message.Message, attachments ...message.Attachment) ([]fantasy.Message, []fantasy.FilePart) {
669+ var history []fantasy.Message
1500670 if !a.isSubAgent {
1501671 history = append(history, fantasy.NewUserMessage(
1502− fmt.Sprintf(
1503− "<system_reminder>%s</system_reminder>",
672+ fmt.Sprintf("<system_reminder>%s</system_reminder>",
1504673 `This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.
1505674If you are working on tasks that would benefit from a todo list please use the "todos" tool to create one.
1506675If not, please feel free to ignore. Again do not mention this message to the user.`,
1507676 ),
1508677 ))
1509678 }
1510− // Collect all tool call IDs present in assistant messages and all tool
1511− // result IDs present in tool messages. This lets us detect both orphaned
1512− // tool results (result without a call) and orphaned tool calls (call
1513− // without a result).
1514− knownToolCallIDs := make(map[string]struct{})
1515− knownToolResultIDs := make(map[string]struct{})
1516− for _, m := range msgs {
1517− switch m.Role {
1518− case message.Assistant:
1519− for _, tc := range m.ToolCalls() {
1520− knownToolCallIDs[tc.ID] = struct{}{}
1521− }
1522− case message.Tool:
1523− for _, tr := range m.ToolResults() {
1524− knownToolResultIDs[tr.ToolCallID] = struct{}{}
1525− }
1526− }
1527− }
1528−
1529679 for _, m := range msgs {
1530680 if len(m.Parts) == 0 {
1531681 continue
1532682 }
1533− // Assistant message without content or tool calls (cancelled before it returned anything).
683+ // Assistant message without content or tool calls (cancelled before it
684+ // returned anything).
1534685 if m.Role == message.Assistant && len(m.ToolCalls()) == 0 && m.Content().Text == "" && m.ReasoningContent().String() == "" {
1535686 continue
1536687 }
1537− if m.Role == message.Tool {
1538− if msg, ok := filterOrphanedToolResults(m, knownToolCallIDs); ok {
1539− history = append(history, msg)
1540− }
1541− continue
1542− }
1543− aiMsgs := m.ToAIMessage()
1544− if !supportsImages {
1545− for i := range aiMsgs {
1546− if aiMsgs[i].Role == fantasy.MessageRoleUser {
1547− aiMsgs[i].Content = filterFileParts(aiMsgs[i].Content)
1548− }
1549− }
1550− }
1551− history = append(history, aiMsgs...)
1552−
1553− if m.Role == message.Assistant {
1554− if msg, ok := syntheticToolResultsForOrphanedCalls(m, knownToolResultIDs); ok {
1555− history = append(history, msg)
1556− }
1557− }
688+ history = append(history, m.ToAIMessage()...)
1558689 }
1559690
1560691 var files []fantasy.FilePart
@@ -1572,224 +703,71 @@ If not, please feel free to ignore. Again do not mention this message to the use
1572703 return history, files
1573704}
1574705
1575−// filterFileParts removes fantasy.FilePart entries from a slice of message
1576−// parts. Used to strip image attachments from historical user messages when
1577−// the current model does not support them.
1578−func filterFileParts(parts []fantasy.MessagePart) []fantasy.MessagePart {
1579− filtered := make([]fantasy.MessagePart, 0, len(parts))
1580− for _, part := range parts {
1581− if _, ok := fantasy.AsMessagePart[fantasy.FilePart](part); ok {
1582− continue
1583− }
1584− filtered = append(filtered, part)
1585− }
1586− return filtered
1587−}
1588−
1589−// filterOrphanedToolResults converts a tool message to a fantasy.Message,
1590−// dropping any tool result parts whose tool_call_id has no matching tool call
1591−// in the known set. An orphaned result causes API validation to fail on every
1592−// subsequent turn, permanently locking the session. Returns the filtered
1593−// message and true if at least one valid part remains.
1594−func filterOrphanedToolResults(m message.Message, knownToolCallIDs map[string]struct{}) (fantasy.Message, bool) {
1595− aiMsgs := m.ToAIMessage()
1596− if len(aiMsgs) == 0 {
1597− return fantasy.Message{}, false
1598− }
1599− validParts := make([]fantasy.MessagePart, 0, len(aiMsgs[0].Content))
1600− for _, part := range aiMsgs[0].Content {
1601− tr, ok := fantasy.AsMessagePart[fantasy.ToolResultPart](part)
1602− if !ok {
1603− validParts = append(validParts, part)
1604− continue
1605− }
1606− if _, known := knownToolCallIDs[tr.ToolCallID]; known {
1607− validParts = append(validParts, part)
1608− } else {
1609− slog.Warn(
1610− "Dropping orphaned tool result with no matching tool call",
1611− "tool_call_id", tr.ToolCallID,
1612− )
1613− }
1614− }
1615− if len(validParts) == 0 {
1616− return fantasy.Message{}, false
1617− }
1618− msg := aiMsgs[0]
1619− msg.Content = validParts
1620− return msg, true
1621−}
1622−
1623−// syntheticToolResultsForOrphanedCalls returns a tool message containing
1624−// synthetic tool results for any tool calls in the assistant message that
1625−// have no matching result in knownToolResultIDs. LLM APIs require every
1626−// tool_use to be immediately followed by a tool_result; an interrupted
1627−// session can leave orphaned tool_use blocks that permanently lock the
1628−// conversation. Returns the message and true if any synthetic results were
1629−// produced.
1630−func syntheticToolResultsForOrphanedCalls(m message.Message, knownToolResultIDs map[string]struct{}) (fantasy.Message, bool) {
1631− syntheticParts := make([]fantasy.MessagePart, 0, len(m.ToolCalls()))
1632− for _, tc := range m.ToolCalls() {
1633− if _, hasResult := knownToolResultIDs[tc.ID]; hasResult {
1634− continue
1635− }
1636− slog.Warn(
1637− "Injecting synthetic tool result for orphaned tool call",
1638− "tool_call_id", tc.ID,
1639− "tool_name", tc.Name,
1640− )
1641− syntheticParts = append(syntheticParts, fantasy.ToolResultPart{
1642− ToolCallID: tc.ID,
1643− Output: fantasy.ToolResultOutputContentError{
1644− Error: errors.New("tool call was interrupted and did not produce a result, you may retry this call if the result is still needed"),
1645− },
1646− })
1647− }
1648− if len(syntheticParts) == 0 {
1649− return fantasy.Message{}, false
1650− }
1651− return fantasy.Message{
1652− Role: fantasy.MessageRoleTool,
1653− Content: syntheticParts,
1654− }, true
1655−}
1656−
1657706func (a *sessionAgent) getSessionMessages(ctx context.Context, session session.Session) ([]message.Message, error) {
1658− if session.SummaryMessageID != "" {
1659− msgs, err := a.messages.ListAfter(ctx, session.ID, session.SummaryMessageID)
1660− if err != nil {
1661− return nil, fmt.Errorf("failed to list messages after summary: %w", err)
1662− }
1663− if len(msgs) > 0 {
1664− msgs[0].Role = message.User
1665− }
1666− return msgs, nil
1667− }
1668−
1669707 msgs, err := a.messages.List(ctx, session.ID)
1670708 if err != nil {
1671709 return nil, fmt.Errorf("failed to list messages: %w", err)
1672710 }
1673− return msgs, nil
1674−}
1675711
1676−// hasUserTextMessage reports whether any user message in msgs contains
1677−// text content (as opposed to only shell commands or other non-text parts).
1678−func hasUserTextMessage(msgs []message.Message) bool {
1679− for _, msg := range msgs {
1680− if msg.Role != message.User {
1681− continue
1682− }
1683− for _, part := range msg.Parts {
1684− if tc, ok := part.(message.TextContent); ok && tc.Text != "" {
1685− return true
712+ if session.SummaryMessageID != "" {
713+ summaryMsgInex := -1
714+ for i, msg := range msgs {
715+ if msg.ID == session.SummaryMessageID {
716+ summaryMsgInex = i
717+ break
1686718 }
1687719 }
720+ if summaryMsgInex != -1 {
721+ msgs = msgs[summaryMsgInex:]
722+ msgs[0].Role = message.User
723+ }
1688724 }
1689− return false
725+ return msgs, nil
1690726}
1691727
1692−// GenerateTitle generates a session title based on the initial prompt.
1693−func (a *sessionAgent) GenerateTitle(ctx context.Context, sessionID string, userPrompt string) {
1694− if userPrompt == "" {
728+func (a *sessionAgent) generateTitle(ctx context.Context, sessionID string, prompt string) {
729+ if prompt == "" {
1695730 return
1696731 }
1697732
1698− // Ensure the session always gets a title even if every path below
1699− // fails or the context is cancelled before we finish.
1700− var titleSaved bool
1701− defer func() {
1702− if !titleSaved {
1703− fallbackCtx, cancel := context.WithTimeout(context.WithoutCancel(ctx), 5*time.Second)
1704− defer cancel()
1705− if err := a.sessions.Rename(fallbackCtx, sessionID, DefaultSessionName); err != nil {
1706− slog.Error("Failed to save fallback session title", "error", err)
1707− }
1708− }
1709− }()
1710−
1711− smallModel := a.smallModel.Get()
1712− largeModel := a.largeModel.Get()
1713− systemPromptPrefix := a.systemPromptPrefix.Get()
1714−
1715− newAgent := func(m fantasy.LanguageModel, p []byte, tok int64) fantasy.Agent {
1716− return fantasy.NewAgent(
1717− m,
1718− fantasy.WithSystemPrompt(string(p)+"\n /no_think"),
1719− fantasy.WithMaxOutputTokens(tok),
1720− fantasy.WithUserAgent(userAgent),
1721− )
733+ var maxOutput int64 = 40
734+ if a.smallModel.CatwalkCfg.CanReason {
735+ maxOutput = a.smallModel.CatwalkCfg.DefaultMaxTokens
1722736 }
1723737
1724− streamCall := fantasy.AgentStreamCall{
1725− Prompt: fmt.Sprintf("Generate a concise title for the following content:\n\n%s\n <think>\n\n</think>", userPrompt),
1726− PrepareStep: func(callCtx context.Context, opts fantasy.PrepareStepFunctionOptions) (_ context.Context, prepared fantasy.PrepareStepResult, err error) {
1727− prepared.Messages = opts.Messages
1728− if systemPromptPrefix != "" {
1729− prepared.Messages = append([]fantasy.Message{
1730− fantasy.NewSystemMessage(systemPromptPrefix),
1731− }, prepared.Messages...)
738+ agent := fantasy.NewAgent(a.smallModel.Model,
739+ fantasy.WithSystemPrompt(string(titlePrompt)+"\n /no_think"),
740+ fantasy.WithMaxOutputTokens(maxOutput),
741+ )
742+
743+ resp, err := agent.Stream(ctx, fantasy.AgentStreamCall{
744+ Prompt: fmt.Sprintf("Generate a concise title for the following content:\n\n%s\n <think>\n\n</think>", prompt),
745+ PrepareStep: func(callContext context.Context, options fantasy.PrepareStepFunctionOptions) (_ context.Context, prepared fantasy.PrepareStepResult, err error) {
746+ prepared.Messages = options.Messages
747+ if a.systemPromptPrefix != "" {
748+ prepared.Messages = append([]fantasy.Message{fantasy.NewSystemMessage(a.systemPromptPrefix)}, prepared.Messages...)
1732749 }
1733− return callCtx, prepared, nil
750+ return callContext, prepared, nil
1734751 },
1735− }
1736−
1737− type modelAttempt struct {
1738− name string
1739− model Model
1740− }
1741− attempts := []modelAttempt{
1742− {"small", smallModel},
1743− {"large", largeModel},
1744− }
1745−
1746− var resp *fantasy.AgentResult
1747− var err error
1748− var model Model
1749− var success bool
1750− for _, attempt := range attempts {
1751− tok := int64(40)
1752− if attempt.model.CatwalkCfg.CanReason {
1753− tok = attempt.model.CatwalkCfg.DefaultMaxTokens
1754− }
1755− agent := newAgent(attempt.model.Model, titlePrompt, tok)
1756− resp, err = agent.Stream(ctx, streamCall)
1757− if err == nil && resp.Response.FinishReason != fantasy.FinishReasonLength {
1758− model = attempt.model
1759− slog.Debug("Generated title with " + attempt.name + " model")
1760− success = true
1761− break
1762− }
1763− if err != nil {
1764− slog.Error("Error generating title with "+attempt.name+" model; trying next", "err", err)
1765− } else {
1766− slog.Error("Title generation hit token limit with " + attempt.name + " model; trying next")
1767− }
1768− }
1769− if !success {
1770− // The deferred fallback will save the default session name.
752+ })
753+ if err != nil {
754+ slog.Error("error generating title", "err", err)
1771755 return
1772756 }
1773757
1774− // Clean up title.
1775− var title string
1776− title = strings.ReplaceAll(resp.Response.Content.Text(), "\n", " ")
758+ title := resp.Response.Content.Text()
759+
760+ title = strings.ReplaceAll(title, "\n", " ")
1777761
1778762 // Remove thinking tags if present.
1779− title = thinkTagRegex.ReplaceAllString(title, "")
1780− title = orphanThinkTagRegex.ReplaceAllString(title, "")
763+ if idx := strings.Index(title, "</think>"); idx > 0 {
764+ title = title[idx+len("</think>"):]
765+ }
1781766
1782767 title = strings.TrimSpace(title)
1783768 if title == "" {
1784− // LLM returned empty content. Use the prompt itself as a
1785− // fallback title, truncated to 50 chars, before resorting to
1786− // the generic default.
1787− fallback := strings.ReplaceAll(userPrompt, "\n", " ")
1788− fallback = strings.TrimSpace(fallback)
1789− if len(fallback) > 50 {
1790− fallback = ansi.Truncate(fallback, 50, "…")
1791− }
1792− title = cmp.Or(fallback, DefaultSessionName)
769+ slog.Warn("failed to generate title", "warn", "empty title")
770+ return
1793771 }
1794772
1795773 // Calculate usage and cost.
@@ -1803,36 +781,33 @@ func (a *sessionAgent) GenerateTitle(ctx context.Context, sessionID string, user
1803781 }
1804782 openrouterCost = &newCost
1805783 }
1806− extractHyperCredits(step.ProviderMetadata)
1807784 }
1808785
1809− modelConfig := model.CatwalkCfg
786+ modelConfig := a.smallModel.CatwalkCfg
1810787 cost := modelConfig.CostPer1MInCached/1e6*float64(resp.TotalUsage.CacheCreationTokens) +
1811788 modelConfig.CostPer1MOutCached/1e6*float64(resp.TotalUsage.CacheReadTokens) +
1812789 modelConfig.CostPer1MIn/1e6*float64(resp.TotalUsage.InputTokens) +
1813790 modelConfig.CostPer1MOut/1e6*float64(resp.TotalUsage.OutputTokens)
1814791
792+ if a.isClaudeCode() {
793+ cost = 0
794+ }
795+
1815796 // Use override cost if available (e.g., from OpenRouter).
1816797 if openrouterCost != nil {
1817798 cost = *openrouterCost
1818799 }
1819800
1820− // Skip cost accumulation
1821− if model.FlatRate {
1822− cost = 0
1823− }
1824−
1825801 promptTokens := resp.TotalUsage.InputTokens + resp.TotalUsage.CacheCreationTokens
1826− completionTokens := resp.TotalUsage.OutputTokens
802+ completionTokens := resp.TotalUsage.OutputTokens + resp.TotalUsage.CacheReadTokens
1827803
1828804 // Atomically update only title and usage fields to avoid overriding other
1829805 // concurrent session updates.
1830806 saveErr := a.sessions.UpdateTitleAndUsage(ctx, sessionID, title, promptTokens, completionTokens, cost)
1831807 if saveErr != nil {
1832− slog.Error("Failed to save session title and usage", "error", saveErr)
808+ slog.Error("failed to save session title & usage", "error", saveErr)
1833809 return
1834810 }
1835− titleSaved = true
1836811}
1837812
1838813func (a *sessionAgent) openrouterCost(metadata fantasy.ProviderMetadata) *float64 {
@@ -1848,134 +823,52 @@ func (a *sessionAgent) openrouterCost(metadata fantasy.ProviderMetadata) *float6
1848823 return &opts.Usage.Cost
1849824}
1850825
1851−// extractHyperCredits reads usage.remaining.hypercredits from OpenAI
1852−// provider metadata and stores it for the next FetchCredits call.
1853−func extractHyperCredits(metadata fantasy.ProviderMetadata) {
1854− openaiMeta, ok := metadata[openai.Name]
1855− if !ok {
1856− return
1857− }
1858− pm, ok := openaiMeta.(*openai.ProviderMetadata)
1859− if !ok {
1860− return
1861− }
1862− var remaining struct {
1863− Hypercredits float64 `json:"hypercredits"`
1864− }
1865− if pm.ExtraField("remaining", &remaining) && remaining.Hypercredits > 0 {
1866− hyper.SetBalance(int(math.Round(remaining.Hypercredits)))
1867− }
1868−}
1869−
1870−func (a *sessionAgent) updateSessionUsage(model Model, session *session.Session, usage fantasy.Usage, overrideCost *float64, estimated bool) {
1871− if !usageIsZero(usage) {
1872− session.EstimatedUsage = estimated
1873− }
1874−
826+func (a *sessionAgent) updateSessionUsage(model Model, session *session.Session, usage fantasy.Usage, overrideCost *float64) {
1875827 modelConfig := model.CatwalkCfg
1876828 cost := modelConfig.CostPer1MInCached/1e6*float64(usage.CacheCreationTokens) +
1877829 modelConfig.CostPer1MOutCached/1e6*float64(usage.CacheReadTokens) +
1878830 modelConfig.CostPer1MIn/1e6*float64(usage.InputTokens) +
1879831 modelConfig.CostPer1MOut/1e6*float64(usage.OutputTokens)
1880832
1881− if !estimated {
1882− a.eventTokensUsed(session.ID, model, usage, cost)
1883− }
1884−
1885− if estimated {
833+ if a.isClaudeCode() {
1886834 cost = 0
1887− } else {
1888− // Use override cost if available (e.g., from OpenRouter).
1889− if overrideCost != nil {
1890− cost = *overrideCost
1891− }
1892−
1893− // Skip cost accumulation
1894− if model.FlatRate {
1895− cost = 0
1896− }
1897835 }
1898836
1899− session.Cost += cost
1900− updateSessionTokenCounters(session, usage)
1901−}
837+ a.eventTokensUsed(session.ID, model, usage, cost)
1902838
1903−func updateSessionTokenCounters(session *session.Session, usage fantasy.Usage) {
1904− if usage.OutputTokens != 0 {
1905− session.CompletionTokens = usage.OutputTokens
1906− }
1907− if promptTokens := usage.InputTokens + usage.CacheReadTokens; promptTokens != 0 {
1908− session.PromptTokens = promptTokens
839+ if overrideCost != nil {
840+ session.Cost += *overrideCost
841+ } else {
842+ session.Cost += cost
1909843 }
1910−}
1911844
1912−func summaryCompletionTokens(usage fantasy.Usage, summaryMessage message.Message) int64 {
1913− if usage.OutputTokens != 0 {
1914− return usage.OutputTokens
1915− }
1916− return approxTokenCount(summaryMessage.Content().Text) + approxTokenCount(summaryMessage.ReasoningContent().String())
845+ session.CompletionTokens = usage.OutputTokens + usage.CacheReadTokens
846+ session.PromptTokens = usage.InputTokens + usage.CacheCreationTokens
1917847}
1918848
1919849func (a *sessionAgent) Cancel(sessionID string) {
1920− // Serialize against the dispatch handoff in Run so the accepted ->
1921− // (cancel-on-entry | queued | active) transition is atomic against
1922− // this cancel. Every cancel observes at least one of: an active
1923− // request, an accepted run (recorded as a pending cancel), or a
1924− // queue entry it then clears. If none of those hold, an idle Escape
1925− // is a true no-op and must not poison the next prompt.
1926− mu := a.sessionMu(sessionID)
1927− mu.Lock()
1928− defer mu.Unlock()
1929−
1930− // Cancel regular requests. Don't use Take() here - we need the entry to
1931− // remain in activeRequests so IsBusy() returns true until the goroutine
1932− // fully completes (including error handling that may access the DB).
1933− // The defer in processRequest will clean up the entry.
1934− if cancel, ok := a.activeRequests.Get(sessionID); ok && cancel != nil {
1935− slog.Debug("Request cancellation initiated", "session_id", sessionID)
850+ // Cancel regular requests.
851+ if cancel, ok := a.activeRequests.Take(sessionID); ok && cancel != nil {
852+ slog.Info("Request cancellation initiated", "session_id", sessionID)
1936853 cancel()
1937854 }
1938855
1939856 // Also check for summarize requests.
1940− if cancel, ok := a.activeRequests.Get(sessionID + "-summarize"); ok && cancel != nil {
1941− slog.Debug("Summarize cancellation initiated", "session_id", sessionID)
857+ if cancel, ok := a.activeRequests.Take(sessionID + "-summarize"); ok && cancel != nil {
858+ slog.Info("Summarize cancellation initiated", "session_id", sessionID)
1942859 cancel()
1943860 }
1944861
1945− // Record a pending cancel only when a dispatched-but-not-yet-active
1946− // run exists. This catches runs still in the goroutine scheduler or
1947− // about to enter Run's busy-queue branch, while leaving an idle
1948− // session untouched. Active and accepted are not mutually exclusive:
1949− // when a run is active and a follow-up has been accepted, both the
1950− // cancel above and this pending record fire.
1951− //
1952− // Raise the session's cancel mark to the latest accept sequence
1953− // assigned so far. Every prompt currently accepted-but-not-yet-
1954− // active has a sequence at or below that value, so one cancel covers
1955− // all of them; a prompt accepted after this cancel gets a strictly
1956− // higher sequence and is never poisoned. Using max keeps repeated
1957− // cancels idempotent while the same prompts are in flight and lets a
1958− // later cancel extend coverage to prompts accepted since.
1959− a.acceptedMu.Lock()
1960− count, ok := a.acceptedRuns.Get(sessionID)
1961− mark := a.acceptSeqGen
1962− a.acceptedMu.Unlock()
1963− if ok && count > 0 {
1964− slog.Debug("Recording cancel mark for accepted runs", "session_id", sessionID, "count", count, "mark", mark)
1965− existing, _ := a.cancelMark.Get(sessionID)
1966− a.cancelMark.Set(sessionID, max(existing, mark))
1967− }
1968−
1969862 if a.QueuedPrompts(sessionID) > 0 {
1970− slog.Debug("Clearing queued prompts", "session_id", sessionID)
1971− a.clearQueueAndNotify(sessionID)
863+ slog.Info("Clearing queued prompts", "session_id", sessionID)
864+ a.messageQueue.Del(sessionID)
1972865 }
1973866}
1974867
1975868func (a *sessionAgent) ClearQueue(sessionID string) {
1976869 if a.QueuedPrompts(sessionID) > 0 {
1977− slog.Debug("Clearing queued prompts", "session_id", sessionID)
1978− a.clearQueueAndNotify(sessionID)
870+ slog.Info("Clearing queued prompts", "session_id", sessionID)
871+ a.messageQueue.Del(sessionID)
1979872 }
1980873}
1981874
@@ -1999,10 +892,14 @@ func (a *sessionAgent) CancelAll() {
1999892}
2000893
2001894func (a *sessionAgent) IsBusy() bool {
2002− // activeRequests only ever holds non-nil cancel funcs (Set with a
2003− // real func, removed via Del), so a length check is exact — and it
2004− // avoids cloning the whole map, which Seq() does on every call.
2005− return a.activeRequests.Len() > 0
895+ var busy bool
896+ for cancelFunc := range a.activeRequests.Seq() {
897+ if cancelFunc != nil {
898+ busy = true
899+ break
900+ }
901+ }
902+ return busy
2006903}
2007904
2008905func (a *sessionAgent) IsSessionBusy(sessionID string) bool {
@@ -2031,21 +928,29 @@ func (a *sessionAgent) QueuedPromptsList(sessionID string) []string {
2031928}
2032929
2033930func (a *sessionAgent) SetModels(large Model, small Model) {
2034− a.largeModel.Set(large)
2035− a.smallModel.Set(small)
931+ a.largeModel = large
932+ a.smallModel = small
2036933}
2037934
2038935func (a *sessionAgent) SetTools(tools []fantasy.AgentTool) {
2039− a.tools.SetSlice(tools)
2040− a.toolsGen.Add(1)
936+ a.tools = tools
937+}
938+
939+func (a *sessionAgent) Model() Model {
940+ return a.largeModel
2041941}
2042942
2043−func (a *sessionAgent) SetSystemPrompt(systemPrompt string) {
2044− a.systemPrompt.Set(systemPrompt)
943+func (a *sessionAgent) promptPrefix() string {
944+ if a.isClaudeCode() {
945+ return "You are Claude Code, Anthropic's official CLI for Claude."
946+ }
947+ return a.systemPromptPrefix
2045948}
2046949
2047−func (a *sessionAgent) Model() Model {
2048− return a.largeModel.Get()
950+func (a *sessionAgent) isClaudeCode() bool {
951+ cfg := config.Get()
952+ pc, ok := cfg.Providers.Get(a.largeModel.ModelCfg.Provider)
953+ return ok && pc.ID == string(catwalk.InferenceProviderAnthropic) && pc.OAuthToken != nil
2049954}
2050955
2051956// convertToToolResult converts a fantasy tool result to a message tool result.
@@ -2068,23 +973,13 @@ func (a *sessionAgent) convertToToolResult(result fantasy.ToolResultContent) mes
2068973 }
2069974 case fantasy.ToolResultContentTypeMedia:
2070975 if r, ok := fantasy.AsToolResultOutputType[fantasy.ToolResultOutputContentMedia](result.Result); ok {
2071− if !stringext.IsValidBase64(r.Data) {
2072− slog.Warn(
2073− "Tool returned media with invalid base64 data, discarding image",
2074− "tool", result.ToolName,
2075− "tool_call_id", result.ToolCallID,
2076− )
2077− baseResult.Content = "Tool returned image data with invalid encoding"
2078− baseResult.IsError = true
2079− } else {
2080− content := r.Text
2081− if content == "" {
2082− content = fmt.Sprintf("Loaded %s content", r.MediaType)
2083− }
2084− baseResult.Content = content
2085− baseResult.Data = r.Data
2086− baseResult.MIMEType = r.MediaType
976+ content := r.Text
977+ if content == "" {
978+ content = fmt.Sprintf("Loaded %s content", r.MediaType)
2087979 }
980+ baseResult.Content = content
981+ baseResult.Data = r.Data
982+ baseResult.MIMEType = r.MediaType
2088983 }
2089984 }
2090985
@@ -2112,17 +1007,14 @@ func (a *sessionAgent) convertToToolResult(result fantasy.ToolResultContent) mes
21121007//
21131008// BEFORE: [tool result: image data]
21141009// AFTER: [tool result: "Image loaded - see attached"], [user: image attachment]
2115−func (a *sessionAgent) workaroundProviderMediaLimitations(messages []fantasy.Message, largeModel Model) []fantasy.Message {
2116− providerSupportsMedia := largeModel.ModelCfg.Provider == string(catwalk.InferenceProviderAnthropic) ||
2117− largeModel.ModelCfg.Provider == string(catwalk.InferenceProviderBedrock) ||
2118− largeModel.ModelCfg.Provider == string(catwalk.InferenceProviderBedrockEurope)
1010+func (a *sessionAgent) workaroundProviderMediaLimitations(messages []fantasy.Message) []fantasy.Message {
1011+ providerSupportsMedia := a.largeModel.ModelCfg.Provider == string(catwalk.InferenceProviderAnthropic) ||
1012+ a.largeModel.ModelCfg.Provider == string(catwalk.InferenceProviderBedrock)
21191013
21201014 if providerSupportsMedia {
21211015 return messages
21221016 }
21231017
2124− supportsImages := largeModel.CatwalkCfg.SupportsImages
2125−
21261018 convertedMessages := make([]fantasy.Message, 0, len(messages))
21271019
21281020 for _, msg := range messages {
@@ -2142,24 +1034,9 @@ func (a *sessionAgent) workaroundProviderMediaLimitations(messages []fantasy.Mes
21421034 }
21431035
21441036 if media, ok := fantasy.AsToolResultOutputType[fantasy.ToolResultOutputContentMedia](toolResult.Output); ok {
2145− if !supportsImages {
2146− // Model cannot process images. Replace with a text
2147− // placeholder and skip creating a synthetic user
2148− // message with FilePart, which would brick the
2149− // session on text-only models.
2150− textParts = append(textParts, fantasy.ToolResultPart{
2151− ToolCallID: toolResult.ToolCallID,
2152− Output: fantasy.ToolResultOutputContentText{
2153− Text: "[Image/media content not supported by this model]",
2154− },
2155− ProviderOptions: toolResult.ProviderOptions,
2156− })
2157− continue
2158− }
2159−
21601037 decoded, err := base64.StdEncoding.DecodeString(media.Data)
21611038 if err != nil {
2162− slog.Warn("Failed to decode media data", "error", err)
1039+ slog.Warn("failed to decode media data", "error", err)
21631040 textParts = append(textParts, part)
21641041 continue
21651042 }
@@ -2197,52 +1074,3 @@ func (a *sessionAgent) workaroundProviderMediaLimitations(messages []fantasy.Mes
21971074
21981075 return convertedMessages
21991076}
2200−
2201−// buildSummaryPrompt constructs the prompt text for session summarization.
2202−func buildSummaryPrompt(todos []session.Todo) string {
2203− var sb strings.Builder
2204− sb.WriteString("Provide a detailed summary of our conversation above.")
2205− if len(todos) > 0 {
2206− sb.WriteString("\n\n## Current Todo List\n\n")
2207− for _, t := range todos {
2208− fmt.Fprintf(&sb, "- [%s] %s\n", t.Status, t.Content)
2209− }
2210− sb.WriteString("\nInclude these tasks and their statuses in your summary. ")
2211− sb.WriteString("Instruct the resuming assistant to use the `todos` tool to continue tracking progress on these tasks.")
2212− }
2213− return sb.String()
2214−}
2215−
2216−func providerRetryLogFields(err *fantasy.ProviderError, delay time.Duration) []any {
2217− fields := []any{
2218− "retry_delay", delay.String(),
2219− }
2220− if err == nil {
2221− return fields
2222− }
2223− fields = append(fields, "status_code", err.StatusCode)
2224− if err.Title != "" {
2225− fields = append(fields, "title", err.Title)
2226− }
2227− if err.Message != "" {
2228− fields = append(fields, "message", err.Message)
2229− }
2230− return fields
2231−}
2232−
2233−// sanitizeToolInput validates tool call JSON from the provider.
2234−// Malformed input is replaced with an empty object to prevent
2235−// stuck conversations from truncated or malformed model output.
2236−// The second return value indicates whether sanitization occurred.
2237−func sanitizeToolInput(toolName, toolCallID, input string) (string, bool) {
2238− if !json.Valid([]byte(input)) {
2239− slog.Warn(
2240− "Malformed tool call JSON from provider, replacing with empty object",
2241− "tool", toolName,
2242− "id", toolCallID,
2243− "input_len", len(input),
2244− )
2245− return "{}", true
2246− }
2247− return input, false
2248−}
internal/agent/agent_test.go+8−402
@@ -1,36 +1,27 @@
11package agent
22
33import (
4− "encoding/base64"
5− "fmt"
6− "log/slog"
74 "os"
85 "path/filepath"
96 "runtime"
107 "strings"
118 "testing"
12− "time"
139
14− "charm.land/catwalk/pkg/catwalk"
1510 "charm.land/fantasy"
1611 "charm.land/x/vcr"
1712 "github.com/charmbracelet/crush/internal/agent/tools"
18− "github.com/charmbracelet/crush/internal/config"
1913 "github.com/charmbracelet/crush/internal/message"
20− "github.com/charmbracelet/crush/internal/session"
2114 "github.com/stretchr/testify/assert"
2215 "github.com/stretchr/testify/require"
2316
2417 _ "github.com/joho/godotenv/autoload"
2518)
2619
27−func TestMain(m *testing.M) {
28− slog.SetLogLoggerLevel(slog.LevelError)
29− m.Run()
30−}
31−
3220var modelPairs = []modelPair{
33− {"glm-5.1", hyperBuilder("glm-5.1"), hyperBuilder("gpt-oss-120b")},
21+ {"anthropic-sonnet", anthropicBuilder("claude-sonnet-4-5-20250929"), anthropicBuilder("claude-3-5-haiku-20241022")},
22+ {"openai-gpt-5", openaiBuilder("gpt-5"), openaiBuilder("gpt-4o")},
23+ {"openrouter-kimi-k2", openRouterBuilder("moonshotai/kimi-k2-0905"), openRouterBuilder("qwen/qwen3-next-80b-a3b-instruct")},
24+ {"zai-glm4.6", zAIBuilder("glm-4.6"), zAIBuilder("glm-4.5-air")},
3425}
3526
3627func getModels(t *testing.T, r *vcr.Recorder, pair modelPair) (fantasy.LanguageModel, fantasy.LanguageModel) {
@@ -462,6 +453,10 @@ func TestCoderAgent(t *testing.T) {
462453 require.Contains(t, string(content), "Hello, Crush!", "Expected file to contain 'Hello, Crush!'")
463454 })
464455 t.Run("sourcegraph tool", func(t *testing.T) {
456+ if runtime.GOOS == "darwin" {
457+ t.Skip("skipping flacky test on macos for now")
458+ }
459+
465460 agent, env := setupAgent(t, pair)
466461
467462 session, err := env.sessions.Create(t.Context(), "New Session")
@@ -624,392 +619,3 @@ func TestCoderAgent(t *testing.T) {
624619 })
625620 }
626621}
627−
628−func makeTestTodos(n int) []session.Todo {
629− todos := make([]session.Todo, n)
630− for i := range n {
631− todos[i] = session.Todo{
632− Status: session.TodoStatusPending,
633− Content: fmt.Sprintf("Task %d: Implement feature with some description that makes it realistic", i),
634− }
635− }
636− return todos
637−}
638−
639−func BenchmarkBuildSummaryPrompt(b *testing.B) {
640− cases := []struct {
641− name string
642− numTodos int
643− }{
644− {"0todos", 0},
645− {"5todos", 5},
646− {"10todos", 10},
647− {"50todos", 50},
648− }
649−
650− for _, tc := range cases {
651− todos := makeTestTodos(tc.numTodos)
652−
653− b.Run(tc.name, func(b *testing.B) {
654− b.ReportAllocs()
655− for range b.N {
656− _ = buildSummaryPrompt(todos)
657− }
658− })
659− }
660−}
661−
662−func TestPreparePrompt_FiltersImageAttachments(t *testing.T) {
663− env := testEnv(t)
664− sa := testSessionAgent(env, nil, nil, "test prompt")
665− agent := sa.(*sessionAgent)
666−
667− ctx := t.Context()
668− sess, err := env.sessions.Create(ctx, "test")
669− require.NoError(t, err)
670−
671− // User message with text, a text attachment, and an image attachment.
672− _, err = env.messages.Create(ctx, sess.ID, message.CreateMessageParams{
673− Role: message.User,
674− Parts: []message.ContentPart{
675− message.TextContent{Text: "hello world"},
676− message.BinaryContent{Path: "notes.txt", MIMEType: "text/plain", Data: []byte("important notes")},
677− message.BinaryContent{Path: "image.png", MIMEType: "image/png", Data: []byte("fake-image-data")},
678− },
679− })
680− require.NoError(t, err)
681−
682− msgs, err := env.messages.List(ctx, sess.ID)
683− require.NoError(t, err)
684−
685− // When supportsImages is false, image attachments should be stripped.
686− history, _ := agent.preparePrompt(msgs, false)
687− // First message is the system reminder, second is the user message.
688− require.Len(t, history, 2)
689− require.Len(t, history[1].Content, 1)
690− text, ok := fantasy.AsMessagePart[fantasy.TextPart](history[1].Content[0])
691− require.True(t, ok)
692− require.Contains(t, text.Text, "hello world")
693− require.Contains(t, text.Text, "important notes")
694−
695− // When supportsImages is true, image attachments should remain.
696− history, _ = agent.preparePrompt(msgs, true)
697− require.Len(t, history, 2)
698− require.Len(t, history[1].Content, 2)
699− text, ok = fantasy.AsMessagePart[fantasy.TextPart](history[1].Content[0])
700− require.True(t, ok)
701− require.Contains(t, text.Text, "hello world")
702− file, ok := fantasy.AsMessagePart[fantasy.FilePart](history[1].Content[1])
703− require.True(t, ok)
704− require.Equal(t, "image.png", file.Filename)
705−}
706−
707−func TestPreparePrompt_OrphanedToolUse(t *testing.T) {
708− env := testEnv(t)
709− sa := testSessionAgent(env, nil, nil, "test prompt")
710− agent := sa.(*sessionAgent)
711−
712− ctx := t.Context()
713− sess, err := env.sessions.Create(ctx, "test")
714− require.NoError(t, err)
715−
716− // Create a user message.
717− _, err = env.messages.Create(ctx, sess.ID, message.CreateMessageParams{
718− Role: message.User,
719− Parts: []message.ContentPart{
720− message.TextContent{Text: "hello"},
721− },
722− })
723− require.NoError(t, err)
724−
725− // Create an assistant message with a tool call but no tool result —
726− // this simulates a cancelled/interrupted agent tool call.
727− _, err = env.messages.Create(ctx, sess.ID, message.CreateMessageParams{
728− Role: message.Assistant,
729− Parts: []message.ContentPart{
730− message.TextContent{Text: "let me check"},
731− message.ToolCall{
732− ID: "call_orphaned_1",
733− Name: "agent",
734− Input: `{"prompt":"do something"}`,
735− Finished: true,
736− },
737− },
738− })
739− require.NoError(t, err)
740−
741− // Create the next user message (the one that interrupted the tool call).
742− _, err = env.messages.Create(ctx, sess.ID, message.CreateMessageParams{
743− Role: message.User,
744− Parts: []message.ContentPart{
745− message.TextContent{Text: "Fix #2"},
746− },
747− })
748− require.NoError(t, err)
749−
750− msgs, err := env.messages.List(ctx, sess.ID)
751− require.NoError(t, err)
752−
753− history, _ := agent.preparePrompt(msgs, true)
754−
755− // The history must contain a synthetic tool result for the orphaned call.
756− found := false
757− for _, msg := range history {
758− if msg.Role != fantasy.MessageRoleTool {
759− continue
760− }
761− for _, part := range msg.Content {
762− if tr, ok := fantasy.AsMessagePart[fantasy.ToolResultPart](part); ok {
763− if tr.ToolCallID == "call_orphaned_1" {
764− found = true
765− _, isError := tr.Output.(fantasy.ToolResultOutputContentError)
766− require.True(t, isError, "orphaned tool result should be an error")
767− }
768− }
769− }
770− }
771− require.True(t, found, "expected synthetic tool result for orphaned tool call")
772−}
773−
774−func TestPreparePrompt_OrphanedToolUseMixed(t *testing.T) {
775− env := testEnv(t)
776− sa := testSessionAgent(env, nil, nil, "test prompt")
777− agent := sa.(*sessionAgent)
778−
779− ctx := t.Context()
780− sess, err := env.sessions.Create(ctx, "test")
781− require.NoError(t, err)
782−
783− _, err = env.messages.Create(ctx, sess.ID, message.CreateMessageParams{
784− Role: message.User,
785− Parts: []message.ContentPart{
786− message.TextContent{Text: "hello"},
787− },
788− })
789− require.NoError(t, err)
790−
791− // Assistant with 2 tool calls: one has a result, one is orphaned.
792− _, err = env.messages.Create(ctx, sess.ID, message.CreateMessageParams{
793− Role: message.Assistant,
794− Parts: []message.ContentPart{
795− message.ToolCall{
796− ID: "call_ok",
797− Name: "view",
798− Input: `{"path":"/foo"}`,
799− Finished: true,
800− },
801− message.ToolCall{
802− ID: "call_orphaned",
803− Name: "agent",
804− Input: `{"prompt":"search"}`,
805− Finished: true,
806− },
807− },
808− })
809− require.NoError(t, err)
810−
811− // Only one tool result — for call_ok.
812− _, err = env.messages.Create(ctx, sess.ID, message.CreateMessageParams{
813− Role: message.Tool,
814− Parts: []message.ContentPart{
815− message.ToolResult{
816− ToolCallID: "call_ok",
817− Name: "view",
818− Content: "file contents",
819− },
820− },
821− })
822− require.NoError(t, err)
823−
824− msgs, err := env.messages.List(ctx, sess.ID)
825− require.NoError(t, err)
826−
827− history, _ := agent.preparePrompt(msgs, true)
828−
829− // Should have a synthetic result only for the orphaned call.
830− var syntheticCount int
831− for _, msg := range history {
832− if msg.Role != fantasy.MessageRoleTool {
833− continue
834− }
835− for _, part := range msg.Content {
836− if tr, ok := fantasy.AsMessagePart[fantasy.ToolResultPart](part); ok {
837− if tr.ToolCallID == "call_orphaned" {
838− syntheticCount++
839− }
840− }
841− }
842− }
843− require.Equal(t, 1, syntheticCount, "expected exactly one synthetic result for the orphaned call")
844−}
845−
846−func TestWorkaroundProviderMediaLimitations_TextOnlyModel(t *testing.T) {
847− env := testEnv(t)
848− sa := testSessionAgent(env, nil, nil, "test prompt")
849− agent := sa.(*sessionAgent)
850−
851− pngBase64 := base64.StdEncoding.EncodeToString([]byte("fake-png-data"))
852−
853− messages := []fantasy.Message{
854− {
855− Role: fantasy.MessageRoleTool,
856− Content: []fantasy.MessagePart{
857− fantasy.ToolResultPart{
858− ToolCallID: "call_1",
859− Output: fantasy.ToolResultOutputContentMedia{
860− Data: pngBase64,
861− MediaType: "image/png",
862− },
863− },
864− },
865− },
866− }
867−
868− // Non-Anthropic provider, no image support — should replace media with
869− // a text placeholder and not create a synthetic user message.
870− largeModel := Model{
871− ModelCfg: config.SelectedModel{Provider: "openai"},
872− CatwalkCfg: catwalk.Model{
873− SupportsImages: false,
874− },
875− }
876−
877− result := agent.workaroundProviderMediaLimitations(messages, largeModel)
878−
879− // Should produce exactly one message: the tool message with a text
880− // placeholder. No synthetic user message with FilePart.
881− require.Len(t, result, 1)
882− require.Equal(t, fantasy.MessageRoleTool, result[0].Role)
883−
884− tr, ok := fantasy.AsMessagePart[fantasy.ToolResultPart](result[0].Content[0])
885− require.True(t, ok)
886− _, ok = fantasy.AsToolResultOutputType[fantasy.ToolResultOutputContentText](tr.Output)
887− require.True(t, ok)
888−}
889−
890−func TestWorkaroundProviderMediaLimitations_VisionModel(t *testing.T) {
891− env := testEnv(t)
892− sa := testSessionAgent(env, nil, nil, "test prompt")
893− agent := sa.(*sessionAgent)
894−
895− pngBase64 := base64.StdEncoding.EncodeToString([]byte("fake-png-data"))
896−
897− messages := []fantasy.Message{
898− {
899− Role: fantasy.MessageRoleTool,
900− Content: []fantasy.MessagePart{
901− fantasy.ToolResultPart{
902− ToolCallID: "call_1",
903− Output: fantasy.ToolResultOutputContentMedia{
904− Data: pngBase64,
905− MediaType: "image/png",
906− },
907− },
908− },
909− },
910− }
911−
912− // Non-Anthropic provider, image support — should create a synthetic
913− // user message with FilePart.
914− largeModel := Model{
915− ModelCfg: config.SelectedModel{Provider: "openai"},
916− CatwalkCfg: catwalk.Model{
917− SupportsImages: true,
918− },
919− }
920−
921− result := agent.workaroundProviderMediaLimitations(messages, largeModel)
922−
923− // Should produce two messages: tool message with placeholder text,
924− // and synthetic user message with FilePart.
925− require.Len(t, result, 2)
926− require.Equal(t, fantasy.MessageRoleTool, result[0].Role)
927− require.Equal(t, fantasy.MessageRoleUser, result[1].Role)
928−
929− // The tool message should have text placeholder.
930− tr, ok := fantasy.AsMessagePart[fantasy.ToolResultPart](result[0].Content[0])
931− require.True(t, ok)
932− textOutput, ok := fantasy.AsToolResultOutputType[fantasy.ToolResultOutputContentText](tr.Output)
933− require.True(t, ok)
934− require.Contains(t, textOutput.Text, "see attached file")
935−
936− // The synthetic user message should contain a TextPart and a FilePart.
937− require.Len(t, result[1].Content, 2)
938− file, ok := fantasy.AsMessagePart[fantasy.FilePart](result[1].Content[1])
939− require.True(t, ok)
940− require.Equal(t, "image/png", file.MediaType)
941−}
942−
943−func TestWorkaroundProviderMediaLimitations_AnthropicProvider(t *testing.T) {
944− env := testEnv(t)
945− sa := testSessionAgent(env, nil, nil, "test prompt")
946− agent := sa.(*sessionAgent)
947−
948− pngBase64 := base64.StdEncoding.EncodeToString([]byte("fake-png-data"))
949−
950− messages := []fantasy.Message{
951− {
952− Role: fantasy.MessageRoleTool,
953− Content: []fantasy.MessagePart{
954− fantasy.ToolResultPart{
955− ToolCallID: "call_1",
956− Output: fantasy.ToolResultOutputContentMedia{
957− Data: pngBase64,
958− MediaType: "image/png",
959− },
960− },
961− },
962− },
963− }
964−
965− // Anthropic provider — should return messages unchanged regardless of
966− // SupportsImages, since Anthropic handles media in tool results natively.
967− largeModel := Model{
968− ModelCfg: config.SelectedModel{Provider: string(catwalk.InferenceProviderAnthropic)},
969− CatwalkCfg: catwalk.Model{
970− SupportsImages: true,
971− },
972− }
973−
974− result := agent.workaroundProviderMediaLimitations(messages, largeModel)
975− require.Len(t, result, 1)
976− require.Equal(t, fantasy.MessageRoleTool, result[0].Role)
977−
978− // The media should still be in the tool result, untouched.
979− tr, ok := fantasy.AsMessagePart[fantasy.ToolResultPart](result[0].Content[0])
980− require.True(t, ok)
981− media, ok := fantasy.AsToolResultOutputType[fantasy.ToolResultOutputContentMedia](tr.Output)
982− require.True(t, ok)
983− require.Equal(t, "image/png", media.MediaType)
984−}
985−
986−func TestProviderRetryLogFields(t *testing.T) {
987− t.Run("nil provider error", func(t *testing.T) {
988− fields := providerRetryLogFields(nil, 2*time.Second)
989− require.Equal(t, []any{"retry_delay", "2s"}, fields)
990− })
991−
992− t.Run("provider error with title and message", func(t *testing.T) {
993− fields := providerRetryLogFields(&fantasy.ProviderError{
994− StatusCode: 429,
995− Title: "rate limit",
996− Message: "too many requests",
997− }, 1500*time.Millisecond)
998− require.Equal(t, []any{
999− "retry_delay", "1.5s",
1000− "status_code", 429,
1001− "title", "rate limit",
1002− "message", "too many requests",
1003− }, fields)
1004− })
1005−
1006− t.Run("provider error without optional strings", func(t *testing.T) {
1007− fields := providerRetryLogFields(&fantasy.ProviderError{
1008− StatusCode: 503,
1009− }, time.Second)
1010− require.Equal(t, []any{
1011− "retry_delay", "1s",
1012− "status_code", 503,
1013− }, fields)
1014− })
1015−}
internal/agent/agent_tool.go+49−12
@@ -4,6 +4,7 @@ import (
44 "context"
55 _ "embed"
66 "errors"
7+ "fmt"
78
89 "charm.land/fantasy"
910
@@ -13,7 +14,7 @@ import (
1314)
1415
1516//go:embed templates/agent_tool.md
16−var agentToolDescription string
17+var agentToolDescription []byte
1718
1819type AgentParams struct {
1920 Prompt string `json:"prompt" description:"The task for the agent to perform"`
@@ -24,7 +25,7 @@ const (
2425)
2526
2627func (c *coordinator) agentTool(ctx context.Context) (fantasy.AgentTool, error) {
27− agentCfg, ok := c.cfg.Config().Agents[config.AgentTask]
28+ agentCfg, ok := c.cfg.Agents[config.AgentTask]
2829 if !ok {
2930 return nil, errors.New("task agent not configured")
3031 }
@@ -39,7 +40,7 @@ func (c *coordinator) agentTool(ctx context.Context) (fantasy.AgentTool, error)
3940 }
4041 return fantasy.NewParallelAgentTool(
4142 AgentToolName,
42− agentToolDescription,
43+ string(agentToolDescription),
4344 func(ctx context.Context, params AgentParams, call fantasy.ToolCall) (fantasy.ToolResponse, error) {
4445 if params.Prompt == "" {
4546 return fantasy.NewTextErrorResponse("prompt is required"), nil
@@ -55,14 +56,50 @@ func (c *coordinator) agentTool(ctx context.Context) (fantasy.AgentTool, error)
5556 return fantasy.ToolResponse{}, errors.New("agent message id missing from context")
5657 }
5758
58− return c.runSubAgent(ctx, subAgentParams{
59− Agent: agent,
60− SessionID: sessionID,
61− AgentMessageID: agentMessageID,
62− ToolCallID: call.ID,
63− Prompt: params.Prompt,
64− SessionTitle: "New Agent Session",
59+ agentToolSessionID := c.sessions.CreateAgentToolSessionID(agentMessageID, call.ID)
60+ session, err := c.sessions.CreateTaskSession(ctx, agentToolSessionID, sessionID, "New Agent Session")
61+ if err != nil {
62+ return fantasy.ToolResponse{}, fmt.Errorf("error creating session: %s", err)
63+ }
64+ model := agent.Model()
65+ maxTokens := model.CatwalkCfg.DefaultMaxTokens
66+ if model.ModelCfg.MaxTokens != 0 {
67+ maxTokens = model.ModelCfg.MaxTokens
68+ }
69+
70+ providerCfg, ok := c.cfg.Providers.Get(model.ModelCfg.Provider)
71+ if !ok {
72+ return fantasy.ToolResponse{}, errors.New("model provider not configured")
73+ }
74+ result, err := agent.Run(ctx, SessionAgentCall{
75+ SessionID: session.ID,
76+ Prompt: params.Prompt,
77+ MaxOutputTokens: maxTokens,
78+ ProviderOptions: getProviderOptions(model, providerCfg),
79+ Temperature: model.ModelCfg.Temperature,
80+ TopP: model.ModelCfg.TopP,
81+ TopK: model.ModelCfg.TopK,
82+ FrequencyPenalty: model.ModelCfg.FrequencyPenalty,
83+ PresencePenalty: model.ModelCfg.PresencePenalty,
6584 })
66− },
67− ), nil
85+ if err != nil {
86+ return fantasy.NewTextErrorResponse("error generating response"), nil
87+ }
88+ updatedSession, err := c.sessions.Get(ctx, session.ID)
89+ if err != nil {
90+ return fantasy.ToolResponse{}, fmt.Errorf("error getting session: %s", err)
91+ }
92+ parentSession, err := c.sessions.Get(ctx, sessionID)
93+ if err != nil {
94+ return fantasy.ToolResponse{}, fmt.Errorf("error getting parent session: %s", err)
95+ }
96+
97+ parentSession.Cost += updatedSession.Cost
98+
99+ _, err = c.sessions.Save(ctx, parentSession)
100+ if err != nil {
101+ return fantasy.ToolResponse{}, fmt.Errorf("error saving parent session: %s", err)
102+ }
103+ return fantasy.NewTextResponse(result.Response.Content.Text()), nil
104+ }), nil
68105}
internal/agent/agentic_fetch_tool.go+65−40
@@ -17,7 +17,7 @@ import (
1717)
1818
1919//go:embed templates/agentic_fetch.md
20−var agenticFetchToolDescription string
20+var agenticFetchToolDescription []byte
2121
2222// agenticFetchValidationResult holds the validated parameters from the tool call context.
2323type agenticFetchValidationResult struct {
@@ -52,20 +52,19 @@ var agenticFetchPromptTmpl []byte
5252
5353func (c *coordinator) agenticFetchTool(_ context.Context, client *http.Client) (fantasy.AgentTool, error) {
5454 if client == nil {
55− transport := http.DefaultTransport.(*http.Transport).Clone()
56− transport.MaxIdleConns = 100
57− transport.MaxIdleConnsPerHost = 10
58− transport.IdleConnTimeout = 90 * time.Second
59−
6055 client = &http.Client{
61− Timeout: 30 * time.Second,
62− Transport: transport,
56+ Timeout: 30 * time.Second,
57+ Transport: &http.Transport{
58+ MaxIdleConns: 100,
59+ MaxIdleConnsPerHost: 10,
60+ IdleConnTimeout: 90 * time.Second,
61+ },
6362 }
6463 }
6564
6665 return fantasy.NewParallelAgentTool(
6766 tools.AgenticFetchToolName,
68− agenticFetchToolDescription,
67+ string(agenticFetchToolDescription),
6968 func(ctx context.Context, params tools.AgenticFetchParams, call fantasy.ToolCall) (fantasy.ToolResponse, error) {
7069 validationResult, err := validateAgenticFetchParams(ctx, params)
7170 if err != nil {
@@ -80,8 +79,7 @@ func (c *coordinator) agenticFetchTool(_ context.Context, client *http.Client) (
8079 description = "Search the web and analyze results"
8180 }
8281
83− p, err := c.permissions.Request(
84− ctx,
82+ p := c.permissions.Request(
8583 permission.CreatePermissionRequest{
8684 SessionID: validationResult.SessionID,
8785 Path: c.cfg.WorkingDir(),
@@ -92,14 +90,12 @@ func (c *coordinator) agenticFetchTool(_ context.Context, client *http.Client) (
9290 Params: tools.AgenticFetchPermissionsParams(params),
9391 },
9492 )
95− if err != nil {
96− return fantasy.ToolResponse{}, err
97− }
93+
9894 if !p {
99− return tools.NewPermissionDeniedResponse(), nil
95+ return fantasy.ToolResponse{}, permission.ErrorPermissionDenied
10096 }
10197
102− tmpDir, err := os.MkdirTemp(c.cfg.Config().Options.DataDirectory, "crush-fetch-*")
98+ tmpDir, err := os.MkdirTemp(c.cfg.Options.DataDirectory, "crush-fetch-*")
10399 if err != nil {
104100 return fantasy.NewTextErrorResponse(fmt.Sprintf("Failed to create temporary directory: %s", err)), nil
105101 }
@@ -147,17 +143,17 @@ func (c *coordinator) agenticFetchTool(_ context.Context, client *http.Client) (
147143 return fantasy.ToolResponse{}, fmt.Errorf("error creating prompt: %s", err)
148144 }
149145
150− _, small, err := c.buildAgentModels(ctx, true)
146+ _, small, err := c.buildAgentModels(ctx)
151147 if err != nil {
152148 return fantasy.ToolResponse{}, fmt.Errorf("error building models: %s", err)
153149 }
154150
155− systemPrompt, err := promptTemplate.Build(ctx, small.Model.Provider(), small.Model.Model(), c.cfg)
151+ systemPrompt, err := promptTemplate.Build(ctx, small.Model.Provider(), small.Model.Model(), *c.cfg)
156152 if err != nil {
157153 return fantasy.ToolResponse{}, fmt.Errorf("error building system prompt: %s", err)
158154 }
159155
160− smallProviderCfg, ok := c.cfg.Config().Providers.Get(small.ModelCfg.Provider)
156+ smallProviderCfg, ok := c.cfg.Providers.Get(small.ModelCfg.Provider)
161157 if !ok {
162158 return fantasy.ToolResponse{}, errors.New("small model provider not configured")
163159 }
@@ -167,40 +163,69 @@ func (c *coordinator) agenticFetchTool(_ context.Context, client *http.Client) (
167163 fetchTools := []fantasy.AgentTool{
168164 webFetchTool,
169165 webSearchTool,
170− tools.NewGlobTool(tmpDir, c.cfg.Config().Tools.Glob),
171− tools.NewGrepTool(tmpDir, c.cfg.Config().Tools.Grep),
166+ tools.NewGlobTool(tmpDir),
167+ tools.NewGrepTool(tmpDir),
172168 tools.NewSourcegraphTool(client),
173− tools.NewViewTool(c.lspManager, c.permissions, c.filetracker, nil, tmpDir),
169+ tools.NewViewTool(c.lspClients, c.permissions, tmpDir),
174170 }
175171
176− // Sub-agent tools run without hook interception. The top-level
177− // `agentic_fetch` call itself is already wrapped from the coder's
178− // side; firing hooks again for every inner tool call would run
179− // the user's hooks N times per delegated turn.
180−
181172 agent := NewSessionAgent(SessionAgentOptions{
182173 LargeModel: small, // Use small model for both (fetch doesn't need large)
183174 SmallModel: small,
184175 SystemPromptPrefix: smallProviderCfg.SystemPromptPrefix,
185176 SystemPrompt: systemPrompt,
186− DisableAutoSummarize: c.cfg.Config().Options.DisableAutoSummarize,
177+ DisableAutoSummarize: c.cfg.Options.DisableAutoSummarize,
187178 IsYolo: c.permissions.SkipRequests(),
188179 Sessions: c.sessions,
189180 Messages: c.messages,
190181 Tools: fetchTools,
191182 })
192183
193− return c.runSubAgent(ctx, subAgentParams{
194− Agent: agent,
195− SessionID: validationResult.SessionID,
196− AgentMessageID: validationResult.AgentMessageID,
197− ToolCallID: call.ID,
198− Prompt: fullPrompt,
199− SessionTitle: "Fetch Analysis",
200− SessionSetup: func(sessionID string) {
201− c.permissions.AutoApproveSession(sessionID)
202− },
184+ agentToolSessionID := c.sessions.CreateAgentToolSessionID(validationResult.AgentMessageID, call.ID)
185+ session, err := c.sessions.CreateTaskSession(ctx, agentToolSessionID, validationResult.SessionID, "Fetch Analysis")
186+ if err != nil {
187+ return fantasy.ToolResponse{}, fmt.Errorf("error creating session: %s", err)
188+ }
189+
190+ c.permissions.AutoApproveSession(session.ID)
191+
192+ // Use small model for web content analysis (faster and cheaper)
193+ maxTokens := small.CatwalkCfg.DefaultMaxTokens
194+ if small.ModelCfg.MaxTokens != 0 {
195+ maxTokens = small.ModelCfg.MaxTokens
196+ }
197+
198+ result, err := agent.Run(ctx, SessionAgentCall{
199+ SessionID: session.ID,
200+ Prompt: fullPrompt,
201+ MaxOutputTokens: maxTokens,
202+ ProviderOptions: getProviderOptions(small, smallProviderCfg),
203+ Temperature: small.ModelCfg.Temperature,
204+ TopP: small.ModelCfg.TopP,
205+ TopK: small.ModelCfg.TopK,
206+ FrequencyPenalty: small.ModelCfg.FrequencyPenalty,
207+ PresencePenalty: small.ModelCfg.PresencePenalty,
203208 })
204− },
205− ), nil
209+ if err != nil {
210+ return fantasy.NewTextErrorResponse("error generating response"), nil
211+ }
212+
213+ updatedSession, err := c.sessions.Get(ctx, session.ID)
214+ if err != nil {
215+ return fantasy.ToolResponse{}, fmt.Errorf("error getting session: %s", err)
216+ }
217+ parentSession, err := c.sessions.Get(ctx, validationResult.SessionID)
218+ if err != nil {
219+ return fantasy.ToolResponse{}, fmt.Errorf("error getting parent session: %s", err)
220+ }
221+
222+ parentSession.Cost += updatedSession.Cost
223+
224+ _, err = c.sessions.Save(ctx, parentSession)
225+ if err != nil {
226+ return fantasy.ToolResponse{}, fmt.Errorf("error saving parent session: %s", err)
227+ }
228+
229+ return fantasy.NewTextResponse(result.Response.Content.Text()), nil
230+ }), nil
206231}
internal/agent/agenttest/coordinator.godeleted−80
@@ -1,80 +0,0 @@
1−// Package agenttest provides test-only constructors for wiring a real
2−// production agent.Coordinator without booting a full app.App. It is
3−// imported only from _test.go files (e.g. internal/backend integration
4−// tests) and is never referenced by production code, so it is compiled
5−// only under tests and never ships in the production binary or API.
6−package agenttest
7−
8−import (
9− "context"
10−
11− "charm.land/catwalk/pkg/catwalk"
12− "charm.land/fantasy/providers/openaicompat"
13− "github.com/charmbracelet/crush/internal/agent"
14− "github.com/charmbracelet/crush/internal/config"
15− "github.com/charmbracelet/crush/internal/message"
16− "github.com/charmbracelet/crush/internal/permission"
17− "github.com/charmbracelet/crush/internal/session"
18−)
19−
20−// NewCoordinator builds a real agent.Coordinator through the production
21−// agent.NewCoordinator constructor so the RunAccepted / BeginAccepted /
22−// run path (including UpdateModels) is the actual code under test.
23−//
24−// It installs a minimal config with a single openai-compatible provider
25−// whose model resolves offline. run rebuilds the model on every call, so
26−// the provider must construct without network I/O; the cancel-on-entry
27−// path this helper is built to exercise returns before any model call,
28−// so no request is ever issued. The coder agent's allowed-tools list is
29−// cleared to keep tool construction cheap and free of sub-agent wiring.
30−//
31−// The optional coordinator dependencies (history, filetracker, LSP,
32−// notify, runComplete, skills) are nil: run guards the publisher fields
33−// and the cancel-on-entry path never touches the others.
34−func NewCoordinator(
35− ctx context.Context,
36− workingDir string,
37− sessions session.Service,
38− messages message.Service,
39−) (agent.Coordinator, error) {
40− cfg, err := config.Init(workingDir, "", false)
41− if err != nil {
42− return nil, err
43− }
44−
45− const (
46− providerID = "test-openai-compat"
47− modelID = "test-model"
48− )
49− cfg.Config().Providers.Set(providerID, config.ProviderConfig{
50− ID: providerID,
51− Name: "Test",
52− Type: openaicompat.Name,
53− BaseURL: "http://127.0.0.1:0/v1",
54− APIKey: "test",
55− Models: []catwalk.Model{{ID: modelID, DefaultMaxTokens: 4096}},
56− })
57− selected := config.SelectedModel{Provider: providerID, Model: modelID}
58− cfg.OverridePreferredModel(config.SelectedModelTypeLarge, selected)
59− cfg.OverridePreferredModel(config.SelectedModelTypeSmall, selected)
60− cfg.SetupAgents()
61−
62− // Keep buildTools light: no sub-agent or agentic-fetch construction.
63− coderCfg := cfg.Config().Agents[config.AgentCoder]
64− coderCfg.AllowedTools = nil
65− cfg.Config().Agents[config.AgentCoder] = coderCfg
66−
67− return agent.NewCoordinator(
68− ctx,
69− cfg,
70− sessions,
71− messages,
72− permission.NewPermissionService(workingDir, true, nil),
73− nil,
74− nil,
75− nil,
76− nil,
77− nil,
78− nil,
79− )
80−}
internal/agent/common_test.go+59−36
@@ -8,16 +8,18 @@ import (
88 "testing"
99 "time"
1010
11− "charm.land/catwalk/pkg/catwalk"
1211 "charm.land/fantasy"
12+ "charm.land/fantasy/providers/anthropic"
13+ "charm.land/fantasy/providers/openai"
1314 "charm.land/fantasy/providers/openaicompat"
15+ "charm.land/fantasy/providers/openrouter"
1416 "charm.land/x/vcr"
17+ "github.com/charmbracelet/catwalk/pkg/catwalk"
1518 "github.com/charmbracelet/crush/internal/agent/prompt"
1619 "github.com/charmbracelet/crush/internal/agent/tools"
1720 "github.com/charmbracelet/crush/internal/config"
1821 "github.com/charmbracelet/crush/internal/csync"
1922 "github.com/charmbracelet/crush/internal/db"
20− "github.com/charmbracelet/crush/internal/filetracker"
2123 "github.com/charmbracelet/crush/internal/history"
2224 "github.com/charmbracelet/crush/internal/lsp"
2325 "github.com/charmbracelet/crush/internal/message"
@@ -35,7 +37,6 @@ type fakeEnv struct {
3537 messages message.Service
3638 permissions permission.Service
3739 history history.Service
38− filetracker *filetracker.Service
3940 lspClients *csync.Map[string, *lsp.Client]
4041}
4142
@@ -47,11 +48,50 @@ type modelPair struct {
4748 smallModel builderFunc
4849}
4950
50−func hyperBuilder(model string) builderFunc {
51+func anthropicBuilder(model string) builderFunc {
52+ return func(t *testing.T, r *vcr.Recorder) (fantasy.LanguageModel, error) {
53+ provider, err := anthropic.New(
54+ anthropic.WithAPIKey(os.Getenv("CRUSH_ANTHROPIC_API_KEY")),
55+ anthropic.WithHTTPClient(&http.Client{Transport: r}),
56+ )
57+ if err != nil {
58+ return nil, err
59+ }
60+ return provider.LanguageModel(t.Context(), model)
61+ }
62+}
63+
64+func openaiBuilder(model string) builderFunc {
65+ return func(t *testing.T, r *vcr.Recorder) (fantasy.LanguageModel, error) {
66+ provider, err := openai.New(
67+ openai.WithAPIKey(os.Getenv("CRUSH_OPENAI_API_KEY")),
68+ openai.WithHTTPClient(&http.Client{Transport: r}),
69+ )
70+ if err != nil {
71+ return nil, err
72+ }
73+ return provider.LanguageModel(t.Context(), model)
74+ }
75+}
76+
77+func openRouterBuilder(model string) builderFunc {
78+ return func(t *testing.T, r *vcr.Recorder) (fantasy.LanguageModel, error) {
79+ provider, err := openrouter.New(
80+ openrouter.WithAPIKey(os.Getenv("CRUSH_OPENROUTER_API_KEY")),
81+ openrouter.WithHTTPClient(&http.Client{Transport: r}),
82+ )
83+ if err != nil {
84+ return nil, err
85+ }
86+ return provider.LanguageModel(t.Context(), model)
87+ }
88+}
89+
90+func zAIBuilder(model string) builderFunc {
5191 return func(t *testing.T, r *vcr.Recorder) (fantasy.LanguageModel, error) {
5292 provider, err := openaicompat.New(
53− openaicompat.WithBaseURL("https://hyper.charm.land/v1"),
54− openaicompat.WithAPIKey(os.Getenv("CRUSH_HYPER_API_KEY")),
93+ openaicompat.WithBaseURL("https://api.z.ai/api/coding/paas/v4"),
94+ openaicompat.WithAPIKey(os.Getenv("CRUSH_ZAI_API_KEY")),
5595 openaicompat.WithHTTPClient(&http.Client{Transport: r}),
5696 )
5797 if err != nil {
@@ -72,12 +112,11 @@ func testEnv(t *testing.T) fakeEnv {
72112 require.NoError(t, err)
73113
74114 q := db.New(conn)
75− sessions := session.NewService(q, conn)
115+ sessions := session.NewService(q)
76116 messages := message.NewService(q)
77117
78118 permissions := permission.NewPermissionService(workingDir, true, []string{})
79119 history := history.NewService(q, conn)
80− filetrackerService := filetracker.NewService(q)
81120 lspClients := csync.NewMap[string, *lsp.Client]()
82121
83122 t.Cleanup(func() {
@@ -91,7 +130,6 @@ func testEnv(t *testing.T) fakeEnv {
91130 messages,
92131 permissions,
93132 history,
94− &filetrackerService,
95133 lspClients,
96134 }
97135}
@@ -111,15 +149,7 @@ func testSessionAgent(env fakeEnv, large, small fantasy.LanguageModel, systemPro
111149 DefaultMaxTokens: 10000,
112150 },
113151 }
114− agent := NewSessionAgent(SessionAgentOptions{
115− LargeModel: largeModel,
116− SmallModel: smallModel,
117− SystemPrompt: systemPrompt,
118− IsYolo: true,
119− Sessions: env.sessions,
120− Messages: env.messages,
121− Tools: tools,
122− })
152+ agent := NewSessionAgent(SessionAgentOptions{largeModel, smallModel, "", systemPrompt, false, false, true, env.sessions, env.messages, tools})
123153 return agent
124154}
125155
@@ -143,41 +173,34 @@ func coderAgent(r *vcr.Recorder, env fakeEnv, large, small fantasy.LanguageModel
143173
144174 // NOTE(@andreynering): Set a fixed config to ensure cassettes match
145175 // independently of user config on `$HOME/.config/crush/crush.json`.
146− cfg.Config().Options.Attribution = &config.Attribution{
176+ cfg.Options.Attribution = &config.Attribution{
147177 TrailerStyle: "co-authored-by",
148178 GeneratedWith: true,
149179 }
150180
151− // Clear some fields to avoid issues with VCR cassette matching.
152− cfg.Config().Options.SkillsPaths = nil
153− cfg.Config().Options.DisabledSkills = []string{"crush-config"}
154− cfg.Config().Options.ContextPaths = nil
155− cfg.Config().Options.GlobalContextPaths = nil
156− cfg.Config().LSP = nil
157−
158− systemPrompt, err := prompt.Build(context.TODO(), large.Provider(), large.Model(), cfg)
181+ systemPrompt, err := prompt.Build(context.TODO(), large.Provider(), large.Model(), *cfg)
159182 if err != nil {
160183 return nil, err
161184 }
162185
163186 // Get the model name for the bash tool
164187 modelName := large.Model() // fallback to ID if Name not available
165− if model := cfg.Config().GetModel(large.Provider(), large.Model()); model != nil {
188+ if model := cfg.GetModel(large.Provider(), large.Model()); model != nil {
166189 modelName = model.Name
167190 }
168191
169192 allTools := []fantasy.AgentTool{
170− tools.NewBashTool(env.permissions, env.workingDir, cfg.Config().Options.Attribution, modelName),
193+ tools.NewBashTool(env.permissions, env.workingDir, cfg.Options.Attribution, modelName),
171194 tools.NewDownloadTool(env.permissions, env.workingDir, r.GetDefaultClient()),
172− tools.NewEditTool(nil, env.permissions, env.history, *env.filetracker, env.workingDir),
173− tools.NewMultiEditTool(nil, env.permissions, env.history, *env.filetracker, env.workingDir),
195+ tools.NewEditTool(env.lspClients, env.permissions, env.history, env.workingDir),
196+ tools.NewMultiEditTool(env.lspClients, env.permissions, env.history, env.workingDir),
174197 tools.NewFetchTool(env.permissions, env.workingDir, r.GetDefaultClient()),
175− tools.NewGlobTool(env.workingDir, cfg.Config().Tools.Glob),
176− tools.NewGrepTool(env.workingDir, cfg.Config().Tools.Grep),
177− tools.NewLsTool(env.permissions, env.workingDir, cfg.Config().Tools.Ls),
198+ tools.NewGlobTool(env.workingDir),
199+ tools.NewGrepTool(env.workingDir),
200+ tools.NewLsTool(env.permissions, env.workingDir, cfg.Tools.Ls),
178201 tools.NewSourcegraphTool(r.GetDefaultClient()),
179− tools.NewViewTool(nil, env.permissions, *env.filetracker, nil, env.workingDir),
180− tools.NewWriteTool(nil, env.permissions, env.history, *env.filetracker, env.workingDir),
202+ tools.NewViewTool(env.lspClients, env.permissions, env.workingDir),
203+ tools.NewWriteTool(env.lspClients, env.permissions, env.history, env.workingDir),
181204 }
182205
183206 return testSessionAgent(env, large, small, systemPrompt, allTools...), nil
internal/agent/convert_test.godeleted−94
@@ -1,94 +0,0 @@
1−package agent
2−
3−import (
4− "encoding/base64"
5− "testing"
6−
7− "charm.land/fantasy"
8− "github.com/stretchr/testify/require"
9−)
10−
11−func TestConvertToToolResult_InvalidBase64(t *testing.T) {
12− t.Parallel()
13−
14− a := &sessionAgent{}
15− result := fantasy.ToolResultContent{
16− ToolCallID: "call_123",
17− ToolName: "test_tool",
18− Result: fantasy.ToolResultOutputContentMedia{
19− Data: "abc\x80def",
20− MediaType: "image/png",
21− },
22− }
23−
24− tr := a.convertToToolResult(result)
25− require.True(t, tr.IsError)
26− require.Empty(t, tr.Data)
27− require.Contains(t, tr.Content, "invalid encoding")
28− require.Equal(t, "call_123", tr.ToolCallID)
29− require.Equal(t, "test_tool", tr.Name)
30−}
31−
32−func TestConvertToToolResult_ValidMedia(t *testing.T) {
33− t.Parallel()
34−
35− a := &sessionAgent{}
36− validData := base64.StdEncoding.EncodeToString([]byte("test image data"))
37−
38− result := fantasy.ToolResultContent{
39− ToolCallID: "call_456",
40− ToolName: "screenshot",
41− Result: fantasy.ToolResultOutputContentMedia{
42− Data: validData,
43− MediaType: "image/png",
44− Text: "Screenshot captured",
45− },
46− }
47−
48− tr := a.convertToToolResult(result)
49− require.False(t, tr.IsError)
50− require.Equal(t, validData, tr.Data)
51− require.Equal(t, "image/png", tr.MIMEType)
52− require.Equal(t, "Screenshot captured", tr.Content)
53−}
54−
55−func TestConvertToToolResult_ValidMediaNoText(t *testing.T) {
56− t.Parallel()
57−
58− a := &sessionAgent{}
59− validData := base64.StdEncoding.EncodeToString([]byte("test image data"))
60−
61− result := fantasy.ToolResultContent{
62− ToolCallID: "call_789",
63− ToolName: "view",
64− Result: fantasy.ToolResultOutputContentMedia{
65− Data: validData,
66− MediaType: "image/jpeg",
67− },
68− }
69−
70− tr := a.convertToToolResult(result)
71− require.False(t, tr.IsError)
72− require.Equal(t, validData, tr.Data)
73− require.Equal(t, "image/jpeg", tr.MIMEType)
74− require.Equal(t, "Loaded image/jpeg content", tr.Content)
75−}
76−
77−func TestConvertToToolResult_ASCIIButInvalidBase64(t *testing.T) {
78− t.Parallel()
79−
80− a := &sessionAgent{}
81− result := fantasy.ToolResultContent{
82− ToolCallID: "call_abc",
83− ToolName: "mcp_tool",
84− Result: fantasy.ToolResultOutputContentMedia{
85− Data: "not-valid-base64!!!",
86− MediaType: "image/png",
87− },
88− }
89−
90− tr := a.convertToToolResult(result)
91− require.True(t, tr.IsError)
92− require.Empty(t, tr.Data)
93− require.Contains(t, tr.Content, "invalid encoding")
94−}
internal/agent/coordinator.go+175−978
@@ -12,34 +12,22 @@ import (
1212 "maps"
1313 "net/http"
1414 "os"
15− "path/filepath"
1615 "slices"
1716 "strings"
18− "sync"
19− "sync/atomic"
2017
21− "charm.land/catwalk/pkg/catwalk"
2218 "charm.land/fantasy"
19+ "github.com/charmbracelet/catwalk/pkg/catwalk"
2320 "github.com/charmbracelet/crush/internal/agent/hyper"
24− "github.com/charmbracelet/crush/internal/agent/notify"
2521 "github.com/charmbracelet/crush/internal/agent/prompt"
2622 "github.com/charmbracelet/crush/internal/agent/tools"
27− "github.com/charmbracelet/crush/internal/agent/tools/mcp"
2823 "github.com/charmbracelet/crush/internal/config"
2924 "github.com/charmbracelet/crush/internal/csync"
30− "github.com/charmbracelet/crush/internal/discover"
31− "github.com/charmbracelet/crush/internal/event"
32− "github.com/charmbracelet/crush/internal/filetracker"
3325 "github.com/charmbracelet/crush/internal/history"
34− "github.com/charmbracelet/crush/internal/hooks"
3526 "github.com/charmbracelet/crush/internal/log"
3627 "github.com/charmbracelet/crush/internal/lsp"
3728 "github.com/charmbracelet/crush/internal/message"
38− "github.com/charmbracelet/crush/internal/oauth/copilot"
3929 "github.com/charmbracelet/crush/internal/permission"
40− "github.com/charmbracelet/crush/internal/pubsub"
4130 "github.com/charmbracelet/crush/internal/session"
42− "github.com/charmbracelet/crush/internal/skills"
4331 "golang.org/x/sync/errgroup"
4432
4533 "charm.land/fantasy/providers/anthropic"
@@ -49,52 +37,14 @@ import (
4937 "charm.land/fantasy/providers/openai"
5038 "charm.land/fantasy/providers/openaicompat"
5139 "charm.land/fantasy/providers/openrouter"
52− "charm.land/fantasy/providers/vercel"
53− openaisdk "github.com/charmbracelet/openai-go/option"
40+ openaisdk "github.com/openai/openai-go/v2/option"
5441 "github.com/qjebbs/go-jsons"
5542)
5643
57−// Coordinator errors.
58−var (
59− errCoderAgentNotConfigured = errors.New("coder agent not configured")
60− errModelProviderNotConfigured = errors.New("model provider not configured")
61− errLargeModelNotSelected = errors.New("large model not selected")
62− errSmallModelNotSelected = errors.New("small model not selected")
63− errLargeModelProviderNotConfigured = errors.New("large model provider not configured")
64− errSmallModelProviderNotConfigured = errors.New("small model provider not configured")
65− errLargeModelNotFound = errors.New("large model not found in provider config")
66− errSmallModelNotFound = errors.New("small model not found in provider config")
67−)
68−
69−// Copilot models that use the Responses API instead of Chat Completions.
70−var copilotResponsesModels = map[string]bool{
71− "gpt-5.2": true,
72− "gpt-5.2-codex": true,
73− "gpt-5.3-codex": true,
74− "gpt-5.4": true,
75− "gpt-5.4-mini": true,
76− "gpt-5.5": true,
77− "gpt-5-mini": true,
78−}
79−
80−// OpenCode models that user Anthropic Messages API instead of Chat Completions.
81−var opencodeMessagesModels = map[string]bool{
82− "qwen3.7-max": true,
83−}
84−
8544type Coordinator interface {
8645 // INFO: (kujtim) this is not used yet we will use this when we have multiple agents
8746 // SetMainAgent(string)
8847 Run(ctx context.Context, sessionID, prompt string, attachments ...message.Attachment) (*fantasy.AgentResult, error)
89− // RunAccepted runs a call that was already accepted via
90− // BeginAccepted on the fire-and-forget dispatch path. The handle is
91− // the only carrier of accept-state across the backend.runAgent /
92− // Coordinator / sessionAgent.Run layers: it reaches
93− // sessionAgent.Run as SessionAgentCall.Accepted, where it is
94− // consumed under dispatchMu once the accepted -> (cancel-on-entry |
95− // queued | active) transition is chosen.
96− RunAccepted(ctx context.Context, accept *AcceptedRun, sessionID, prompt string, attachments ...message.Attachment) (*fantasy.AgentResult, error)
97− BeginAccepted(sessionID string) *AcceptedRun
9848 Cancel(sessionID string)
9949 CancelAll()
10050 IsSessionBusy(sessionID string) bool
@@ -105,104 +55,44 @@ type Coordinator interface {
10555 Summarize(context.Context, string) error
10656 Model() Model
10757 UpdateModels(ctx context.Context) error
108− GenerateTitle(ctx context.Context, sessionID, prompt string)
10958}
11059
11160type coordinator struct {
112− cfg *config.ConfigStore
61+ cfg *config.Config
11362 sessions session.Service
11463 messages message.Service
11564 permissions permission.Service
11665 history history.Service
117− filetracker filetracker.Service
118− lspManager *lsp.Manager
119− notify pubsub.Publisher[notify.Notification]
120− runComplete pubsub.Publisher[notify.RunComplete]
66+ lspClients *csync.Map[string, *lsp.Client]
12167
12268 currentAgent SessionAgent
12369 agents map[string]SessionAgent
12470
125− // Skills discovery results (session-start snapshot).
126− allSkills []*skills.Skill // Pre-filter: all discovered after dedup.
127− activeSkills []*skills.Skill // Post-filter: active skills only.
128− skillTracker *skills.Tracker
129−
130− // providerClients caches built provider clients keyed by their fully
131− // resolved configuration. UpdateModels rebuilds models every turn;
132− // without this, each turn discards the provider's HTTP client and its
133− // keep-alive connection pool, forcing a fresh TLS handshake. The key
134− // captures every input buildProvider depends on, so any config/model/
135− // credential change misses the cache and rebuilds.
136− providerClients *csync.Map[string, fantasy.Provider]
137−
138− // toolsCache avoids rebuilding the tool set on every UpdateModels call.
139− // The cache is invalidated when the config pointer changes (reload or
140− // mutation) or when mcpToolsGen is bumped (MCP server connect/disconnect
141− // or tools/list_changed notification).
142− toolsCacheMu sync.Mutex
143− toolsCache []fantasy.AgentTool
144− toolsCacheCfg *config.Config
145− toolsCacheMCP uint64
146− mcpToolsGen atomic.Uint64
147−
148− // providerOptsCache avoids repeating the 3× JSON marshal + merge +
149− // unmarshal in getProviderOptions on every turn when the model and
150− // config have not changed. Keyed by config pointer + model CatwalkCfg
151− // ID + provider name.
152− providerOptsCacheMu sync.Mutex
153− providerOptsCache fantasy.ProviderOptions
154− providerOptsCacheKey string
155−
15671 readyWg errgroup.Group
15772}
15873
15974func NewCoordinator(
16075 ctx context.Context,
161− cfg *config.ConfigStore,
76+ cfg *config.Config,
16277 sessions session.Service,
16378 messages message.Service,
16479 permissions permission.Service,
16580 history history.Service,
166− filetracker filetracker.Service,
167− lspManager *lsp.Manager,
168− notify pubsub.Publisher[notify.Notification],
169− runComplete pubsub.Publisher[notify.RunComplete],
170− skillsMgr *skills.Manager,
81+ lspClients *csync.Map[string, *lsp.Client],
17182) (Coordinator, error) {
172− // Skills are pre-discovered by the caller (see app.New /
173− // backend.CreateWorkspace) and passed in via the manager. If no
174− // manager was provided (legacy callers), fall back to an in-line
175− // discovery so the coordinator still works.
176− var allSkills, activeSkills []*skills.Skill
177− if skillsMgr != nil {
178− allSkills = skillsMgr.AllSkills()
179− activeSkills = skillsMgr.ActiveSkills()
180− } else {
181− allSkills, activeSkills = discoverSkills(cfg)
182− }
183− skillTracker := skills.NewTracker(activeSkills)
184−
18583 c := &coordinator{
186− cfg: cfg,
187− sessions: sessions,
188− messages: messages,
189− permissions: permissions,
190− history: history,
191− filetracker: filetracker,
192− lspManager: lspManager,
193− notify: notify,
194− runComplete: runComplete,
195− agents: make(map[string]SessionAgent),
196− allSkills: allSkills,
197− activeSkills: activeSkills,
198− skillTracker: skillTracker,
199−
200− providerClients: csync.NewMap[string, fantasy.Provider](),
201− }
202−
203− agentCfg, ok := cfg.Config().Agents[config.AgentCoder]
84+ cfg: cfg,
85+ sessions: sessions,
86+ messages: messages,
87+ permissions: permissions,
88+ history: history,
89+ lspClients: lspClients,
90+ agents: make(map[string]SessionAgent),
91+ }
92+
93+ agentCfg, ok := cfg.Agents[config.AgentCoder]
20494 if !ok {
205− return nil, errCoderAgentNotConfigured
95+ return nil, errors.New("coder agent not configured")
20696 }
20797
20898 // TODO: make this dynamic when we support multiple agents
@@ -217,45 +107,15 @@ func NewCoordinator(
217107 }
218108 c.currentAgent = agent
219109 c.agents[config.AgentCoder] = agent
220−
221− // Subscribe to MCP tool-list changes so the tools cache is invalidated
222− // when MCP servers connect/disconnect or announce new tools.
223− go func() {
224− for ev := range mcp.SubscribeEvents(ctx) {
225− if ev.Payload.Type == mcp.EventToolsListChanged || ev.Payload.Type == mcp.EventStateChanged {
226− c.mcpToolsGen.Add(1)
227− }
228− }
229− }()
230−
231110 return c, nil
232111}
233112
234113// Run implements Coordinator.
235114func (c *coordinator) Run(ctx context.Context, sessionID string, prompt string, attachments ...message.Attachment) (*fantasy.AgentResult, error) {
236− return c.run(ctx, nil, sessionID, prompt, attachments...)
237−}
238−
239−// RunAccepted implements Coordinator.
240−func (c *coordinator) RunAccepted(ctx context.Context, accept *AcceptedRun, sessionID string, prompt string, attachments ...message.Attachment) (*fantasy.AgentResult, error) {
241− return c.run(ctx, accept, sessionID, prompt, attachments...)
242−}
243−
244−// run is the shared implementation behind Run and RunAccepted. When
245−// accept is non-nil it is threaded onto the SessionAgentCall as
246−// Accepted so sessionAgent.Run can consume the accept reservation under
247−// dispatchMu; when nil (the in-process/local path) no accept tracking
248−// applies.
249−func (c *coordinator) run(ctx context.Context, accept *AcceptedRun, sessionID string, prompt string, attachments ...message.Attachment) (*fantasy.AgentResult, error) {
250115 if err := c.readyWg.Wait(); err != nil {
251116 return nil, err
252117 }
253118
254− // refresh models before each run
255− if err := c.UpdateModels(ctx); err != nil {
256− return nil, fmt.Errorf("failed to update models: %w", err)
257− }
258−
259119 model := c.currentAgent.Model()
260120 maxTokens := model.CatwalkCfg.DefaultMaxTokens
261121 if model.ModelCfg.MaxTokens != 0 {
@@ -273,47 +133,23 @@ func (c *coordinator) run(ctx context.Context, accept *AcceptedRun, sessionID st
273133 attachments = filteredAttachments
274134 }
275135
276− providerCfg, ok := c.cfg.Config().Providers.Get(model.ModelCfg.Provider)
136+ providerCfg, ok := c.cfg.Providers.Get(model.ModelCfg.Provider)
277137 if !ok {
278− return nil, errModelProviderNotConfigured
138+ return nil, errors.New("model provider not configured")
279139 }
280140
281− mergedOptions, temp, topP, topK, freqPenalty, presPenalty := c.cachedMergeCallOptions(model, providerCfg)
141+ mergedOptions, temp, topP, topK, freqPenalty, presPenalty := mergeCallOptions(model, providerCfg)
282142
283− if err := c.refreshTokenIfExpired(ctx, providerCfg); err != nil {
284− // NOTE(@andreynering): We don't return here because the event handling to ask the user to reauthenticate
285− // depends on the flow below. If refresh fails, proceed with the token we have.
286− slog.Error("Failed to refresh OAuth2 token. Proceeding with existing token.", "error", err)
143+ if providerCfg.OAuthToken != nil && providerCfg.OAuthToken.IsExpired() {
144+ slog.Info("Token needs to be refreshed", "provider", providerCfg.ID)
145+ if err := c.refreshOAuth2Token(ctx, providerCfg); err != nil {
146+ return nil, err
147+ }
287148 }
288149
289− // Coalesce per-attempt RunComplete payloads so only the final
290− // outcome reaches subscribers. Without this, the first attempt's
291− // failed RunComplete (unauthorized) would race ahead of the
292− // retry's success, and `crush run` would exit on the stale error
293− // before ever seeing the retry result. Each attempt's
294− // SessionAgentCall.OnComplete hook overwrites latest; we publish
295− // exactly once after retries resolve, via PublishMustDeliver, so
296− // a momentarily-full subscriber buffer can't silently drop the
297− // terminal event.
298− var (
299− latest notify.RunComplete
300− hasLatest bool
301− )
302− onComplete := func(rc notify.RunComplete) {
303− latest = rc
304− hasLatest = true
305− }
306− // Propagate the caller-supplied RunID (set via agent.WithRunID
307− // at the HTTP boundary in backend.SendMessage) onto the
308− // SessionAgentCall so the terminal RunComplete event echoes it
309− // back. Both attempts in the retry chain reuse the same RunID;
310− // the coalesce closure publishes the final outcome under that
311− // same correlator.
312− runID := RunIDFromContext(ctx)
313150 run := func() (*fantasy.AgentResult, error) {
314151 return c.currentAgent.Run(ctx, SessionAgentCall{
315152 SessionID: sessionID,
316− RunID: runID,
317153 Prompt: prompt,
318154 Attachments: attachments,
319155 MaxOutputTokens: maxTokens,
@@ -323,57 +159,30 @@ func (c *coordinator) run(ctx context.Context, accept *AcceptedRun, sessionID st
323159 TopK: topK,
324160 FrequencyPenalty: freqPenalty,
325161 PresencePenalty: presPenalty,
326− OnComplete: onComplete,
327− Accepted: accept,
328− })
329− }
330− beforeLoaded := c.skillTracker.LoadedNames()
331− var result *fantasy.AgentResult
332− originalErr := c.runWithUnauthorizedRetry(ctx, providerCfg, func() error {
333− var err error
334− result, err = run()
335− return err
336− })
337− logTurnSkillUsage(sessionID, prompt, c.activeSkills, c.skillTracker, beforeLoaded)
338−
339− // Notify only if still unauthorized after retry — a successful
340− // retry means the user doesn't need to re-authenticate.
341− if originalErr != nil && c.isUnauthorized(originalErr) && c.notify != nil && model.ModelCfg.Provider == hyper.Name {
342− c.notify.Publish(pubsub.CreatedEvent, notify.Notification{
343− Type: notify.TypeReAuthenticate,
344− ProviderID: model.ModelCfg.Provider,
345162 })
346163 }
164+ result, originalErr := run()
347165
348− if hasLatest && c.runComplete != nil {
349− c.runComplete.PublishMustDeliver(ctx, pubsub.UpdatedEvent, latest)
350− // Signal to the dispatcher (backend.runAgent) that the
351− // authoritative terminal RunComplete for this run was already
352− // emitted, so it does not publish a duplicate fallback for the
353− // error it is about to receive.
354− MarkRunCompletePublished(ctx)
355− }
356− return result, originalErr
357−}
358−
359−// effectiveReasoningEffort returns the reasoning effort to apply for provider calls.
360−// It prefers the user-selected effort when valid, otherwise the model default when
361−// valid, and finally falls back to the first configured reasoning level.
362−func effectiveReasoningEffort(model Model) string {
363− if !model.CatwalkCfg.CanReason {
364− return ""
166+ if c.isUnauthorized(originalErr) {
167+ switch {
168+ case providerCfg.OAuthToken != nil:
169+ slog.Info("Received 401. Refreshing token and retrying", "provider", providerCfg.ID)
170+ if err := c.refreshOAuth2Token(ctx, providerCfg); err != nil {
171+ return nil, originalErr
172+ }
173+ slog.Info("Retrying request with refreshed OAuth token", "provider", providerCfg.ID)
174+ return run()
175+ case strings.Contains(providerCfg.APIKeyTemplate, "$"):
176+ slog.Info("Received 401. Refreshing API Key template and retrying", "provider", providerCfg.ID)
177+ if err := c.refreshApiKeyTemplate(ctx, providerCfg); err != nil {
178+ return nil, originalErr
179+ }
180+ slog.Info("Retrying request with refreshed API key", "provider", providerCfg.ID)
181+ return run()
182+ }
365183 }
366184
367− if effort := model.ModelCfg.ReasoningEffort; effort != "" && slices.Contains(model.CatwalkCfg.ReasoningLevels, effort) {
368− return effort
369− }
370− if effort := model.CatwalkCfg.DefaultReasoningEffort; effort != "" && slices.Contains(model.CatwalkCfg.ReasoningLevels, effort) {
371− return effort
372− }
373− if len(model.CatwalkCfg.ReasoningLevels) > 0 {
374− return model.CatwalkCfg.ReasoningLevels[0]
375− }
376− return ""
185+ return result, originalErr
377186}
378187
379188func getProviderOptions(model Model, providerCfg config.ProviderConfig) fantasy.ProviderOptions {
@@ -424,16 +233,11 @@ func getProviderOptions(model Model, providerCfg config.ProviderConfig) fantasy.
424233 return options
425234 }
426235
427− reasoningEffort := effectiveReasoningEffort(model)
428− shouldSetEffort := model.CatwalkCfg.CanReason &&
429− reasoningEffort != "" &&
430− slices.Contains(model.CatwalkCfg.ReasoningLevels, reasoningEffort)
431−
432236 switch providerCfg.Type {
433237 case openai.Name, azure.Name:
434238 _, hasReasoningEffort := mergedOptions["reasoning_effort"]
435− if !hasReasoningEffort && shouldSetEffort {
436− mergedOptions["reasoning_effort"] = reasoningEffort
239+ if !hasReasoningEffort && model.ModelCfg.ReasoningEffort != "" {
240+ mergedOptions["reasoning_effort"] = model.ModelCfg.ReasoningEffort
437241 }
438242 if openai.IsResponsesModel(model.CatwalkCfg.ID) {
439243 if openai.IsResponsesReasoningModel(model.CatwalkCfg.ID) {
@@ -450,37 +254,14 @@ func getProviderOptions(model Model, providerCfg config.ProviderConfig) fantasy.
450254 options[openai.Name] = parsed
451255 }
452256 }
453−
454− case anthropic.Name, bedrock.Name:
455− var (
456− _, hasEffort = mergedOptions["effort"]
457− _, hasThink = mergedOptions["thinking"]
458− extraBody = make(map[string]any)
459− )
460−
461− switch providerCfg.ID {
462− case string(catwalk.InferenceProviderAlibabaSingapore), string(catwalk.InferenceProviderAlibabaUS):
463− switch {
464− case !hasEffort && shouldSetEffort:
465− extraBody["reasoning_effort"] = reasoningEffort
466− case !hasThink && model.CatwalkCfg.CanReason:
467− if model.ModelCfg.Think {
468− extraBody["thinking"] = map[string]any{"type": "enabled"}
469− } else {
470− extraBody["thinking"] = map[string]any{"type": "disabled"}
471− }
472− }
473− mergedOptions["extra_body"] = extraBody
474−
475− default:
476− switch {
477− case !hasEffort && shouldSetEffort:
478− mergedOptions["effort"] = reasoningEffort
479− case !hasThink && model.ModelCfg.Think:
480− mergedOptions["thinking"] = map[string]any{"budget_tokens": 2000}
257+ case anthropic.Name:
258+ _, hasThink := mergedOptions["thinking"]
259+ if !hasThink && model.ModelCfg.Think {
260+ mergedOptions["thinking"] = map[string]any{
261+ // TODO: kujtim see if we need to make this dynamic
262+ "budget_tokens": 2000,
481263 }
482264 }
483−
484265 parsed, err := anthropic.ParseOptions(mergedOptions)
485266 if err == nil {
486267 options[anthropic.Name] = parsed
@@ -488,123 +269,37 @@ func getProviderOptions(model Model, providerCfg config.ProviderConfig) fantasy.
488269
489270 case openrouter.Name:
490271 _, hasReasoning := mergedOptions["reasoning"]
491− if !hasReasoning && shouldSetEffort {
272+ if !hasReasoning && model.ModelCfg.ReasoningEffort != "" {
492273 mergedOptions["reasoning"] = map[string]any{
493274 "enabled": true,
494− "effort": reasoningEffort,
275+ "effort": model.ModelCfg.ReasoningEffort,
495276 }
496277 }
497278 parsed, err := openrouter.ParseOptions(mergedOptions)
498279 if err == nil {
499280 options[openrouter.Name] = parsed
500281 }
501−
502− case vercel.Name:
503− _, hasReasoning := mergedOptions["reasoning"]
504− if !hasReasoning && shouldSetEffort {
505− mergedOptions["reasoning"] = map[string]any{
506− "enabled": true,
507− "effort": reasoningEffort,
508− }
509− }
510− parsed, err := vercel.ParseOptions(mergedOptions)
511− if err == nil {
512− options[vercel.Name] = parsed
513− }
514−
515282 case google.Name:
516283 _, hasReasoning := mergedOptions["thinking_config"]
517284 if !hasReasoning {
518− if strings.HasPrefix(model.CatwalkCfg.ID, "gemini-2") {
519− mergedOptions["thinking_config"] = map[string]any{
520− "thinking_budget": 2000,
521− "include_thoughts": true,
522− }
523− } else {
524− mergedOptions["thinking_config"] = map[string]any{
525− "thinking_level": reasoningEffort,
526− "include_thoughts": true,
527− }
285+ mergedOptions["thinking_config"] = map[string]any{
286+ "thinking_budget": 2000,
287+ "include_thoughts": true,
528288 }
529289 }
530290 parsed, err := google.ParseOptions(mergedOptions)
531291 if err == nil {
532292 options[google.Name] = parsed
533293 }
534−
535− case openaicompat.Name, hyper.Name:
536− extraBody := make(map[string]any)
537−
294+ case openaicompat.Name:
538295 _, hasReasoningEffort := mergedOptions["reasoning_effort"]
539− if !hasReasoningEffort && shouldSetEffort {
540− switch providerCfg.ID {
541− case string(catwalk.InferenceProviderIoNet):
542− extraBody["reasoning"] = map[string]string{"effort": reasoningEffort}
543− default:
544− mergedOptions["reasoning_effort"] = reasoningEffort
545− }
546− }
547−
548− // "reasoning effort" is a standard OpenAI field, but "thinking" is not.
549− // Setting it in the right way for each provider.
550− // TODO: Abstract this in Fantasy somehow?
551− // TODO: Allow custom providers to specify how to set this?
552− switch providerCfg.ID {
553− case hyper.Name:
554− extraBody["thinking"] = model.ModelCfg.Think
555− case string(catwalk.InferenceProviderIoNet):
556− if _, ok := extraBody["reasoning"]; !ok && model.CatwalkCfg.CanReason {
557− if model.ModelCfg.Think {
558− extraBody["reasoning"] = map[string]string{"effort": "medium"}
559− } else {
560− extraBody["reasoning"] = map[string]string{"effort": "none"}
561− }
562− }
563−
564− case string(catwalk.InferenceProviderZAI), string(catwalk.InferenceProviderDeepSeek):
565− if model.ModelCfg.Think || reasoningEffort != "" {
566− extraBody["thinking"] = map[string]any{"type": "enabled"}
567− } else {
568− extraBody["thinking"] = map[string]any{"type": "disabled"}
569− }
570−
571− case string(catwalk.InferenceProviderFireworks):
572− // NOTE: Fireworks break if we set both `reasoning_effort` and `thinking`.
573− if reasoningEffort == "" {
574− if model.ModelCfg.Think {
575− extraBody["thinking"] = map[string]any{"type": "enabled"}
576− } else {
577− extraBody["thinking"] = map[string]any{"type": "disabled"}
578− }
579− }
580−
581− case string(catwalk.InferenceProviderBaseten):
582− extraBody["chat_template_args"] = map[string]any{
583− "enable_thinking": model.ModelCfg.Think || reasoningEffort != "",
584− }
585−
586− case string(catwalk.InferenceProviderAlibabaSingapore), string(catwalk.InferenceProviderAlibabaUS):
587− if model.CatwalkCfg.CanReason {
588− extraBody["enable_thinking"] = model.ModelCfg.Think || reasoningEffort != ""
589− }
296+ if !hasReasoningEffort && model.ModelCfg.ReasoningEffort != "" {
297+ mergedOptions["reasoning_effort"] = model.ModelCfg.ReasoningEffort
590298 }
591−
592− mergedOptions["extra_body"] = extraBody
593−
594299 parsed, err := openaicompat.ParseOptions(mergedOptions)
595300 if err == nil {
596301 options[openaicompat.Name] = parsed
597302 }
598−
599− default:
600− // Known custom providers (litellm, ollama, omlx) are
601− // openai-compat under the hood.
602− if discover.IsKnownCustomProvider(string(providerCfg.Type)) {
603− parsed, err := openaicompat.ParseOptions(mergedOptions)
604− if err == nil {
605− options[openaicompat.Name] = parsed
606− }
607− }
608303 }
609304
610305 return options
@@ -620,72 +315,32 @@ func mergeCallOptions(model Model, cfg config.ProviderConfig) (fantasy.ProviderO
620315 return modelOptions, temp, topP, topK, freqPenalty, presPenalty
621316}
622317
623−// cachedMergeCallOptions wraps mergeCallOptions with a memoization cache.
624−// The provider options JSON merge is expensive (3× marshal + merge +
625−// unmarshal) and the inputs rarely change between turns. The cache key
626−// combines the config pointer identity with the model's catwalk ID and
627−// provider name so any config reload or model switch misses the cache.
628−func (c *coordinator) cachedMergeCallOptions(model Model, cfg config.ProviderConfig) (fantasy.ProviderOptions, *float64, *float64, *int64, *float64, *float64) {
629− key := fmt.Sprintf("%p|%s|%s", c.cfg.Config(), model.CatwalkCfg.ID, model.ModelCfg.Provider)
630−
631− c.providerOptsCacheMu.Lock()
632− if c.providerOptsCacheKey == key {
633− opts := c.providerOptsCache
634− c.providerOptsCacheMu.Unlock()
635− // Recompute the scalar overrides (cheap) since they don't need
636− // the JSON merge — they're just cmp.Or calls.
637− temp := cmp.Or(model.ModelCfg.Temperature, model.CatwalkCfg.Options.Temperature)
638− topP := cmp.Or(model.ModelCfg.TopP, model.CatwalkCfg.Options.TopP)
639− topK := cmp.Or(model.ModelCfg.TopK, model.CatwalkCfg.Options.TopK)
640− freqPenalty := cmp.Or(model.ModelCfg.FrequencyPenalty, model.CatwalkCfg.Options.FrequencyPenalty)
641− presPenalty := cmp.Or(model.ModelCfg.PresencePenalty, model.CatwalkCfg.Options.PresencePenalty)
642− return opts, temp, topP, topK, freqPenalty, presPenalty
643− }
644− c.providerOptsCacheMu.Unlock()
645−
646− opts, temp, topP, topK, freqPenalty, presPenalty := mergeCallOptions(model, cfg)
647−
648− c.providerOptsCacheMu.Lock()
649− c.providerOptsCache = opts
650− c.providerOptsCacheKey = key
651− c.providerOptsCacheMu.Unlock()
652−
653− return opts, temp, topP, topK, freqPenalty, presPenalty
654−}
655−
656318func (c *coordinator) buildAgent(ctx context.Context, prompt *prompt.Prompt, agent config.Agent, isSubAgent bool) (SessionAgent, error) {
657− large, small, err := c.buildAgentModels(ctx, isSubAgent)
319+ large, small, err := c.buildAgentModels(ctx)
320+ if err != nil {
321+ return nil, err
322+ }
323+
324+ systemPrompt, err := prompt.Build(ctx, large.Model.Provider(), large.Model.Model(), *c.cfg)
658325 if err != nil {
659326 return nil, err
660327 }
661328
662− largeProviderCfg, _ := c.cfg.Config().Providers.Get(large.ModelCfg.Provider)
329+ largeProviderCfg, _ := c.cfg.Providers.Get(large.ModelCfg.Provider)
663330 result := NewSessionAgent(SessionAgentOptions{
664− LargeModel: large,
665− SmallModel: small,
666− SystemPromptPrefix: largeProviderCfg.SystemPromptPrefix,
667− SystemPrompt: "",
668− IsSubAgent: isSubAgent,
669− DisableAutoSummarize: c.cfg.Config().Options.DisableAutoSummarize,
670− IsYolo: c.permissions.SkipRequests(),
671− Sessions: c.sessions,
672− Messages: c.messages,
673− Tools: nil,
674− Notify: c.notify,
675− RunComplete: c.runComplete,
331+ large,
332+ small,
333+ largeProviderCfg.SystemPromptPrefix,
334+ systemPrompt,
335+ isSubAgent,
336+ c.cfg.Options.DisableAutoSummarize,
337+ c.permissions.SkipRequests(),
338+ c.sessions,
339+ c.messages,
340+ nil,
676341 })
677−
678342 c.readyWg.Go(func() error {
679− systemPrompt, err := prompt.Build(ctx, large.Model.Provider(), large.Model.Model(), c.cfg)
680− if err != nil {
681− return err
682− }
683− result.SetSystemPrompt(systemPrompt)
684− return nil
685− })
686−
687− c.readyWg.Go(func() error {
688− tools, err := c.buildTools(ctx, agent, isSubAgent)
343+ tools, err := c.buildTools(ctx, agent)
689344 if err != nil {
690345 return err
691346 }
@@ -696,7 +351,7 @@ func (c *coordinator) buildAgent(ctx context.Context, prompt *prompt.Prompt, age
696351 return result, nil
697352}
698353
699−func (c *coordinator) buildTools(ctx context.Context, agent config.Agent, isSubAgent bool) ([]fantasy.AgentTool, error) {
354+func (c *coordinator) buildTools(ctx context.Context, agent config.Agent) ([]fantasy.AgentTool, error) {
700355 var allTools []fantasy.AgentTool
701356 if slices.Contains(agent.AllowedTools, AgentToolName) {
702357 agentTool, err := c.agentTool(ctx)
@@ -715,52 +370,32 @@ func (c *coordinator) buildTools(ctx context.Context, agent config.Agent, isSubA
715370 }
716371
717372 // Get the model name for the agent
718− modelID := ""
719− if modelCfg, ok := c.cfg.Config().Models[agent.Model]; ok {
720− if model := c.cfg.Config().GetModel(modelCfg.Provider, modelCfg.Model); model != nil {
721− modelID = model.ID
373+ modelName := ""
374+ if modelCfg, ok := c.cfg.Models[agent.Model]; ok {
375+ if model := c.cfg.GetModel(modelCfg.Provider, modelCfg.Model); model != nil {
376+ modelName = model.Name
722377 }
723378 }
724379
725− logFile := filepath.Join(c.cfg.Config().Options.DataDirectory, "logs", "crush.log")
726−
727− // Build hook runner if PreToolUse hooks are configured.
728− var hookRunner *hooks.Runner
729− if preToolHooks := c.cfg.Config().Hooks[hooks.EventPreToolUse]; len(preToolHooks) > 0 {
730− hookRunner = hooks.NewRunner(preToolHooks, c.cfg.WorkingDir(), c.cfg.WorkingDir())
731− }
732−
733− allTools = append(
734− allTools,
735− tools.NewBashTool(c.permissions, c.cfg.WorkingDir(), c.cfg.Config().Options.Attribution, modelID),
736− tools.NewCrushInfoTool(c.cfg, c.lspManager, c.allSkills, c.activeSkills, c.skillTracker),
737− tools.NewCrushLogsTool(logFile),
380+ allTools = append(allTools,
381+ tools.NewBashTool(c.permissions, c.cfg.WorkingDir(), c.cfg.Options.Attribution, modelName),
738382 tools.NewJobOutputTool(),
739383 tools.NewJobKillTool(),
740384 tools.NewDownloadTool(c.permissions, c.cfg.WorkingDir(), nil),
741− tools.NewEditTool(c.lspManager, c.permissions, c.history, c.filetracker, c.cfg.WorkingDir()),
742− tools.NewMultiEditTool(c.lspManager, c.permissions, c.history, c.filetracker, c.cfg.WorkingDir()),
385+ tools.NewEditTool(c.lspClients, c.permissions, c.history, c.cfg.WorkingDir()),
386+ tools.NewMultiEditTool(c.lspClients, c.permissions, c.history, c.cfg.WorkingDir()),
743387 tools.NewFetchTool(c.permissions, c.cfg.WorkingDir(), nil),
744− tools.NewGlobTool(c.cfg.WorkingDir(), c.cfg.Config().Tools.Glob),
745− tools.NewGrepTool(c.cfg.WorkingDir(), c.cfg.Config().Tools.Grep),
746− tools.NewLsTool(c.permissions, c.cfg.WorkingDir(), c.cfg.Config().Tools.Ls),
388+ tools.NewGlobTool(c.cfg.WorkingDir()),
389+ tools.NewGrepTool(c.cfg.WorkingDir()),
390+ tools.NewLsTool(c.permissions, c.cfg.WorkingDir(), c.cfg.Tools.Ls),
747391 tools.NewSourcegraphTool(nil),
748392 tools.NewTodosTool(c.sessions),
749− tools.NewViewTool(c.lspManager, c.permissions, c.filetracker, c.skillTracker, c.cfg.WorkingDir(), c.cfg.Config().Options.SkillsPaths...),
750− tools.NewWriteTool(c.lspManager, c.permissions, c.history, c.filetracker, c.cfg.WorkingDir()),
393+ tools.NewViewTool(c.lspClients, c.permissions, c.cfg.WorkingDir()),
394+ tools.NewWriteTool(c.lspClients, c.permissions, c.history, c.cfg.WorkingDir()),
751395 )
752396
753− // Add LSP tools if user has configured LSPs or auto_lsp is enabled (nil or true).
754− if len(c.cfg.Config().LSP) > 0 || c.cfg.Config().Options.AutoLSP == nil || *c.cfg.Config().Options.AutoLSP {
755− allTools = append(allTools, tools.NewDiagnosticsTool(c.lspManager), tools.NewReferencesTool(c.lspManager), tools.NewLSPRestartTool(c.lspManager))
756− }
757−
758− if len(c.cfg.Config().MCP) > 0 {
759− allTools = append(
760− allTools,
761− tools.NewListMCPResourcesTool(c.cfg, c.permissions),
762− tools.NewReadMCPResourceTool(c.cfg, c.permissions),
763− )
397+ if len(c.cfg.LSP) > 0 {
398+ allTools = append(allTools, tools.NewDiagnosticsTool(c.lspClients), tools.NewReferencesTool(c.lspClients))
764399 }
765400
766401 var filteredTools []fantasy.AgentTool
@@ -770,7 +405,13 @@ func (c *coordinator) buildTools(ctx context.Context, agent config.Agent, isSubA
770405 }
771406 }
772407
773− for _, tool := range tools.GetMCPTools(c.permissions, c.cfg, c.cfg.WorkingDir()) {
408+ for _, tool := range tools.GetMCPTools(c.permissions, c.cfg.WorkingDir()) {
409+ // Check MCP-specific disabled tools.
410+ if mcpCfg, ok := c.cfg.MCP[tool.MCP()]; ok {
411+ if slices.Contains(mcpCfg.DisabledTools, tool.MCPToolName()) {
412+ continue
413+ }
414+ }
774415 if agent.AllowedMCP == nil {
775416 // No MCP restrictions
776417 filteredTools = append(filteredTools, tool)
@@ -778,7 +419,7 @@ func (c *coordinator) buildTools(ctx context.Context, agent config.Agent, isSubA
778419 }
779420 if len(agent.AllowedMCP) == 0 {
780421 // No MCPs allowed
781− slog.Debug("No MCPs allowed", "tool", tool.Name(), "agent", agent.Name)
422+ slog.Debug("no MCPs allowed", "tool", tool.Name(), "agent", agent.Name)
782423 break
783424 }
784425
@@ -788,52 +429,43 @@ func (c *coordinator) buildTools(ctx context.Context, agent config.Agent, isSubA
788429 }
789430 if len(tools) == 0 || slices.Contains(tools, tool.MCPToolName()) {
790431 filteredTools = append(filteredTools, tool)
791− break
792432 }
793− slog.Debug("MCP not allowed", "tool", tool.Name(), "agent", agent.Name)
794433 }
434+ slog.Debug("MCP not allowed", "tool", tool.Name(), "agent", agent.Name)
795435 }
796436 slices.SortFunc(filteredTools, func(a, b fantasy.AgentTool) int {
797437 return strings.Compare(a.Info().Name, b.Info().Name)
798438 })
799−
800− // Wrap tools with hook interception for the top-level agent only.
801− // Sub-agents (the `agent` task tool, `agentic_fetch`, etc.) run
802− // without hook interception to avoid firing the user's hook N times
803− // per delegated turn. The top-level invocation of the sub-agent tool
804− // itself is still wrapped from the coder's side.
805− filteredTools = wrapToolsWithHooks(filteredTools, hookRunner, isSubAgent)
806−
807439 return filteredTools, nil
808440}
809441
810442// TODO: when we support multiple agents we need to change this so that we pass in the agent specific model config
811−func (c *coordinator) buildAgentModels(ctx context.Context, isSubAgent bool) (Model, Model, error) {
812− largeModelCfg, ok := c.cfg.Config().Models[config.SelectedModelTypeLarge]
443+func (c *coordinator) buildAgentModels(ctx context.Context) (Model, Model, error) {
444+ largeModelCfg, ok := c.cfg.Models[config.SelectedModelTypeLarge]
813445 if !ok {
814− return Model{}, Model{}, errLargeModelNotSelected
446+ return Model{}, Model{}, errors.New("large model not selected")
815447 }
816− smallModelCfg, ok := c.cfg.Config().Models[config.SelectedModelTypeSmall]
448+ smallModelCfg, ok := c.cfg.Models[config.SelectedModelTypeSmall]
817449 if !ok {
818− return Model{}, Model{}, errSmallModelNotSelected
450+ return Model{}, Model{}, errors.New("small model not selected")
819451 }
820452
821− largeProviderCfg, ok := c.cfg.Config().Providers.Get(largeModelCfg.Provider)
453+ largeProviderCfg, ok := c.cfg.Providers.Get(largeModelCfg.Provider)
822454 if !ok {
823− return Model{}, Model{}, errLargeModelProviderNotConfigured
455+ return Model{}, Model{}, errors.New("large model provider not configured")
824456 }
825457
826− largeProvider, err := c.buildProvider(largeProviderCfg, largeModelCfg, isSubAgent)
458+ largeProvider, err := c.buildProvider(largeProviderCfg, largeModelCfg)
827459 if err != nil {
828460 return Model{}, Model{}, err
829461 }
830462
831− smallProviderCfg, ok := c.cfg.Config().Providers.Get(smallModelCfg.Provider)
463+ smallProviderCfg, ok := c.cfg.Providers.Get(smallModelCfg.Provider)
832464 if !ok {
833− return Model{}, Model{}, errSmallModelProviderNotConfigured
465+ return Model{}, Model{}, errors.New("large model provider not configured")
834466 }
835467
836− smallProvider, err := c.buildProvider(smallProviderCfg, smallModelCfg, true)
468+ smallProvider, err := c.buildProvider(smallProviderCfg, largeModelCfg)
837469 if err != nil {
838470 return Model{}, Model{}, err
839471 }
@@ -853,11 +485,11 @@ func (c *coordinator) buildAgentModels(ctx context.Context, isSubAgent bool) (Mo
853485 }
854486
855487 if largeCatwalkModel == nil {
856− return Model{}, Model{}, errLargeModelNotFound
488+ return Model{}, Model{}, errors.New("large model not found in provider config")
857489 }
858490
859491 if smallCatwalkModel == nil {
860− return Model{}, Model{}, errSmallModelNotFound
492+ return Model{}, Model{}, errors.New("snall model not found in provider config")
861493 }
862494
863495 largeModelID := largeModelCfg.Model
@@ -884,28 +516,21 @@ func (c *coordinator) buildAgentModels(ctx context.Context, isSubAgent bool) (Mo
884516 Model: largeModel,
885517 CatwalkCfg: *largeCatwalkModel,
886518 ModelCfg: largeModelCfg,
887− FlatRate: largeProviderCfg.FlatRate,
888519 }, Model{
889520 Model: smallModel,
890521 CatwalkCfg: *smallCatwalkModel,
891522 ModelCfg: smallModelCfg,
892− FlatRate: smallProviderCfg.FlatRate,
893523 }, nil
894524}
895525
896−func (c *coordinator) buildAnthropicProvider(baseURL, apiKey string, headers map[string]string, providerID string) (fantasy.Provider, error) {
526+func (c *coordinator) buildAnthropicProvider(baseURL, apiKey string, headers map[string]string, isOauth bool) (fantasy.Provider, error) {
897527 var opts []anthropic.Option
898528
899− switch {
900− case strings.HasPrefix(apiKey, "Bearer "):
529+ if isOauth {
901530 // NOTE: Prevent the SDK from picking up the API key from env.
902531 os.Setenv("ANTHROPIC_API_KEY", "")
903− headers["Authorization"] = apiKey
904− case providerID == string(catwalk.InferenceProviderMiniMax) || providerID == string(catwalk.InferenceProviderMiniMaxChina):
905− // NOTE: Prevent the SDK from picking up the API key from env.
906− os.Setenv("ANTHROPIC_API_KEY", "")
907− headers["Authorization"] = "Bearer " + apiKey
908− case apiKey != "":
532+ headers["Authorization"] = fmt.Sprintf("Bearer %s", apiKey)
533+ } else if apiKey != "" {
909534 // X-Api-Key header
910535 opts = append(opts, anthropic.WithAPIKey(apiKey))
911536 }
@@ -918,7 +543,7 @@ func (c *coordinator) buildAnthropicProvider(baseURL, apiKey string, headers map
918543 opts = append(opts, anthropic.WithBaseURL(baseURL))
919544 }
920545
921− if c.cfg.Config().Options.Debug {
546+ if c.cfg.Options.Debug {
922547 httpClient := log.NewHTTPClient()
923548 opts = append(opts, anthropic.WithHTTPClient(httpClient))
924549 }
@@ -930,7 +555,7 @@ func (c *coordinator) buildOpenaiProvider(baseURL, apiKey string, headers map[st
930555 openai.WithAPIKey(apiKey),
931556 openai.WithUseResponsesAPI(),
932557 }
933− if c.cfg.Config().Options.Debug {
558+ if c.cfg.Options.Debug {
934559 httpClient := log.NewHTTPClient()
935560 opts = append(opts, openai.WithHTTPClient(httpClient))
936561 }
@@ -947,7 +572,7 @@ func (c *coordinator) buildOpenrouterProvider(_, apiKey string, headers map[stri
947572 opts := []openrouter.Option{
948573 openrouter.WithAPIKey(apiKey),
949574 }
950− if c.cfg.Config().Options.Debug {
575+ if c.cfg.Options.Debug {
951576 httpClient := log.NewHTTPClient()
952577 opts = append(opts, openrouter.WithHTTPClient(httpClient))
953578 }
@@ -957,46 +582,15 @@ func (c *coordinator) buildOpenrouterProvider(_, apiKey string, headers map[stri
957582 return openrouter.New(opts...)
958583}
959584
960−func (c *coordinator) buildVercelProvider(_, apiKey string, headers map[string]string) (fantasy.Provider, error) {
961− opts := []vercel.Option{
962− vercel.WithAPIKey(apiKey),
963− }
964− if c.cfg.Config().Options.Debug {
965− httpClient := log.NewHTTPClient()
966− opts = append(opts, vercel.WithHTTPClient(httpClient))
967− }
968− if len(headers) > 0 {
969− opts = append(opts, vercel.WithHeaders(headers))
970− }
971− return vercel.New(opts...)
972−}
973−
974−func (c *coordinator) buildOpenaiCompatProvider(baseURL, apiKey string, headers map[string]string, extraBody map[string]any, providerID string, isSubAgent bool) (fantasy.Provider, error) {
585+func (c *coordinator) buildOpenaiCompatProvider(baseURL, apiKey string, headers map[string]string, extraBody map[string]any) (fantasy.Provider, error) {
975586 opts := []openaicompat.Option{
976587 openaicompat.WithBaseURL(baseURL),
977588 openaicompat.WithAPIKey(apiKey),
978589 }
979−
980− // Set HTTP client based on provider and debug mode.
981− var httpClient *http.Client
982− switch providerID {
983− case string(catwalk.InferenceProviderCopilot):
984− opts = append(
985− opts,
986− openaicompat.WithUseResponsesAPI(),
987− openaicompat.WithResponsesAPIFunc(func(modelID string) bool {
988− return copilotResponsesModels[modelID]
989− }),
990− )
991− httpClient = copilot.NewClient(isSubAgent, c.cfg.Config().Options.Debug)
992− }
993− if httpClient == nil && c.cfg.Config().Options.Debug {
994− httpClient = log.NewHTTPClient()
995− }
996− if httpClient != nil {
590+ if c.cfg.Options.Debug {
591+ httpClient := log.NewHTTPClient()
997592 opts = append(opts, openaicompat.WithHTTPClient(httpClient))
998593 }
999−
1000594 if len(headers) > 0 {
1001595 opts = append(opts, openaicompat.WithHeaders(headers))
1002596 }
@@ -1014,7 +608,7 @@ func (c *coordinator) buildAzureProvider(baseURL, apiKey string, headers map[str
1014608 azure.WithAPIKey(apiKey),
1015609 azure.WithUseResponsesAPI(),
1016610 }
1017− if c.cfg.Config().Options.Debug {
611+ if c.cfg.Options.Debug {
1018612 httpClient := log.NewHTTPClient()
1019613 opts = append(opts, azure.WithHTTPClient(httpClient))
1020614 }
@@ -1031,32 +625,19 @@ func (c *coordinator) buildAzureProvider(baseURL, apiKey string, headers map[str
1031625 return azure.New(opts...)
1032626}
1033627
1034−func (c *coordinator) buildBedrockProvider(apiKey string, headers map[string]string, providerID string) (fantasy.Provider, error) {
628+func (c *coordinator) buildBedrockProvider(headers map[string]string) (fantasy.Provider, error) {
1035629 var opts []bedrock.Option
1036− if c.cfg.Config().Options.Debug {
630+ if c.cfg.Options.Debug {
1037631 httpClient := log.NewHTTPClient()
1038632 opts = append(opts, bedrock.WithHTTPClient(httpClient))
1039633 }
1040634 if len(headers) > 0 {
1041635 opts = append(opts, bedrock.WithHeaders(headers))
1042636 }
1043−
1044− switch {
1045− case apiKey != "":
1046− opts = append(opts, bedrock.WithAPIKey(apiKey))
1047− case os.Getenv("AWS_BEARER_TOKEN_BEDROCK") != "":
1048− opts = append(opts, bedrock.WithAPIKey(os.Getenv("AWS_BEARER_TOKEN_BEDROCK")))
1049− default:
1050− // Skip, let the SDK do authentication.
1051− }
1052−
1053− switch providerID {
1054− case string(catwalk.InferenceProviderBedrockEurope):
1055− opts = append(opts, bedrock.WithRegion("eu-west-1"))
1056− default:
1057− opts = append(opts, bedrock.WithRegion("us-east-1"))
637+ bearerToken := os.Getenv("AWS_BEARER_TOKEN_BEDROCK")
638+ if bearerToken != "" {
639+ opts = append(opts, bedrock.WithAPIKey(bearerToken))
1058640 }
1059−
1060641 return bedrock.New(opts...)
1061642}
1062643
@@ -1065,7 +646,7 @@ func (c *coordinator) buildGoogleProvider(baseURL, apiKey string, headers map[st
1065646 google.WithBaseURL(baseURL),
1066647 google.WithGeminiAPIKey(apiKey),
1067648 }
1068− if c.cfg.Config().Options.Debug {
649+ if c.cfg.Options.Debug {
1069650 httpClient := log.NewHTTPClient()
1070651 opts = append(opts, google.WithHTTPClient(httpClient))
1071652 }
@@ -1077,7 +658,7 @@ func (c *coordinator) buildGoogleProvider(baseURL, apiKey string, headers map[st
1077658
1078659func (c *coordinator) buildGoogleVertexProvider(headers map[string]string, options map[string]string) (fantasy.Provider, error) {
1079660 opts := []google.Option{}
1080− if c.cfg.Config().Options.Debug {
661+ if c.cfg.Options.Debug {
1081662 httpClient := log.NewHTTPClient()
1082663 opts = append(opts, google.WithHTTPClient(httpClient))
1083664 }
@@ -1093,15 +674,38 @@ func (c *coordinator) buildGoogleVertexProvider(headers map[string]string, optio
1093674 return google.New(opts...)
1094675}
1095676
677+func (c *coordinator) buildHyperProvider(baseURL, apiKey string) (fantasy.Provider, error) {
678+ opts := []hyper.Option{
679+ hyper.WithBaseURL(baseURL),
680+ hyper.WithAPIKey(apiKey),
681+ }
682+ if c.cfg.Options.Debug {
683+ httpClient := log.NewHTTPClient()
684+ opts = append(opts, hyper.WithHTTPClient(httpClient))
685+ }
686+ return hyper.New(opts...)
687+}
688+
1096689func (c *coordinator) isAnthropicThinking(model config.SelectedModel) bool {
1097690 if model.Think {
1098691 return true
1099692 }
693+
694+ if model.ProviderOptions == nil {
695+ return false
696+ }
697+
1100698 opts, err := anthropic.ParseOptions(model.ProviderOptions)
1101− return err == nil && opts.Thinking != nil
699+ if err != nil {
700+ return false
701+ }
702+ if opts.Thinking != nil {
703+ return true
704+ }
705+ return false
1102706}
1103707
1104−func (c *coordinator) buildProvider(providerCfg config.ProviderConfig, model config.SelectedModel, isSubAgent bool) (fantasy.Provider, error) {
708+func (c *coordinator) buildProvider(providerCfg config.ProviderConfig, model config.SelectedModel) (fantasy.Provider, error) {
1105709 headers := maps.Clone(providerCfg.ExtraHeaders)
1106710 if headers == nil {
1107711 headers = make(map[string]string)
@@ -1119,117 +723,32 @@ func (c *coordinator) buildProvider(providerCfg config.ProviderConfig, model con
1119723 apiKey, _ := c.cfg.Resolve(providerCfg.APIKey)
1120724 baseURL, _ := c.cfg.Resolve(providerCfg.BaseURL)
1121725
1122− // Reuse a previously built client when nothing that affects it has
1123− // changed, so the HTTP keep-alive pool survives across turns. The key
1124− // is derived from the resolved inputs above (plus the debug flag); the
1125− // per-provider adjustments inside the switch below are deterministic
1126− // functions of these, so identical inputs always yield an identical
1127− // client.
1128− cacheKey := c.providerCacheKey(providerCfg, model, apiKey, baseURL, headers, isSubAgent)
1129− if p, ok := c.providerClients.Get(cacheKey); ok {
1130− return p, nil
1131− }
1132− provider, err := c.buildProviderUncached(providerCfg, model, apiKey, baseURL, headers, isSubAgent)
1133− if err != nil {
1134− return nil, err
1135− }
1136− c.providerClients.Set(cacheKey, provider)
1137− return provider, nil
1138−}
1139−
1140−// providerCacheKey builds a stable key from every input buildProvider's
1141−// switch consumes, so any credential, endpoint, header, or option change
1142−// produces a distinct key (and thus a rebuilt client).
1143−func (c *coordinator) providerCacheKey(providerCfg config.ProviderConfig, model config.SelectedModel, apiKey, baseURL string, headers map[string]string, isSubAgent bool) string {
1144− var b strings.Builder
1145− b.WriteString(providerCfg.ID)
1146− b.WriteByte(0)
1147− b.WriteString(string(providerCfg.Type))
1148− b.WriteByte(0)
1149− // The opencode providers pick their client type from the model, so the
1150− // model must participate in the key.
1151− b.WriteString(model.Model)
1152− b.WriteByte(0)
1153− b.WriteString(apiKey)
1154− b.WriteByte(0)
1155− // Bedrock falls back to AWS_BEARER_TOKEN_BEDROCK when no apiKey is
1156− // configured, and that token is baked into the built client. Fold it
1157− // into the key so a rotated token rebuilds the client instead of
1158− // reusing a stale one.
1159− if apiKey == "" && providerCfg.Type == bedrock.Name {
1160− b.WriteString(os.Getenv("AWS_BEARER_TOKEN_BEDROCK"))
1161− }
1162− b.WriteByte(0)
1163− b.WriteString(baseURL)
1164− b.WriteByte(0)
1165− for _, k := range slices.Sorted(maps.Keys(headers)) {
1166− b.WriteString(k)
1167− b.WriteByte('=')
1168− b.WriteString(headers[k])
1169− b.WriteByte(1)
1170− }
1171− b.WriteByte(0)
1172− if extra, err := json.Marshal(providerCfg.ExtraBody); err == nil {
1173− b.Write(extra)
1174− }
1175− b.WriteByte(0)
1176− if extra, err := json.Marshal(providerCfg.ExtraParams); err == nil {
1177− b.Write(extra)
1178− }
1179− b.WriteByte(0)
1180− if isSubAgent {
1181− b.WriteByte('s')
1182− }
1183− if c.cfg.Config().Options.Debug {
1184− b.WriteByte('d')
1185− }
1186− return b.String()
1187−}
1188−
1189−func (c *coordinator) buildProviderUncached(providerCfg config.ProviderConfig, model config.SelectedModel, apiKey, baseURL string, headers map[string]string, isSubAgent bool) (fantasy.Provider, error) {
1190− switch providerCfg.ID {
1191− case string(catwalk.InferenceProviderOpenCodeGo), string(catwalk.InferenceProviderOpenCodeZen):
1192− if opencodeMessagesModels[model.Model] {
1193− baseURL = strings.TrimSuffix(baseURL, "/v1")
1194− return c.buildAnthropicProvider(baseURL, apiKey, headers, providerCfg.ID)
1195− }
1196− }
1197−
1198726 switch providerCfg.Type {
1199727 case openai.Name:
1200728 return c.buildOpenaiProvider(baseURL, apiKey, headers)
1201729 case anthropic.Name:
1202− return c.buildAnthropicProvider(baseURL, apiKey, headers, providerCfg.ID)
730+ return c.buildAnthropicProvider(baseURL, apiKey, headers, providerCfg.OAuthToken != nil)
1203731 case openrouter.Name:
1204732 return c.buildOpenrouterProvider(baseURL, apiKey, headers)
1205− case vercel.Name:
1206− return c.buildVercelProvider(baseURL, apiKey, headers)
1207733 case azure.Name:
1208734 return c.buildAzureProvider(baseURL, apiKey, headers, providerCfg.ExtraParams)
1209735 case bedrock.Name:
1210− return c.buildBedrockProvider(apiKey, headers, providerCfg.ID)
736+ return c.buildBedrockProvider(headers)
1211737 case google.Name:
1212738 return c.buildGoogleProvider(baseURL, apiKey, headers)
1213739 case "google-vertex":
1214740 return c.buildGoogleVertexProvider(headers, providerCfg.ExtraParams)
1215− case openaicompat.Name, hyper.Name:
1216− switch providerCfg.ID {
1217− case hyper.Name:
1218− baseURL = hyper.BaseURL() + "/v1"
1219− headers["x-crush-id"] = event.GetID()
1220− case string(catwalk.InferenceProviderZAI):
741+ case openaicompat.Name:
742+ if providerCfg.ID == string(catwalk.InferenceProviderZAI) {
1221743 if providerCfg.ExtraBody == nil {
1222744 providerCfg.ExtraBody = map[string]any{}
1223745 }
1224746 providerCfg.ExtraBody["tool_stream"] = true
1225747 }
1226− return c.buildOpenaiCompatProvider(baseURL, apiKey, headers, providerCfg.ExtraBody, providerCfg.ID, isSubAgent)
748+ return c.buildOpenaiCompatProvider(baseURL, apiKey, headers, providerCfg.ExtraBody)
749+ case hyper.Name:
750+ return c.buildHyperProvider(baseURL, apiKey)
1227751 default:
1228− // Known custom providers (litellm, ollama, omlx) are
1229− // openai-compat under the hood.
1230− if discover.IsKnownCustomProvider(string(providerCfg.Type)) {
1231− return c.buildOpenaiCompatProvider(baseURL, apiKey, headers, providerCfg.ExtraBody, providerCfg.ID, isSubAgent)
1232− }
1233752 return nil, fmt.Errorf("provider type not supported: %q", providerCfg.Type)
1234753 }
1235754}
@@ -1245,15 +764,6 @@ func isExactoSupported(modelID string) bool {
1245764 return slices.Contains(supportedModels, modelID)
1246765}
1247766
1248−// BeginAccepted reserves an accept slot for sessionID on the active
1249−// agent and returns the ownership handle. It is the fire-and-forget
1250−// dispatch path's only way to mark a run as accepted-but-not-yet-active
1251−// so a cancel arriving before the run registers in activeRequests is not
1252−// lost.
1253−func (c *coordinator) BeginAccepted(sessionID string) *AcceptedRun {
1254− return c.currentAgent.BeginAccepted(sessionID)
1255−}
1256−
1257767func (c *coordinator) Cancel(sessionID string) {
1258768 c.currentAgent.Cancel(sessionID)
1259769}
@@ -1280,40 +790,21 @@ func (c *coordinator) Model() Model {
1280790
1281791func (c *coordinator) UpdateModels(ctx context.Context) error {
1282792 // build the models again so we make sure we get the latest config
1283− large, small, err := c.buildAgentModels(ctx, false)
793+ large, small, err := c.buildAgentModels(ctx)
1284794 if err != nil {
1285795 return err
1286796 }
1287797 c.currentAgent.SetModels(large, small)
1288798
1289− cfg := c.cfg.Config()
1290− agentCfg, ok := cfg.Agents[config.AgentCoder]
799+ agentCfg, ok := c.cfg.Agents[config.AgentCoder]
1291800 if !ok {
1292− return errCoderAgentNotConfigured
801+ return errors.New("coder agent not configured")
1293802 }
1294803
1295− // Fast path: reuse cached tools when neither the config nor the MCP
1296− // tool set has changed since the last build.
1297− mcpGen := c.mcpToolsGen.Load()
1298− c.toolsCacheMu.Lock()
1299− if c.toolsCache != nil && c.toolsCacheCfg == cfg && c.toolsCacheMCP == mcpGen {
1300− c.currentAgent.SetTools(c.toolsCache)
1301− c.toolsCacheMu.Unlock()
1302− return nil
1303− }
1304− c.toolsCacheMu.Unlock()
1305−
1306− tools, err := c.buildTools(ctx, agentCfg, false)
804+ tools, err := c.buildTools(ctx, agentCfg)
1307805 if err != nil {
1308806 return err
1309807 }
1310−
1311− c.toolsCacheMu.Lock()
1312− c.toolsCache = tools
1313− c.toolsCacheCfg = cfg
1314− c.toolsCacheMCP = mcpGen
1315− c.toolsCacheMu.Unlock()
1316−
1317808 c.currentAgent.SetTools(tools)
1318809 return nil
1319810}
@@ -1327,67 +818,11 @@ func (c *coordinator) QueuedPromptsList(sessionID string) []string {
1327818}
1328819
1329820func (c *coordinator) Summarize(ctx context.Context, sessionID string) error {
1330− providerCfg, ok := c.cfg.Config().Providers.Get(c.currentAgent.Model().ModelCfg.Provider)
821+ providerCfg, ok := c.cfg.Providers.Get(c.currentAgent.Model().ModelCfg.Provider)
1331822 if !ok {
1332− return errModelProviderNotConfigured
1333− }
1334−
1335− if err := c.refreshTokenIfExpired(ctx, providerCfg); err != nil {
1336− slog.Error("Failed to refresh OAuth2 token before summarize. Proceeding with existing token.", "error", err)
1337− }
1338−
1339− summarize := func() error {
1340− return c.currentAgent.Summarize(ctx, sessionID, getProviderOptions(c.currentAgent.Model(), providerCfg))
1341− }
1342−
1343− return c.runWithUnauthorizedRetry(ctx, providerCfg, summarize)
1344−}
1345−
1346−// GenerateTitle generates a session title using the current agent.
1347−func (c *coordinator) GenerateTitle(ctx context.Context, sessionID, prompt string) {
1348− if c.currentAgent == nil {
1349− return
1350− }
1351− c.currentAgent.GenerateTitle(ctx, sessionID, prompt)
1352−}
1353−
1354−// refreshTokenIfExpired proactively refreshes the OAuth token if it has expired.
1355−func (c *coordinator) refreshTokenIfExpired(ctx context.Context, providerCfg config.ProviderConfig) error {
1356− if providerCfg.OAuthToken == nil || !providerCfg.OAuthToken.IsExpired() {
1357− return nil
1358− }
1359− slog.Debug("Token needs to be refreshed", "provider", providerCfg.ID)
1360− return c.refreshOAuth2Token(ctx, providerCfg)
1361−}
1362−
1363−// runWithUnauthorizedRetry executes fn. If fn returns a 401 error, it
1364−// attempts to refresh credentials and re-runs fn once. Returns the
1365−// final error: from the retry if a retry was attempted, otherwise from
1366−// the original run. Callers that need to notify the user on persistent
1367−// failure should check isUnauthorized on the returned error.
1368−func (c *coordinator) runWithUnauthorizedRetry(ctx context.Context, providerCfg config.ProviderConfig, fn func() error) error {
1369− err := fn()
1370− if err != nil && c.isUnauthorized(err) {
1371− if retryErr := c.retryAfterUnauthorized(ctx, providerCfg); retryErr == nil {
1372− return fn()
1373− }
1374− }
1375− return err
1376−}
1377−
1378−// retryAfterUnauthorized attempts to refresh credentials after receiving a 401
1379−// and returns nil if retry should be attempted.
1380−func (c *coordinator) retryAfterUnauthorized(ctx context.Context, providerCfg config.ProviderConfig) error {
1381− switch {
1382− case providerCfg.OAuthToken != nil:
1383− slog.Debug("Received 401. Refreshing token and retrying", "provider", providerCfg.ID)
1384− return c.refreshOAuth2Token(ctx, providerCfg)
1385− case strings.Contains(providerCfg.APIKeyTemplate, "$"):
1386− slog.Debug("Received 401. Refreshing API Key template and retrying", "provider", providerCfg.ID)
1387− return c.refreshApiKeyTemplate(ctx, providerCfg)
1388− default:
1389− return nil
823+ return errors.New("model provider not configured")
1390824 }
825+ return c.currentAgent.Summarize(ctx, sessionID, getProviderOptions(c.currentAgent.Model(), providerCfg))
1391826}
1392827
1393828func (c *coordinator) isUnauthorized(err error) bool {
@@ -1396,7 +831,7 @@ func (c *coordinator) isUnauthorized(err error) bool {
1396831}
1397832
1398833func (c *coordinator) refreshOAuth2Token(ctx context.Context, providerCfg config.ProviderConfig) error {
1399− if err := c.cfg.RefreshOAuthToken(ctx, config.ScopeGlobal, providerCfg.ID); err != nil {
834+ if err := c.cfg.RefreshOAuthToken(ctx, providerCfg.ID); err != nil {
1400835 slog.Error("Failed to refresh OAuth token after 401 error", "provider", providerCfg.ID, "error", err)
1401836 return err
1402837 }
@@ -1414,248 +849,10 @@ func (c *coordinator) refreshApiKeyTemplate(ctx context.Context, providerCfg con
1414849 }
1415850
1416851 providerCfg.APIKey = newAPIKey
1417− c.cfg.Config().Providers.Set(providerCfg.ID, providerCfg)
852+ c.cfg.Providers.Set(providerCfg.ID, providerCfg)
1418853
1419854 if err := c.UpdateModels(ctx); err != nil {
1420855 return err
1421856 }
1422857 return nil
1423858}
1424−
1425−// subAgentParams holds the parameters for running a sub-agent.
1426−type subAgentParams struct {
1427− Agent SessionAgent
1428− SessionID string
1429− AgentMessageID string
1430− ToolCallID string
1431− Prompt string
1432− SessionTitle string
1433− // SessionSetup is an optional callback invoked after session creation
1434− // but before agent execution, for custom session configuration.
1435− SessionSetup func(sessionID string)
1436−}
1437−
1438−// runSubAgent runs a sub-agent and handles session management and cost accumulation.
1439−// It creates a sub-session, runs the agent with the given prompt, and propagates
1440−// the cost to the parent session.
1441−func (c *coordinator) runSubAgent(ctx context.Context, params subAgentParams) (fantasy.ToolResponse, error) {
1442− // Create sub-session
1443− agentToolSessionID := c.sessions.CreateAgentToolSessionID(params.AgentMessageID, params.ToolCallID)
1444− session, err := c.sessions.CreateTaskSession(ctx, agentToolSessionID, params.SessionID, params.SessionTitle)
1445− if err != nil {
1446− return fantasy.ToolResponse{}, fmt.Errorf("create session: %w", err)
1447− }
1448−
1449− // Call session setup function if provided
1450− if params.SessionSetup != nil {
1451− params.SessionSetup(session.ID)
1452− }
1453−
1454− // Get model configuration
1455− model := params.Agent.Model()
1456− maxTokens := model.CatwalkCfg.DefaultMaxTokens
1457− if model.ModelCfg.MaxTokens != 0 {
1458− maxTokens = model.ModelCfg.MaxTokens
1459− }
1460−
1461− providerCfg, ok := c.cfg.Config().Providers.Get(model.ModelCfg.Provider)
1462− if !ok {
1463− return fantasy.ToolResponse{}, errModelProviderNotConfigured
1464− }
1465−
1466− // Run the agent
1467− run := func() (*fantasy.AgentResult, error) {
1468− return params.Agent.Run(ctx, SessionAgentCall{
1469− SessionID: session.ID,
1470− Prompt: params.Prompt,
1471− MaxOutputTokens: maxTokens,
1472− ProviderOptions: getProviderOptions(model, providerCfg),
1473− Temperature: model.ModelCfg.Temperature,
1474− TopP: model.ModelCfg.TopP,
1475− TopK: model.ModelCfg.TopK,
1476− FrequencyPenalty: model.ModelCfg.FrequencyPenalty,
1477− PresencePenalty: model.ModelCfg.PresencePenalty,
1478− NonInteractive: true,
1479− })
1480− }
1481− var result *fantasy.AgentResult
1482− err = c.runWithUnauthorizedRetry(ctx, providerCfg, func() error {
1483− var runErr error
1484− result, runErr = run()
1485− return runErr
1486− })
1487− // Notify only if still unauthorized after retry.
1488− if err != nil && c.isUnauthorized(err) && c.notify != nil && model.ModelCfg.Provider == hyper.Name {
1489− c.notify.Publish(pubsub.CreatedEvent, notify.Notification{
1490− Type: notify.TypeReAuthenticate,
1491− ProviderID: model.ModelCfg.Provider,
1492− })
1493− }
1494− if err != nil {
1495− return fantasy.NewTextErrorResponse(fmt.Sprintf("Failed to generate response: %s", err)), nil
1496− }
1497−
1498− // Update parent session cost on a best-effort basis. A failure here must
1499− // not discard the sub-agent output that was already produced.
1500− if err := c.updateParentSessionCost(ctx, session.ID, params.SessionID); err != nil {
1501− slog.Warn(
1502− "Failed to update parent session cost",
1503− "child_session", session.ID,
1504− "parent_session", params.SessionID,
1505− "error", err,
1506− )
1507− }
1508−
1509− output := subAgentOutput(result)
1510− if output == "" {
1511− return fantasy.NewTextErrorResponse("Sub-agent completed but produced no text output."), nil
1512− }
1513− return fantasy.NewTextResponse(output), nil
1514−}
1515−
1516−func subAgentOutput(result *fantasy.AgentResult) string {
1517− if result == nil {
1518− return ""
1519− }
1520− return result.Response.Content.Text()
1521−}
1522−
1523−// updateParentSessionCost accumulates the cost from a child session to its parent session.
1524−func (c *coordinator) updateParentSessionCost(ctx context.Context, childSessionID, parentSessionID string) error {
1525− childSession, err := c.sessions.Get(ctx, childSessionID)
1526− if err != nil {
1527− return fmt.Errorf("get child session: %w", err)
1528− }
1529−
1530− parentSession, err := c.sessions.Get(ctx, parentSessionID)
1531− if err != nil {
1532− return fmt.Errorf("get parent session: %w", err)
1533− }
1534−
1535− parentSession.Cost += childSession.Cost
1536−
1537− if _, err := c.sessions.Save(ctx, parentSession); err != nil {
1538− return fmt.Errorf("save parent session: %w", err)
1539− }
1540−
1541− return nil
1542−}
1543−
1544−// discoverSkills is a thin fallback wrapper used only when no
1545−// skills.Manager has been threaded through to the coordinator. All
1546−// production call sites (backend.CreateWorkspace, setupLocalWorkspace)
1547−// run discovery in advance and pass the results via the manager;
1548−// reaching this path means a caller bypassed both. It deliberately does
1549−// NOT publish to the package-level broker — there are no subscribers in
1550−// that case, so doing so would be misleading without delivering the
1551−// snapshot anywhere useful.
1552−func discoverSkills(cfg *config.ConfigStore) (allSkills, activeSkills []*skills.Skill) {
1553− opts := cfg.Config().Options
1554− var paths, disabled []string
1555− if opts != nil {
1556− paths = opts.SkillsPaths
1557− disabled = opts.DisabledSkills
1558− }
1559− var resolver func(string) (string, error)
1560− if r := cfg.Resolver(); r != nil {
1561− resolver = r.ResolveValue
1562− }
1563− allSkills, activeSkills, states := skills.DiscoverFromConfig(skills.DiscoveryConfig{
1564− SkillsPaths: paths,
1565− DisabledSkills: disabled,
1566− Resolver: resolver,
1567− })
1568− logDiscoveryStats(states, paths, allSkills, activeSkills, disabled)
1569− return allSkills, activeSkills
1570−}
1571−
1572−// logTurnSkillUsage emits a per-turn diagnostic line showing which skills
1573−// (if any) were loaded during this turn and which looked relevant based on
1574−// a cheap keyword match against the user prompt. The goal is to surface
1575−// "should-have-loaded but didn't" situations for later analysis.
1576−//
1577−// Logged at Info level under component=skills; heavy fields are elided when
1578−// there is nothing interesting to report.
1579−func logTurnSkillUsage(
1580− sessionID string,
1581− prompt string,
1582− activeSkills []*skills.Skill,
1583− tracker *skills.Tracker,
1584− before []string,
1585−) {
1586− if tracker == nil || len(activeSkills) == 0 {
1587− return
1588− }
1589−
1590− after := tracker.LoadedNames()
1591−
1592− beforeSet := make(map[string]bool, len(before))
1593− for _, n := range before {
1594− beforeSet[n] = true
1595− }
1596− var loadedThisTurn []string
1597− for _, n := range after {
1598− if !beforeSet[n] {
1599− loadedThisTurn = append(loadedThisTurn, n)
1600− }
1601− }
1602−
1603− slog.Info(
1604− "Skill turn summary",
1605− "component", "skills",
1606− "session_id", sessionID,
1607− "prompt_len", len(prompt),
1608− "active_total", len(activeSkills),
1609− "loaded_total", len(after),
1610− "loaded_this_turn", loadedThisTurn,
1611− )
1612−}
1613−
1614−// logDiscoveryStats emits a single structured log line summarising skill
1615−// discovery for the current session. It is intentionally low-volume: one
1616−// line per session start. Builtin vs user counts are derived from the
1617−// SkillState.Path — builtin states use the "builtin/" embed prefix.
1618−func logDiscoveryStats(
1619− states []*skills.SkillState,
1620− userPaths []string,
1621− allSkills, activeSkills []*skills.Skill,
1622− disabled []string,
1623−) {
1624− var builtinOK, builtinErr, userOK, userErr int
1625− for _, s := range states {
1626− isBuiltin := strings.HasPrefix(s.Path, "builtin/")
1627− switch {
1628− case isBuiltin && s.State == skills.StateNormal:
1629− builtinOK++
1630− case isBuiltin && s.State == skills.StateError:
1631− builtinErr++
1632− case !isBuiltin && s.State == skills.StateNormal:
1633− userOK++
1634− case !isBuiltin && s.State == skills.StateError:
1635− userErr++
1636− }
1637− }
1638−
1639− activeNames := make([]string, 0, len(activeSkills))
1640− for _, s := range activeSkills {
1641− activeNames = append(activeNames, s.Name)
1642− }
1643−
1644− xml := skills.ToPromptXML(activeSkills)
1645−
1646− slog.Info(
1647− "Skill discovery complete",
1648− "component", "skills",
1649− "builtin_ok", builtinOK,
1650− "builtin_errors", builtinErr,
1651− "user_ok", userOK,
1652− "user_errors", userErr,
1653− "user_paths", len(userPaths),
1654− "deduped_total", len(allSkills),
1655− "active", len(activeSkills),
1656− "disabled", len(disabled),
1657− "prompt_bytes", len(xml),
1658− "prompt_tok_est", skills.ApproxTokenCount(xml),
1659− "active_names", activeNames,
1660− )
1661−}
internal/agent/coordinator_test.godeleted−554
@@ -1,554 +0,0 @@
1−package agent
2−
3−import (
4− "context"
5− "errors"
6− "testing"
7−
8− "charm.land/catwalk/pkg/catwalk"
9− "charm.land/fantasy"
10− "charm.land/fantasy/providers/anthropic"
11− "charm.land/fantasy/providers/bedrock"
12− "charm.land/fantasy/providers/openaicompat"
13− "github.com/charmbracelet/crush/internal/config"
14− "github.com/stretchr/testify/assert"
15− "github.com/stretchr/testify/require"
16−)
17−
18−// mockSessionAgent is a minimal mock for the SessionAgent interface.
19−type mockSessionAgent struct {
20− model Model
21− runFunc func(ctx context.Context, call SessionAgentCall) (*fantasy.AgentResult, error)
22− cancelled []string
23−}
24−
25−func (m *mockSessionAgent) Run(ctx context.Context, call SessionAgentCall) (*fantasy.AgentResult, error) {
26− return m.runFunc(ctx, call)
27−}
28−
29−func (m *mockSessionAgent) BeginAccepted(sessionID string) *AcceptedRun {
30− return &AcceptedRun{sessionID: sessionID}
31−}
32−
33−func (m *mockSessionAgent) Model() Model { return m.model }
34−func (m *mockSessionAgent) SetModels(large, small Model) {}
35−func (m *mockSessionAgent) SetTools(tools []fantasy.AgentTool) {}
36−func (m *mockSessionAgent) SetSystemPrompt(systemPrompt string) {}
37−func (m *mockSessionAgent) Cancel(sessionID string) {
38− m.cancelled = append(m.cancelled, sessionID)
39−}
40−func (m *mockSessionAgent) CancelAll() {}
41−func (m *mockSessionAgent) IsSessionBusy(sessionID string) bool { return false }
42−func (m *mockSessionAgent) IsBusy() bool { return false }
43−func (m *mockSessionAgent) QueuedPrompts(sessionID string) int { return 0 }
44−func (m *mockSessionAgent) QueuedPromptsList(sessionID string) []string { return nil }
45−func (m *mockSessionAgent) ClearQueue(sessionID string) {}
46−func (m *mockSessionAgent) Summarize(context.Context, string, fantasy.ProviderOptions) error {
47− return nil
48−}
49−func (m *mockSessionAgent) GenerateTitle(context.Context, string, string) {}
50−
51−// newTestCoordinator creates a minimal coordinator for unit testing runSubAgent.
52−func newTestCoordinator(t *testing.T, env fakeEnv, providerID string, providerCfg config.ProviderConfig) *coordinator {
53− cfg, err := config.Init(env.workingDir, "", false)
54− require.NoError(t, err)
55− cfg.Config().Providers.Set(providerID, providerCfg)
56− return &coordinator{
57− cfg: cfg,
58− sessions: env.sessions,
59− messages: env.messages,
60− }
61−}
62−
63−// newMockAgent creates a mockSessionAgent with the given provider and run function.
64−func newMockAgent(providerID string, maxTokens int64, runFunc func(context.Context, SessionAgentCall) (*fantasy.AgentResult, error)) *mockSessionAgent {
65− return &mockSessionAgent{
66− model: Model{
67− CatwalkCfg: catwalk.Model{
68− DefaultMaxTokens: maxTokens,
69− },
70− ModelCfg: config.SelectedModel{
71− Provider: providerID,
72− },
73− },
74− runFunc: runFunc,
75− }
76−}
77−
78−// agentResultWithText creates a minimal AgentResult with the given text response.
79−func agentResultWithText(text string) *fantasy.AgentResult {
80− return &fantasy.AgentResult{
81− Response: fantasy.Response{
82− Content: fantasy.ResponseContent{
83− fantasy.TextContent{Text: text},
84− },
85− },
86− }
87−}
88−
89−func TestRunSubAgent(t *testing.T) {
90− const providerID = "test-provider"
91− providerCfg := config.ProviderConfig{ID: providerID}
92−
93− t.Run("happy path", func(t *testing.T) {
94− env := testEnv(t)
95− coord := newTestCoordinator(t, env, providerID, providerCfg)
96−
97− parentSession, err := env.sessions.Create(t.Context(), "Parent")
98− require.NoError(t, err)
99−
100− agent := newMockAgent(providerID, 4096, func(_ context.Context, call SessionAgentCall) (*fantasy.AgentResult, error) {
101− assert.Equal(t, "do something", call.Prompt)
102− assert.Equal(t, int64(4096), call.MaxOutputTokens)
103− return agentResultWithText("done"), nil
104− })
105−
106− resp, err := coord.runSubAgent(t.Context(), subAgentParams{
107− Agent: agent,
108− SessionID: parentSession.ID,
109− AgentMessageID: "msg-1",
110− ToolCallID: "call-1",
111− Prompt: "do something",
112− SessionTitle: "Test Session",
113− })
114− require.NoError(t, err)
115− assert.Equal(t, "done", resp.Content)
116− assert.False(t, resp.IsError)
117− })
118−
119− t.Run("cost update failure preserves output", func(t *testing.T) {
120− env := testEnv(t)
121− coord := newTestCoordinator(t, env, providerID, providerCfg)
122−
123− agent := newMockAgent(providerID, 4096, func(_ context.Context, _ SessionAgentCall) (*fantasy.AgentResult, error) {
124− return agentResultWithText("output before cost failure"), nil
125− })
126−
127− resp, err := coord.runSubAgent(t.Context(), subAgentParams{
128− Agent: agent,
129− SessionID: "missing-parent-session",
130− AgentMessageID: "msg-1",
131− ToolCallID: "call-1",
132− Prompt: "test",
133− SessionTitle: "Test",
134− })
135− require.NoError(t, err)
136− assert.False(t, resp.IsError)
137− assert.Equal(t, "output before cost failure", resp.Content)
138− })
139−
140− t.Run("response with text returns it", func(t *testing.T) {
141− env := testEnv(t)
142− coord := newTestCoordinator(t, env, providerID, providerCfg)
143−
144− parentSession, err := env.sessions.Create(t.Context(), "Parent")
145− require.NoError(t, err)
146−
147− agent := newMockAgent(providerID, 4096, func(_ context.Context, _ SessionAgentCall) (*fantasy.AgentResult, error) {
148− return agentResultWithText("the answer"), nil
149− })
150−
151− resp, err := coord.runSubAgent(t.Context(), subAgentParams{
152− Agent: agent,
153− SessionID: parentSession.ID,
154− AgentMessageID: "msg-1",
155− ToolCallID: "call-1",
156− Prompt: "test",
157− SessionTitle: "Test",
158− })
159− require.NoError(t, err)
160− assert.False(t, resp.IsError)
161− assert.Equal(t, "the answer", resp.Content)
162− })
163−
164− t.Run("nil result returns error response", func(t *testing.T) {
165− env := testEnv(t)
166− coord := newTestCoordinator(t, env, providerID, providerCfg)
167−
168− parentSession, err := env.sessions.Create(t.Context(), "Parent")
169− require.NoError(t, err)
170−
171− agent := newMockAgent(providerID, 4096, func(_ context.Context, _ SessionAgentCall) (*fantasy.AgentResult, error) {
172− return nil, nil
173− })
174−
175− resp, err := coord.runSubAgent(t.Context(), subAgentParams{
176− Agent: agent,
177− SessionID: parentSession.ID,
178− AgentMessageID: "msg-1",
179− ToolCallID: "call-1",
180− Prompt: "test",
181− SessionTitle: "Test",
182− })
183− require.NoError(t, err)
184− assert.True(t, resp.IsError)
185− assert.Equal(t, "Sub-agent completed but produced no text output.", resp.Content)
186− })
187−
188− t.Run("empty result returns error response", func(t *testing.T) {
189− env := testEnv(t)
190− coord := newTestCoordinator(t, env, providerID, providerCfg)
191−
192− parentSession, err := env.sessions.Create(t.Context(), "Parent")
193− require.NoError(t, err)
194−
195− agent := newMockAgent(providerID, 4096, func(_ context.Context, _ SessionAgentCall) (*fantasy.AgentResult, error) {
196− return &fantasy.AgentResult{}, nil
197− })
198−
199− resp, err := coord.runSubAgent(t.Context(), subAgentParams{
200− Agent: agent,
201− SessionID: parentSession.ID,
202− AgentMessageID: "msg-1",
203− ToolCallID: "call-1",
204− Prompt: "test",
205− SessionTitle: "Test",
206− })
207− require.NoError(t, err)
208− assert.True(t, resp.IsError)
209− assert.Equal(t, "Sub-agent completed but produced no text output.", resp.Content)
210− })
211−
212− t.Run("ModelCfg.MaxTokens overrides default", func(t *testing.T) {
213− env := testEnv(t)
214− coord := newTestCoordinator(t, env, providerID, providerCfg)
215−
216− parentSession, err := env.sessions.Create(t.Context(), "Parent")
217− require.NoError(t, err)
218−
219− agent := &mockSessionAgent{
220− model: Model{
221− CatwalkCfg: catwalk.Model{
222− DefaultMaxTokens: 4096,
223− },
224− ModelCfg: config.SelectedModel{
225− Provider: providerID,
226− MaxTokens: 8192,
227− },
228− },
229− runFunc: func(_ context.Context, call SessionAgentCall) (*fantasy.AgentResult, error) {
230− assert.Equal(t, int64(8192), call.MaxOutputTokens)
231− return agentResultWithText("ok"), nil
232− },
233− }
234−
235− resp, err := coord.runSubAgent(t.Context(), subAgentParams{
236− Agent: agent,
237− SessionID: parentSession.ID,
238− AgentMessageID: "msg-1",
239− ToolCallID: "call-1",
240− Prompt: "test",
241− SessionTitle: "Test",
242− })
243− require.NoError(t, err)
244− assert.Equal(t, "ok", resp.Content)
245− })
246−
247− t.Run("session creation failure with canceled context", func(t *testing.T) {
248− env := testEnv(t)
249− coord := newTestCoordinator(t, env, providerID, providerCfg)
250−
251− parentSession, err := env.sessions.Create(t.Context(), "Parent")
252− require.NoError(t, err)
253−
254− agent := newMockAgent(providerID, 4096, nil)
255−
256− // Use a canceled context to trigger CreateTaskSession failure.
257− ctx, cancel := context.WithCancel(t.Context())
258− cancel()
259−
260− _, err = coord.runSubAgent(ctx, subAgentParams{
261− Agent: agent,
262− SessionID: parentSession.ID,
263− AgentMessageID: "msg-1",
264− ToolCallID: "call-1",
265− Prompt: "test",
266− SessionTitle: "Test",
267− })
268− require.Error(t, err)
269− })
270−
271− t.Run("provider not configured", func(t *testing.T) {
272− env := testEnv(t)
273− coord := newTestCoordinator(t, env, providerID, providerCfg)
274−
275− parentSession, err := env.sessions.Create(t.Context(), "Parent")
276− require.NoError(t, err)
277−
278− // Agent references a provider that doesn't exist in config.
279− agent := newMockAgent("unknown-provider", 4096, nil)
280−
281− _, err = coord.runSubAgent(t.Context(), subAgentParams{
282− Agent: agent,
283− SessionID: parentSession.ID,
284− AgentMessageID: "msg-1",
285− ToolCallID: "call-1",
286− Prompt: "test",
287− SessionTitle: "Test",
288− })
289− require.Error(t, err)
290− assert.Contains(t, err.Error(), "model provider not configured")
291− })
292−
293− t.Run("agent run error returns error response", func(t *testing.T) {
294− env := testEnv(t)
295− coord := newTestCoordinator(t, env, providerID, providerCfg)
296−
297− parentSession, err := env.sessions.Create(t.Context(), "Parent")
298− require.NoError(t, err)
299−
300− agent := newMockAgent(providerID, 4096, func(_ context.Context, _ SessionAgentCall) (*fantasy.AgentResult, error) {
301− return nil, errors.New("provider request failed")
302− })
303−
304− resp, err := coord.runSubAgent(t.Context(), subAgentParams{
305− Agent: agent,
306− SessionID: parentSession.ID,
307− AgentMessageID: "msg-1",
308− ToolCallID: "call-1",
309− Prompt: "test",
310− SessionTitle: "Test",
311− })
312− // runSubAgent returns (errorResponse, nil) when agent.Run fails — not a Go error.
313− require.NoError(t, err)
314− assert.True(t, resp.IsError)
315− assert.Equal(t, "Failed to generate response: provider request failed", resp.Content)
316− })
317−
318− t.Run("session setup callback is invoked", func(t *testing.T) {
319− env := testEnv(t)
320− coord := newTestCoordinator(t, env, providerID, providerCfg)
321−
322− parentSession, err := env.sessions.Create(t.Context(), "Parent")
323− require.NoError(t, err)
324−
325− var setupCalledWith string
326− agent := newMockAgent(providerID, 4096, func(_ context.Context, _ SessionAgentCall) (*fantasy.AgentResult, error) {
327− return agentResultWithText("ok"), nil
328− })
329−
330− _, err = coord.runSubAgent(t.Context(), subAgentParams{
331− Agent: agent,
332− SessionID: parentSession.ID,
333− AgentMessageID: "msg-1",
334− ToolCallID: "call-1",
335− Prompt: "test",
336− SessionTitle: "Test",
337− SessionSetup: func(sessionID string) {
338− setupCalledWith = sessionID
339− },
340− })
341− require.NoError(t, err)
342− assert.NotEmpty(t, setupCalledWith, "SessionSetup should have been called")
343− })
344−
345− t.Run("cost propagation to parent session", func(t *testing.T) {
346− env := testEnv(t)
347− coord := newTestCoordinator(t, env, providerID, providerCfg)
348−
349− parentSession, err := env.sessions.Create(t.Context(), "Parent")
350− require.NoError(t, err)
351−
352− agent := newMockAgent(providerID, 4096, func(ctx context.Context, call SessionAgentCall) (*fantasy.AgentResult, error) {
353− // Simulate the agent incurring cost by updating the child session.
354− childSession, err := env.sessions.Get(ctx, call.SessionID)
355− if err != nil {
356− return nil, err
357− }
358− childSession.Cost = 0.05
359− _, err = env.sessions.Save(ctx, childSession)
360− if err != nil {
361− return nil, err
362− }
363− return agentResultWithText("ok"), nil
364− })
365−
366− _, err = coord.runSubAgent(t.Context(), subAgentParams{
367− Agent: agent,
368− SessionID: parentSession.ID,
369− AgentMessageID: "msg-1",
370− ToolCallID: "call-1",
371− Prompt: "test",
372− SessionTitle: "Test",
373− })
374− require.NoError(t, err)
375−
376− updated, err := env.sessions.Get(t.Context(), parentSession.ID)
377− require.NoError(t, err)
378− assert.InDelta(t, 0.05, updated.Cost, 1e-9)
379− })
380−}
381−
382−func TestUpdateParentSessionCost(t *testing.T) {
383− t.Run("accumulates cost correctly", func(t *testing.T) {
384− env := testEnv(t)
385− cfg, err := config.Init(env.workingDir, "", false)
386− require.NoError(t, err)
387− coord := &coordinator{cfg: cfg, sessions: env.sessions}
388−
389− parent, err := env.sessions.Create(t.Context(), "Parent")
390− require.NoError(t, err)
391−
392− child, err := env.sessions.CreateTaskSession(t.Context(), "tool-1", parent.ID, "Child")
393− require.NoError(t, err)
394−
395− // Set child cost.
396− child.Cost = 0.10
397− _, err = env.sessions.Save(t.Context(), child)
398− require.NoError(t, err)
399−
400− err = coord.updateParentSessionCost(t.Context(), child.ID, parent.ID)
401− require.NoError(t, err)
402−
403− updated, err := env.sessions.Get(t.Context(), parent.ID)
404− require.NoError(t, err)
405− assert.InDelta(t, 0.10, updated.Cost, 1e-9)
406− })
407−
408− t.Run("accumulates multiple child costs", func(t *testing.T) {
409− env := testEnv(t)
410− cfg, err := config.Init(env.workingDir, "", false)
411− require.NoError(t, err)
412− coord := &coordinator{cfg: cfg, sessions: env.sessions}
413−
414− parent, err := env.sessions.Create(t.Context(), "Parent")
415− require.NoError(t, err)
416−
417− child1, err := env.sessions.CreateTaskSession(t.Context(), "tool-1", parent.ID, "Child1")
418− require.NoError(t, err)
419− child1.Cost = 0.05
420− _, err = env.sessions.Save(t.Context(), child1)
421− require.NoError(t, err)
422−
423− child2, err := env.sessions.CreateTaskSession(t.Context(), "tool-2", parent.ID, "Child2")
424− require.NoError(t, err)
425− child2.Cost = 0.03
426− _, err = env.sessions.Save(t.Context(), child2)
427− require.NoError(t, err)
428−
429− err = coord.updateParentSessionCost(t.Context(), child1.ID, parent.ID)
430− require.NoError(t, err)
431− err = coord.updateParentSessionCost(t.Context(), child2.ID, parent.ID)
432− require.NoError(t, err)
433−
434− updated, err := env.sessions.Get(t.Context(), parent.ID)
435− require.NoError(t, err)
436− assert.InDelta(t, 0.08, updated.Cost, 1e-9)
437− })
438−
439− t.Run("child session not found", func(t *testing.T) {
440− env := testEnv(t)
441− cfg, err := config.Init(env.workingDir, "", false)
442− require.NoError(t, err)
443− coord := &coordinator{cfg: cfg, sessions: env.sessions}
444−
445− parent, err := env.sessions.Create(t.Context(), "Parent")
446− require.NoError(t, err)
447−
448− err = coord.updateParentSessionCost(t.Context(), "non-existent", parent.ID)
449− require.Error(t, err)
450− assert.Contains(t, err.Error(), "get child session")
451− })
452−
453− t.Run("parent session not found", func(t *testing.T) {
454− env := testEnv(t)
455− cfg, err := config.Init(env.workingDir, "", false)
456− require.NoError(t, err)
457− coord := &coordinator{cfg: cfg, sessions: env.sessions}
458−
459− parent, err := env.sessions.Create(t.Context(), "Parent")
460− require.NoError(t, err)
461− child, err := env.sessions.CreateTaskSession(t.Context(), "tool-1", parent.ID, "Child")
462− require.NoError(t, err)
463−
464− err = coord.updateParentSessionCost(t.Context(), child.ID, "non-existent")
465− require.Error(t, err)
466− assert.Contains(t, err.Error(), "get parent session")
467− })
468−
469− t.Run("zero cost handled correctly", func(t *testing.T) {
470− env := testEnv(t)
471− cfg, err := config.Init(env.workingDir, "", false)
472− require.NoError(t, err)
473− coord := &coordinator{cfg: cfg, sessions: env.sessions}
474−
475− parent, err := env.sessions.Create(t.Context(), "Parent")
476− require.NoError(t, err)
477− child, err := env.sessions.CreateTaskSession(t.Context(), "tool-1", parent.ID, "Child")
478− require.NoError(t, err)
479−
480− err = coord.updateParentSessionCost(t.Context(), child.ID, parent.ID)
481− require.NoError(t, err)
482−
483− updated, err := env.sessions.Get(t.Context(), parent.ID)
484− require.NoError(t, err)
485− assert.InDelta(t, 0.0, updated.Cost, 1e-9)
486− })
487−}
488−
489−func TestGetProviderOptionsReasoningEffort(t *testing.T) {
490− // Bedrock is Fantasy's Anthropic under a different provider name; options
491− // must land under anthropic.Name so the Anthropic language model picks them up.
492− tests := []struct {
493− name string
494− providerType catwalk.Type
495− }{
496− {"anthropic honors reasoning_effort", catwalk.Type(anthropic.Name)},
497− {"bedrock honors reasoning_effort", catwalk.Type(bedrock.Name)},
498− }
499− for _, tc := range tests {
500− t.Run(tc.name, func(t *testing.T) {
501− model := Model{
502− CatwalkCfg: catwalk.Model{
503− ID: "claude-opus-4-7",
504− CanReason: true,
505− ReasoningLevels: []string{"max"},
506− },
507− ModelCfg: config.SelectedModel{
508− Provider: "test",
509− ReasoningEffort: "max",
510− },
511− }
512− providerCfg := config.ProviderConfig{ID: "test", Type: tc.providerType}
513−
514− opts := getProviderOptions(model, providerCfg)
515−
516− raw, ok := opts[anthropic.Name]
517− require.True(t, ok, "options should be keyed under anthropic.Name for type %q", tc.providerType)
518− parsed, ok := raw.(*anthropic.ProviderOptions)
519− require.True(t, ok)
520− require.NotNil(t, parsed.Effort)
521− assert.Equal(t, anthropic.Effort("max"), *parsed.Effort)
522− })
523− }
524−}
525−
526−func TestGetProviderOptionsReasoningEffortFallback(t *testing.T) {
527− model := Model{
528− CatwalkCfg: catwalk.Model{
529− ID: "glm-5.2",
530− CanReason: true,
531− ReasoningLevels: []string{"high", "max"},
532− },
533− ModelCfg: config.SelectedModel{
534− Provider: "zai",
535− },
536− }
537− providerCfg := config.ProviderConfig{
538− ID: string(catwalk.InferenceProviderZAI),
539− Type: openaicompat.Name,
540− }
541−
542− opts := getProviderOptions(model, providerCfg)
543−
544− raw, ok := opts[openaicompat.Name]
545− require.True(t, ok)
546− parsed, ok := raw.(*openaicompat.ProviderOptions)
547− require.True(t, ok)
548− require.NotNil(t, parsed.ReasoningEffort)
549− assert.Equal(t, "high", string(*parsed.ReasoningEffort))
550−
551− thinking, ok := parsed.ExtraBody["thinking"].(map[string]any)
552− require.True(t, ok)
553− assert.Equal(t, "enabled", thinking["type"])
554−}
internal/agent/dispatch_cancel_test.godeleted−447
@@ -1,447 +0,0 @@
1−package agent
2−
3−import (
4− "context"
5− "errors"
6− "sync/atomic"
7− "testing"
8− "time"
9−
10− "charm.land/fantasy"
11− "github.com/charmbracelet/crush/internal/agent/notify"
12− "github.com/charmbracelet/crush/internal/message"
13− "github.com/charmbracelet/crush/internal/pubsub"
14− "github.com/stretchr/testify/assert"
15− "github.com/stretchr/testify/require"
16−)
17−
18−// finishStreamModel is a minimal fantasy.LanguageModel that streams a
19−// single text part followed by a normal (FinishReasonStop) finish. It
20−// is enough to drive sessionAgent.Run through PrepareStep and a clean
21−// completion without a recorded provider cassette.
22−type finishStreamModel struct {
23− text string
24−}
25−
26−func (m *finishStreamModel) Provider() string { return "fake" }
27−func (m *finishStreamModel) Model() string { return "fake-model" }
28−
29−func (m *finishStreamModel) Generate(ctx context.Context, call fantasy.Call) (*fantasy.Response, error) {
30− return &fantasy.Response{
31− Content: fantasy.ResponseContent{fantasy.TextContent{Text: m.text}},
32− FinishReason: fantasy.FinishReasonStop,
33− }, nil
34−}
35−
36−func (m *finishStreamModel) Stream(ctx context.Context, call fantasy.Call) (fantasy.StreamResponse, error) {
37− text := m.text
38− return func(yield func(fantasy.StreamPart) bool) {
39− if !yield(fantasy.StreamPart{Type: fantasy.StreamPartTypeTextStart, ID: "1"}) {
40− return
41− }
42− if !yield(fantasy.StreamPart{Type: fantasy.StreamPartTypeTextDelta, ID: "1", Delta: text}) {
43− return
44− }
45− if !yield(fantasy.StreamPart{Type: fantasy.StreamPartTypeTextEnd, ID: "1"}) {
46− return
47− }
48− yield(fantasy.StreamPart{Type: fantasy.StreamPartTypeFinish, FinishReason: fantasy.FinishReasonStop})
49− }, nil
50−}
51−
52−func (m *finishStreamModel) GenerateObject(ctx context.Context, call fantasy.ObjectCall) (*fantasy.ObjectResponse, error) {
53− return nil, errors.New("not implemented")
54−}
55−
56−func (m *finishStreamModel) StreamObject(ctx context.Context, call fantasy.ObjectCall) (fantasy.ObjectStreamResponse, error) {
57− return nil, errors.New("not implemented")
58−}
59−
60−func newStreamTestAgent(t *testing.T) (*sessionAgent, fakeEnv) {
61− t.Helper()
62− env := testEnv(t)
63− model := &finishStreamModel{text: "done"}
64− sa := testSessionAgent(env, model, model, "system").(*sessionAgent)
65− return sa, env
66−}
67−
68−// TestCancel_ActiveAndAcceptedFiresBothBranches covers the case where a
69−// session is actively running (activeRequests set) AND a follow-up has
70−// been accepted (acceptedRuns > 0). A single Cancel must fire both: it
71−// invokes the active cancel func and records a pending cancel for the
72−// accepted follow-up.
73−func TestCancel_ActiveAndAcceptedFiresBothBranches(t *testing.T) {
74− t.Parallel()
75− sa, _ := newCancelTestAgent(t)
76−
77− const sid = "sid"
78− var activeCanceled atomic.Bool
79− sa.activeRequests.Set(sid, func() { activeCanceled.Store(true) })
80−
81− accept := sa.BeginAccepted(sid)
82− defer accept.Close()
83−
84− sa.Cancel(sid)
85−
86− require.True(t, activeCanceled.Load(), "active cancel func must fire")
87− require.True(t, sa.hasPendingCancel(sid), "accepted follow-up must record a pending cancel")
88−}
89−
90−// TestRun_BusyWithPendingCancelTakesCancelOnEntry covers the busy-queue
91−// branch consulting pendingCancels: when the session is busy AND a
92−// cancel has been recorded for an accepted follow-up, Run must take the
93−// cancel-on-entry path (persist a canceled turn) instead of enqueueing
94−// the call behind the active run.
95−func TestRun_BusyWithPendingCancelTakesCancelOnEntry(t *testing.T) {
96− t.Parallel()
97− sa, env := newCancelTestAgent(t)
98−
99− sess, err := env.sessions.Create(t.Context(), "session")
100− require.NoError(t, err)
101−
102− // Make the session look busy: an earlier prompt is active.
103− sa.activeRequests.Set(sess.ID, func() {})
104−
105− accept := sa.BeginAccepted(sess.ID)
106− // A cancel arrives while this follow-up is accepted-but-not-active.
107− sa.Cancel(sess.ID)
108− require.True(t, sa.hasPendingCancel(sess.ID))
109−
110− result, err := sa.Run(t.Context(), SessionAgentCall{
111− SessionID: sess.ID,
112− Prompt: "follow-up",
113− Accepted: accept,
114− })
115− require.NoError(t, err)
116− require.Nil(t, result)
117−
118− // The follow-up was canceled on entry, not enqueued.
119− require.Equal(t, 0, sa.QueuedPrompts(sess.ID),
120− "cancel-on-entry must not enqueue the follow-up behind the active run")
121− require.False(t, sa.hasPendingCancel(sess.ID), "pending cancel must be consumed")
122− require.Equal(t, 0, sa.acceptedCount(sess.ID), "accept reservation must be released")
123−
124− msgs, err := env.messages.List(t.Context(), sess.ID)
125− require.NoError(t, err)
126− require.Len(t, msgs, 2)
127− assert.Equal(t, message.User, msgs[0].Role)
128− assert.Equal(t, message.Assistant, msgs[1].Role)
129− assert.Equal(t, message.FinishReasonCanceled, msgs[1].FinishReason())
130−}
131−
132−// TestRun_PrepareStepDrainSkipsQueuedOnPendingCancel verifies that the
133−// queue drain inside PrepareStep skips queued follow-up prompts when a
134−// cancel has been recorded for the session: the queued prompt must not
135−// be folded into the active turn as an extra user message.
136−func TestRun_PrepareStepDrainSkipsQueuedOnPendingCancel(t *testing.T) {
137− t.Parallel()
138− sa, env := newStreamTestAgent(t)
139−
140− sess, err := env.sessions.Create(t.Context(), "session")
141− require.NoError(t, err)
142−
143− // A follow-up prompt sits queued for the session.
144− sa.enqueueCall(SessionAgentCall{SessionID: sess.ID, Prompt: "queued-followup"})
145− // A cancel was recorded for the session while it sat in the queue.
146− sa.cancelMark.Set(sess.ID, 1)
147−
148− result, err := sa.Run(t.Context(), SessionAgentCall{
149− SessionID: sess.ID,
150− Prompt: "main",
151− })
152− require.NoError(t, err)
153− require.NotNil(t, result)
154−
155− // Only the main prompt produced a user message; the queued
156− // follow-up was skipped, not folded into the turn.
157− msgs, err := env.messages.List(t.Context(), sess.ID)
158− require.NoError(t, err)
159− var userMsgs []message.Message
160− for _, m := range msgs {
161− if m.Role == message.User {
162− userMsgs = append(userMsgs, m)
163− }
164− }
165− require.Len(t, userMsgs, 1, "queued follow-up must not create a user message")
166− assert.Equal(t, "main", userMsgs[0].Content().String())
167−
168− // The queue was drained and the pending cancel consumed.
169− require.Equal(t, 0, sa.QueuedPrompts(sess.ID))
170− require.False(t, sa.hasPendingCancel(sess.ID))
171−}
172−
173−// TestRun_NormalCompletionClearsStalePendingCancel verifies that a Run
174−// which completes normally clears any stale pending-cancel entry for the
175−// session, so it cannot catch a future run.
176−func TestRun_NormalCompletionClearsStalePendingCancel(t *testing.T) {
177− t.Parallel()
178− sa, env := newStreamTestAgent(t)
179−
180− sess, err := env.sessions.Create(t.Context(), "session")
181− require.NoError(t, err)
182−
183− // A stale cancel mark lingers (no queued work, no accepted run).
184− sa.cancelMark.Set(sess.ID, 1)
185−
186− result, err := sa.Run(t.Context(), SessionAgentCall{
187− SessionID: sess.ID,
188− Prompt: "main",
189− })
190− require.NoError(t, err)
191− require.NotNil(t, result)
192−
193− require.False(t, sa.hasPendingCancel(sess.ID),
194− "normal completion must clear the stale pending cancel")
195−
196− msgs, err := env.messages.List(t.Context(), sess.ID)
197− require.NoError(t, err)
198− require.Len(t, msgs, 2)
199− assert.Equal(t, message.Assistant, msgs[1].Role)
200− assert.Equal(t, message.FinishReasonEndTurn, msgs[1].FinishReason())
201−}
202−
203−// newCancelTestAgentWithRunComplete builds a DB-backed sessionAgent wired
204−// to a RunComplete broker so tests can observe the terminal event a
205−// RunID-bearing caller (e.g. `crush run`) blocks on.
206−func newCancelTestAgentWithRunComplete(t *testing.T) (*sessionAgent, fakeEnv, *pubsub.Broker[notify.RunComplete]) {
207− t.Helper()
208− env := testEnv(t)
209− broker := pubsub.NewBroker[notify.RunComplete]()
210− t.Cleanup(broker.Shutdown)
211− sa := NewSessionAgent(SessionAgentOptions{
212− Sessions: env.sessions,
213− Messages: env.messages,
214− RunComplete: broker,
215− }).(*sessionAgent)
216− return sa, env, broker
217−}
218−
219−// TestRun_CancelOnEntryPublishesRunComplete covers the first review
220−// finding: the cancel-on-entry path returned before the streaming defer
221−// that publishes RunComplete was installed. A caller that dispatches a
222−// run with a RunID and blocks on RunComplete (ignoring message events,
223−// like `crush run`) would hang on an immediately-canceled accepted run.
224−// The cancel-on-entry path must publish a terminal RunComplete carrying
225−// the originating RunID.
226−func TestRun_CancelOnEntryPublishesRunComplete(t *testing.T) {
227− t.Parallel()
228− sa, env, broker := newCancelTestAgentWithRunComplete(t)
229−
230− sess, err := env.sessions.Create(t.Context(), "session")
231− require.NoError(t, err)
232−
233− ctx, cancel := context.WithCancel(t.Context())
234− defer cancel()
235− ch := broker.Subscribe(ctx)
236−
237− accept := sa.BeginAccepted(sess.ID)
238− // A cancel arrives in the accepted-but-not-yet-active window.
239− sa.Cancel(sess.ID)
240− require.True(t, sa.hasPendingCancel(sess.ID))
241−
242− result, err := sa.Run(t.Context(), SessionAgentCall{
243− SessionID: sess.ID,
244− RunID: "run-cancel-on-entry",
245− Prompt: "hello",
246− Accepted: accept,
247− })
248− require.NoError(t, err)
249− require.Nil(t, result)
250−
251− select {
252− case got := <-ch:
253− assert.Equal(t, "run-cancel-on-entry", got.Payload.RunID,
254− "RunComplete must echo the originating RunID")
255− assert.Equal(t, sess.ID, got.Payload.SessionID)
256− assert.True(t, got.Payload.Cancelled,
257− "cancel-on-entry RunComplete must be marked cancelled")
258− case <-time.After(2 * time.Second):
259− t.Fatal("cancel-on-entry must publish RunComplete; a RunID caller would hang otherwise")
260− }
261−}
262−
263−// TestCancel_TwoAcceptedBothObserveCancellation covers the second review
264−// finding: a single cancel with two accepted-not-yet-active prompts must
265−// cancel both. The cancel raises the session's high-water mark to the
266−// latest accept sequence, so every prompt accepted-but-not-yet-active at
267−// cancel time is covered and both take the cancel-on-entry path.
268−func TestCancel_TwoAcceptedBothObserveCancellation(t *testing.T) {
269− t.Parallel()
270− sa, env := newCancelTestAgent(t)
271−
272− sess, err := env.sessions.Create(t.Context(), "session")
273− require.NoError(t, err)
274−
275− // Two prompts are accepted-but-not-yet-active for the same session.
276− accept1 := sa.BeginAccepted(sess.ID)
277− accept2 := sa.BeginAccepted(sess.ID)
278− require.Equal(t, 2, sa.acceptedCount(sess.ID))
279−
280− // A single cancel arrives before either becomes active.
281− sa.Cancel(sess.ID)
282− require.Equal(t, accept2.seq, sa.pendingCancelMark(sess.ID),
283− "one cancel must mark every currently-accepted prompt as canceled")
284− require.GreaterOrEqual(t, sa.pendingCancelMark(sess.ID), accept1.seq,
285− "the mark must cover the earlier accepted prompt too")
286−
287− // Both prompts enter Run; each must take cancel-on-entry, not run.
288− r1, err := sa.Run(t.Context(), SessionAgentCall{
289− SessionID: sess.ID,
290− Prompt: "first",
291− Accepted: accept1,
292− })
293− require.NoError(t, err)
294− require.Nil(t, r1)
295−
296− r2, err := sa.Run(t.Context(), SessionAgentCall{
297− SessionID: sess.ID,
298− Prompt: "second",
299− Accepted: accept2,
300− })
301− require.NoError(t, err)
302− require.Nil(t, r2)
303−
304− require.False(t, sa.hasPendingCancel(sess.ID),
305− "both reserved units must be consumed")
306− require.Equal(t, 0, sa.acceptedCount(sess.ID),
307− "both accept reservations must be released")
308−
309− // Each canceled-on-entry turn writes a user + canceled assistant
310− // message, and neither prompt was enqueued to run normally.
311− require.Equal(t, 0, sa.QueuedPrompts(sess.ID),
312− "neither accepted prompt may be enqueued to run normally")
313− msgs, err := env.messages.List(t.Context(), sess.ID)
314− require.NoError(t, err)
315− require.Len(t, msgs, 4, "two canceled turns produce two user + two assistant messages")
316− var canceled int
317− for _, m := range msgs {
318− if m.Role == message.Assistant {
319− assert.Equal(t, message.FinishReasonCanceled, m.FinishReason())
320− canceled++
321− }
322− }
323− require.Equal(t, 2, canceled, "both turns must finish canceled")
324−}
325−
326−// TestRun_IdleCancelDoesNotPoisonNextPrompt covers the idle-cancel
327−// no-op guarantee end-to-end: an Escape on an idle session must not
328−// record a pending cancel that leaks into the next accepted prompt, which
329−// must run normally to completion.
330−func TestRun_IdleCancelDoesNotPoisonNextPrompt(t *testing.T) {
331− t.Parallel()
332− sa, env := newStreamTestAgent(t)
333−
334− sess, err := env.sessions.Create(t.Context(), "session")
335− require.NoError(t, err)
336−
337− // Idle Escape: no accepted run, no active request.
338− sa.Cancel(sess.ID)
339− require.False(t, sa.hasPendingCancel(sess.ID),
340− "idle cancel must not record a pending cancel")
341−
342− // The next accepted prompt must run normally, not cancel on entry.
343− accept := sa.BeginAccepted(sess.ID)
344− result, err := sa.Run(t.Context(), SessionAgentCall{
345− SessionID: sess.ID,
346− Prompt: "next",
347− Accepted: accept,
348− })
349− require.NoError(t, err)
350− require.NotNil(t, result, "next prompt must run normally after an idle cancel")
351−
352− msgs, err := env.messages.List(t.Context(), sess.ID)
353− require.NoError(t, err)
354− require.Len(t, msgs, 2)
355− assert.Equal(t, message.User, msgs[0].Role)
356− assert.Equal(t, message.Assistant, msgs[1].Role)
357− assert.Equal(t, message.FinishReasonEndTurn, msgs[1].FinishReason(),
358− "the prompt must finish normally, not canceled")
359−}
360−
361−// TestCancel_AcceptedAfterCancelIsNotPoisoned is the regression test for
362−// the reviewer's finding: a counted session-level pending cancel let a
363−// prompt accepted after the cancel enter Run first and consume a unit
364−// reserved for the earlier prompts. With a sequence high-water mark, a
365−// single cancel covers exactly the prompts accepted-but-not-yet-active at
366−// cancel time (A and B); a prompt accepted afterwards (C) gets a higher
367−// sequence and must run normally without consuming A or B's cancellation.
368−// C is run first to prove it neither cancels nor drains the mark, then A
369−// and B are run and must both cancel on entry.
370−func TestCancel_AcceptedAfterCancelIsNotPoisoned(t *testing.T) {
371− t.Parallel()
372− sa, env := newStreamTestAgent(t)
373−
374− sess, err := env.sessions.Create(t.Context(), "session")
375− require.NoError(t, err)
376−
377− // A and B are accepted-but-not-yet-active.
378− acceptA := sa.BeginAccepted(sess.ID)
379− acceptB := sa.BeginAccepted(sess.ID)
380−
381− // One cancel arrives covering both A and B.
382− sa.Cancel(sess.ID)
383− require.True(t, sa.hasPendingCancel(sess.ID))
384− require.Equal(t, acceptB.seq, sa.pendingCancelMark(sess.ID),
385− "the mark must cover every prompt accepted before the cancel")
386−
387− // C is accepted AFTER the cancel; its sequence is above the mark.
388− acceptC := sa.BeginAccepted(sess.ID)
389− require.Greater(t, acceptC.seq, sa.pendingCancelMark(sess.ID),
390− "a prompt accepted after the cancel must not be covered by the mark")
391−
392− // Run C first. It must run normally to completion and must not
393− // consume or clear the cancellation reserved for A and B.
394− rc, err := sa.Run(t.Context(), SessionAgentCall{
395− SessionID: sess.ID,
396− Prompt: "C",
397− Accepted: acceptC,
398− })
399− require.NoError(t, err)
400− require.NotNil(t, rc, "C was accepted after the cancel and must run normally")
401− require.True(t, sa.hasPendingCancel(sess.ID),
402− "running C must not drain the cancellation reserved for A and B")
403−
404− // Now A and B run. Both were accepted before the cancel and must
405− // take the cancel-on-entry path.
406− ra, err := sa.Run(t.Context(), SessionAgentCall{
407− SessionID: sess.ID,
408− Prompt: "A",
409− Accepted: acceptA,
410− })
411− require.NoError(t, err)
412− require.Nil(t, ra, "A must cancel on entry, not run")
413−
414− rb, err := sa.Run(t.Context(), SessionAgentCall{
415− SessionID: sess.ID,
416− Prompt: "B",
417− Accepted: acceptB,
418− })
419− require.NoError(t, err)
420− require.Nil(t, rb, "B must cancel on entry, not run")
421−
422− require.False(t, sa.hasPendingCancel(sess.ID),
423− "the mark clears once all covered handles are resolved")
424− require.Equal(t, 0, sa.acceptedCount(sess.ID))
425− require.Equal(t, 0, sa.QueuedPrompts(sess.ID),
426− "neither A nor B may be enqueued to run normally")
427−
428− // C produced a normal turn; A and B each produced a canceled turn.
429− msgs, err := env.messages.List(t.Context(), sess.ID)
430− require.NoError(t, err)
431− require.Len(t, msgs, 6, "C normal + A canceled + B canceled = 3 user + 3 assistant")
432−
433− var normal, canceled int
434− for _, m := range msgs {
435− if m.Role != message.Assistant {
436− continue
437− }
438− switch m.FinishReason() {
439− case message.FinishReasonEndTurn:
440− normal++
441− case message.FinishReasonCanceled:
442− canceled++
443− }
444− }
445− require.Equal(t, 1, normal, "only C finished normally")
446− require.Equal(t, 2, canceled, "both A and B finished canceled")
447−}
internal/agent/event.go+6−6
@@ -7,23 +7,23 @@ import (
77 "github.com/charmbracelet/crush/internal/event"
88)
99
10−func (a *sessionAgent) eventPromptSent(sessionID string) {
10+func (a sessionAgent) eventPromptSent(sessionID string) {
1111 event.PromptSent(
12− a.eventCommon(sessionID, a.largeModel.Get())...,
12+ a.eventCommon(sessionID, a.largeModel)...,
1313 )
1414}
1515
16−func (a *sessionAgent) eventPromptResponded(sessionID string, duration time.Duration) {
16+func (a sessionAgent) eventPromptResponded(sessionID string, duration time.Duration) {
1717 event.PromptResponded(
1818 append(
19− a.eventCommon(sessionID, a.largeModel.Get()),
19+ a.eventCommon(sessionID, a.largeModel),
2020 "prompt duration pretty", duration.String(),
2121 "prompt duration in seconds", int64(duration.Seconds()),
2222 )...,
2323 )
2424}
2525
26−func (a *sessionAgent) eventTokensUsed(sessionID string, model Model, usage fantasy.Usage, cost float64) {
26+func (a sessionAgent) eventTokensUsed(sessionID string, model Model, usage fantasy.Usage, cost float64) {
2727 event.TokensUsed(
2828 append(
2929 a.eventCommon(sessionID, model),
@@ -37,7 +37,7 @@ func (a *sessionAgent) eventTokensUsed(sessionID string, model Model, usage fant
3737 )
3838}
3939
40−func (a *sessionAgent) eventCommon(sessionID string, model Model) []any {
40+func (a sessionAgent) eventCommon(sessionID string, model Model) []any {
4141 m := model.ModelCfg
4242
4343 return []any{
internal/agent/hooked_tool.godeleted−142
@@ -1,142 +0,0 @@
1−package agent
2−
3−import (
4− "context"
5− "encoding/json"
6− "fmt"
7− "log/slog"
8−
9− "charm.land/fantasy"
10− "github.com/charmbracelet/crush/internal/agent/tools"
11− "github.com/charmbracelet/crush/internal/hooks"
12− "github.com/charmbracelet/crush/internal/permission"
13− "github.com/tidwall/sjson"
14−)
15−
16−// hookedTool wraps a fantasy.AgentTool to run PreToolUse hooks before
17−// delegating to the inner tool.
18−type hookedTool struct {
19− inner fantasy.AgentTool
20− runner *hooks.Runner
21−}
22−
23−func newHookedTool(inner fantasy.AgentTool, runner *hooks.Runner) *hookedTool {
24− return &hookedTool{inner: inner, runner: runner}
25−}
26−
27−// wrapToolsWithHooks returns a tool slice with each entry wrapped in a
28−// hookedTool. Returns the original slice unchanged when runner is nil or
29−// when isSubAgent is true — sub-agents never fire hooks, the top-level
30−// invocation of the sub-agent tool itself is wrapped on the caller's side.
31−func wrapToolsWithHooks(tools []fantasy.AgentTool, runner *hooks.Runner, isSubAgent bool) []fantasy.AgentTool {
32− if runner == nil || isSubAgent {
33− return tools
34− }
35− out := make([]fantasy.AgentTool, len(tools))
36− for i, tool := range tools {
37− out[i] = newHookedTool(tool, runner)
38− }
39− return out
40−}
41−
42−func (h *hookedTool) Info() fantasy.ToolInfo {
43− return h.inner.Info()
44−}
45−
46−func (h *hookedTool) ProviderOptions() fantasy.ProviderOptions {
47− return h.inner.ProviderOptions()
48−}
49−
50−func (h *hookedTool) SetProviderOptions(opts fantasy.ProviderOptions) {
51− h.inner.SetProviderOptions(opts)
52−}
53−
54−func (h *hookedTool) Run(ctx context.Context, call fantasy.ToolCall) (fantasy.ToolResponse, error) {
55− sessionID := tools.GetSessionFromContext(ctx)
56− result, err := h.runner.Run(ctx, hooks.EventPreToolUse, sessionID, call.Name, call.Input)
57− if err != nil {
58− slog.Warn("Hook execution error, proceeding with tool call",
59− "tool", call.Name, "error", err)
60− }
61−
62− if result.Decision == hooks.DecisionDeny || result.Halt {
63− reason := fmt.Sprintf("Tool call blocked by hook. Reason: %s", result.Reason)
64− if result.Halt {
65− reason = fmt.Sprintf("Turn halted by hook. Reason: %s", result.Reason)
66− }
67− resp := fantasy.NewTextErrorResponse(reason)
68− // Halt ends the whole turn; a plain deny only blocks this tool
69− // call so the model can see the error and try something else.
70− resp.StopTurn = result.Halt
71− resp.Metadata = hookMetadataJSON(result)
72− return resp, nil
73− }
74−
75− if result.UpdatedInput != "" {
76− call.Input = result.UpdatedInput
77− }
78−
79− // An explicit allow from a hook pre-approves the permission prompt for
80− // this tool call. Deny is already handled above; silence falls through
81− // to the normal permission flow.
82− if result.Decision == hooks.DecisionAllow {
83− ctx = permission.WithHookApproval(ctx, call.ID)
84− }
85−
86− resp, err := h.inner.Run(ctx, call)
87− if err != nil {
88− return resp, err
89− }
90−
91− if result.Context != "" {
92− if resp.Content != "" {
93− resp.Content += "\n"
94− }
95− resp.Content += result.Context
96− }
97−
98− resp.Metadata = mergeHookMetadata(resp.Metadata, result)
99− return resp, nil
100−}
101−
102−// buildHookMetadata creates a HookMetadata from an AggregateResult.
103−func buildHookMetadata(result hooks.AggregateResult) hooks.HookMetadata {
104− return hooks.HookMetadata{
105− HookCount: result.HookCount,
106− Decision: result.Decision.String(),
107− Halt: result.Halt,
108− Reason: result.Reason,
109− InputRewrite: result.UpdatedInput != "",
110− Hooks: result.Hooks,
111− }
112−}
113−
114−// hookMetadataJSON builds a JSON string containing only the hook metadata.
115−func hookMetadataJSON(result hooks.AggregateResult) string {
116− meta := buildHookMetadata(result)
117− data, err := json.Marshal(meta)
118− if err != nil {
119− return ""
120− }
121− return `{"hook":` + string(data) + `}`
122−}
123−
124−// mergeHookMetadata injects hook metadata into existing tool metadata.
125−func mergeHookMetadata(existing string, result hooks.AggregateResult) string {
126− if result.HookCount == 0 {
127− return existing
128− }
129− meta := buildHookMetadata(result)
130− data, err := json.Marshal(meta)
131− if err != nil {
132− return existing
133− }
134− if existing == "" {
135− existing = "{}"
136− }
137− merged, err := sjson.SetRaw(existing, "hook", string(data))
138− if err != nil {
139− return existing
140− }
141− return merged
142−}
internal/agent/hooked_tool_test.godeleted−147
@@ -1,147 +0,0 @@
1−package agent
2−
3−import (
4− "context"
5− "testing"
6−
7− "charm.land/fantasy"
8− "github.com/charmbracelet/crush/internal/config"
9− "github.com/charmbracelet/crush/internal/hooks"
10− "github.com/charmbracelet/crush/internal/permission"
11− "github.com/stretchr/testify/require"
12−)
13−
14−// fakeTool records the context it was invoked with so tests can assert on
15−// values stamped onto it by the hookedTool decorator.
16−type fakeTool struct {
17− name string
18− called bool
19− gotCtx context.Context
20− resp fantasy.ToolResponse
21−}
22−
23−func (f *fakeTool) Info() fantasy.ToolInfo {
24− return fantasy.ToolInfo{Name: f.name}
25−}
26−
27−func (f *fakeTool) Run(ctx context.Context, _ fantasy.ToolCall) (fantasy.ToolResponse, error) {
28− f.called = true
29− f.gotCtx = ctx
30− return f.resp, nil
31−}
32−
33−func (f *fakeTool) ProviderOptions() fantasy.ProviderOptions { return nil }
34−func (f *fakeTool) SetProviderOptions(_ fantasy.ProviderOptions) {}
35−
36−// newRunner builds a hooks.Runner from a single HookConfig, running the
37−// config-loader path that compiles the matcher regex.
38−func newRunner(t *testing.T, cmd string) *hooks.Runner {
39− t.Helper()
40− cfg := &config.Config{
41− Hooks: map[string][]config.HookConfig{
42− hooks.EventPreToolUse: {{Command: cmd}},
43− },
44− }
45− require.NoError(t, cfg.ValidateHooks())
46− return hooks.NewRunner(cfg.Hooks[hooks.EventPreToolUse], t.TempDir(), t.TempDir())
47−}
48−
49−func TestHookedTool_AllowStampsHookApproval(t *testing.T) {
50− t.Parallel()
51−
52− inner := &fakeTool{name: "view", resp: fantasy.NewTextResponse("ok")}
53− runner := newRunner(t, `echo '{"decision":"allow"}'`)
54− tool := newHookedTool(inner, runner)
55−
56− _, err := tool.Run(t.Context(), fantasy.ToolCall{ID: "call-1", Name: "view"})
57− require.NoError(t, err)
58− require.True(t, inner.called, "inner tool should have run")
59−
60− // The inner tool's permission service can now treat call-1 as pre-approved.
61− svc := permission.NewPermissionService(t.TempDir(), false, nil)
62− granted, err := svc.Request(inner.gotCtx, permission.CreatePermissionRequest{
63− SessionID: "s1",
64− ToolCallID: "call-1",
65− ToolName: "view",
66− Action: "read",
67− Path: t.TempDir(),
68− })
69− require.NoError(t, err)
70− require.True(t, granted, "hook allow should bypass the permission prompt")
71−}
72−
73−func TestHookedTool_SilentDoesNotStampApproval(t *testing.T) {
74− t.Parallel()
75−
76− inner := &fakeTool{name: "view", resp: fantasy.NewTextResponse("ok")}
77− runner := newRunner(t, `exit 0`) // no stdout, no decision
78− tool := newHookedTool(inner, runner)
79−
80− _, err := tool.Run(t.Context(), fantasy.ToolCall{ID: "call-2", Name: "view"})
81− require.NoError(t, err)
82− require.True(t, inner.called)
83−
84− // With no hook opinion, a fresh permission request has nothing stamped
85− // and must fall through to the normal flow. We verify by checking that
86− // the context does not look pre-approved for this call ID: sending a
87− // request that no subscriber resolves will block until cancelled.
88− svc := permission.NewPermissionService(t.TempDir(), false, nil)
89− ctx, cancel := context.WithCancel(inner.gotCtx)
90− cancel()
91− granted, err := svc.Request(ctx, permission.CreatePermissionRequest{
92− SessionID: "s1",
93− ToolCallID: "call-2",
94− ToolName: "view",
95− Action: "read",
96− Path: t.TempDir(),
97− })
98− require.Error(t, err, "no approval stamped => request should reach the prompt path")
99− require.False(t, granted)
100−}
101−
102−func TestHookedTool_DenySkipsInnerTool(t *testing.T) {
103− t.Parallel()
104−
105− inner := &fakeTool{name: "bash"}
106− runner := newRunner(t, `echo "blocked" >&2; exit 2`)
107− tool := newHookedTool(inner, runner)
108−
109− resp, err := tool.Run(t.Context(), fantasy.ToolCall{ID: "call-3", Name: "bash"})
110− require.NoError(t, err)
111− require.False(t, inner.called, "denied call must not reach the inner tool")
112− require.True(t, resp.IsError)
113− require.Contains(t, resp.Content, "blocked")
114−}
115−
116−func TestWrapToolsWithHooks(t *testing.T) {
117− t.Parallel()
118−
119− runner := newRunner(t, `exit 0`)
120− inputs := []fantasy.AgentTool{&fakeTool{name: "a"}, &fakeTool{name: "b"}}
121−
122− t.Run("top-level agent wraps every tool", func(t *testing.T) {
123− t.Parallel()
124− out := wrapToolsWithHooks(inputs, runner, false)
125− require.Len(t, out, len(inputs))
126− for i, tool := range out {
127− _, ok := tool.(*hookedTool)
128− require.Truef(t, ok, "tool %d should be a *hookedTool", i)
129− }
130− })
131−
132− t.Run("sub-agent skips the wrap", func(t *testing.T) {
133− t.Parallel()
134− out := wrapToolsWithHooks(inputs, runner, true)
135− require.Equal(t, inputs, out, "sub-agent tools should be returned unwrapped")
136− for _, tool := range out {
137− _, isHooked := tool.(*hookedTool)
138− require.False(t, isHooked, "sub-agent tool should not be wrapped")
139− }
140− })
141−
142− t.Run("nil runner skips the wrap for both agent kinds", func(t *testing.T) {
143− t.Parallel()
144− require.Equal(t, inputs, wrapToolsWithHooks(inputs, nil, false))
145− require.Equal(t, inputs, wrapToolsWithHooks(inputs, nil, true))
146− })
147−}
internal/agent/hyper/provider.go+274−49
@@ -2,34 +2,54 @@
22package hyper
33
44import (
5+ "bufio"
6+ "bytes"
57 "cmp"
68 "context"
79 _ "embed"
810 "encoding/json"
11+ "errors"
912 "fmt"
13+ "io"
1014 "log/slog"
15+ "maps"
1116 "net/http"
17+ "net/url"
1218 "os"
19+ "strconv"
20+ "strings"
1321 "sync"
14− "sync/atomic"
1522 "time"
1623
17− "charm.land/catwalk/pkg/catwalk"
24+ "charm.land/fantasy"
25+ "charm.land/fantasy/object"
26+ "github.com/charmbracelet/catwalk/pkg/catwalk"
27+ "github.com/charmbracelet/crush/internal/event"
1828)
1929
20−//go:generate wget -O provider.json https://hyper.charm.land/v1/provider
30+//go:generate wget -O provider.json https://console.charm.land/api/v1/provider
2131
2232//go:embed provider.json
2333var embedded []byte
2434
35+// Enabled returns true if hyper is enabled.
36+var Enabled = sync.OnceValue(func() bool {
37+ b, _ := strconv.ParseBool(
38+ cmp.Or(
39+ os.Getenv("HYPER"),
40+ os.Getenv("HYPERCRUSH"),
41+ os.Getenv("HYPER_ENABLE"),
42+ os.Getenv("HYPER_ENABLED"),
43+ ),
44+ )
45+ return b
46+})
47+
2548// Embedded returns the embedded Hyper provider.
2649var Embedded = sync.OnceValue(func() catwalk.Provider {
2750 var provider catwalk.Provider
2851 if err := json.Unmarshal(embedded, &provider); err != nil {
29− slog.Error("Could not use embedded provider data", "err", err)
30− }
31− if e := os.Getenv("HYPER_URL"); e != "" {
32− provider.APIEndpoint = e + "/api/v1/fantasy"
52+ slog.Error("could not use embedded provider data", "err", err)
3353 }
3454 return provider
3555})
@@ -37,10 +57,9 @@ var Embedded = sync.OnceValue(func() catwalk.Provider {
3757const (
3858 // Name is the default name of this meta provider.
3959 Name = "hyper"
40− // DisplayName is the display name of Hyper.
41− DisplayName = "Charm Hyper"
4260 // defaultBaseURL is the default proxy URL.
43− defaultBaseURL = "https://hyper.charm.land"
61+ // TODO: change this to production URL when ready.
62+ defaultBaseURL = "https://console.charm.land"
4463)
4564
4665// BaseURL returns the base URL, which is either $HYPER_URL or the default.
@@ -48,58 +67,264 @@ var BaseURL = sync.OnceValue(func() string {
4867 return cmp.Or(os.Getenv("HYPER_URL"), defaultBaseURL)
4968})
5069
51−// lastKnownBalance stores the most recently extracted hypercredit balance
52−// from API response metadata. FetchCredits checks this before making a
53−// separate HTTP call.
54−var lastKnownBalance atomic.Int64
70+var ErrNoCredits = errors.New("you're out of credits")
5571
56−// hasBalance tracks whether lastKnownBalance has been set.
57−var hasBalance atomic.Bool
72+type options struct {
73+ baseURL string
74+ apiKey string
75+ name string
76+ headers map[string]string
77+ client *http.Client
78+}
79+
80+// Option configures the proxy provider.
81+type Option = func(*options)
5882
59−// SetBalance stores a credit balance extracted from API response metadata.
60−func SetBalance(balance int) {
61− lastKnownBalance.Store(int64(balance))
62− hasBalance.Store(true)
83+// New creates a new proxy provider.
84+func New(opts ...Option) (fantasy.Provider, error) {
85+ o := options{
86+ baseURL: BaseURL() + "/api/v1/fantasy",
87+ name: Name,
88+ headers: map[string]string{
89+ "x-crush-id": event.GetID(),
90+ },
91+ client: &http.Client{Timeout: 0}, // stream-safe
92+ }
93+ for _, opt := range opts {
94+ opt(&o)
95+ }
96+ return &provider{options: o}, nil
6397}
6498
65−// FetchCredits returns the remaining hypercredit balance. It first checks
66−// for a balance extracted from the most recent API response's usage
67−// metadata. If none is available, it falls back to calling the /v1/credits
68−// endpoint directly.
69−func FetchCredits(ctx context.Context, apiKey string) (int, error) {
70− if hasBalance.Load() {
71− hasBalance.Store(false)
72− return int(lastKnownBalance.Load()), nil
73− }
74−
75− req, err := http.NewRequestWithContext(
76− ctx,
77− http.MethodGet,
78− BaseURL()+"/v1/credits",
79− nil,
80− )
99+// WithBaseURL sets the proxy base URL (e.g. http://localhost:8080).
100+func WithBaseURL(url string) Option { return func(o *options) { o.baseURL = url } }
101+
102+// WithName sets the provider name.
103+func WithName(name string) Option { return func(o *options) { o.name = name } }
104+
105+// WithHeaders sets extra headers sent to the proxy.
106+func WithHeaders(headers map[string]string) Option {
107+ return func(o *options) {
108+ maps.Copy(o.headers, headers)
109+ }
110+}
111+
112+// WithHTTPClient sets custom HTTP client.
113+func WithHTTPClient(c *http.Client) Option { return func(o *options) { o.client = c } }
114+
115+// WithAPIKey sets the API key.
116+func WithAPIKey(key string) Option {
117+ return func(o *options) {
118+ o.apiKey = key
119+ }
120+}
121+
122+type provider struct{ options options }
123+
124+func (p *provider) Name() string { return p.options.name }
125+
126+// LanguageModel implements fantasy.Provider.
127+func (p *provider) LanguageModel(_ context.Context, modelID string) (fantasy.LanguageModel, error) {
128+ if modelID == "" {
129+ return nil, errors.New("missing model id")
130+ }
131+ return &languageModel{modelID: modelID, provider: p.options.name, opts: p.options}, nil
132+}
133+
134+type languageModel struct {
135+ provider string
136+ modelID string
137+ opts options
138+}
139+
140+// GenerateObject implements fantasy.LanguageModel.
141+func (m *languageModel) GenerateObject(ctx context.Context, call fantasy.ObjectCall) (*fantasy.ObjectResponse, error) {
142+ return object.GenerateWithTool(ctx, m, call)
143+}
144+
145+// StreamObject implements fantasy.LanguageModel.
146+func (m *languageModel) StreamObject(ctx context.Context, call fantasy.ObjectCall) (fantasy.ObjectStreamResponse, error) {
147+ return object.StreamWithTool(ctx, m, call)
148+}
149+
150+func (m *languageModel) Provider() string { return m.provider }
151+func (m *languageModel) Model() string { return m.modelID }
152+
153+// Generate implements fantasy.LanguageModel by calling the proxy JSON endpoint.
154+func (m *languageModel) Generate(ctx context.Context, call fantasy.Call) (*fantasy.Response, error) {
155+ resp, err := m.doRequest(ctx, false, call)
156+ if err != nil {
157+ return nil, err
158+ }
159+ defer func() { _ = resp.Body.Close() }()
160+ if resp.StatusCode < 200 || resp.StatusCode >= 300 {
161+ b, _ := ioReadAllLimit(resp.Body, 64*1024)
162+ return nil, fmt.Errorf("proxy generate error: %s", strings.TrimSpace(string(b)))
163+ }
164+ var out fantasy.Response
165+ if err := json.NewDecoder(resp.Body).Decode(&out); err != nil {
166+ return nil, err
167+ }
168+ return &out, nil
169+}
170+
171+// Stream implements fantasy.LanguageModel using SSE from the proxy.
172+func (m *languageModel) Stream(ctx context.Context, call fantasy.Call) (fantasy.StreamResponse, error) {
173+ // Prefer explicit /stream endpoint
174+ resp, err := m.doRequest(ctx, true, call)
175+ if err != nil {
176+ return nil, err
177+ }
178+ switch resp.StatusCode {
179+ case http.StatusTooManyRequests:
180+ _ = resp.Body.Close()
181+ return nil, toProviderError(resp, retryAfter(resp))
182+ case http.StatusUnauthorized:
183+ _ = resp.Body.Close()
184+ return nil, toProviderError(resp, "")
185+ case http.StatusPaymentRequired:
186+ _ = resp.Body.Close()
187+ return nil, ErrNoCredits
188+ }
189+
190+ if resp.StatusCode < 200 || resp.StatusCode >= 300 {
191+ defer func() { _ = resp.Body.Close() }()
192+ b, _ := ioReadAllLimit(resp.Body, 64*1024)
193+ return nil, &fantasy.ProviderError{
194+ Title: "Stream Error",
195+ Message: strings.TrimSpace(string(b)),
196+ StatusCode: resp.StatusCode,
197+ }
198+ }
199+
200+ return func(yield func(fantasy.StreamPart) bool) {
201+ defer func() { _ = resp.Body.Close() }()
202+ scanner := bufio.NewScanner(resp.Body)
203+ buf := make([]byte, 0, 64*1024)
204+ scanner.Buffer(buf, 4*1024*1024)
205+
206+ var (
207+ event string
208+ dataBuf bytes.Buffer
209+ sawFinish bool
210+ dispatch = func() bool {
211+ if dataBuf.Len() == 0 || event == "" {
212+ dataBuf.Reset()
213+ event = ""
214+ return true
215+ }
216+ var part fantasy.StreamPart
217+ if err := json.Unmarshal(dataBuf.Bytes(), &part); err != nil {
218+ return yield(fantasy.StreamPart{Type: fantasy.StreamPartTypeError, Error: err})
219+ }
220+ if part.Type == fantasy.StreamPartTypeFinish {
221+ sawFinish = true
222+ }
223+ ok := yield(part)
224+ dataBuf.Reset()
225+ event = ""
226+ return ok
227+ }
228+ )
229+
230+ for scanner.Scan() {
231+ line := scanner.Text()
232+ if line == "" { // event boundary
233+ if !dispatch() {
234+ return
235+ }
236+ continue
237+ }
238+ if strings.HasPrefix(line, ":") { // comment / ping
239+ continue
240+ }
241+ if strings.HasPrefix(line, "event: ") {
242+ event = strings.TrimSpace(line[len("event: "):])
243+ continue
244+ }
245+ if strings.HasPrefix(line, "data: ") {
246+ if dataBuf.Len() > 0 {
247+ dataBuf.WriteByte('\n')
248+ }
249+ dataBuf.WriteString(line[len("data: "):])
250+ continue
251+ }
252+ }
253+ if err := scanner.Err(); err != nil &&
254+ !errors.Is(err, context.Canceled) &&
255+ !errors.Is(err, context.DeadlineExceeded) {
256+ yield(fantasy.StreamPart{Type: fantasy.StreamPartTypeError, Error: err})
257+ return
258+ }
259+ // flush any pending data
260+ _ = dispatch()
261+ if !sawFinish {
262+ _ = yield(fantasy.StreamPart{Type: fantasy.StreamPartTypeFinish})
263+ }
264+ }, nil
265+}
266+
267+func (m *languageModel) doRequest(ctx context.Context, stream bool, call fantasy.Call) (*http.Response, error) {
268+ addr, err := url.Parse(m.opts.baseURL)
269+ if err != nil {
270+ return nil, err
271+ }
272+ addr = addr.JoinPath(m.modelID)
273+ if stream {
274+ addr = addr.JoinPath("stream")
275+ } else {
276+ addr = addr.JoinPath("generate")
277+ }
278+
279+ body, err := json.Marshal(call)
81280 if err != nil {
82− return 0, fmt.Errorf("could not create request: %w", err)
281+ return nil, err
83282 }
84− req.Header.Set("Authorization", "Bearer "+apiKey)
85283
86− client := &http.Client{Timeout: 10 * time.Second}
87− resp, err := client.Do(req)
284+ req, err := http.NewRequestWithContext(ctx, http.MethodPost, addr.String(), bytes.NewReader(body))
88285 if err != nil {
89− return 0, fmt.Errorf("failed to make request: %w", err)
286+ return nil, err
287+ }
288+ req.Header.Set("Content-Type", "application/json")
289+ if stream {
290+ req.Header.Set("Accept", "text/event-stream")
291+ } else {
292+ req.Header.Set("Accept", "application/json")
293+ }
294+ for k, v := range m.opts.headers {
295+ req.Header.Set(k, v)
90296 }
91− defer resp.Body.Close()
92297
93− if resp.StatusCode != http.StatusOK {
94− return 0, fmt.Errorf("unexpected status code: %d", resp.StatusCode)
298+ if m.opts.apiKey != "" {
299+ req.Header.Set("Authorization", m.opts.apiKey)
95300 }
301+ return m.opts.client.Do(req)
302+}
96303
97− var result struct {
98− Balance int `json:"balance"`
304+// ioReadAllLimit reads up to n bytes.
305+func ioReadAllLimit(r io.Reader, n int64) ([]byte, error) {
306+ var b bytes.Buffer
307+ if n <= 0 {
308+ n = 1 << 20
99309 }
100− if err := json.NewDecoder(resp.Body).Decode(&result); err != nil {
101− return 0, fmt.Errorf("failed to decode response: %w", err)
310+ lr := &io.LimitedReader{R: r, N: n}
311+ _, err := b.ReadFrom(lr)
312+ return b.Bytes(), err
313+}
314+
315+func toProviderError(resp *http.Response, message string) error {
316+ return &fantasy.ProviderError{
317+ Title: fantasy.ErrorTitleForStatusCode(resp.StatusCode),
318+ Message: message,
319+ StatusCode: resp.StatusCode,
102320 }
321+}
103322
104− return result.Balance, nil
323+func retryAfter(resp *http.Response) string {
324+ after, err := strconv.Atoi(resp.Header.Get("Retry-After"))
325+ if err == nil && after > 0 {
326+ d := time.Duration(after) * time.Second
327+ return "Try again in " + d.String()
328+ }
329+ return "Try again in later"
105330}
internal/agent/hyper/provider.json+1−295
@@ -1,295 +1 @@
1−{
2− "name": "Charm Hyper",
3− "id": "hyper",
4− "api_endpoint": "https://hyper.charm.land/api/v1/fantasy",
5− "type": "hyper",
6− "default_large_model_id": "qwen3.7-plus",
7− "default_small_model_id": "deepseek-v4-flash",
8− "models": [
9− {
10− "id": "deepseek-v4-flash",
11− "name": "DeepSeek V4 Flash",
12− "cost_per_1m_in": 0.14,
13− "cost_per_1m_out": 0.28,
14− "cost_per_1m_in_cached": 0.0028,
15− "cost_per_1m_out_cached": 0,
16− "context_window": 1000000,
17− "default_max_tokens": 384000,
18− "can_reason": true,
19− "reasoning_levels": [
20− "high",
21− "xhigh"
22− ],
23− "default_reasoning_effort": "high",
24− "supports_attachments": false
25− },
26− {
27− "id": "deepseek-v4-pro",
28− "name": "DeepSeek V4 Pro",
29− "cost_per_1m_in": 0.435,
30− "cost_per_1m_out": 0.87,
31− "cost_per_1m_in_cached": 0.0036,
32− "cost_per_1m_out_cached": 0,
33− "context_window": 1000000,
34− "default_max_tokens": 384000,
35− "can_reason": true,
36− "reasoning_levels": [
37− "high",
38− "xhigh"
39− ],
40− "default_reasoning_effort": "high",
41− "supports_attachments": false
42− },
43− {
44− "id": "gemma-4-26b-a4b-it",
45− "name": "Gemma 4 26B A4B",
46− "cost_per_1m_in": 0.126,
47− "cost_per_1m_out": 0.42,
48− "cost_per_1m_in_cached": 0.063,
49− "cost_per_1m_out_cached": 0,
50− "context_window": 256000,
51− "default_max_tokens": 25600,
52− "can_reason": true,
53− "supports_attachments": false
54− },
55− {
56− "id": "glm-5",
57− "name": "GLM-5",
58− "cost_per_1m_in": 0.86,
59− "cost_per_1m_out": 2.784,
60− "cost_per_1m_in_cached": 0.43,
61− "cost_per_1m_out_cached": 0,
62− "context_window": 202752,
63− "default_max_tokens": 20275,
64− "can_reason": true,
65− "supports_attachments": false
66− },
67− {
68− "id": "glm-5.1",
69− "name": "GLM-5.1",
70− "cost_per_1m_in": 1.3,
71− "cost_per_1m_out": 4.3,
72− "cost_per_1m_in_cached": 0.26,
73− "cost_per_1m_out_cached": 0,
74− "context_window": 202000,
75− "default_max_tokens": 202000,
76− "can_reason": true,
77− "reasoning_levels": [
78− "low",
79− "medium",
80− "high"
81− ],
82− "default_reasoning_effort": "medium",
83− "supports_attachments": false
84− },
85− {
86− "id": "glm-5.2",
87− "name": "GLM-5.2",
88− "cost_per_1m_in": 1.5,
89− "cost_per_1m_out": 4.5,
90− "cost_per_1m_in_cached": 0.3,
91− "cost_per_1m_out_cached": 0,
92− "context_window": 1000000,
93− "default_max_tokens": 128000,
94− "can_reason": true,
95− "reasoning_levels": [
96− "high",
97− "xhigh"
98− ],
99− "default_reasoning_effort": "high",
100− "supports_attachments": false
101− },
102− {
103− "id": "gpt-oss-120b",
104− "name": "gpt-oss-120b",
105− "cost_per_1m_in": 0.168,
106− "cost_per_1m_out": 0.562,
107− "cost_per_1m_in_cached": 0.084,
108− "cost_per_1m_out_cached": 0,
109− "context_window": 131072,
110− "default_max_tokens": 13107,
111− "can_reason": true,
112− "reasoning_levels": [
113− "low",
114− "medium",
115− "high"
116− ],
117− "default_reasoning_effort": "medium",
118− "supports_attachments": false
119− },
120− {
121− "id": "kimi-k2.5",
122− "name": "Kimi K2.5",
123− "cost_per_1m_in": 0.51,
124− "cost_per_1m_out": 2.67,
125− "cost_per_1m_in_cached": 0.255,
126− "cost_per_1m_out_cached": 0,
127− "context_window": 262144,
128− "default_max_tokens": 26214,
129− "can_reason": true,
130− "supports_attachments": false
131− },
132− {
133− "id": "kimi-k2.6",
134− "name": "Kimi K2.6",
135− "cost_per_1m_in": 0.95,
136− "cost_per_1m_out": 4,
137− "cost_per_1m_in_cached": 0.16,
138− "cost_per_1m_out_cached": 0,
139− "context_window": 262000,
140− "default_max_tokens": 262000,
141− "can_reason": true,
142− "reasoning_levels": [
143− "low",
144− "medium",
145− "high"
146− ],
147− "default_reasoning_effort": "medium",
148− "supports_attachments": true
149− },
150− {
151− "id": "kimi-k2.7-code",
152− "name": "Kimi K2.7 Code",
153− "cost_per_1m_in": 0.95,
154− "cost_per_1m_out": 4,
155− "cost_per_1m_in_cached": 0.19,
156− "cost_per_1m_out_cached": 0,
157− "context_window": 256000,
158− "default_max_tokens": 32768,
159− "can_reason": true,
160− "reasoning_levels": [
161− "low",
162− "medium",
163− "high"
164− ],
165− "default_reasoning_effort": "medium",
166− "supports_attachments": true
167− },
168− {
169− "id": "llama-3.3-70b-instruct",
170− "name": "Llama 3.3 70B Instruct",
171− "cost_per_1m_in": 0.6066,
172− "cost_per_1m_out": 1.0386,
173− "cost_per_1m_in_cached": 0.3033,
174− "cost_per_1m_out_cached": 0,
175− "context_window": 128000,
176− "default_max_tokens": 12800,
177− "can_reason": true,
178− "supports_attachments": false
179− },
180− {
181− "id": "llama-4-maverick-17b-128e-instruct-fp8",
182− "name": "Llama 4 Maverick 17B 128E Instruct FP8",
183− "cost_per_1m_in": 0.274,
184− "cost_per_1m_out": 0.894,
185− "cost_per_1m_in_cached": 0.137,
186− "cost_per_1m_out_cached": 0,
187− "context_window": 430000,
188− "default_max_tokens": 43000,
189− "can_reason": true,
190− "supports_attachments": false
191− },
192− {
193− "id": "minimax-m2.7",
194− "name": "MiniMax M2.7",
195− "cost_per_1m_in": 0.3,
196− "cost_per_1m_out": 1.2,
197− "cost_per_1m_in_cached": 0.06,
198− "cost_per_1m_out_cached": 0.375,
199− "context_window": 204800,
200− "default_max_tokens": 131000,
201− "can_reason": true,
202− "reasoning_levels": [
203− "low",
204− "medium",
205− "high"
206− ],
207− "default_reasoning_effort": "medium",
208− "supports_attachments": false
209− },
210− {
211− "id": "qwen3.6-flash",
212− "name": "Qwen3.6-Flash",
213− "cost_per_1m_in": 1,
214− "cost_per_1m_out": 4,
215− "cost_per_1m_in_cached": 1.25,
216− "cost_per_1m_out_cached": 0.1,
217− "context_window": 1000000,
218− "default_max_tokens": 64000,
219− "can_reason": true,
220− "supports_attachments": true
221− },
222− {
223− "id": "qwen3.6-max",
224− "name": "Qwen3.6-Max",
225− "cost_per_1m_in": 2,
226− "cost_per_1m_out": 12,
227− "cost_per_1m_in_cached": 2.5,
228− "cost_per_1m_out_cached": 0.2,
229− "context_window": 256000,
230− "default_max_tokens": 64000,
231− "can_reason": true,
232− "supports_attachments": false
233− },
234− {
235− "id": "qwen3.6-plus",
236− "name": "Qwen3.6-Plus",
237− "cost_per_1m_in": 2,
238− "cost_per_1m_out": 6,
239− "cost_per_1m_in_cached": 2.5,
240− "cost_per_1m_out_cached": 0.2,
241− "context_window": 1000000,
242− "default_max_tokens": 64000,
243− "can_reason": true,
244− "supports_attachments": true
245− },
246− {
247− "id": "qwen3.7-max",
248− "name": "Qwen3.7-Max",
249− "cost_per_1m_in": 2.5,
250− "cost_per_1m_out": 7.5,
251− "cost_per_1m_in_cached": 3.125,
252− "cost_per_1m_out_cached": 0.25,
253− "context_window": 1000000,
254− "default_max_tokens": 64000,
255− "can_reason": true,
256− "supports_attachments": false
257− },
258− {
259− "id": "qwen3.7-plus",
260− "name": "Qwen3.7-Plus",
261− "cost_per_1m_in": 1.2,
262− "cost_per_1m_out": 4.8,
263− "cost_per_1m_in_cached": 1.5,
264− "cost_per_1m_out_cached": 0.12,
265− "context_window": 1000000,
266− "default_max_tokens": 64000,
267− "can_reason": true,
268− "supports_attachments": true
269− },
270− {
271− "id": "qwen3-coder-480b-a35b-instruct-int4-mixed-ar",
272− "name": "Qwen3 Coder 480B A35B Instruct INT4 Mixed AR",
273− "cost_per_1m_in": 0.557,
274− "cost_per_1m_out": 2.545,
275− "cost_per_1m_in_cached": 0.2785,
276− "cost_per_1m_out_cached": 0,
277− "context_window": 106000,
278− "default_max_tokens": 10600,
279− "can_reason": false,
280− "supports_attachments": false
281− },
282− {
283− "id": "qwen3-next-80b-a3b-instruct",
284− "name": "Qwen3 Next 80B A3B Instruct",
285− "cost_per_1m_in": 0.128,
286− "cost_per_1m_out": 1.28,
287− "cost_per_1m_in_cached": 0.064,
288− "cost_per_1m_out_cached": 0,
289− "context_window": 262144,
290− "default_max_tokens": 26214,
291− "can_reason": false,
292− "supports_attachments": false
293− }
294− ]
295−}
1+{"name":"Charm Hyper","id":"hyper","api_endpoint":"https://console.charm.land/api/v1/fantasy","type":"hyper","default_large_model_id":"claude-sonnet-4-5","default_small_model_id":"claude-3-5-haiku","models":[{"id":"Kimi-K2-0905","name":"Kimi K2 0905","cost_per_1m_in":0.55,"cost_per_1m_out":2.19,"cost_per_1m_in_cached":0,"cost_per_1m_out_cached":0,"context_window":256000,"default_max_tokens":10000,"can_reason":true,"default_reasoning_effort":"medium","supports_attachments":false,"options":{}},{"id":"claude-3-5-haiku","name":"Claude 3.5 Haiku","cost_per_1m_in":0.7999999999999999,"cost_per_1m_out":4,"cost_per_1m_in_cached":1,"cost_per_1m_out_cached":0.08,"context_window":200000,"default_max_tokens":5000,"can_reason":false,"supports_attachments":true,"options":{}},{"id":"claude-3-5-sonnet","name":"Claude 3.5 Sonnet (New)","cost_per_1m_in":3,"cost_per_1m_out":15,"cost_per_1m_in_cached":3.75,"cost_per_1m_out_cached":0.3,"context_window":200000,"default_max_tokens":5000,"can_reason":false,"supports_attachments":true,"options":{}},{"id":"claude-3-7-sonnet","name":"Claude 3.7 Sonnet","cost_per_1m_in":3,"cost_per_1m_out":15,"cost_per_1m_in_cached":3.75,"cost_per_1m_out_cached":0.3,"context_window":200000,"default_max_tokens":50000,"can_reason":true,"supports_attachments":true,"options":{}},{"id":"claude-haiku-4-5","name":"Claude 4.5 Haiku","cost_per_1m_in":1,"cost_per_1m_out":5,"cost_per_1m_in_cached":1.25,"cost_per_1m_out_cached":0.09999999999999999,"context_window":200000,"default_max_tokens":32000,"can_reason":true,"supports_attachments":true,"options":{}},{"id":"claude-opus-4","name":"Claude Opus 4","cost_per_1m_in":15,"cost_per_1m_out":75,"cost_per_1m_in_cached":18.75,"cost_per_1m_out_cached":1.5,"context_window":200000,"default_max_tokens":32000,"can_reason":true,"supports_attachments":true,"options":{}},{"id":"claude-opus-4-1","name":"Claude Opus 4.1","cost_per_1m_in":15,"cost_per_1m_out":75,"cost_per_1m_in_cached":18.75,"cost_per_1m_out_cached":1.5,"context_window":200000,"default_max_tokens":32000,"can_reason":true,"supports_attachments":true,"options":{}},{"id":"claude-opus-4-5","name":"Claude Opus 4.5","cost_per_1m_in":5,"cost_per_1m_out":25,"cost_per_1m_in_cached":6.25,"cost_per_1m_out_cached":0.5,"context_window":200000,"default_max_tokens":50000,"can_reason":true,"supports_attachments":true,"options":{}},{"id":"claude-sonnet-4","name":"Claude Sonnet 4","cost_per_1m_in":3,"cost_per_1m_out":15,"cost_per_1m_in_cached":3.75,"cost_per_1m_out_cached":0.3,"context_window":200000,"default_max_tokens":50000,"can_reason":true,"supports_attachments":true,"options":{}},{"id":"claude-sonnet-4-5","name":"Claude Sonnet 4.5","cost_per_1m_in":3,"cost_per_1m_out":15,"cost_per_1m_in_cached":3.75,"cost_per_1m_out_cached":0.3,"context_window":200000,"default_max_tokens":50000,"can_reason":true,"supports_attachments":true,"options":{}},{"id":"gemini-2.5-flash","name":"Gemini 2.5 Flash","cost_per_1m_in":0.3,"cost_per_1m_out":2.5,"cost_per_1m_in_cached":0.3833,"cost_per_1m_out_cached":0.075,"context_window":1048576,"default_max_tokens":50000,"can_reason":true,"supports_attachments":true,"options":{}},{"id":"gemini-2.5-pro","name":"Gemini 2.5 Pro","cost_per_1m_in":1.25,"cost_per_1m_out":10,"cost_per_1m_in_cached":1.625,"cost_per_1m_out_cached":0.31,"context_window":1048576,"default_max_tokens":50000,"can_reason":true,"supports_attachments":true,"options":{}},{"id":"glm-4.6","name":"GLM-4.6","cost_per_1m_in":0.6,"cost_per_1m_out":2.2,"cost_per_1m_in_cached":0.11,"cost_per_1m_out_cached":0,"context_window":204800,"default_max_tokens":131072,"can_reason":true,"default_reasoning_effort":"medium","supports_attachments":false,"options":{}},{"id":"gpt-4.1","name":"GPT-4.1","cost_per_1m_in":2,"cost_per_1m_out":8,"cost_per_1m_in_cached":0,"cost_per_1m_out_cached":0.5,"context_window":1047576,"default_max_tokens":16384,"can_reason":false,"supports_attachments":true,"options":{}},{"id":"gpt-4.1-mini","name":"GPT-4.1 Mini","cost_per_1m_in":0.39999999999999997,"cost_per_1m_out":1.5999999999999999,"cost_per_1m_in_cached":0,"cost_per_1m_out_cached":0.09999999999999999,"context_window":1047576,"default_max_tokens":16384,"can_reason":false,"supports_attachments":true,"options":{}},{"id":"gpt-4.1-nano","name":"GPT-4.1 Nano","cost_per_1m_in":0.09999999999999999,"cost_per_1m_out":0.39999999999999997,"cost_per_1m_in_cached":0,"cost_per_1m_out_cached":0.024999999999999998,"context_window":1047576,"default_max_tokens":16384,"can_reason":false,"supports_attachments":true,"options":{}},{"id":"gpt-4o","name":"GPT-4o","cost_per_1m_in":2.5,"cost_per_1m_out":10,"cost_per_1m_in_cached":0,"cost_per_1m_out_cached":1.25,"context_window":128000,"default_max_tokens":8192,"can_reason":false,"supports_attachments":true,"options":{}},{"id":"gpt-4o-mini","name":"GPT-4o-mini","cost_per_1m_in":0.15,"cost_per_1m_out":0.6,"cost_per_1m_in_cached":0,"cost_per_1m_out_cached":0.075,"context_window":128000,"default_max_tokens":8192,"can_reason":false,"supports_attachments":true,"options":{}},{"id":"gpt-5","name":"GPT-5","cost_per_1m_in":1.25,"cost_per_1m_out":10,"cost_per_1m_in_cached":0.125,"cost_per_1m_out_cached":0.125,"context_window":400000,"default_max_tokens":128000,"can_reason":true,"reasoning_levels":["minimal","low","medium","high"],"default_reasoning_effort":"medium","supports_attachments":true,"options":{}},{"id":"gpt-5-codex","name":"GPT-5 Codex","cost_per_1m_in":1.25,"cost_per_1m_out":10,"cost_per_1m_in_cached":0.125,"cost_per_1m_out_cached":0.125,"context_window":400000,"default_max_tokens":128000,"can_reason":true,"reasoning_levels":["minimal","low","medium","high"],"default_reasoning_effort":"medium","supports_attachments":true,"options":{}},{"id":"gpt-5-mini","name":"GPT-5 Mini","cost_per_1m_in":0.25,"cost_per_1m_out":2,"cost_per_1m_in_cached":0.025,"cost_per_1m_out_cached":0.025,"context_window":400000,"default_max_tokens":128000,"can_reason":true,"reasoning_levels":["low","medium","high"],"default_reasoning_effort":"medium","supports_attachments":true,"options":{}},{"id":"gpt-5-nano","name":"GPT-5 Nano","cost_per_1m_in":0.05,"cost_per_1m_out":0.4,"cost_per_1m_in_cached":0.005,"cost_per_1m_out_cached":0.005,"context_window":400000,"default_max_tokens":128000,"can_reason":true,"reasoning_levels":["low","medium","high"],"default_reasoning_effort":"medium","supports_attachments":true,"options":{}},{"id":"gpt-5.1","name":"GPT-5.1","cost_per_1m_in":1.25,"cost_per_1m_out":10,"cost_per_1m_in_cached":0.125,"cost_per_1m_out_cached":0.125,"context_window":400000,"default_max_tokens":128000,"can_reason":true,"reasoning_levels":["minimal","low","medium","high"],"default_reasoning_effort":"medium","supports_attachments":true,"options":{}},{"id":"gpt-5.1-codex","name":"GPT-5.1 Codex","cost_per_1m_in":1.25,"cost_per_1m_out":10,"cost_per_1m_in_cached":0.125,"cost_per_1m_out_cached":0.125,"context_window":400000,"default_max_tokens":128000,"can_reason":true,"reasoning_levels":["minimal","low","medium","high"],"default_reasoning_effort":"medium","supports_attachments":true,"options":{}},{"id":"gpt-5.1-codex-max","name":"GPT-5.1 Codex Max","cost_per_1m_in":1.25,"cost_per_1m_out":10,"cost_per_1m_in_cached":0.125,"cost_per_1m_out_cached":0.125,"context_window":400000,"default_max_tokens":128000,"can_reason":true,"reasoning_levels":["minimal","low","medium","high"],"default_reasoning_effort":"medium","supports_attachments":true,"options":{}},{"id":"gpt-5.1-codex-mini","name":"GPT-5.1 Codex Mini","cost_per_1m_in":0.25,"cost_per_1m_out":2,"cost_per_1m_in_cached":0.025,"cost_per_1m_out_cached":0.025,"context_window":400000,"default_max_tokens":128000,"can_reason":true,"reasoning_levels":["low","medium","high"],"default_reasoning_effort":"medium","supports_attachments":true,"options":{}},{"id":"gpt-5.2","name":"GPT-5.2","cost_per_1m_in":1.75,"cost_per_1m_out":14,"cost_per_1m_in_cached":0.175,"cost_per_1m_out_cached":0.175,"context_window":400000,"default_max_tokens":128000,"can_reason":true,"reasoning_levels":["minimal","low","medium","high"],"default_reasoning_effort":"medium","supports_attachments":true,"options":{}},{"id":"o3","name":"o3","cost_per_1m_in":2,"cost_per_1m_out":8,"cost_per_1m_in_cached":0,"cost_per_1m_out_cached":0.5,"context_window":200000,"default_max_tokens":50000,"can_reason":true,"reasoning_levels":["low","medium","high"],"default_reasoning_effort":"medium","supports_attachments":true,"options":{}},{"id":"o3-mini","name":"o3 Mini","cost_per_1m_in":1.1,"cost_per_1m_out":4.4,"cost_per_1m_in_cached":0,"cost_per_1m_out_cached":0.55,"context_window":200000,"default_max_tokens":50000,"can_reason":true,"reasoning_levels":["low","medium","high"],"default_reasoning_effort":"medium","supports_attachments":false,"options":{}},{"id":"o4-mini","name":"o4 Mini","cost_per_1m_in":1.1,"cost_per_1m_out":4.4,"cost_per_1m_in_cached":0,"cost_per_1m_out_cached":0.275,"context_window":200000,"default_max_tokens":50000,"can_reason":true,"reasoning_levels":["low","medium","high"],"default_reasoning_effort":"medium","supports_attachments":true,"options":{}},{"id":"qwen3-coder-480b-a35b-instruct","name":"Qwen 3 480B Coder","cost_per_1m_in":0.82,"cost_per_1m_out":3.29,"cost_per_1m_in_cached":0,"cost_per_1m_out_cached":0,"context_window":131072,"default_max_tokens":65536,"can_reason":false,"supports_attachments":false,"options":{}}]}
internal/agent/loop_detection.godeleted−92
@@ -1,92 +0,0 @@
1−package agent
2−
3−import (
4− "hash/fnv"
5− "io"
6−
7− "charm.land/fantasy"
8−)
9−
10−const (
11− loopDetectionWindowSize = 10
12− loopDetectionMaxRepeats = 5
13−)
14−
15−// hasRepeatedToolCalls checks whether the agent is stuck in a loop by looking
16−// at recent steps. It examines the last windowSize steps and returns true if
17−// any tool-call signature appears more than maxRepeats times.
18−func hasRepeatedToolCalls(steps []fantasy.StepResult, windowSize, maxRepeats int) bool {
19− if len(steps) < windowSize {
20− return false
21− }
22−
23− window := steps[len(steps)-windowSize:]
24− counts := make(map[uint64]int, windowSize)
25−
26− for _, step := range window {
27− sig := getToolInteractionSignature(step.Content)
28− if sig == 0 {
29− continue
30− }
31− counts[sig]++
32− if counts[sig] > maxRepeats {
33− return true
34− }
35− }
36−
37− return false
38−}
39−
40−// getToolInteractionSignature computes a hash signature for the tool
41−// interactions in a single step's content. It pairs tool calls with their
42−// results (matched by ToolCallID) and returns an FNV-1a hash. FNV is ~10x
43−// faster than SHA-256 and collision risk is negligible for loop detection
44−// over a 10-step window. If the step contains no tool calls, it returns 0.
45−func getToolInteractionSignature(content fantasy.ResponseContent) uint64 {
46− toolCalls := content.ToolCalls()
47− if len(toolCalls) == 0 {
48− return 0
49− }
50−
51− // Index tool results by their ToolCallID for fast lookup.
52− resultsByID := make(map[string]fantasy.ToolResultContent, len(toolCalls))
53− for _, tr := range content.ToolResults() {
54− resultsByID[tr.ToolCallID] = tr
55− }
56−
57− h := fnv.New64a()
58− for _, tc := range toolCalls {
59− output := ""
60− if tr, ok := resultsByID[tc.ToolCallID]; ok {
61− output = toolResultOutputString(tr.Result)
62− }
63− _, _ = io.WriteString(h, tc.ToolName)
64− h.Write([]byte{0})
65− _, _ = io.WriteString(h, tc.Input)
66− h.Write([]byte{0})
67− _, _ = io.WriteString(h, output)
68− h.Write([]byte{0})
69− }
70− return h.Sum64()
71−}
72−
73−// toolResultOutputString converts a ToolResultOutputContent to a stable string
74−// representation for signature comparison.
75−func toolResultOutputString(result fantasy.ToolResultOutputContent) string {
76− if result == nil {
77− return ""
78− }
79− if text, ok := fantasy.AsToolResultOutputType[fantasy.ToolResultOutputContentText](result); ok {
80− return text.Text
81− }
82− if errResult, ok := fantasy.AsToolResultOutputType[fantasy.ToolResultOutputContentError](result); ok {
83− if errResult.Error != nil {
84− return errResult.Error.Error()
85− }
86− return ""
87− }
88− if media, ok := fantasy.AsToolResultOutputType[fantasy.ToolResultOutputContentMedia](result); ok {
89− return media.Data
90− }
91− return ""
92−}
internal/agent/loop_detection_test.godeleted−205
@@ -1,205 +0,0 @@
1−package agent
2−
3−import (
4− "fmt"
5− "testing"
6−
7− "charm.land/fantasy"
8−)
9−
10−// makeStep creates a StepResult with the given tool calls and results in its Content.
11−func makeStep(calls []fantasy.ToolCallContent, results []fantasy.ToolResultContent) fantasy.StepResult {
12− var content fantasy.ResponseContent
13− for _, c := range calls {
14− content = append(content, c)
15− }
16− for _, r := range results {
17− content = append(content, r)
18− }
19− return fantasy.StepResult{
20− Response: fantasy.Response{
21− Content: content,
22− },
23− }
24−}
25−
26−// makeToolStep creates a step with a single tool call and matching text result.
27−func makeToolStep(name, input, output string) fantasy.StepResult {
28− callID := fmt.Sprintf("call_%s_%s", name, input)
29− return makeStep(
30− []fantasy.ToolCallContent{
31− {ToolCallID: callID, ToolName: name, Input: input},
32− },
33− []fantasy.ToolResultContent{
34− {ToolCallID: callID, ToolName: name, Result: fantasy.ToolResultOutputContentText{Text: output}},
35− },
36− )
37−}
38−
39−// makeEmptyStep creates a step with no tool calls (e.g. a text-only response).
40−func makeEmptyStep() fantasy.StepResult {
41− return fantasy.StepResult{
42− Response: fantasy.Response{
43− Content: fantasy.ResponseContent{
44− fantasy.TextContent{Text: "thinking..."},
45− },
46− },
47− }
48−}
49−
50−func TestHasRepeatedToolCalls(t *testing.T) {
51− t.Run("no steps", func(t *testing.T) {
52− result := hasRepeatedToolCalls(nil, 10, 5)
53− if result {
54− t.Error("expected false for empty steps")
55− }
56− })
57−
58− t.Run("fewer steps than window", func(t *testing.T) {
59− steps := make([]fantasy.StepResult, 5)
60− for i := range steps {
61− steps[i] = makeToolStep("read", `{"file":"a.go"}`, "content")
62− }
63− result := hasRepeatedToolCalls(steps, 10, 5)
64− if result {
65− t.Error("expected false when fewer steps than window size")
66− }
67− })
68−
69− t.Run("all different signatures", func(t *testing.T) {
70− steps := make([]fantasy.StepResult, 10)
71− for i := range steps {
72− steps[i] = makeToolStep("tool", fmt.Sprintf(`{"i":%d}`, i), fmt.Sprintf("result-%d", i))
73− }
74− result := hasRepeatedToolCalls(steps, 10, 5)
75− if result {
76− t.Error("expected false when all signatures are different")
77− }
78− })
79−
80− t.Run("exact repeat at threshold not detected", func(t *testing.T) {
81− // maxRepeats=5 means > 5 is needed, so exactly 5 should return false
82− steps := make([]fantasy.StepResult, 10)
83− for i := range 5 {
84− steps[i] = makeToolStep("read", `{"file":"a.go"}`, "content")
85− }
86− for i := 5; i < 10; i++ {
87− steps[i] = makeToolStep("tool", fmt.Sprintf(`{"i":%d}`, i), fmt.Sprintf("result-%d", i))
88− }
89− result := hasRepeatedToolCalls(steps, 10, 5)
90− if result {
91− t.Error("expected false when count equals maxRepeats (threshold is >)")
92− }
93− })
94−
95− t.Run("loop detected", func(t *testing.T) {
96− // 6 identical steps in a window of 10 with maxRepeats=5 → detected
97− steps := make([]fantasy.StepResult, 10)
98− for i := range 6 {
99− steps[i] = makeToolStep("read", `{"file":"a.go"}`, "content")
100− }
101− for i := 6; i < 10; i++ {
102− steps[i] = makeToolStep("tool", fmt.Sprintf(`{"i":%d}`, i), fmt.Sprintf("result-%d", i))
103− }
104− result := hasRepeatedToolCalls(steps, 10, 5)
105− if !result {
106− t.Error("expected true when same signature appears more than maxRepeats times")
107− }
108− })
109−
110− t.Run("steps without tool calls are skipped", func(t *testing.T) {
111− // Mix of tool steps and empty steps — empty ones should not affect counts
112− steps := make([]fantasy.StepResult, 10)
113− for i := range 4 {
114− steps[i] = makeToolStep("read", `{"file":"a.go"}`, "content")
115− }
116− for i := 4; i < 8; i++ {
117− steps[i] = makeEmptyStep()
118− }
119− for i := 8; i < 10; i++ {
120− steps[i] = makeToolStep("write", `{"file":"b.go"}`, "ok")
121− }
122− result := hasRepeatedToolCalls(steps, 10, 5)
123− if result {
124− t.Error("expected false: only 4 repeated tool calls, empty steps should be skipped")
125− }
126− })
127−
128− t.Run("multiple different patterns alternating", func(t *testing.T) {
129− // Two patterns alternating: each appears 5 times — not above threshold
130− steps := make([]fantasy.StepResult, 10)
131− for i := range steps {
132− if i%2 == 0 {
133− steps[i] = makeToolStep("read", `{"file":"a.go"}`, "content-a")
134− } else {
135− steps[i] = makeToolStep("write", `{"file":"b.go"}`, "content-b")
136− }
137− }
138− result := hasRepeatedToolCalls(steps, 10, 5)
139− if result {
140− t.Error("expected false: two patterns each appearing 5 times (not > 5)")
141− }
142− })
143−}
144−
145−func TestGetToolInteractionSignature(t *testing.T) {
146− t.Run("empty content returns empty string", func(t *testing.T) {
147− sig := getToolInteractionSignature(fantasy.ResponseContent{})
148− if sig != 0 {
149− t.Errorf("expected zero signature, got %d", sig)
150− }
151− })
152−
153− t.Run("text only content returns zero signature", func(t *testing.T) {
154− content := fantasy.ResponseContent{
155− fantasy.TextContent{Text: "hello"},
156− }
157− sig := getToolInteractionSignature(content)
158− if sig != 0 {
159− t.Errorf("expected zero signature, got %d", sig)
160− }
161− })
162−
163− t.Run("tool call with result produces signature", func(t *testing.T) {
164− content := fantasy.ResponseContent{
165− fantasy.ToolCallContent{ToolCallID: "1", ToolName: "read", Input: `{"file":"a.go"}`},
166− fantasy.ToolResultContent{ToolCallID: "1", ToolName: "read", Result: fantasy.ToolResultOutputContentText{Text: "content"}},
167− }
168− sig := getToolInteractionSignature(content)
169− if sig == 0 {
170− t.Error("expected non-zero signature")
171− }
172− })
173−
174− t.Run("same interactions produce same signature", func(t *testing.T) {
175− content1 := fantasy.ResponseContent{
176− fantasy.ToolCallContent{ToolCallID: "1", ToolName: "read", Input: `{"file":"a.go"}`},
177− fantasy.ToolResultContent{ToolCallID: "1", ToolName: "read", Result: fantasy.ToolResultOutputContentText{Text: "content"}},
178− }
179− content2 := fantasy.ResponseContent{
180− fantasy.ToolCallContent{ToolCallID: "2", ToolName: "read", Input: `{"file":"a.go"}`},
181− fantasy.ToolResultContent{ToolCallID: "2", ToolName: "read", Result: fantasy.ToolResultOutputContentText{Text: "content"}},
182− }
183− sig1 := getToolInteractionSignature(content1)
184− sig2 := getToolInteractionSignature(content2)
185− if sig1 != sig2 {
186− t.Errorf("expected same signature for same interactions, got %d and %d", sig1, sig2)
187− }
188− })
189−
190− t.Run("different inputs produce different signatures", func(t *testing.T) {
191− content1 := fantasy.ResponseContent{
192− fantasy.ToolCallContent{ToolCallID: "1", ToolName: "read", Input: `{"file":"a.go"}`},
193− fantasy.ToolResultContent{ToolCallID: "1", ToolName: "read", Result: fantasy.ToolResultOutputContentText{Text: "content"}},
194− }
195− content2 := fantasy.ResponseContent{
196− fantasy.ToolCallContent{ToolCallID: "1", ToolName: "read", Input: `{"file":"b.go"}`},
197− fantasy.ToolResultContent{ToolCallID: "1", ToolName: "read", Result: fantasy.ToolResultOutputContentText{Text: "content"}},
198− }
199− sig1 := getToolInteractionSignature(content1)
200− sig2 := getToolInteractionSignature(content2)
201− if sig1 == sig2 {
202− t.Error("expected different signatures for different inputs")
203− }
204− })
205−}
internal/agent/notify/notify.godeleted−63
@@ -1,63 +0,0 @@
1−// Package notify defines domain notification types for agent events.
2−// These types are decoupled from UI concerns so the agent can publish
3−// events without importing UI packages.
4−package notify
5−
6−// Type identifies the kind of agent notification.
7−type Type string
8−
9−const (
10− // TypeAgentFinished indicates the agent has completed its turn.
11− TypeAgentFinished Type = "agent_finished"
12− // TypeReAuthenticate indicates the agent encountered an
13− // authentication error and the user needs to re-authenticate.
14− TypeReAuthenticate Type = "re_authenticate"
15− // TypeAgentError indicates the agent's turn terminated with an
16− // error. The error text is carried in Notification.Message.
17− TypeAgentError Type = "error"
18−)
19−
20−// Notification represents a domain event published by the agent.
21−type Notification struct {
22− SessionID string
23− SessionTitle string
24− Type Type
25− ProviderID string
26− // RunID, when non-empty, is the caller-supplied correlator
27− // (proto.AgentMessage.RunID) for the run that produced this
28− // notification. It lets observers attribute a TypeAgentError to a
29− // specific request rather than to any in-flight run on the
30− // session. Empty when no caller set one.
31− RunID string
32− // Message carries the error text for TypeAgentError. Other
33− // notification types ignore it.
34− Message string
35−}
36−
37−// RunComplete is the authoritative end-of-run signal for a session.
38−// It is published exactly once per top-level agent run (per
39−// [sessionAgent.Run] invocation that actually executed) after all
40−// message updates for the turn have been flushed via
41−// message.Service.FlushAll. Carries the final assistant text and
42−// message ID so non-interactive clients can reconcile stdout even if
43−// SSE events arrive out of order or are dropped by the broker. Error
44−// is non-empty when the run terminated with an error; Cancelled is
45−// true when the run terminated due to context cancellation. The two
46−// are mutually exclusive in the success case but may overlap when a
47−// cancel triggers a downstream error.
48−//
49−// RunID identifies the specific request that produced this event.
50−// It is the value the caller set on `proto.AgentMessage.RunID` (or
51−// equivalently propagated via agent.WithRunID on the context that
52−// reaches the coordinator); empty when no caller set one. Filtering
53−// by RunID lets a client correlate a SendMessage call with its
54−// terminal event even when the session is busy and other turns are
55−// finishing on the same session.
56−type RunComplete struct {
57− SessionID string
58− RunID string
59− MessageID string
60− Text string
61− Error string
62− Cancelled bool
63−}
internal/agent/prompt/prompt.go+39−85
@@ -4,7 +4,6 @@ import (
44 "cmp"
55 "context"
66 "fmt"
7− "log/slog"
87 "os"
98 "path/filepath"
109 "runtime"
@@ -13,10 +12,8 @@ import (
1312 "time"
1413
1514 "github.com/charmbracelet/crush/internal/config"
16− "github.com/charmbracelet/crush/internal/filepathext"
1715 "github.com/charmbracelet/crush/internal/home"
1816 "github.com/charmbracelet/crush/internal/shell"
19− "github.com/charmbracelet/crush/internal/skills"
2017)
2118
2219// Prompt represents a template-based prompt generator.
@@ -29,17 +26,15 @@ type Prompt struct {
2926}
3027
3128type PromptDat struct {
32− Provider string
33− Model string
34− Config config.Config
35− WorkingDir string
36− IsGitRepo bool
37− Platform string
38− Date string
39− GitStatus string
40− ContextFiles []ContextFile
41− GlobalContextFiles []ContextFile
42− AvailSkillXML string
29+ Provider string
30+ Model string
31+ Config config.Config
32+ WorkingDir string
33+ IsGitRepo bool
34+ Platform string
35+ Date string
36+ GitStatus string
37+ ContextFiles []ContextFile
4338}
4439
4540type ContextFile struct {
@@ -79,13 +74,13 @@ func NewPrompt(name, promptTemplate string, opts ...Option) (*Prompt, error) {
7974 return p, nil
8075}
8176
82−func (p *Prompt) Build(ctx context.Context, provider, model string, store *config.ConfigStore) (string, error) {
77+func (p *Prompt) Build(ctx context.Context, provider, model string, cfg config.Config) (string, error) {
8378 t, err := template.New(p.name).Parse(p.template)
8479 if err != nil {
8580 return "", fmt.Errorf("parsing template: %w", err)
8681 }
8782 var sb strings.Builder
88− d, err := p.promptData(ctx, provider, model, store)
83+ d, err := p.promptData(ctx, provider, model, cfg)
8984 if err != nil {
9085 return "", err
9186 }
@@ -107,15 +102,18 @@ func processFile(filePath string) *ContextFile {
107102 }
108103}
109104
110−func processContextPath(p string, store *config.ConfigStore) []ContextFile {
105+func processContextPath(p string, cfg config.Config) []ContextFile {
111106 var contexts []ContextFile
112− fullPath := filepathext.SmartJoin(store.WorkingDir(), p)
107+ fullPath := p
108+ if !filepath.IsAbs(p) {
109+ fullPath = filepath.Join(cfg.WorkingDir(), p)
110+ }
113111 info, err := os.Stat(fullPath)
114112 if err != nil {
115113 return contexts
116114 }
117115 if info.IsDir() {
118− _ = filepath.WalkDir(fullPath, func(path string, d os.DirEntry, err error) error {
116+ filepath.WalkDir(fullPath, func(path string, d os.DirEntry, err error) error {
119117 if err != nil {
120118 return err
121119 }
@@ -136,11 +134,11 @@ func processContextPath(p string, store *config.ConfigStore) []ContextFile {
136134}
137135
138136// expandPath expands ~ and environment variables in file paths
139−func expandPath(path string, store *config.ConfigStore) string {
137+func expandPath(path string, cfg config.Config) string {
140138 path = home.Long(path)
141139 // Handle environment variable expansion using the same pattern as config
142140 if strings.HasPrefix(path, "$") {
143− if expanded, err := store.Resolver().ResolveValue(path); err == nil {
141+ if expanded, err := cfg.Resolver().ResolveValue(path); err == nil {
144142 path = expanded
145143 }
146144 }
@@ -148,86 +146,42 @@ func expandPath(path string, store *config.ConfigStore) string {
148146 return path
149147}
150148
151−// loadContextFiles loads and deduplicates context files from a list of paths.
152−func loadContextFiles(paths []string, store *config.ConfigStore) map[string][]ContextFile {
149+func (p *Prompt) promptData(ctx context.Context, provider, model string, cfg config.Config) (PromptDat, error) {
150+ workingDir := cmp.Or(p.workingDir, cfg.WorkingDir())
151+ platform := cmp.Or(p.platform, runtime.GOOS)
152+
153153 files := map[string][]ContextFile{}
154− for _, pth := range paths {
155− expanded := expandPath(pth, store)
154+
155+ for _, pth := range cfg.Options.ContextPaths {
156+ expanded := expandPath(pth, cfg)
156157 pathKey := strings.ToLower(expanded)
157158 if _, ok := files[pathKey]; ok {
158159 continue
159160 }
160− files[pathKey] = processContextPath(expanded, store)
161− }
162− return files
163−}
164−
165−func (p *Prompt) promptData(ctx context.Context, provider, model string, store *config.ConfigStore) (PromptDat, error) {
166− workingDir := cmp.Or(p.workingDir, store.WorkingDir())
167− platform := cmp.Or(p.platform, runtime.GOOS)
168−
169− cfg := store.Config()
170− contextFiles := loadContextFiles(cfg.Options.ContextPaths, store)
171− globalContextFiles := loadContextFiles(cfg.Options.GlobalContextPaths, store)
172−
173− // Discover and load skills metadata.
174− var availSkillXML string
175−
176− // Start with builtin skills.
177− allSkills := skills.DiscoverBuiltin()
178− builtinNames := make(map[string]bool, len(allSkills))
179− for _, s := range allSkills {
180− builtinNames[s.Name] = true
161+ content := processContextPath(expanded, cfg)
162+ files[pathKey] = content
181163 }
182164
183− // Discover user skills from configured paths.
184− if len(cfg.Options.SkillsPaths) > 0 {
185− expandedPaths := make([]string, 0, len(cfg.Options.SkillsPaths))
186− for _, pth := range cfg.Options.SkillsPaths {
187− expandedPaths = append(expandedPaths, expandPath(pth, store))
188− }
189− for _, userSkill := range skills.Discover(expandedPaths) {
190− if builtinNames[userSkill.Name] {
191− slog.Warn("User skill overrides builtin skill", "name", userSkill.Name)
192− }
193− allSkills = append(allSkills, userSkill)
194− }
195− }
196−
197− // Deduplicate: user skills override builtins with the same name.
198− allSkills = skills.Deduplicate(allSkills)
199−
200− // Filter out disabled skills.
201− allSkills = skills.Filter(allSkills, cfg.Options.DisabledSkills)
202−
203− if len(allSkills) > 0 {
204− availSkillXML = skills.ToPromptXML(allSkills)
205− }
206−
207− isGit := isGitRepo(store.WorkingDir())
165+ isGit := isGitRepo(cfg.WorkingDir())
208166 data := PromptDat{
209− Provider: provider,
210− Model: model,
211− Config: *cfg,
212− WorkingDir: filepath.ToSlash(workingDir),
213− IsGitRepo: isGit,
214− Platform: platform,
215− Date: p.now().Format("1/2/2006"),
216− AvailSkillXML: availSkillXML,
167+ Provider: provider,
168+ Model: model,
169+ Config: cfg,
170+ WorkingDir: filepath.ToSlash(workingDir),
171+ IsGitRepo: isGit,
172+ Platform: platform,
173+ Date: p.now().Format("1/2/2006"),
217174 }
218175 if isGit {
219176 var err error
220− data.GitStatus, err = getGitStatus(ctx, store.WorkingDir())
177+ data.GitStatus, err = getGitStatus(ctx, cfg.WorkingDir())
221178 if err != nil {
222179 return PromptDat{}, err
223180 }
224181 }
225182
226− for _, files := range contextFiles {
227− data.ContextFiles = append(data.ContextFiles, files...)
228− }
229− for _, files := range globalContextFiles {
230− data.GlobalContextFiles = append(data.GlobalContextFiles, files...)
183+ for _, contextFiles := range files {
184+ data.ContextFiles = append(data.ContextFiles, contextFiles...)
231185 }
232186 return data, nil
233187}
internal/agent/prompts.go+1−1
@@ -33,7 +33,7 @@ func taskPrompt(opts ...prompt.Option) (*prompt.Prompt, error) {
3333 return systemPrompt, nil
3434}
3535
36−func InitializePrompt(cfg *config.ConfigStore) (string, error) {
36+func InitializePrompt(cfg config.Config) (string, error) {
3737 systemPrompt, err := prompt.NewPrompt("initialize", string(initializePromptTmpl))
3838 if err != nil {
3939 return "", err
internal/agent/queued_runid_test.godeleted−181
@@ -1,181 +0,0 @@
1−package agent
2−
3−import (
4− "context"
5− "errors"
6− "sync/atomic"
7− "testing"
8− "time"
9−
10− "charm.land/catwalk/pkg/catwalk"
11− "charm.land/fantasy"
12− "github.com/charmbracelet/crush/internal/agent/notify"
13− "github.com/charmbracelet/crush/internal/message"
14− "github.com/charmbracelet/crush/internal/pubsub"
15− "github.com/stretchr/testify/require"
16−)
17−
18−// gatedStreamModel streams a single text part followed by a clean finish,
19−// but blocks the very first Stream call until its gate is released. That
20−// lets a test hold a run "active" (past PrepareStep, inside Stream) just
21−// long enough to enqueue a follow-up prompt behind the busy session.
22−// Subsequent Stream calls (e.g. the recursive run draining the queue)
23−// proceed immediately.
24−type gatedStreamModel struct {
25− text string
26− gate chan struct{}
27− entered chan struct{}
28− calls atomic.Int64
29−}
30−
31−func (m *gatedStreamModel) Provider() string { return "fake" }
32−func (m *gatedStreamModel) Model() string { return "fake-model" }
33−
34−func (m *gatedStreamModel) Generate(ctx context.Context, call fantasy.Call) (*fantasy.Response, error) {
35− return &fantasy.Response{
36− Content: fantasy.ResponseContent{fantasy.TextContent{Text: m.text}},
37− FinishReason: fantasy.FinishReasonStop,
38− }, nil
39−}
40−
41−func (m *gatedStreamModel) Stream(ctx context.Context, call fantasy.Call) (fantasy.StreamResponse, error) {
42− if m.calls.Add(1) == 1 {
43− close(m.entered)
44− select {
45− case <-m.gate:
46− case <-ctx.Done():
47− }
48− }
49− text := m.text
50− return func(yield func(fantasy.StreamPart) bool) {
51− if !yield(fantasy.StreamPart{Type: fantasy.StreamPartTypeTextStart, ID: "1"}) {
52− return
53− }
54− if !yield(fantasy.StreamPart{Type: fantasy.StreamPartTypeTextDelta, ID: "1", Delta: text}) {
55− return
56− }
57− if !yield(fantasy.StreamPart{Type: fantasy.StreamPartTypeTextEnd, ID: "1"}) {
58− return
59− }
60− yield(fantasy.StreamPart{Type: fantasy.StreamPartTypeFinish, FinishReason: fantasy.FinishReasonStop})
61− }, nil
62−}
63−
64−func (m *gatedStreamModel) GenerateObject(ctx context.Context, call fantasy.ObjectCall) (*fantasy.ObjectResponse, error) {
65− return nil, errors.New("not implemented")
66−}
67−
68−func (m *gatedStreamModel) StreamObject(ctx context.Context, call fantasy.ObjectCall) (fantasy.ObjectStreamResponse, error) {
69− return nil, errors.New("not implemented")
70−}
71−
72−// TestRun_QueuedRunIDPromptRunsRecursivelyAndPublishesRunComplete is the
73−// end-to-end proof of fix 2: a prompt carrying a RunID that is queued
74−// behind a busy session must NOT be silently folded into the active turn.
75−// It runs as its own turn via the recursive run path and publishes its
76−// own terminal RunComplete, so a `crush run` caller blocking on that
77−// RunID does not hang. The active turn keeps its own RunComplete too.
78−func TestRun_QueuedRunIDPromptRunsRecursivelyAndPublishesRunComplete(t *testing.T) {
79− t.Parallel()
80−
81− env := testEnv(t)
82− broker := pubsub.NewBroker[notify.RunComplete]()
83− t.Cleanup(broker.Shutdown)
84−
85− large := &gatedStreamModel{
86− text: "done",
87− gate: make(chan struct{}),
88− entered: make(chan struct{}),
89− }
90− small := &finishStreamModel{text: "title"}
91−
92− sa := NewSessionAgent(SessionAgentOptions{
93− LargeModel: Model{Model: large, CatwalkCfg: catwalk.Model{ContextWindow: 200000, DefaultMaxTokens: 10000}},
94− SmallModel: Model{Model: small, CatwalkCfg: catwalk.Model{ContextWindow: 200000, DefaultMaxTokens: 10000}},
95− IsYolo: true,
96− Sessions: env.sessions,
97− Messages: env.messages,
98− RunComplete: broker,
99− }).(*sessionAgent)
100−
101− sess, err := env.sessions.Create(t.Context(), "session")
102− require.NoError(t, err)
103−
104− subCtx, subCancel := context.WithCancel(t.Context())
105− defer subCancel()
106− ch := broker.Subscribe(subCtx)
107−
108− // Start the main turn; it blocks inside Stream once active.
109− mainDone := make(chan error, 1)
110− go func() {
111− _, runErr := sa.Run(t.Context(), SessionAgentCall{
112− SessionID: sess.ID,
113− RunID: "run-main",
114− Prompt: "main",
115− })
116− mainDone <- runErr
117− }()
118−
119− // Wait until the main turn is active (inside Stream).
120− select {
121− case <-large.entered:
122− case <-time.After(5 * time.Second):
123− t.Fatal("main run never entered Stream")
124− }
125− require.True(t, sa.IsSessionBusy(sess.ID), "main run must be active before enqueueing the follow-up")
126−
127− // Enqueue a RunID-bearing follow-up behind the busy session.
128− res, err := sa.Run(t.Context(), SessionAgentCall{
129− SessionID: sess.ID,
130− RunID: "run-follow",
131− Prompt: "follow",
132− })
133− require.NoError(t, err)
134− require.Nil(t, res, "a busy-session follow-up must enqueue and return (nil, nil)")
135− require.Equal(t, 1, sa.QueuedPrompts(sess.ID), "the follow-up must be queued, not folded")
136−
137− // Release the main turn so it completes and hands off to the queue.
138− close(large.gate)
139− require.NoError(t, <-mainDone)
140−
141− // Both turns must publish their own terminal RunComplete.
142− got := map[string]notify.RunComplete{}
143− deadline := time.After(5 * time.Second)
144− for len(got) < 2 {
145− select {
146− case ev := <-ch:
147− got[ev.Payload.RunID] = ev.Payload
148− case <-deadline:
149− t.Fatalf("timed out waiting for both RunCompletes; got %v", got)
150− }
151− }
152−
153− main, ok := got["run-main"]
154− require.True(t, ok, "the active turn must publish its own RunComplete")
155− require.Empty(t, main.Error)
156− require.False(t, main.Cancelled)
157−
158− follow, ok := got["run-follow"]
159− require.True(t, ok,
160− "the queued RunID prompt must publish its own RunComplete instead of being folded silently")
161− require.Empty(t, follow.Error)
162− require.False(t, follow.Cancelled)
163− require.Equal(t, "done", follow.Text, "the queued prompt ran as its own turn")
164−
165− // Two distinct assistant turns prove the follow-up was not folded.
166− msgs, err := env.messages.List(t.Context(), sess.ID)
167− require.NoError(t, err)
168− var assistants, follows int
169− for _, m := range msgs {
170− switch m.Role {
171− case message.Assistant:
172− assistants++
173− case message.User:
174− if m.Content().String() == "follow" {
175− follows++
176− }
177− }
178− }
179− require.Equal(t, 2, assistants, "the active turn and the recursive turn each produce one assistant message")
180− require.Equal(t, 1, follows, "the follow-up prompt is its own user turn")
181−}
internal/agent/run_complete_test.godeleted−322
@@ -1,322 +0,0 @@
1−package agent
2−
3−import (
4− "context"
5− "testing"
6− "time"
7−
8− "github.com/charmbracelet/crush/internal/agent/notify"
9− "github.com/charmbracelet/crush/internal/pubsub"
10− "github.com/stretchr/testify/require"
11−)
12−
13−// TestSessionAgentRun_QueueStripsOnComplete verifies that when a Run
14−// call is enqueued (because the session is already busy), the
15−// OnComplete hook is NOT propagated onto the queued copy. The hook
16−// belongs to the caller's retry/coalesce scope (typically
17−// coordinator.Run) which has already returned by the time the queue
18−// drains; carrying it forward would silently funnel the terminal
19−// event into a closure nobody reads, and subscribers (`crush run`)
20−// would hang waiting for a RunComplete that never publishes.
21−func TestSessionAgentRun_QueueStripsOnComplete(t *testing.T) {
22− t.Parallel()
23−
24− env := testEnv(t)
25− a := NewSessionAgent(SessionAgentOptions{
26− Sessions: env.sessions,
27− Messages: env.messages,
28− }).(*sessionAgent)
29−
30− const sessionID = "queued-session"
31− // Mark the session as busy so Run takes the queue branch
32− // without needing a real model.
33− a.activeRequests.Set(sessionID, func() {})
34−
35− var called bool
36− hook := func(notify.RunComplete) { called = true }
37−
38− res, err := a.Run(t.Context(), SessionAgentCall{
39− SessionID: sessionID,
40− RunID: "run-xyz",
41− Prompt: "queued prompt",
42− OnComplete: hook,
43− })
44− require.NoError(t, err)
45− require.Nil(t, res, "queued Run must return (nil, nil)")
46− require.False(t, called,
47− "OnComplete must not fire on the enqueue path; the caller's scope is still live")
48−
49− queued, ok := a.messageQueue.Get(sessionID)
50− require.True(t, ok)
51− require.Len(t, queued, 1)
52− require.Nil(t, queued[0].OnComplete,
53− "queued SessionAgentCall must have OnComplete stripped so the drain falls back to the default broker publish")
54− require.Equal(t, "queued prompt", queued[0].Prompt,
55− "all other fields must be preserved on the queued copy")
56− require.Equal(t, "run-xyz", queued[0].RunID,
57− "RunID must be preserved on the queued copy so the drained turn's "+
58− "RunComplete still correlates with the originating SendMessage")
59−}
60−
61−// TestDrainQueueForStep_FiltersUnderDispatchLock verifies that the queue
62−// drain evaluates the per-session cancel mark while holding the dispatch
63−// mutex (canceledBySeq's documented precondition). Queued calls at or
64−// below the cancel high-water mark are dropped, calls queued after the
65−// cancel (higher seq) are folded, untracked enqueues (seq == 0) are
66−// dropped whenever any mark is present, and the queue is cleared. These
67−// calls carry no RunID, so all foldable survivors are returned for
68−// folding (the existing follow-up behavior).
69−func TestDrainQueueForStep_FiltersUnderDispatchLock(t *testing.T) {
70− t.Parallel()
71−
72− env := testEnv(t)
73− a := NewSessionAgent(SessionAgentOptions{
74− Sessions: env.sessions,
75− Messages: env.messages,
76− }).(*sessionAgent)
77−
78− const sessionID = "drain-session"
79− a.messageQueue.Set(sessionID, []SessionAgentCall{
80− {SessionID: sessionID, Prompt: "below", acceptSeq: 1},
81− {SessionID: sessionID, Prompt: "at-mark", acceptSeq: 2},
82− {SessionID: sessionID, Prompt: "after", acceptSeq: 3},
83− {SessionID: sessionID, Prompt: "untracked", acceptSeq: 0},
84− })
85− // Cancel high-water mark at seq 2: seq <= 2 and seq == 0 are covered.
86− a.cancelMark.Set(sessionID, 2)
87−
88− fold, canceledWithRunID := a.drainQueueForStep(sessionID)
89−
90− require.Len(t, fold, 1,
91− "only the follow-up queued after the cancel (seq > mark) must be folded")
92− require.Equal(t, "after", fold[0].Prompt)
93− require.Empty(t, canceledWithRunID,
94− "no dropped call carried a RunID, so none need a terminal RunComplete")
95−
96− _, ok := a.messageQueue.Get(sessionID)
97− require.False(t, ok, "drain must clear the session message queue when nothing is kept")
98−}
99−
100−// TestDrainQueueForStep_NoMarkFoldsAllNonRunID verifies that with no
101−// cancel mark recorded, every queued call without a RunID is folded.
102−func TestDrainQueueForStep_NoMarkFoldsAllNonRunID(t *testing.T) {
103− t.Parallel()
104−
105− env := testEnv(t)
106− a := NewSessionAgent(SessionAgentOptions{
107− Sessions: env.sessions,
108− Messages: env.messages,
109− }).(*sessionAgent)
110−
111− const sessionID = "drain-nomark"
112− a.messageQueue.Set(sessionID, []SessionAgentCall{
113− {SessionID: sessionID, Prompt: "a", acceptSeq: 0},
114− {SessionID: sessionID, Prompt: "b", acceptSeq: 5},
115− })
116−
117− fold, canceledWithRunID := a.drainQueueForStep(sessionID)
118− require.Len(t, fold, 2, "no cancel mark means all non-RunID queued calls are folded")
119− require.Empty(t, canceledWithRunID)
120−}
121−
122−// TestDrainQueueForStep_KeepsRunIDPromptsQueued is the core of fix 2: a
123−// queued prompt that carries a RunID must NOT be folded into the active
124−// turn. Folding it would silently absorb it into another turn and never
125−// publish a RunComplete for its RunID, hanging a `crush run` caller that
126−// blocks on that event. Such prompts are left in the queue so the
127−// recursive run path gives each its own turn and its own RunComplete.
128−// Non-RunID prompts are still folded.
129−func TestDrainQueueForStep_KeepsRunIDPromptsQueued(t *testing.T) {
130− t.Parallel()
131−
132− env := testEnv(t)
133− a := NewSessionAgent(SessionAgentOptions{
134− Sessions: env.sessions,
135− Messages: env.messages,
136− }).(*sessionAgent)
137−
138− const sessionID = "drain-runid"
139− a.messageQueue.Set(sessionID, []SessionAgentCall{
140− {SessionID: sessionID, Prompt: "fold-me", acceptSeq: 1},
141− {SessionID: sessionID, RunID: "run-a", Prompt: "keep-me", acceptSeq: 2},
142− {SessionID: sessionID, RunID: "run-b", Prompt: "keep-me-too", acceptSeq: 3},
143− })
144−
145− fold, canceledWithRunID := a.drainQueueForStep(sessionID)
146−
147− require.Len(t, fold, 1, "only the non-RunID prompt is folded into the active turn")
148− require.Equal(t, "fold-me", fold[0].Prompt)
149− require.Empty(t, canceledWithRunID)
150−
151− kept, ok := a.messageQueue.Get(sessionID)
152− require.True(t, ok, "RunID-bearing prompts must remain queued for the recursive run path")
153− require.Len(t, kept, 2)
154− require.Equal(t, "run-a", kept[0].RunID)
155− require.Equal(t, "run-b", kept[1].RunID)
156−}
157−
158−// TestDrainQueueForStep_ReportsCanceledRunIDDrops verifies that a queued
159−// prompt carrying a RunID that is dropped because a cancel covers it is
160−// reported in canceledWithRunID so the caller can publish its terminal
161−// cancelled RunComplete. A canceled prompt without a RunID is dropped
162−// silently as before.
163−func TestDrainQueueForStep_ReportsCanceledRunIDDrops(t *testing.T) {
164− t.Parallel()
165−
166− env := testEnv(t)
167− a := NewSessionAgent(SessionAgentOptions{
168− Sessions: env.sessions,
169− Messages: env.messages,
170− }).(*sessionAgent)
171−
172− const sessionID = "drain-cancel-runid"
173− a.messageQueue.Set(sessionID, []SessionAgentCall{
174− {SessionID: sessionID, RunID: "run-canceled", Prompt: "canceled", acceptSeq: 1},
175− {SessionID: sessionID, Prompt: "canceled-no-runid", acceptSeq: 1},
176− {SessionID: sessionID, RunID: "run-survives", Prompt: "survives", acceptSeq: 5},
177− })
178− a.cancelMark.Set(sessionID, 2)
179−
180− fold, canceledWithRunID := a.drainQueueForStep(sessionID)
181−
182− require.Empty(t, fold, "no uncanceled non-RunID prompts to fold")
183− require.Len(t, canceledWithRunID, 1,
184− "only the dropped RunID-bearing prompt needs a terminal RunComplete")
185− require.Equal(t, "run-canceled", canceledWithRunID[0].RunID)
186−
187− kept, ok := a.messageQueue.Get(sessionID)
188− require.True(t, ok)
189− require.Len(t, kept, 1, "the uncanceled RunID prompt stays queued")
190− require.Equal(t, "run-survives", kept[0].RunID)
191−}
192−
193−// TestRunCompletePublisher_MustDeliverOverTakesPublish exercises the
194−// pubsub.Publisher interface change end-to-end: a Broker is the only
195−// concrete Publisher implementation and must satisfy both Publish and
196−// PublishMustDeliver. The coordinator's final RunComplete emit relies
197−// on PublishMustDeliver to apply bounded-blocking semantics so a
198−// momentarily-full subscriber buffer can't silently drop the
199−// authoritative end-of-run event.
200−func TestRunCompletePublisher_MustDeliverOverTakesPublish(t *testing.T) {
201− t.Parallel()
202−
203− broker := pubsub.NewBroker[notify.RunComplete]()
204− t.Cleanup(broker.Shutdown)
205−
206− // Subscribe before publishing so the event is delivered.
207− ctx, cancel := context.WithCancel(t.Context())
208− defer cancel()
209− ch := broker.Subscribe(ctx)
210−
211− rc := notify.RunComplete{SessionID: "S", MessageID: "m", Text: "ok"}
212− var pub pubsub.Publisher[notify.RunComplete] = broker
213− pub.PublishMustDeliver(t.Context(), pubsub.UpdatedEvent, rc)
214−
215− select {
216− case got := <-ch:
217− require.Equal(t, rc, got.Payload)
218− case <-time.After(time.Second):
219− t.Fatal("PublishMustDeliver did not deliver event")
220− }
221−}
222−
223−// requireSingleCancelledRunComplete reads exactly one RunComplete from ch,
224−// asserts it is the cancelled terminal event for runID, and verifies no
225−// second event arrives. This observes the published pubsub event rather
226−// than internal bookkeeping, which is the contract a `crush run` caller
227−// blocking on the broker actually relies on.
228−func requireSingleCancelledRunComplete(t *testing.T, ch <-chan pubsub.Event[notify.RunComplete], sessionID, runID string) {
229− t.Helper()
230− select {
231− case ev := <-ch:
232− require.Equal(t, runID, ev.Payload.RunID,
233− "the published RunComplete must carry the dropped queued prompt's RunID")
234− require.Equal(t, sessionID, ev.Payload.SessionID)
235− require.True(t, ev.Payload.Cancelled,
236− "a dropped queued prompt must publish a cancelled RunComplete")
237− case <-time.After(5 * time.Second):
238− t.Fatal("timed out waiting for the cancelled RunComplete")
239− }
240− select {
241− case extra := <-ch:
242− t.Fatalf("expected exactly one RunComplete, got a second: %+v", extra.Payload)
243− case <-time.After(100 * time.Millisecond):
244− }
245−}
246−
247−// TestCancel_QueuedRunIDPromptPublishesCancelledRunComplete proves the
248−// terminal-event behavior end-to-end: a RunID-bearing prompt sitting in
249−// the queue that is canceled while queued (via the public Cancel path,
250−// which routes through clearQueueAndNotify -> publishCanceledQueueDrops)
251−// must emit exactly one cancelled RunComplete on the broker for its
252−// RunID. A queued prompt without a RunID is dropped silently. This is the
253−// coverage the earlier drain test lacked: it asserted the returned
254−// bookkeeping slice, not the published event a `crush run` caller awaits.
255−func TestCancel_QueuedRunIDPromptPublishesCancelledRunComplete(t *testing.T) {
256− t.Parallel()
257−
258− env := testEnv(t)
259− broker := pubsub.NewBroker[notify.RunComplete]()
260− t.Cleanup(broker.Shutdown)
261−
262− a := NewSessionAgent(SessionAgentOptions{
263− Sessions: env.sessions,
264− Messages: env.messages,
265− RunComplete: broker,
266− }).(*sessionAgent)
267−
268− subCtx, subCancel := context.WithCancel(t.Context())
269− defer subCancel()
270− ch := broker.Subscribe(subCtx)
271−
272− const sessionID = "cancel-queued-runid"
273− a.messageQueue.Set(sessionID, []SessionAgentCall{
274− {SessionID: sessionID, Prompt: "no-runid", acceptSeq: 1},
275− {SessionID: sessionID, RunID: "run-queued", Prompt: "queued", acceptSeq: 2},
276− })
277−
278− a.Cancel(sessionID)
279−
280− requireSingleCancelledRunComplete(t, ch, sessionID, "run-queued")
281−
282− _, ok := a.messageQueue.Get(sessionID)
283− require.False(t, ok, "Cancel must clear the queue")
284−}
285−
286−// TestDrainQueueForStep_DroppedRunIDPublishesCancelledRunComplete drives
287−// the production drain sequence (drainQueueForStep then
288−// publishCanceledQueueDrops, mirroring the PrepareStep handoff) and
289−// asserts the dropped RunID-bearing prompt actually publishes exactly one
290−// cancelled RunComplete on the broker. The companion bookkeeping test
291−// covers the returned slice; this one covers the observable terminal
292−// event.
293−func TestDrainQueueForStep_DroppedRunIDPublishesCancelledRunComplete(t *testing.T) {
294− t.Parallel()
295−
296− env := testEnv(t)
297− broker := pubsub.NewBroker[notify.RunComplete]()
298− t.Cleanup(broker.Shutdown)
299−
300− a := NewSessionAgent(SessionAgentOptions{
301− Sessions: env.sessions,
302− Messages: env.messages,
303− RunComplete: broker,
304− }).(*sessionAgent)
305−
306− subCtx, subCancel := context.WithCancel(t.Context())
307− defer subCancel()
308− ch := broker.Subscribe(subCtx)
309−
310− const sessionID = "drain-drop-runid"
311− a.messageQueue.Set(sessionID, []SessionAgentCall{
312− {SessionID: sessionID, RunID: "run-dropped", Prompt: "dropped", acceptSeq: 1},
313− {SessionID: sessionID, Prompt: "dropped-no-runid", acceptSeq: 1},
314− })
315− a.cancelMark.Set(sessionID, 2)
316−
317− _, canceledWithRunID := a.drainQueueForStep(sessionID)
318− require.Len(t, canceledWithRunID, 1)
319− a.publishCanceledQueueDrops(canceledWithRunID)
320−
321− requireSingleCancelledRunComplete(t, ch, sessionID, "run-dropped")
322−}
internal/agent/run_marker.godeleted−52
@@ -1,52 +0,0 @@
1−package agent
2−
3−import (
4− "context"
5− "sync/atomic"
6−)
7−
8−// runCompleteMarkerKey is the unexported context key carrying a
9−// [runCompleteMarker] from the dispatch boundary (backend.runAgent)
10−// down into the coordinator. It lets the dispatcher learn whether the
11−// coordinator already published the authoritative terminal
12−// notify.RunComplete for the run, so a fallback terminal event is only
13−// emitted when one is actually missing (e.g. an error returned before
14−// sessionAgent.Run ever executed). It avoids a breaking change to the
15−// Coordinator interface.
16−type runCompleteMarkerKey struct{}
17−
18−// runCompleteMarker records whether a terminal RunComplete has been
19−// published for a run. It is shared by pointer through the context so
20−// a publish deep in the call stack is observable by the dispatcher
21−// after the call returns.
22−type runCompleteMarker struct {
23− published atomic.Bool
24−}
25−
26−// WithRunCompleteMarker returns ctx carrying a fresh marker the
27−// coordinator can flag via [MarkRunCompletePublished] once it emits the
28−// run's terminal RunComplete. Callers read the result with
29−// [RunCompletePublished]. Attaching the marker is optional: code paths
30−// without one simply skip the dedup signal.
31−func WithRunCompleteMarker(ctx context.Context) context.Context {
32− return context.WithValue(ctx, runCompleteMarkerKey{}, &runCompleteMarker{})
33−}
34−
35−// MarkRunCompletePublished records that the authoritative terminal
36−// RunComplete has been published for the run carried by ctx. It is a
37−// no-op when no marker is present (e.g. the in-process/local Run path,
38−// which is not dispatched through backend.runAgent).
39−func MarkRunCompletePublished(ctx context.Context) {
40− if m, ok := ctx.Value(runCompleteMarkerKey{}).(*runCompleteMarker); ok {
41− m.published.Store(true)
42− }
43−}
44−
45−// RunCompletePublished reports whether [MarkRunCompletePublished] was
46−// called on ctx's marker. It returns false when no marker is present.
47−func RunCompletePublished(ctx context.Context) bool {
48− if m, ok := ctx.Value(runCompleteMarkerKey{}).(*runCompleteMarker); ok {
49− return m.published.Load()
50− }
51− return false
52−}
internal/agent/runid.godeleted−33
@@ -1,33 +0,0 @@
1−package agent
2−
3−import "context"
4−
5−// runIDContextKey is the unexported context key used to carry a
6−// caller-supplied RunID from the workspace HTTP boundary
7−// (backend.SendMessage) down into coordinator.Run without forcing a
8−// breaking change to the Coordinator.Run signature. The value is
9−// then copied onto SessionAgentCall.RunID by the coordinator so the
10−// agent's terminal RunComplete event can echo it back to the
11−// originating caller.
12−type runIDContextKey struct{}
13−
14−// WithRunID returns ctx tagged with a per-request RunID. It is the
15−// boundary helper for callers that need their SendMessage→Run
16−// terminal event to be uniquely correlatable (e.g. `crush run`
17−// against a session that may be busy). Empty runIDs are stored
18−// as-is; downstream code treats an empty RunID as "caller did not
19−// supply one" and falls back to SessionID-only correlation.
20−func WithRunID(ctx context.Context, runID string) context.Context {
21− return context.WithValue(ctx, runIDContextKey{}, runID)
22−}
23−
24−// RunIDFromContext returns the RunID set by [WithRunID], or "" if
25−// none was set or the value is not a string. Exported because the
26−// coordinator and tests in other packages need to read it; safe to
27−// call on any context.
28−func RunIDFromContext(ctx context.Context) string {
29− if v, ok := ctx.Value(runIDContextKey{}).(string); ok {
30− return v
31− }
32− return ""
33−}
internal/agent/templates/agent_tool.md+15−1
@@ -1 +1,15 @@
1−Launch a new agent that has access to the following tools: glob, grep, ls, view. When you are searching for a keyword or file and are not confident that you will find the right match on the first try, use the agent tool to perform the search for you.
1+Launch a new agent that has access to the following tools: GlobTool, GrepTool, LS, View. When you are searching for a keyword or file and are not confident that you will find the right match on the first try, use the Agent tool to perform the search for you.
2+
3+<usage>
4+- If you are searching for a keyword like "config" or "logger", or for questions like "which file does X?", the Agent tool is strongly recommended
5+- If you want to read a specific file path, use the View or GlobTool tool instead of the Agent tool, to find the match more quickly
6+- If you are searching for a specific class definition like "class Foo", use the GlobTool tool instead, to find the match more quickly
7+</usage>
8+
9+<usage_notes>
10+1. Launch multiple agents concurrently whenever possible, to maximize performance; to do that, use a single message with multiple tool uses
11+2. When the agent is done, it will return a single message back to you. The result returned by the agent is not visible to the user. To show the user the result, you should send a text message back to the user with a concise summary of the result.
12+3. Each agent invocation is stateless. You will not be able to send additional messages to the agent, nor will the agent be able to communicate with you outside of its final report. Therefore, your prompt should contain a highly detailed task description for the agent to perform autonomously and you should specify exactly what information the agent should return back to you in its final and only message to you.
13+4. The agent's outputs should generally be trusted
14+5. IMPORTANT: The agent can not use Bash, Replace, Edit, so can not modify files. If you want to use these tools, use them directly instead of going through the agent.
15+</usage_notes>
internal/agent/templates/agentic_fetch.md+64−1
@@ -1 +1,64 @@
1−Fetch a URL or search the web using an AI sub-agent that can extract, summarize, and answer questions. Slower and costlier than fetch; use fetch for raw content or API responses.
1+Fetches content from a URL or searches the web, then processes it using an AI model to extract information or answer questions.
2+
3+<when_to_use>
4+Use this tool when you need to:
5+- Search the web for information (omit the url parameter)
6+- Extract specific information from a webpage (provide a url)
7+- Answer questions about web content
8+- Summarize or analyze web pages
9+- Research topics by searching and following links
10+
11+DO NOT use this tool when:
12+- You just need raw content without analysis (use fetch instead - faster and cheaper)
13+- You want direct access to API responses or JSON (use fetch instead)
14+- You don't need the content processed or interpreted (use fetch instead)
15+</when_to_use>
16+
17+<usage>
18+- Provide a prompt describing what information you want to find or extract (required)
19+- Optionally provide a URL to fetch and analyze specific content
20+- If no URL is provided, the agent will search the web to find relevant information
21+- The tool spawns a sub-agent with web_search, web_fetch, and analysis tools
22+- Returns the agent's response about the content
23+</usage>
24+
25+<parameters>
26+- prompt: What information you want to find or extract (required)
27+- url: The URL to fetch content from (optional - if not provided, agent will search the web)
28+</parameters>
29+
30+<usage_notes>
31+- IMPORTANT: If an MCP-provided web fetch tool is available, prefer using that tool instead of this one, as it may have fewer restrictions. All MCP-provided tools start with "mcp_".
32+- When using URL mode: The URL must be a fully-formed valid URL. HTTP URLs will be automatically upgraded to HTTPS.
33+- When searching: Just provide the prompt describing what you want to find - the agent will search and fetch relevant pages.
34+- The sub-agent can perform multiple searches and fetch multiple pages to gather comprehensive information.
35+- This tool is read-only and does not modify any files.
36+- Results will be summarized if the content is very large.
37+- This tool uses AI processing and costs more tokens than the simple fetch tool.
38+</usage_notes>
39+
40+<limitations>
41+- Max response size: 5MB per page
42+- Only supports HTTP and HTTPS protocols
43+- Cannot handle authentication or cookies
44+- Some websites may block automated requests
45+- Uses additional tokens for AI processing
46+- Search results depend on DuckDuckGo availability
47+</limitations>
48+
49+<tips>
50+- Be specific in your prompt about what information you want
51+- For research tasks, omit the URL and let the agent search and follow relevant links
52+- For complex pages, ask the agent to focus on specific sections
53+- The agent has access to web_search, web_fetch, grep, and view tools
54+- If you just need raw content, use the fetch tool instead to save tokens
55+</tips>
56+
57+<examples>
58+Search for information:
59+- prompt: "What are the main new features in the latest Python release?"
60+
61+Fetch and analyze a URL:
62+- url: "https://docs.python.org/3/whatsnew/3.12.html"
63+- prompt: "Summarize the key changes in Python 3.12"
64+</examples>
internal/agent/templates/coder.md.tpl+7−55
@@ -3,26 +3,22 @@ You are Crush, a powerful AI Assistant that runs in the CLI.
33<critical_rules>
44These rules override everything else. Follow them strictly:
55
6−1. **READ THE RELEVANT CONTEXT BEFORE EDITING**: Never edit a file you haven't already read the relevant context for in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.
6+1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.
772. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.
883. **TEST AFTER CHANGES**: Run tests immediately after each modification.
994. **BE CONCISE**: Keep output concise (default <4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.
10105. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.
11−6. **NEVER COMMIT**: Unless user explicitly says "commit". When committing, follow the `<git_commits>` format from the bash tool description exactly, including any configured attribution lines.
11+6. **NEVER COMMIT**: Unless user explicitly says "commit".
12127. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.
13138. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.
14149. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.
151510. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.
161611. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.
171712. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.
18−13. **TOOL CONSTRAINTS**: Only use documented tools. Never attempt 'apply_patch' or 'apply_diff' - they don't exist. Use 'edit' or 'multiedit' instead.
19−14. **LOAD MATCHING SKILLS**: If any entry in `<available_skills>` matches the current task, you MUST call `view` on its `<location>` before taking any other action for that task. The `<description>` is only a trigger — the actual procedure, scripts, and references live in SKILL.md. Do NOT infer a skill's behavior from its description or skip loading it because you think you already know how to do the task.
20−15. **LIMIT FILE READS**: Avoid reading entire files, as they can be very large. Read only the sections you need using 'offset' and 'limit' parameters.
2118</critical_rules>
2219
2320<communication_style>
2421Keep responses minimal:
25−- ALWAYS think and respond in the same spoken language the prompt was written in.
2622- Under 4 lines of text (tool use doesn't count)
2723- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.
2824- No preamble ("Here's...", "I'll...")
@@ -134,17 +130,10 @@ Examples of autonomous decisions:
134130</decision_making>
135131
136132<editing_files>
137−**Available edit tools:**
138−- `edit` - Single find/replace in a file
139−- `multiedit` - Multiple find/replace operations in one file
140−- `write` - Create/overwrite entire file
141−
142−Never use `apply_patch` or similar - those tools don't exist.
143−
144−Critical: ALWAYS read the relevant context of files before editing them in this conversation.
133+Critical: ALWAYS read files before editing them in this conversation.
145134
146135When using edit tools:
147−1. Read the relevant context first - note the EXACT indentation (spaces vs tabs, count)
136+1. Read the file first - note the EXACT indentation (spaces vs tabs, count)
1481372. Copy the exact text including ALL whitespace, newlines, and indentation
1491383. Include 3-5 lines of context before and after the target
1501394. Verify your old_string would appear exactly once in the file
@@ -252,7 +241,7 @@ Common errors:
252241<memory_instructions>
253242Memory files store commands, preferences, and codebase info. Update them when you discover:
254243- Build/test/lint commands
255−- Code style preferences
244+- Code style preferences
256245- Important codebase patterns
257246- Useful project information
258247</memory_instructions>
@@ -301,8 +290,6 @@ After significant changes:
301290- Only use the tools you know exist.
302291
303292<bash_commands>
304−**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.
305−
306293When running non-trivial bash commands (especially those that modify the system):
307294- Briefly explain what the command does and why you're running it
308295- This ensures the user understands potentially dangerous operations
@@ -373,48 +360,13 @@ Diagnostics (lint/typecheck) included in tool output.
373360- Ignore issues in files you didn't touch (unless user asks)
374361</lsp>
375362{{end}}
376−{{- if .AvailSkillXML}}
377−
378−{{.AvailSkillXML}}
379−
380−<skills_usage>
381−The `<description>` of each skill is a TRIGGER — it tells you *when* a skill applies. It is NOT a specification of what the skill does or how to do it. The procedure, scripts, commands, references, and required flags live only in the SKILL.md body. You do not know what a skill actually does until you have read its SKILL.md.
382−
383−MANDATORY activation flow:
384−1. Scan `<available_skills>` against the current user task.
385−2. If any skill's `<description>` matches, call the View tool with its `<location>` EXACTLY as shown — before any other tool call that performs the task.
386−3. Read the entire SKILL.md and follow its instructions.
387−4. Only then execute the task, using the skill's prescribed commands/tools.
388−
389−Do NOT skip step 2 because you think you already know how to do the task. Do NOT infer a skill's behavior from its name or description. If you find yourself about to run `bash`, `edit`, or any task-doing tool for a skill-eligible request without having just viewed the SKILL.md, stop and load the skill first.
390−
391−Builtin skills (type=builtin) use virtual `crush://skills/...` location identifiers. The "crush://" prefix is NOT a URL, network address, or MCP resource — it is a special internal identifier the View tool understands natively. Pass the `<location>` verbatim to View.
392−
393−Do not use MCP tools (including read_mcp_resource) to load skills.
394−If a skill mentions scripts, references, or assets, they live in the same folder as the skill itself (e.g., scripts/, references/, assets/ subdirectories within the skill's folder).
395−</skills_usage>
396−{{end}}
397363
398364{{if .ContextFiles}}
399−# Project-Specific Context
400−Make sure to follow the instructions in the context below.
401−<project_context>
365+<memory>
402366{{range .ContextFiles}}
403367<file path="{{.Path}}">
404368{{.Content}}
405369</file>
406370{{end}}
407−</project_context>
408−{{end}}
409−{{if .GlobalContextFiles}}
410−
411−# User context
412−The following is personal content added by the user that they'd like you to follow no matter what project you're working in.
413−<user_preferences>
414−{{range .GlobalContextFiles}}
415−<file path="{{.Path}}">
416−{{.Content}}
417−</file>
418−{{end}}
419−</user_preferences>
371+</memory>
420372{{end}}
internal/agent/templates/initialize.md.tpl+3−5
@@ -2,7 +2,7 @@ Analyze this codebase and create/update **{{.Config.Options.InitializeAs}}** to
22
33**First**: Check if directory is empty or contains only config files. If so, stop and say "Directory appears empty or only contains config. Add source code first, then run this command to generate {{.Config.Options.InitializeAs}}."
44
5−**Goal**: Document what an agent needs to know to work in this codebase - commands, patterns, conventions, gotchas, overall architecture, how components fit together
5+**Goal**: Document what an agent needs to know to work in this codebase - commands, patterns, conventions, gotchas.
66
77**Discovery process**:
88
@@ -10,20 +10,18 @@ Analyze this codebase and create/update **{{.Config.Options.InitializeAs}}** to
10102. Look for existing rule files (`.cursor/rules/*.md`, `.cursorrules`, `.github/copilot-instructions.md`, `claude.md`, `agents.md`) - only read if they exist
11113. Identify project type from config files and directory structure
12124. Find build/test/lint commands from config files, scripts, Makefiles, or CI configs
13−5. Read representative source files to understand code patterns, architecture, control/data flow
13+5. Read representative source files to understand code patterns
14146. If {{.Config.Options.InitializeAs}} exists, read and improve it
1515
1616**Content to include**:
1717
1818- Essential commands (build, test, run, deploy, etc.) - whatever is relevant for this project
19−- Code organization and structure, application architecture and control/data flow
19+- Code organization and structure
2020- Naming conventions and style patterns
2121- Testing approach and patterns
2222- Important gotchas or non-obvious patterns
2323- Any project-specific context from existing rule files
2424
25−**Note:** LLM agents learn and adapt to their context as they obtain it, so mentioning obvious details they would immediately pick up from reading a file or two is actively detrimental. Keep the principles of progressive disclosure in mind and focus primarily on non-obvious knowledge that saves the agent from trial-and-error discovery: gotchas, implicit conventions, commands with surprising flags, and context that isn't self-evident from the code in a single file.
26−
2725**Format**: Clear markdown sections. Use your judgment on structure based on what you find. Aim for completeness over brevity - include everything an agent would need to know.
2826
2927**Critical**: Only document what you actually observe. Never invent commands, patterns, or conventions. If you can't find something, don't include it.
internal/agent/templates/title.md+7−8
@@ -1,11 +1,10 @@
1−You will generate a short title based on the first message a user begins a conversation with.
1+you will generate a short title based on the first message a user begins a conversation with
22
33<rules>
4−- Keep the title in the same language that the user wrote their message in.
5−- Ensure it is not more than 50 characters long.
6−- The title should be a summary of the user's message.
7−- It should be one line long.
8−- Do not use quotes or colons.
9−- The entire text you return will be used as the title.
10−- Never return anything that is more than one sentence (one line) long.
4+- ensure it is not more than 50 characters long
5+- the title should be a summary of the user's message
6+- it should be one line long
7+- do not use quotes or colons
8+- the entire text you return will be used as the title
9+- never return anything that is more than one sentence (one line) long
1110</rules>
internal/agent/testdata/TestCoderAgent/anthropic-sonnet/bash_tool.yamlnew file+201
@@ -0,0 +1,201 @@
1+---
2+version: 2
3+interactions:
4+- id: 0
5+ request:
6+ proto: HTTP/1.1
7+ proto_major: 1
8+ proto_minor: 1
9+ content_length: 802
10+ host: ""
11+ body: '{"max_tokens":40,"messages":[{"content":[{"text":"Generate a concise title for the following content:\n\nuse bash to create a file named test.txt with content ''hello bash''. do not print its timestamp\n \u003cthink\u003e\n\n\u003c/think\u003e","type":"text"}],"role":"user"}],"model":"claude-3-5-haiku-20241022","system":[{"text":"you will generate a short title based on the first message a user begins a conversation with\n\n\u003crules\u003e\n- ensure it is not more than 50 characters long\n- the title should be a summary of the user''s message\n- it should be one line long\n- do not use quotes or colons\n- the entire text you return will be used as the title\n- never return anything that is more than one sentence (one line) long\n\u003c/rules\u003e\n\n /no_think","type":"text"}],"stream":true}'
12+ headers:
13+ Accept:
14+ - application/json
15+ Content-Type:
16+ - application/json
17+ User-Agent:
18+ - Anthropic/Go 1.14.0
19+ url: https://api.anthropic.com/v1/messages
20+ method: POST
21+ response:
22+ proto: HTTP/2.0
23+ proto_major: 2
24+ proto_minor: 0
25+ content_length: -1
26+ body: |+
27+ event: message_start
28+ data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01Ca5xhYzdyJq1rP5TwDth2W","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":152,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":3,"service_tier":"standard"}} }
29+
30+ event: content_block_start
31+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
32+
33+ event: content_block_delta
34+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Bash File"} }
35+
36+ event: content_block_delta
37+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Creation"} }
38+
39+ event: ping
40+ data: {"type": "ping"}
41+
42+ event: content_block_delta
43+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" with"} }
44+
45+ event: content_block_delta
46+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Hello"} }
47+
48+ event: content_block_delta
49+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Content"} }
50+
51+ event: content_block_stop
52+ data: {"type":"content_block_stop","index":0 }
53+
54+ event: message_delta
55+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":152,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":10}}
56+
57+ event: message_stop
58+ data: {"type":"message_stop" }
59+
60+ headers:
61+ Content-Type:
62+ - text/event-stream; charset=utf-8
63+ status: 200 OK
64+ code: 200
65+ duration: 734.910625ms
66+- id: 1
67+ request:
68+ proto: HTTP/1.1
69+ proto_major: 1
70+ proto_minor: 1
71+ content_length: 51899
72+ host: ""
73+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"},{\"text\":\"use bash to create a file named test.txt with content 'hello bash'. do not print its timestamp\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
74+ headers:
75+ Accept:
76+ - application/json
77+ Content-Type:
78+ - application/json
79+ User-Agent:
80+ - Anthropic/Go 1.14.0
81+ url: https://api.anthropic.com/v1/messages
82+ method: POST
83+ response:
84+ proto: HTTP/2.0
85+ proto_major: 2
86+ proto_minor: 0
87+ content_length: -1
88+ body: |+
89+ event: message_start
90+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01BZr4EwHju4DMtd799vtVkK","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4407,"cache_read_input_tokens":9490,"cache_creation":{"ephemeral_5m_input_tokens":4407,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
91+
92+ event: content_block_start
93+ data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_011WeQvXt48UvW4pWWAArMoV","name":"bash","input":{}} }
94+
95+ event: content_block_delta
96+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }
97+
98+ event: content_block_delta
99+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"c"} }
100+
101+ event: content_block_delta
102+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"omma"} }
103+
104+ event: content_block_delta
105+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"nd\": \""} }
106+
107+ event: content_block_delta
108+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"echo 'h"} }
109+
110+ event: content_block_delta
111+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ell"} }
112+
113+ event: content_block_delta
114+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"o b"} }
115+
116+ event: content_block_delta
117+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ash' > tes"}}
118+
119+ event: content_block_delta
120+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"t.txt\""} }
121+
122+ event: content_block_delta
123+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"descript"} }
124+
125+ event: content_block_delta
126+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ion\": "} }
127+
128+ event: content_block_delta
129+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"Create"} }
130+
131+ event: content_block_delta
132+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" test.tx"} }
133+
134+ event: content_block_delta
135+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"t with c"} }
136+
137+ event: content_block_delta
138+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ontent\"}"} }
139+
140+ event: content_block_stop
141+ data: {"type":"content_block_stop","index":0 }
142+
143+ event: message_delta
144+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":4407,"cache_read_input_tokens":9490,"output_tokens":82} }
145+
146+ event: message_stop
147+ data: {"type":"message_stop" }
148+
149+ headers:
150+ Content-Type:
151+ - text/event-stream; charset=utf-8
152+ status: 200 OK
153+ code: 200
154+ duration: 2.028388917s
155+- id: 2
156+ request:
157+ proto: HTTP/1.1
158+ proto_major: 1
159+ proto_minor: 1
160+ content_length: 52250
161+ host: ""
162+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"type\":\"text\"},{\"text\":\"use bash to create a file named test.txt with content 'hello bash'. do not print its timestamp\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_011WeQvXt48UvW4pWWAArMoV\",\"input\":{\"command\":\"echo 'hello bash' \\u003e test.txt\",\"description\":\"Create test.txt with content\"},\"name\":\"bash\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_011WeQvXt48UvW4pWWAArMoV\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"no output\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
163+ headers:
164+ Accept:
165+ - application/json
166+ Content-Type:
167+ - application/json
168+ User-Agent:
169+ - Anthropic/Go 1.14.0
170+ url: https://api.anthropic.com/v1/messages
171+ method: POST
172+ response:
173+ proto: HTTP/2.0
174+ proto_major: 2
175+ proto_minor: 0
176+ content_length: -1
177+ body: |+
178+ event: message_start
179+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01Q387SQNY61cb4vARYrUoux","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":94,"cache_read_input_tokens":13897,"cache_creation":{"ephemeral_5m_input_tokens":94,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
180+
181+ event: content_block_start
182+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
183+
184+ event: content_block_delta
185+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Done"} }
186+
187+ event: content_block_stop
188+ data: {"type":"content_block_stop","index":0 }
189+
190+ event: message_delta
191+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":94,"cache_read_input_tokens":13897,"output_tokens":4} }
192+
193+ event: message_stop
194+ data: {"type":"message_stop" }
195+
196+ headers:
197+ Content-Type:
198+ - text/event-stream; charset=utf-8
199+ status: 200 OK
200+ code: 200
201+ duration: 2.064324458s
internal/agent/testdata/TestCoderAgent/anthropic-sonnet/download_tool.yamlnew file+271
@@ -0,0 +1,271 @@
1+---
2+version: 2
3+interactions:
4+- id: 0
5+ request:
6+ proto: HTTP/1.1
7+ proto_major: 1
8+ proto_minor: 1
9+ content_length: 823
10+ host: ""
11+ body: '{"max_tokens":40,"messages":[{"content":[{"text":"Generate a concise title for the following content:\n\ndownload the file from https://example-files.online-convert.com/document/txt/example.txt and save it as example.txt\n \u003cthink\u003e\n\n\u003c/think\u003e","type":"text"}],"role":"user"}],"model":"claude-3-5-haiku-20241022","system":[{"text":"you will generate a short title based on the first message a user begins a conversation with\n\n\u003crules\u003e\n- ensure it is not more than 50 characters long\n- the title should be a summary of the user''s message\n- it should be one line long\n- do not use quotes or colons\n- the entire text you return will be used as the title\n- never return anything that is more than one sentence (one line) long\n\u003c/rules\u003e\n\n /no_think","type":"text"}],"stream":true}'
12+ headers:
13+ Accept:
14+ - application/json
15+ Content-Type:
16+ - application/json
17+ User-Agent:
18+ - Anthropic/Go 1.14.0
19+ url: https://api.anthropic.com/v1/messages
20+ method: POST
21+ response:
22+ proto: HTTP/2.0
23+ proto_major: 2
24+ proto_minor: 0
25+ content_length: -1
26+ body: |+
27+ event: message_start
28+ data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_012dSg4T5MVDEgj8PUhB7ihp","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":160,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
29+
30+ event: content_block_start
31+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
32+
33+ event: content_block_delta
34+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Downloa"} }
35+
36+ event: content_block_delta
37+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d File"} }
38+
39+ event: ping
40+ data: {"type": "ping"}
41+
42+ event: content_block_delta
43+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" from Example URL"} }
44+
45+ event: content_block_stop
46+ data: {"type":"content_block_stop","index":0 }
47+
48+ event: message_delta
49+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":160,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":8} }
50+
51+ event: message_stop
52+ data: {"type":"message_stop" }
53+
54+ headers:
55+ Content-Type:
56+ - text/event-stream; charset=utf-8
57+ status: 200 OK
58+ code: 200
59+ duration: 733.403208ms
60+- id: 1
61+ request:
62+ proto: HTTP/1.1
63+ proto_major: 1
64+ proto_minor: 1
65+ content_length: 51924
66+ host: ""
67+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"},{\"text\":\"download the file from https://example-files.online-convert.com/document/txt/example.txt and save it as example.txt\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
68+ headers:
69+ Accept:
70+ - application/json
71+ Content-Type:
72+ - application/json
73+ User-Agent:
74+ - Anthropic/Go 1.14.0
75+ url: https://api.anthropic.com/v1/messages
76+ method: POST
77+ response:
78+ proto: HTTP/2.0
79+ proto_major: 2
80+ proto_minor: 0
81+ content_length: -1
82+ body: |+
83+ event: message_start
84+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01TM5NTdVbepnb36c8fo4uB2","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4415,"cache_read_input_tokens":9490,"cache_creation":{"ephemeral_5m_input_tokens":4415,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
85+
86+ event: content_block_start
87+ data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01GZ474w2fSaxPhKUuYW4ikd","name":"download","input":{}} }
88+
89+ event: content_block_delta
90+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }
91+
92+ event: content_block_delta
93+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"url\":"} }
94+
95+ event: content_block_delta
96+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" \"ht"} }
97+
98+ event: content_block_delta
99+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tps:"} }
100+
101+ event: content_block_delta
102+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"//example-fi"} }
103+
104+ event: content_block_delta
105+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"les.onl"} }
106+
107+ event: content_block_delta
108+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ine"} }
109+
110+ event: content_block_delta
111+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"-conve"} }
112+
113+ event: content_block_delta
114+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"rt.co"} }
115+
116+ event: content_block_delta
117+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"m/do"} }
118+
119+ event: content_block_delta
120+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"cumen"} }
121+
122+ event: content_block_delta
123+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"t/txt"} }
124+
125+ event: content_block_delta
126+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"/example.t"} }
127+
128+ event: content_block_delta
129+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"xt\""} }
130+
131+ event: content_block_delta
132+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"file_pa"}}
133+
134+ event: content_block_delta
135+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"th\": \"/tmp"} }
136+
137+ event: content_block_delta
138+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"/cru"}}
139+
140+ event: content_block_delta
141+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"sh-test/Test"} }
142+
143+ event: content_block_delta
144+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"CoderAgent"} }
145+
146+ event: content_block_delta
147+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"/anth"} }
148+
149+ event: content_block_delta
150+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ropic-s"} }
151+
152+ event: content_block_delta
153+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"onnet/d"} }
154+
155+ event: content_block_delta
156+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ownloa"}}
157+
158+ event: content_block_delta
159+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"d_tool/exam"} }
160+
161+ event: content_block_delta
162+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ple.txt\"}"} }
163+
164+ event: content_block_stop
165+ data: {"type":"content_block_stop","index":0 }
166+
167+ event: message_delta
168+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":4415,"cache_read_input_tokens":9490,"output_tokens":112} }
169+
170+ event: message_stop
171+ data: {"type":"message_stop" }
172+
173+ headers:
174+ Content-Type:
175+ - text/event-stream; charset=utf-8
176+ status: 200 OK
177+ code: 200
178+ duration: 2.514324791s
179+- id: 2
180+ request:
181+ proto: HTTP/1.1
182+ proto_major: 1
183+ proto_minor: 1
184+ content_length: 0
185+ host: example-files.online-convert.com
186+ headers:
187+ User-Agent:
188+ - crush/1.0
189+ url: https://example-files.online-convert.com/document/txt/example.txt
190+ method: GET
191+ response:
192+ proto: HTTP/2.0
193+ proto_major: 2
194+ proto_minor: 0
195+ content_length: -1
196+ uncompressed: true
197+ body: |-
198+ TXT test file
199+ Purpose: Provide example of this file type
200+ Document file type: TXT
201+ Version: 1.0
202+ Remark:
203+
204+ Example content:
205+ The names "John Doe" for males, "Jane Doe" or "Jane Roe" for females, or "Jonnie Doe" and "Janie Doe" for children, or just "Doe" non-gender-specifically are used as placeholder names for a party whose true identity is unknown or must be withheld in a legal action, case, or discussion. The names are also used to refer to acorpse or hospital patient whose identity is unknown. This practice is widely used in the United States and Canada, but is rarely used in other English-speaking countries including the United Kingdom itself, from where the use of "John Doe" in a legal context originates. The names Joe Bloggs or John Smith are used in the UK instead, as well as in Australia and New Zealand.
206+
207+ John Doe is sometimes used to refer to a typical male in other contexts as well, in a similar manner to John Q. Public, known in Great Britain as Joe Public, John Smith or Joe Bloggs. For example, the first name listed on a form is often John Doe, along with a fictional address or other fictional information to provide an example of how to fill in the form. The name is also used frequently in popular culture, for example in the Frank Capra film Meet John Doe. John Doe was also the name of a 2002 American television series.
208+
209+ Similarly, a child or baby whose identity is unknown may be referred to as Baby Doe. A notorious murder case in Kansas City, Missouri, referred to the baby victim as Precious Doe. Other unidentified female murder victims are Cali Doe and Princess Doe. Additional persons may be called James Doe, Judy Doe, etc. However, to avoid possible confusion, if two anonymous or unknown parties are cited in a specific case or action, the surnames Doe and Roe may be used simultaneously; for example, "John Doe v. Jane Roe". If several anonymous parties are referenced, they may simply be labelled John Doe #1, John Doe #2, etc. (the U.S. Operation Delego cited 21 (numbered) "John Doe"s) or labelled with other variants of Doe / Roe / Poe / etc. Other early alternatives such as John Stiles and Richard Miles are now rarely used, and Mary Major has been used in some American federal cases.
210+
211+
212+
213+ File created by https://www.online-convert.com
214+ More example files: https://www.online-convert.com/file-type
215+ Text of Example content: Wikipedia (https://en.wikipedia.org/wiki/John_Doe)
216+ License: Attribution-ShareAlike 4.0 (https://creativecommons.org/licenses/by-sa/4.0/)
217+
218+ Feel free to use and share the file according to the license above.
219+ headers:
220+ Content-Type:
221+ - text/plain; charset=UTF-8
222+ status: 200 OK
223+ code: 200
224+ duration: 337.8285ms
225+- id: 3
226+ request:
227+ proto: HTTP/1.1
228+ proto_major: 1
229+ proto_minor: 1
230+ content_length: 52432
231+ host: ""
232+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"type\":\"text\"},{\"text\":\"download the file from https://example-files.online-convert.com/document/txt/example.txt and save it as example.txt\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01GZ474w2fSaxPhKUuYW4ikd\",\"input\":{\"file_path\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/download_tool/example.txt\",\"url\":\"https://example-files.online-convert.com/document/txt/example.txt\"},\"name\":\"download\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01GZ474w2fSaxPhKUuYW4ikd\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"Successfully downloaded 2574 bytes to example.txt (Content-Type: text/plain; charset=UTF-8)\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
233+ headers:
234+ Accept:
235+ - application/json
236+ Content-Type:
237+ - application/json
238+ User-Agent:
239+ - Anthropic/Go 1.14.0
240+ url: https://api.anthropic.com/v1/messages
241+ method: POST
242+ response:
243+ proto: HTTP/2.0
244+ proto_major: 2
245+ proto_minor: 0
246+ content_length: -1
247+ body: |+
248+ event: message_start
249+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01Xj5BG7dxxYGhWanVuUNixA","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":148,"cache_read_input_tokens":13905,"cache_creation":{"ephemeral_5m_input_tokens":148,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
250+
251+ event: content_block_start
252+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""}}
253+
254+ event: content_block_delta
255+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Done"} }
256+
257+ event: content_block_stop
258+ data: {"type":"content_block_stop","index":0 }
259+
260+ event: message_delta
261+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":4,"cache_creation_input_tokens":148,"cache_read_input_tokens":13905,"output_tokens":4} }
262+
263+ event: message_stop
264+ data: {"type":"message_stop" }
265+
266+ headers:
267+ Content-Type:
268+ - text/event-stream; charset=utf-8
269+ status: 200 OK
270+ code: 200
271+ duration: 4.598530167s
internal/agent/testdata/TestCoderAgent/anthropic-sonnet/fetch_tool.yamlnew file+293
@@ -0,0 +1,293 @@
1+---
2+version: 2
3+interactions:
4+- id: 0
5+ request:
6+ proto: HTTP/1.1
7+ proto_major: 1
8+ proto_minor: 1
9+ content_length: 844
10+ host: ""
11+ body: '{"max_tokens":40,"messages":[{"content":[{"text":"Generate a concise title for the following content:\n\nfetch the content from https://example-files.online-convert.com/website/html/example.html and tell me if it contains the word ''John Doe''\n \u003cthink\u003e\n\n\u003c/think\u003e","type":"text"}],"role":"user"}],"model":"claude-3-5-haiku-20241022","system":[{"text":"you will generate a short title based on the first message a user begins a conversation with\n\n\u003crules\u003e\n- ensure it is not more than 50 characters long\n- the title should be a summary of the user''s message\n- it should be one line long\n- do not use quotes or colons\n- the entire text you return will be used as the title\n- never return anything that is more than one sentence (one line) long\n\u003c/rules\u003e\n\n /no_think","type":"text"}],"stream":true}'
12+ headers:
13+ Accept:
14+ - application/json
15+ Content-Type:
16+ - application/json
17+ User-Agent:
18+ - Anthropic/Go 1.14.0
19+ url: https://api.anthropic.com/v1/messages
20+ method: POST
21+ response:
22+ proto: HTTP/2.0
23+ proto_major: 2
24+ proto_minor: 0
25+ content_length: -1
26+ body: |+
27+ event: message_start
28+ data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_0143Jw7v3wgt2bpCFEtGkuHv","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":167,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
29+
30+ event: content_block_start
31+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
32+
33+ event: content_block_delta
34+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Web"} }
35+
36+ event: content_block_delta
37+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Page Search"} }
38+
39+ event: ping
40+ data: {"type": "ping"}
41+
42+ event: content_block_delta
43+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" for"} }
44+
45+ event: content_block_delta
46+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" John"} }
47+
48+ event: content_block_delta
49+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Doe"} }
50+
51+ event: content_block_stop
52+ data: {"type":"content_block_stop","index":0 }
53+
54+ event: message_delta
55+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":167,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":10} }
56+
57+ event: message_stop
58+ data: {"type":"message_stop" }
59+
60+ headers:
61+ Content-Type:
62+ - text/event-stream; charset=utf-8
63+ status: 200 OK
64+ code: 200
65+ duration: 1.120772708s
66+- id: 1
67+ request:
68+ proto: HTTP/1.1
69+ proto_major: 1
70+ proto_minor: 1
71+ content_length: 51942
72+ host: ""
73+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"},{\"text\":\"fetch the content from https://example-files.online-convert.com/website/html/example.html and tell me if it contains the word 'John Doe'\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/fetch_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
74+ headers:
75+ Accept:
76+ - application/json
77+ Content-Type:
78+ - application/json
79+ User-Agent:
80+ - Anthropic/Go 1.14.0
81+ url: https://api.anthropic.com/v1/messages
82+ method: POST
83+ response:
84+ proto: HTTP/2.0
85+ proto_major: 2
86+ proto_minor: 0
87+ content_length: -1
88+ body: |+
89+ event: message_start
90+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01MyF8kbXd9XR2ycVNnFnZYD","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4422,"cache_read_input_tokens":9490,"cache_creation":{"ephemeral_5m_input_tokens":4422,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
91+
92+ event: content_block_start
93+ data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01XMztPb5Th1shQcN5doxede","name":"fetch","input":{}} }
94+
95+ event: content_block_delta
96+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }
97+
98+ event: content_block_delta
99+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"url\": \"h"} }
100+
101+ event: content_block_delta
102+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ttp"} }
103+
104+ event: content_block_delta
105+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"s:"} }
106+
107+ event: content_block_delta
108+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"//exampl"} }
109+
110+ event: content_block_delta
111+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"e-files"} }
112+
113+ event: content_block_delta
114+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".online-"}}
115+
116+ event: content_block_delta
117+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"convert.com"} }
118+
119+ event: content_block_delta
120+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"/websi"} }
121+
122+ event: content_block_delta
123+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"te/html/exam"} }
124+
125+ event: content_block_delta
126+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ple.html\""} }
127+
128+ event: content_block_delta
129+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"form"} }
130+
131+ event: content_block_delta
132+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"at"} }
133+
134+ event: content_block_delta
135+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\": \"t"} }
136+
137+ event: content_block_delta
138+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ext\"}"} }
139+
140+ event: content_block_stop
141+ data: {"type":"content_block_stop","index":0 }
142+
143+ event: message_delta
144+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":4422,"cache_read_input_tokens":9490,"output_tokens":86} }
145+
146+ event: message_stop
147+ data: {"type":"message_stop" }
148+
149+ headers:
150+ Content-Type:
151+ - text/event-stream; charset=utf-8
152+ status: 200 OK
153+ code: 200
154+ duration: 2.369823459s
155+- id: 2
156+ request:
157+ proto: HTTP/1.1
158+ proto_major: 1
159+ proto_minor: 1
160+ content_length: 0
161+ host: example-files.online-convert.com
162+ headers:
163+ User-Agent:
164+ - crush/1.0
165+ url: https://example-files.online-convert.com/website/html/example.html
166+ method: GET
167+ response:
168+ proto: HTTP/2.0
169+ proto_major: 2
170+ proto_minor: 0
171+ content_length: -1
172+ uncompressed: true
173+ body: |-
174+ <!DOCTYPE html>
175+
176+ <html>
177+ <body>
178+
179+ <h1>HTML test file</h1>
180+
181+ <p>Purpose: Provide example of this file type<br>
182+ Document file type: HTML<br>
183+ Version: 1.0<br>
184+ Remark:</p>
185+
186+ <p><img align="right" style="height:5.0551cm;width:7.62cm;" src="data:image/*;base64,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
187+ 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
188+ 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
189+ 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
190+ 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
191+ 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
192+ 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
193+ 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
194+ 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
195+ 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
196+ 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
197+ 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"/>
198+
199+ Example content:<br>
200+ The names "<b>John Doe</b>" for males, "<b>Jane Doe</b>" or "<b>Jane Roe</b>" for females, or "<b>Jonnie Doe</b>" and "<b>Janie Doe</b>" for children, or just "<b>Doe</b>" non-gender-specifically are used as placeholder names for a party whose true identity is unknown or must be withheld in a legal action, case, or discussion. The names are also used to refer to acorpse or hospital patient whose identity is unknown. This practice is widely used in the United States and Canada, but is rarely used in other English-speaking countries including the United Kingdom itself, from where the use of "John Doe" in a legal context originates. The names Joe Bloggs or John Smith are used in the UK instead, as well as in Australia and New Zealand.</p>
201+
202+ <p>John Doe is sometimes used to refer to a typical male in other contexts as well, in a similar manner to John Q. Public, known in Great Britain as Joe Public, John Smith or Joe Bloggs. For example, the first name listed on a form is often John Doe, along with a fictional address or other fictional information to provide an example of how to fill in the form. The name is also used frequently in popular culture, for example in the Frank Capra film <i>Meet John Doe</i>. John Doe was also the name of a 2002 American television series.</p>
203+
204+ <p>Similarly, a child or baby whose identity is unknown may be referred to as <b>Baby Doe</b>. A notorious murder case in Kansas City, Missouri, referred to the baby victim as <b>Precious Doe</b>. Other unidentified female murder victims are Cali Doe and Princess Doe. Additional persons may be called James Doe, Judy Doe, etc. However, to avoid possible confusion, if two anonymous or unknown parties are cited in a specific case or action, the surnames Doe and Roe may be used simultaneously; for example, "John Doe v. Jane Roe". If several anonymous parties are referenced, they may simply be labelled John Doe #1, John Doe #2, etc. (the U.S. Operation Delego cited 21 (numbered) "John Doe"s) or labelled with other variants of Doe / Roe / Poe / etc. Other early alternatives such as <b>John Stiles</b> and <b>Richard Miles</b> are now rarely used, and <b>Mary Major</b> has been used in some American federal cases.</p>
205+
206+ <p><img style="height:1.6881cm;width:1.6881cm;" align="left" src="data:image/*;base64,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
207+ B1/bMVO7nYqfTdlIhfMUvxUd51lhy67Tyq1UqJI9Jew1tnpUt0B6+/rwB89+fbtcyp1Q+gRk7z/Gy9tfzMHyrrfpKG8eqVDetsaC8o5Juz6zqvKuz6GyvKtkeXn3fbDzOauVdwpGynvzd+wv64P1QRgMBZhAGAwFmEAYDAWYQBgMBZhAGAwFmEAYDAWYQBgMBZhAGAwFmEAYDAWYQBgMBZhAGAwFmEAYDAWYQBgMBf4/fQGdtWECNsgAAAAASUVORK5CYII="/>
208+
209+ File created by <a href="https://www.online-convert.com" target="_blank">https://www.online-convert.com</a><br>
210+ More example files: <a href="https://www.online-convert.com/file-type" target="_blank">https://www.online-convert.com/file-type</a><br>
211+ Text of "Example content": <a href="https://en.wikipedia.org/wiki/John_Doe" target="_blank">Wikipedia</a><br>
212+ License: <a href="https://creativecommons.org/licenses/by-sa/3.0/" target="_blank">Attribution-ShareAlike 3.0 Unported</a>
213+
214+ <img style="height:0.6949cm;width:1.9741cm;" align="right" src="data:image/*;base64,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"/></p>
215+
216+ <p>Feel free to use and share the file according to license above.</p>
217+
218+ </body>
219+ </html>
220+ headers:
221+ Content-Type:
222+ - text/html; charset=UTF-8
223+ status: 200 OK
224+ code: 200
225+ duration: 49.286125ms
226+- id: 3
227+ request:
228+ proto: HTTP/1.1
229+ proto_major: 1
230+ proto_minor: 1
231+ content_length: 54790
232+ host: ""
233+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"type\":\"text\"},{\"text\":\"fetch the content from https://example-files.online-convert.com/website/html/example.html and tell me if it contains the word 'John Doe'\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01XMztPb5Th1shQcN5doxede\",\"input\":{\"format\":\"text\",\"url\":\"https://example-files.online-convert.com/website/html/example.html\"},\"name\":\"fetch\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01XMztPb5Th1shQcN5doxede\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"HTML test file Purpose: Provide example of this file type Document file type: HTML Version: 1.0 Remark: Example content: The names \\\"John Doe\\\" for males, \\\"Jane Doe\\\" or \\\"Jane Roe\\\" for females, or \\\"Jonnie Doe\\\" and \\\"Janie Doe\\\" for children, or just \\\"Doe\\\" non-gender-specifically are used as placeholder names for a party whose true identity is unknown or must be withheld in a legal action, case, or discussion. The names are also used to refer to acorpse or hospital patient whose identity is unknown. This practice is widely used in the United States and Canada, but is rarely used in other English-speaking countries including the United Kingdom itself, from where the use of \\\"John Doe\\\" in a legal context originates. The names Joe Bloggs or John Smith are used in the UK instead, as well as in Australia and New Zealand. John Doe is sometimes used to refer to a typical male in other contexts as well, in a similar manner to John Q. Public, known in Great Britain as Joe Public, John Smith or Joe Bloggs. For example, the first name listed on a form is often John Doe, along with a fictional address or other fictional information to provide an example of how to fill in the form. The name is also used frequently in popular culture, for example in the Frank Capra film Meet John Doe. John Doe was also the name of a 2002 American television series. Similarly, a child or baby whose identity is unknown may be referred to as Baby Doe. A notorious murder case in Kansas City, Missouri, referred to the baby victim as Precious Doe. Other unidentified female murder victims are Cali Doe and Princess Doe. Additional persons may be called James Doe, Judy Doe, etc. However, to avoid possible confusion, if two anonymous or unknown parties are cited in a specific case or action, the surnames Doe and Roe may be used simultaneously; for example, \\\"John Doe v. Jane Roe\\\". If several anonymous parties are referenced, they may simply be labelled John Doe #1, John Doe #2, etc. (the U.S. Operation Delego cited 21 (numbered) \\\"John Doe\\\"s) or labelled with other variants of Doe / Roe / Poe / etc. Other early alternatives such as John Stiles and Richard Miles are now rarely used, and Mary Major has been used in some American federal cases. File created by https://www.online-convert.com More example files: https://www.online-convert.com/file-type Text of \\\"Example content\\\": Wikipedia License: Attribution-ShareAlike 3.0 Unported Feel free to use and share the file according to license above.\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/fetch_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
234+ headers:
235+ Accept:
236+ - application/json
237+ Content-Type:
238+ - application/json
239+ User-Agent:
240+ - Anthropic/Go 1.14.0
241+ url: https://api.anthropic.com/v1/messages
242+ method: POST
243+ response:
244+ proto: HTTP/2.0
245+ proto_major: 2
246+ proto_minor: 0
247+ content_length: -1
248+ body: |+
249+ event: message_start
250+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01877MMXxiHj8ZQyTZWxxMKT","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":710,"cache_read_input_tokens":13912,"cache_creation":{"ephemeral_5m_input_tokens":710,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
251+
252+ event: content_block_start
253+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
254+
255+ event: content_block_delta
256+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Yes"} }
257+
258+ event: content_block_delta
259+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":", the content"} }
260+
261+ event: ping
262+ data: {"type": "ping"}
263+
264+ event: content_block_delta
265+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" contains \""} }
266+
267+ event: content_block_delta
268+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"John Doe\" multiple"} }
269+
270+ event: content_block_delta
271+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" times throughout"} }
272+
273+ event: content_block_delta
274+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" the "}}
275+
276+ event: content_block_delta
277+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"document."} }
278+
279+ event: content_block_stop
280+ data: {"type":"content_block_stop","index":0 }
281+
282+ event: message_delta
283+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":4,"cache_creation_input_tokens":710,"cache_read_input_tokens":13912,"output_tokens":19} }
284+
285+ event: message_stop
286+ data: {"type":"message_stop" }
287+
288+ headers:
289+ Content-Type:
290+ - text/event-stream; charset=utf-8
291+ status: 200 OK
292+ code: 200
293+ duration: 2.76421775s
internal/agent/testdata/TestCoderAgent/anthropic-sonnet/glob_tool.yamlnew file+177
@@ -0,0 +1,177 @@
1+---
2+version: 2
3+interactions:
4+- id: 0
5+ request:
6+ proto: HTTP/1.1
7+ proto_major: 1
8+ proto_minor: 1
9+ content_length: 763
10+ host: ""
11+ body: '{"max_tokens":40,"messages":[{"content":[{"text":"Generate a concise title for the following content:\n\nuse glob to find all .go files in the current directory\n \u003cthink\u003e\n\n\u003c/think\u003e","type":"text"}],"role":"user"}],"model":"claude-3-5-haiku-20241022","system":[{"text":"you will generate a short title based on the first message a user begins a conversation with\n\n\u003crules\u003e\n- ensure it is not more than 50 characters long\n- the title should be a summary of the user''s message\n- it should be one line long\n- do not use quotes or colons\n- the entire text you return will be used as the title\n- never return anything that is more than one sentence (one line) long\n\u003c/rules\u003e\n\n /no_think","type":"text"}],"stream":true}'
12+ headers:
13+ Accept:
14+ - application/json
15+ Content-Type:
16+ - application/json
17+ User-Agent:
18+ - Anthropic/Go 1.14.0
19+ url: https://api.anthropic.com/v1/messages
20+ method: POST
21+ response:
22+ proto: HTTP/2.0
23+ proto_major: 2
24+ proto_minor: 0
25+ content_length: -1
26+ body: |+
27+ event: message_start
28+ data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01UJrSNzeuTRKfD6edRAnioA","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":142,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":3,"service_tier":"standard"}} }
29+
30+ event: content_block_start
31+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
32+
33+ event: content_block_delta
34+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Glob Go"} }
35+
36+ event: content_block_delta
37+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Files"} }
38+
39+ event: ping
40+ data: {"type": "ping"}
41+
42+ event: content_block_delta
43+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" in"} }
44+
45+ event: content_block_delta
46+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Current Directory"} }
47+
48+ event: content_block_stop
49+ data: {"type":"content_block_stop","index":0 }
50+
51+ event: message_delta
52+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":142,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":10} }
53+
54+ event: message_stop
55+ data: {"type":"message_stop" }
56+
57+ headers:
58+ Content-Type:
59+ - text/event-stream; charset=utf-8
60+ status: 200 OK
61+ code: 200
62+ duration: 596.908916ms
63+- id: 1
64+ request:
65+ proto: HTTP/1.1
66+ proto_major: 1
67+ proto_minor: 1
68+ content_length: 51860
69+ host: ""
70+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"},{\"text\":\"use glob to find all .go files in the current directory\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
71+ headers:
72+ Accept:
73+ - application/json
74+ Content-Type:
75+ - application/json
76+ User-Agent:
77+ - Anthropic/Go 1.14.0
78+ url: https://api.anthropic.com/v1/messages
79+ method: POST
80+ response:
81+ proto: HTTP/2.0
82+ proto_major: 2
83+ proto_minor: 0
84+ content_length: -1
85+ body: |+
86+ event: message_start
87+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_016ZDoJUax2bDCFrJbiH1x3h","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4397,"cache_read_input_tokens":9490,"cache_creation":{"ephemeral_5m_input_tokens":4397,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
88+
89+ event: content_block_start
90+ data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_018gf2Wp7WKWFaw9LpXgyjrX","name":"glob","input":{}} }
91+
92+ event: content_block_delta
93+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }
94+
95+ event: content_block_delta
96+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"patt"} }
97+
98+ event: content_block_delta
99+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ern\": \""} }
100+
101+ event: content_block_delta
102+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"*.go\"}"} }
103+
104+ event: content_block_stop
105+ data: {"type":"content_block_stop","index":0 }
106+
107+ event: message_delta
108+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":4397,"cache_read_input_tokens":9490,"output_tokens":52} }
109+
110+ event: message_stop
111+ data: {"type":"message_stop" }
112+
113+ headers:
114+ Content-Type:
115+ - text/event-stream; charset=utf-8
116+ status: 200 OK
117+ code: 200
118+ duration: 4.526031625s
119+- id: 2
120+ request:
121+ proto: HTTP/1.1
122+ proto_major: 1
123+ proto_minor: 1
124+ content_length: 52193
125+ host: ""
126+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"type\":\"text\"},{\"text\":\"use glob to find all .go files in the current directory\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_018gf2Wp7WKWFaw9LpXgyjrX\",\"input\":{\"pattern\":\"*.go\"},\"name\":\"glob\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_018gf2Wp7WKWFaw9LpXgyjrX\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/glob_tool/main.go\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
127+ headers:
128+ Accept:
129+ - application/json
130+ Content-Type:
131+ - application/json
132+ User-Agent:
133+ - Anthropic/Go 1.14.0
134+ url: https://api.anthropic.com/v1/messages
135+ method: POST
136+ response:
137+ proto: HTTP/2.0
138+ proto_major: 2
139+ proto_minor: 0
140+ content_length: -1
141+ body: |+
142+ event: message_start
143+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01X6CMPARgv8fNQskeJidtsh","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":86,"cache_read_input_tokens":13887,"cache_creation":{"ephemeral_5m_input_tokens":86,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
144+
145+ event: content_block_start
146+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
147+
148+ event: content_block_delta
149+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Foun"} }
150+
151+ event: content_block_delta
152+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d:"} }
153+
154+ event: ping
155+ data: {"type": "ping"}
156+
157+ event: content_block_delta
158+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" `"} }
159+
160+ event: content_block_delta
161+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"main.go`"} }
162+
163+ event: content_block_stop
164+ data: {"type":"content_block_stop","index":0 }
165+
166+ event: message_delta
167+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":86,"cache_read_input_tokens":13887,"output_tokens":10} }
168+
169+ event: message_stop
170+ data: {"type":"message_stop" }
171+
172+ headers:
173+ Content-Type:
174+ - text/event-stream; charset=utf-8
175+ status: 200 OK
176+ code: 200
177+ duration: 2.079475666s
internal/agent/testdata/TestCoderAgent/anthropic-sonnet/grep_tool.yamlnew file+210
@@ -0,0 +1,210 @@
1+---
2+version: 2
3+interactions:
4+- id: 0
5+ request:
6+ proto: HTTP/1.1
7+ proto_major: 1
8+ proto_minor: 1
9+ content_length: 761
10+ host: ""
11+ body: '{"max_tokens":40,"messages":[{"content":[{"text":"Generate a concise title for the following content:\n\nuse grep to search for the word ''package'' in go files\n \u003cthink\u003e\n\n\u003c/think\u003e","type":"text"}],"role":"user"}],"model":"claude-3-5-haiku-20241022","system":[{"text":"you will generate a short title based on the first message a user begins a conversation with\n\n\u003crules\u003e\n- ensure it is not more than 50 characters long\n- the title should be a summary of the user''s message\n- it should be one line long\n- do not use quotes or colons\n- the entire text you return will be used as the title\n- never return anything that is more than one sentence (one line) long\n\u003c/rules\u003e\n\n /no_think","type":"text"}],"stream":true}'
12+ headers:
13+ Accept:
14+ - application/json
15+ Content-Type:
16+ - application/json
17+ User-Agent:
18+ - Anthropic/Go 1.14.0
19+ url: https://api.anthropic.com/v1/messages
20+ method: POST
21+ response:
22+ proto: HTTP/2.0
23+ proto_major: 2
24+ proto_minor: 0
25+ content_length: -1
26+ body: |+
27+ event: message_start
28+ data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01EPKmtSyVdvAn6uZoDUPvmm","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":144,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":2,"service_tier":"standard"}} }
29+
30+ event: content_block_start
31+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
32+
33+ event: content_block_delta
34+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Searching"} }
35+
36+ event: content_block_delta
37+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" for "} }
38+
39+ event: ping
40+ data: {"type": "ping"}
41+
42+ event: content_block_delta
43+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"'package' in Go"} }
44+
45+ event: content_block_delta
46+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" files with"} }
47+
48+ event: content_block_delta
49+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" grep"}}
50+
51+ event: content_block_stop
52+ data: {"type":"content_block_stop","index":0 }
53+
54+ event: message_delta
55+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":144,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":15} }
56+
57+ event: message_stop
58+ data: {"type":"message_stop" }
59+
60+ headers:
61+ Content-Type:
62+ - text/event-stream; charset=utf-8
63+ status: 200 OK
64+ code: 200
65+ duration: 669.560167ms
66+- id: 1
67+ request:
68+ proto: HTTP/1.1
69+ proto_major: 1
70+ proto_minor: 1
71+ content_length: 51858
72+ host: ""
73+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"},{\"text\":\"use grep to search for the word 'package' in go files\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
74+ headers:
75+ Accept:
76+ - application/json
77+ Content-Type:
78+ - application/json
79+ User-Agent:
80+ - Anthropic/Go 1.14.0
81+ url: https://api.anthropic.com/v1/messages
82+ method: POST
83+ response:
84+ proto: HTTP/2.0
85+ proto_major: 2
86+ proto_minor: 0
87+ content_length: -1
88+ body: |+
89+ event: message_start
90+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01S67CaEocGL6MsDegMLHZbY","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4399,"cache_read_input_tokens":9490,"cache_creation":{"ephemeral_5m_input_tokens":4399,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
91+
92+ event: content_block_start
93+ data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_013HMqxq88TFfKyk6No6XGDu","name":"grep","input":{}} }
94+
95+ event: content_block_delta
96+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }
97+
98+ event: content_block_delta
99+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"pattern"} }
100+
101+ event: content_block_delta
102+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\": \""} }
103+
104+ event: content_block_delta
105+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"pack"} }
106+
107+ event: content_block_delta
108+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ag"} }
109+
110+ event: content_block_delta
111+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"e\""} }
112+
113+ event: content_block_delta
114+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"includ"} }
115+
116+ event: content_block_delta
117+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"e\": \"*.go"} }
118+
119+ event: content_block_delta
120+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"}"} }
121+
122+ event: content_block_stop
123+ data: {"type":"content_block_stop","index":0 }
124+
125+ event: message_delta
126+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":4399,"cache_read_input_tokens":9490,"output_tokens":69} }
127+
128+ event: message_stop
129+ data: {"type":"message_stop" }
130+
131+ headers:
132+ Content-Type:
133+ - text/event-stream; charset=utf-8
134+ status: 200 OK
135+ code: 200
136+ duration: 2.215141375s
137+- id: 2
138+ request:
139+ proto: HTTP/1.1
140+ proto_major: 1
141+ proto_minor: 1
142+ content_length: 52263
143+ host: ""
144+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"type\":\"text\"},{\"text\":\"use grep to search for the word 'package' in go files\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_013HMqxq88TFfKyk6No6XGDu\",\"input\":{\"include\":\"*.go\",\"pattern\":\"package\"},\"name\":\"grep\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_013HMqxq88TFfKyk6No6XGDu\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"Found 1 matches\\n/tmp/crush-test/TestCoderAgent/anthropic-sonnet/grep_tool/main.go:\\n Line 1, Char 1: package main\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
145+ headers:
146+ Accept:
147+ - application/json
148+ Content-Type:
149+ - application/json
150+ User-Agent:
151+ - Anthropic/Go 1.14.0
152+ url: https://api.anthropic.com/v1/messages
153+ method: POST
154+ response:
155+ proto: HTTP/2.0
156+ proto_major: 2
157+ proto_minor: 0
158+ content_length: -1
159+ body: |+
160+ event: message_start
161+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01LAcvCfWUJpKHSYzcJSvgJw","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":125,"cache_read_input_tokens":13889,"cache_creation":{"ephemeral_5m_input_tokens":125,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
162+
163+ event: content_block_start
164+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
165+
166+ event: content_block_delta
167+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Foun"} }
168+
169+ event: content_block_delta
170+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d 1 match"} }
171+
172+ event: ping
173+ data: {"type": "ping"}
174+
175+ event: content_block_delta
176+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" in"} }
177+
178+ event: content_block_delta
179+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" main.go:"} }
180+
181+ event: content_block_delta
182+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"1"} }
183+
184+ event: content_block_delta
185+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" "} }
186+
187+ event: content_block_delta
188+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"containing"} }
189+
190+ event: content_block_delta
191+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" \"package main"} }
192+
193+ event: content_block_delta
194+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"\""} }
195+
196+ event: content_block_stop
197+ data: {"type":"content_block_stop","index":0 }
198+
199+ event: message_delta
200+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":125,"cache_read_input_tokens":13889,"output_tokens":20} }
201+
202+ event: message_stop
203+ data: {"type":"message_stop" }
204+
205+ headers:
206+ Content-Type:
207+ - text/event-stream; charset=utf-8
208+ status: 200 OK
209+ code: 200
210+ duration: 2.087140167s
internal/agent/testdata/TestCoderAgent/anthropic-sonnet/ls_tool.yamlnew file+168
@@ -0,0 +1,168 @@
1+---
2+version: 2
3+interactions:
4+- id: 0
5+ request:
6+ proto: HTTP/1.1
7+ proto_major: 1
8+ proto_minor: 1
9+ content_length: 757
10+ host: ""
11+ body: '{"max_tokens":40,"messages":[{"content":[{"text":"Generate a concise title for the following content:\n\nuse ls to list the files in the current directory\n \u003cthink\u003e\n\n\u003c/think\u003e","type":"text"}],"role":"user"}],"model":"claude-3-5-haiku-20241022","system":[{"text":"you will generate a short title based on the first message a user begins a conversation with\n\n\u003crules\u003e\n- ensure it is not more than 50 characters long\n- the title should be a summary of the user''s message\n- it should be one line long\n- do not use quotes or colons\n- the entire text you return will be used as the title\n- never return anything that is more than one sentence (one line) long\n\u003c/rules\u003e\n\n /no_think","type":"text"}],"stream":true}'
12+ headers:
13+ Accept:
14+ - application/json
15+ Content-Type:
16+ - application/json
17+ User-Agent:
18+ - Anthropic/Go 1.14.0
19+ url: https://api.anthropic.com/v1/messages
20+ method: POST
21+ response:
22+ proto: HTTP/2.0
23+ proto_major: 2
24+ proto_minor: 0
25+ content_length: -1
26+ body: |+
27+ event: message_start
28+ data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01GS9L44gUzv4ei1fm9E5B1T","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":140,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":6,"service_tier":"standard"}}}
29+
30+ event: content_block_start
31+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
32+
33+ event: content_block_delta
34+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Listing Files in Current Directory"} }
35+
36+ event: content_block_stop
37+ data: {"type":"content_block_stop","index":0 }
38+
39+ event: message_delta
40+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":140,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":9} }
41+
42+ event: message_stop
43+ data: {"type":"message_stop" }
44+
45+ headers:
46+ Content-Type:
47+ - text/event-stream; charset=utf-8
48+ status: 200 OK
49+ code: 200
50+ duration: 588.114167ms
51+- id: 1
52+ request:
53+ proto: HTTP/1.1
54+ proto_major: 1
55+ proto_minor: 1
56+ content_length: 51852
57+ host: ""
58+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"},{\"text\":\"use ls to list the files in the current directory\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
59+ headers:
60+ Accept:
61+ - application/json
62+ Content-Type:
63+ - application/json
64+ User-Agent:
65+ - Anthropic/Go 1.14.0
66+ url: https://api.anthropic.com/v1/messages
67+ method: POST
68+ response:
69+ proto: HTTP/2.0
70+ proto_major: 2
71+ proto_minor: 0
72+ content_length: -1
73+ body: |+
74+ event: message_start
75+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01G1VhkiLJ16cNDcWtawWjnV","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4395,"cache_read_input_tokens":9490,"cache_creation":{"ephemeral_5m_input_tokens":4395,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}}}
76+
77+ event: content_block_start
78+ data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01NggiYS4LWTJLoyfDU8MWdb","name":"ls","input":{}}}
79+
80+ event: content_block_delta
81+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }
82+
83+ event: content_block_delta
84+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"path\": \"."} }
85+
86+ event: content_block_delta
87+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"}"} }
88+
89+ event: content_block_stop
90+ data: {"type":"content_block_stop","index":0 }
91+
92+ event: message_delta
93+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":4395,"cache_read_input_tokens":9490,"output_tokens":50} }
94+
95+ event: message_stop
96+ data: {"type":"message_stop"}
97+
98+ headers:
99+ Content-Type:
100+ - text/event-stream; charset=utf-8
101+ status: 200 OK
102+ code: 200
103+ duration: 3.304603s
104+- id: 2
105+ request:
106+ proto: HTTP/1.1
107+ proto_major: 1
108+ proto_minor: 1
109+ content_length: 52199
110+ host: ""
111+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"type\":\"text\"},{\"text\":\"use ls to list the files in the current directory\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01NggiYS4LWTJLoyfDU8MWdb\",\"input\":{\"path\":\".\"},\"name\":\"ls\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01NggiYS4LWTJLoyfDU8MWdb\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\n- /tmp/crush-test/TestCoderAgent/anthropic-sonnet/ls_tool/\\n - go.mod\\n - main.go\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
112+ headers:
113+ Accept:
114+ - application/json
115+ Content-Type:
116+ - application/json
117+ User-Agent:
118+ - Anthropic/Go 1.14.0
119+ url: https://api.anthropic.com/v1/messages
120+ method: POST
121+ response:
122+ proto: HTTP/2.0
123+ proto_major: 2
124+ proto_minor: 0
125+ content_length: -1
126+ body: |+
127+ event: message_start
128+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_014HU1Zs27XGLApRMThG587v","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":97,"cache_read_input_tokens":13885,"cache_creation":{"ephemeral_5m_input_tokens":97,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
129+
130+ event: content_block_start
131+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
132+
133+ event: content_block_delta
134+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"**"} }
135+
136+ event: content_block_delta
137+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"go"} }
138+
139+ event: ping
140+ data: {"type": "ping"}
141+
142+ event: content_block_delta
143+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":".mod**"} }
144+
145+ event: content_block_delta
146+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" "} }
147+
148+ event: content_block_delta
149+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"\n**"}}
150+
151+ event: content_block_delta
152+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"main.go**"} }
153+
154+ event: content_block_stop
155+ data: {"type":"content_block_stop","index":0 }
156+
157+ event: message_delta
158+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":97,"cache_read_input_tokens":13885,"output_tokens":15} }
159+
160+ event: message_stop
161+ data: {"type":"message_stop" }
162+
163+ headers:
164+ Content-Type:
165+ - text/event-stream; charset=utf-8
166+ status: 200 OK
167+ code: 200
168+ duration: 2.995636375s
internal/agent/testdata/TestCoderAgent/anthropic-sonnet/multiedit_tool.yamlnew file+395
@@ -0,0 +1,395 @@
1+---
2+version: 2
3+interactions:
4+- id: 0
5+ request:
6+ proto: HTTP/1.1
7+ proto_major: 1
8+ proto_minor: 1
9+ content_length: 836
10+ host: ""
11+ body: '{"max_tokens":40,"messages":[{"content":[{"text":"Generate a concise title for the following content:\n\nuse multiedit to change ''Hello, World!'' to ''Hello, Crush!'' and add a comment ''// Greeting'' above the fmt.Println line in main.go\n \u003cthink\u003e\n\n\u003c/think\u003e","type":"text"}],"role":"user"}],"model":"claude-3-5-haiku-20241022","system":[{"text":"you will generate a short title based on the first message a user begins a conversation with\n\n\u003crules\u003e\n- ensure it is not more than 50 characters long\n- the title should be a summary of the user''s message\n- it should be one line long\n- do not use quotes or colons\n- the entire text you return will be used as the title\n- never return anything that is more than one sentence (one line) long\n\u003c/rules\u003e\n\n /no_think","type":"text"}],"stream":true}'
12+ headers:
13+ Accept:
14+ - application/json
15+ Content-Type:
16+ - application/json
17+ User-Agent:
18+ - Anthropic/Go 1.14.0
19+ url: https://api.anthropic.com/v1/messages
20+ method: POST
21+ response:
22+ proto: HTTP/2.0
23+ proto_major: 2
24+ proto_minor: 0
25+ content_length: -1
26+ body: |+
27+ event: message_start
28+ data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01Vi9HRV9KsgZmVqi14RD4Qd","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":170,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
29+
30+ event: content_block_start
31+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
32+
33+ event: content_block_delta
34+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Edit"} }
35+
36+ event: content_block_delta
37+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Go"} }
38+
39+ event: ping
40+ data: {"type": "ping"}
41+
42+ event: content_block_delta
43+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Code"} }
44+
45+ event: content_block_delta
46+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Greeting"} }
47+
48+ event: content_block_stop
49+ data: {"type":"content_block_stop","index":0 }
50+
51+ event: message_delta
52+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":170,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":8} }
53+
54+ event: message_stop
55+ data: {"type":"message_stop" }
56+
57+ headers:
58+ Content-Type:
59+ - text/event-stream; charset=utf-8
60+ status: 200 OK
61+ code: 200
62+ duration: 672.068792ms
63+- id: 1
64+ request:
65+ proto: HTTP/1.1
66+ proto_major: 1
67+ proto_minor: 1
68+ content_length: 51938
69+ host: ""
70+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"},{\"text\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
71+ headers:
72+ Accept:
73+ - application/json
74+ Content-Type:
75+ - application/json
76+ User-Agent:
77+ - Anthropic/Go 1.14.0
78+ url: https://api.anthropic.com/v1/messages
79+ method: POST
80+ response:
81+ proto: HTTP/2.0
82+ proto_major: 2
83+ proto_minor: 0
84+ content_length: -1
85+ body: |+
86+ event: message_start
87+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01EFG4Rw6yNizFG7MFXV78ug","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4427,"cache_read_input_tokens":9490,"cache_creation":{"ephemeral_5m_input_tokens":4427,"ephemeral_1h_input_tokens":0},"output_tokens":3,"service_tier":"standard"}} }
88+
89+ event: content_block_start
90+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
91+
92+ event: content_block_delta
93+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"I'll rea"} }
94+
95+ event: content_block_delta
96+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d the file"} }
97+
98+ event: ping
99+ data: {"type": "ping"}
100+
101+ event: content_block_delta
102+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" first to see"}}
103+
104+ event: content_block_delta
105+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" its"} }
106+
107+ event: content_block_delta
108+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" exact"}}
109+
110+ event: content_block_delta
111+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" structure"} }
112+
113+ event: content_block_delta
114+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":", then make"} }
115+
116+ event: content_block_delta
117+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" both"} }
118+
119+ event: content_block_delta
120+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" changes."} }
121+
122+ event: content_block_stop
123+ data: {"type":"content_block_stop","index":0 }
124+
125+ event: content_block_start
126+ data: {"type":"content_block_start","index":1,"content_block":{"type":"tool_use","id":"toolu_01FL5rMQhzmtzd49fkPsEPuU","name":"view","input":{}} }
127+
128+ event: content_block_delta
129+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":""} }
130+
131+ event: content_block_delta
132+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"{\"fil"}}
133+
134+ event: content_block_delta
135+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"e_path\": "} }
136+
137+ event: content_block_delta
138+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"\"/tmp"} }
139+
140+ event: content_block_delta
141+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"/crus"} }
142+
143+ event: content_block_delta
144+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"h-test/Te"} }
145+
146+ event: content_block_delta
147+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"stCoderAgent"} }
148+
149+ event: content_block_delta
150+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"/anth"} }
151+
152+ event: content_block_delta
153+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"ropic-so"} }
154+
155+ event: content_block_delta
156+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"nnet"} }
157+
158+ event: content_block_delta
159+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"/multiedit_"} }
160+
161+ event: content_block_delta
162+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"tool/ma"} }
163+
164+ event: content_block_delta
165+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"in.go\"}"} }
166+
167+ event: content_block_stop
168+ data: {"type":"content_block_stop","index":1 }
169+
170+ event: message_delta
171+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":4427,"cache_read_input_tokens":9490,"output_tokens":97} }
172+
173+ event: message_stop
174+ data: {"type":"message_stop" }
175+
176+ headers:
177+ Content-Type:
178+ - text/event-stream; charset=utf-8
179+ status: 200 OK
180+ code: 200
181+ duration: 2.21571425s
182+- id: 2
183+ request:
184+ proto: HTTP/1.1
185+ proto_major: 1
186+ proto_minor: 1
187+ content_length: 52548
188+ host: ""
189+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"type\":\"text\"},{\"text\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"text\":\"I'll read the file first to see its exact structure, then make both changes.\",\"type\":\"text\"},{\"id\":\"toolu_01FL5rMQhzmtzd49fkPsEPuU\",\"input\":{\"file_path\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool/main.go\"},\"name\":\"view\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01FL5rMQhzmtzd49fkPsEPuU\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cfile\\u003e\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
190+ headers:
191+ Accept:
192+ - application/json
193+ Content-Type:
194+ - application/json
195+ User-Agent:
196+ - Anthropic/Go 1.14.0
197+ url: https://api.anthropic.com/v1/messages
198+ method: POST
199+ response:
200+ proto: HTTP/2.0
201+ proto_major: 2
202+ proto_minor: 0
203+ content_length: -1
204+ body: |+
205+ event: message_start
206+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01FZjc3R2R5Jv94Abuq4ncwz","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":161,"cache_read_input_tokens":13917,"cache_creation":{"ephemeral_5m_input_tokens":161,"ephemeral_1h_input_tokens":0},"output_tokens":25,"service_tier":"standard"}} }
207+
208+ event: content_block_start
209+ data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_012KRYUozSf7fTPFvAWvHNoj","name":"multiedit","input":{}} }
210+
211+ event: content_block_delta
212+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }
213+
214+ event: content_block_delta
215+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"file"} }
216+
217+ event: content_block_delta
218+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"_path\": "} }
219+
220+ event: content_block_delta
221+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"/tm"} }
222+
223+ event: content_block_delta
224+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"p/cru"} }
225+
226+ event: content_block_delta
227+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"sh-test/Te"} }
228+
229+ event: content_block_delta
230+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"stCoderAgent"} }
231+
232+ event: content_block_delta
233+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"/ant"} }
234+
235+ event: content_block_delta
236+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"hropi"} }
237+
238+ event: content_block_delta
239+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"c-sonnet/m"} }
240+
241+ event: content_block_delta
242+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ultied"} }
243+
244+ event: content_block_delta
245+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"it_to"} }
246+
247+ event: content_block_delta
248+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ol/"} }
249+
250+ event: content_block_delta
251+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"main"} }
252+
253+ event: content_block_delta
254+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".go"} }
255+
256+ event: content_block_delta
257+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\""} }
258+
259+ event: content_block_delta
260+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", "} }
261+
262+ event: content_block_delta
263+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"edits\""} }
264+
265+ event: content_block_delta
266+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":": [{\"old"} }
267+
268+ event: content_block_delta
269+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"_string\":"} }
270+
271+ event: content_block_delta
272+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"func m"} }
273+
274+ event: content_block_delta
275+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ain() {"} }
276+
277+ event: content_block_delta
278+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\\n\\tfmt.Pr"} }
279+
280+ event: content_block_delta
281+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"int"}}
282+
283+ event: content_block_delta
284+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ln(\\\"Hel"} }
285+
286+ event: content_block_delta
287+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"lo, World!\\"}}
288+
289+ event: content_block_delta
290+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\")\",\"n"} }
291+
292+ event: content_block_delta
293+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ew"} }
294+
295+ event: content_block_delta
296+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"_string\":"} }
297+
298+ event: content_block_delta
299+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"func m"}}
300+
301+ event: content_block_delta
302+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ain() {\\n\\t"} }
303+
304+ event: content_block_delta
305+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"// G"} }
306+
307+ event: content_block_delta
308+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"re"} }
309+
310+ event: content_block_delta
311+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"eting\\n\\t"} }
312+
313+ event: content_block_delta
314+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"fmt.P"} }
315+
316+ event: content_block_delta
317+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"rintln"} }
318+
319+ event: content_block_delta
320+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"(\\\"H"} }
321+
322+ event: content_block_delta
323+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ello, Cr"} }
324+
325+ event: content_block_delta
326+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ush!"}}
327+
328+ event: content_block_delta
329+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\\\")"} }
330+
331+ event: content_block_delta
332+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"}]}"} }
333+
334+ event: content_block_stop
335+ data: {"type":"content_block_stop","index":0 }
336+
337+ event: message_delta
338+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":161,"cache_read_input_tokens":13917,"output_tokens":171} }
339+
340+ event: message_stop
341+ data: {"type":"message_stop" }
342+
343+ headers:
344+ Content-Type:
345+ - text/event-stream; charset=utf-8
346+ status: 200 OK
347+ code: 200
348+ duration: 2.4914445s
349+- id: 3
350+ request:
351+ proto: HTTP/1.1
352+ proto_major: 1
353+ proto_minor: 1
354+ content_length: 53180
355+ host: ""
356+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"type\":\"text\"},{\"text\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"text\":\"I'll read the file first to see its exact structure, then make both changes.\",\"type\":\"text\"},{\"id\":\"toolu_01FL5rMQhzmtzd49fkPsEPuU\",\"input\":{\"file_path\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool/main.go\"},\"name\":\"view\",\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01FL5rMQhzmtzd49fkPsEPuU\",\"content\":[{\"text\":\"\\u003cfile\\u003e\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_012KRYUozSf7fTPFvAWvHNoj\",\"input\":{\"edits\":[{\"new_string\":\"func main() {\\n\\t// Greeting\\n\\tfmt.Println(\\\"Hello, Crush!\\\")\",\"old_string\":\"func main() {\\n\\tfmt.Println(\\\"Hello, World!\\\")\"}],\"file_path\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool/main.go\"},\"name\":\"multiedit\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_012KRYUozSf7fTPFvAWvHNoj\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cresult\\u003e\\nApplied 1 edits to file: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool/main.go\\n\\u003c/result\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
357+ headers:
358+ Accept:
359+ - application/json
360+ Content-Type:
361+ - application/json
362+ User-Agent:
363+ - Anthropic/Go 1.14.0
364+ url: https://api.anthropic.com/v1/messages
365+ method: POST
366+ response:
367+ proto: HTTP/2.0
368+ proto_major: 2
369+ proto_minor: 0
370+ content_length: -1
371+ body: |+
372+ event: message_start
373+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01UcTibWBQPo8Eap63BxG9FH","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":216,"cache_read_input_tokens":14078,"cache_creation":{"ephemeral_5m_input_tokens":216,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
374+
375+ event: content_block_start
376+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
377+
378+ event: content_block_delta
379+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Done"} }
380+
381+ event: content_block_stop
382+ data: {"type":"content_block_stop","index":0 }
383+
384+ event: message_delta
385+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":216,"cache_read_input_tokens":14078,"output_tokens":4} }
386+
387+ event: message_stop
388+ data: {"type":"message_stop" }
389+
390+ headers:
391+ Content-Type:
392+ - text/event-stream; charset=utf-8
393+ status: 200 OK
394+ code: 200
395+ duration: 2.443325834s
internal/agent/testdata/TestCoderAgent/anthropic-sonnet/parallel_tool_calls.yamlnew file+210
@@ -0,0 +1,210 @@
1+---
2+version: 2
3+interactions:
4+- id: 0
5+ request:
6+ proto: HTTP/1.1
7+ proto_major: 1
8+ proto_minor: 1
9+ content_length: 842
10+ host: ""
11+ body: '{"max_tokens":40,"messages":[{"content":[{"text":"Generate a concise title for the following content:\n\nuse glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\n \u003cthink\u003e\n\n\u003c/think\u003e","type":"text"}],"role":"user"}],"model":"claude-3-5-haiku-20241022","system":[{"text":"you will generate a short title based on the first message a user begins a conversation with\n\n\u003crules\u003e\n- ensure it is not more than 50 characters long\n- the title should be a summary of the user''s message\n- it should be one line long\n- do not use quotes or colons\n- the entire text you return will be used as the title\n- never return anything that is more than one sentence (one line) long\n\u003c/rules\u003e\n\n /no_think","type":"text"}],"stream":true}'
12+ headers:
13+ Accept:
14+ - application/json
15+ Content-Type:
16+ - application/json
17+ User-Agent:
18+ - Anthropic/Go 1.14.0
19+ url: https://api.anthropic.com/v1/messages
20+ method: POST
21+ response:
22+ proto: HTTP/2.0
23+ proto_major: 2
24+ proto_minor: 0
25+ content_length: -1
26+ body: |+
27+ event: message_start
28+ data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01MvZPBgrJ1PxooW6vcTNgTP","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":159,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":2,"service_tier":"standard"}} }
29+
30+ event: content_block_start
31+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
32+
33+ event: content_block_delta
34+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Parallel"} }
35+
36+ event: content_block_delta
37+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Go File"} }
38+
39+ event: ping
40+ data: {"type": "ping"}
41+
42+ event: content_block_delta
43+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Discovery"} }
44+
45+ event: content_block_delta
46+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" and Listing"} }
47+
48+ event: content_block_stop
49+ data: {"type":"content_block_stop","index":0 }
50+
51+ event: message_delta
52+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":159,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":11} }
53+
54+ event: message_stop
55+ data: {"type":"message_stop" }
56+
57+ headers:
58+ Content-Type:
59+ - text/event-stream; charset=utf-8
60+ status: 200 OK
61+ code: 200
62+ duration: 643.790917ms
63+- id: 1
64+ request:
65+ proto: HTTP/1.1
66+ proto_major: 1
67+ proto_minor: 1
68+ content_length: 51949
69+ host: ""
70+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"},{\"text\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/parallel_tool_calls\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
71+ headers:
72+ Accept:
73+ - application/json
74+ Content-Type:
75+ - application/json
76+ User-Agent:
77+ - Anthropic/Go 1.14.0
78+ url: https://api.anthropic.com/v1/messages
79+ method: POST
80+ response:
81+ proto: HTTP/2.0
82+ proto_major: 2
83+ proto_minor: 0
84+ content_length: -1
85+ body: |+
86+ event: message_start
87+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01RgWtDpFNq3FTX7be78fixx","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4416,"cache_read_input_tokens":9490,"cache_creation":{"ephemeral_5m_input_tokens":4416,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
88+
89+ event: content_block_start
90+ data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01PNau6C8sTr6JdX4T99Jvbm","name":"glob","input":{}} }
91+
92+ event: content_block_delta
93+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }
94+
95+ event: content_block_delta
96+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"p"} }
97+
98+ event: content_block_delta
99+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"attern\": \"*"} }
100+
101+ event: content_block_delta
102+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"*/*.go\"}"} }
103+
104+ event: content_block_stop
105+ data: {"type":"content_block_stop","index":0 }
106+
107+ event: content_block_start
108+ data: {"type":"content_block_start","index":1,"content_block":{"type":"tool_use","id":"toolu_011Rdk6SLWamQC58y4HDpdZg","name":"ls","input":{}} }
109+
110+ event: content_block_delta
111+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":""} }
112+
113+ event: content_block_delta
114+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"{\"path\""} }
115+
116+ event: content_block_delta
117+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":": \".\"}"} }
118+
119+ event: content_block_stop
120+ data: {"type":"content_block_stop","index":1 }
121+
122+ event: message_delta
123+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":4416,"cache_read_input_tokens":9490,"output_tokens":86} }
124+
125+ event: message_stop
126+ data: {"type":"message_stop" }
127+
128+ headers:
129+ Content-Type:
130+ - text/event-stream; charset=utf-8
131+ status: 200 OK
132+ code: 200
133+ duration: 1.965059916s
134+- id: 2
135+ request:
136+ proto: HTTP/1.1
137+ proto_major: 1
138+ proto_minor: 1
139+ content_length: 52593
140+ host: ""
141+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"type\":\"text\"},{\"text\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01PNau6C8sTr6JdX4T99Jvbm\",\"input\":{\"pattern\":\"**/*.go\"},\"name\":\"glob\",\"type\":\"tool_use\"},{\"id\":\"toolu_011Rdk6SLWamQC58y4HDpdZg\",\"input\":{\"path\":\".\"},\"name\":\"ls\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01PNau6C8sTr6JdX4T99Jvbm\",\"content\":[{\"text\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/parallel_tool_calls/main.go\",\"type\":\"text\"}],\"type\":\"tool_result\"},{\"tool_use_id\":\"toolu_011Rdk6SLWamQC58y4HDpdZg\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\n- /tmp/crush-test/TestCoderAgent/anthropic-sonnet/parallel_tool_calls/\\n - go.mod\\n - main.go\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/parallel_tool_calls\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
142+ headers:
143+ Accept:
144+ - application/json
145+ Content-Type:
146+ - application/json
147+ User-Agent:
148+ - Anthropic/Go 1.14.0
149+ url: https://api.anthropic.com/v1/messages
150+ method: POST
151+ response:
152+ proto: HTTP/2.0
153+ proto_major: 2
154+ proto_minor: 0
155+ content_length: -1
156+ body: |+
157+ event: message_start
158+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01DitytYy3hzNR9TCFc7Nwnn","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":6,"cache_creation_input_tokens":207,"cache_read_input_tokens":13906,"cache_creation":{"ephemeral_5m_input_tokens":207,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
159+
160+ event: content_block_start
161+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
162+
163+ event: content_block_delta
164+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Foun"} }
165+
166+ event: content_block_delta
167+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d one"} }
168+
169+ event: ping
170+ data: {"type": "ping"}
171+
172+ event: content_block_delta
173+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Go"} }
174+
175+ event: content_block_delta
176+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" file:"} }
177+
178+ event: content_block_delta
179+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" `"} }
180+
181+ event: content_block_delta
182+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"main.go`"} }
183+
184+ event: content_block_delta
185+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"\n\nDirectory"} }
186+
187+ event: content_block_delta
188+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" contains"} }
189+
190+ event: content_block_delta
191+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":": `go"} }
192+
193+ event: content_block_delta
194+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":".mod`, `main.go`"} }
195+
196+ event: content_block_stop
197+ data: {"type":"content_block_stop","index":0 }
198+
199+ event: message_delta
200+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":6,"cache_creation_input_tokens":207,"cache_read_input_tokens":13906,"output_tokens":27} }
201+
202+ event: message_stop
203+ data: {"type":"message_stop" }
204+
205+ headers:
206+ Content-Type:
207+ - text/event-stream; charset=utf-8
208+ status: 200 OK
209+ code: 200
210+ duration: 2.142234792s
internal/agent/testdata/TestCoderAgent/anthropic-sonnet/read_a_file.yamlnew file+213
@@ -0,0 +1,213 @@
1+---
2+version: 2
3+interactions:
4+- id: 0
5+ request:
6+ proto: HTTP/1.1
7+ proto_major: 1
8+ proto_minor: 1
9+ content_length: 723
10+ host: ""
11+ body: '{"max_tokens":40,"messages":[{"content":[{"text":"Generate a concise title for the following content:\n\nRead the go mod\n \u003cthink\u003e\n\n\u003c/think\u003e","type":"text"}],"role":"user"}],"model":"claude-3-5-haiku-20241022","system":[{"text":"you will generate a short title based on the first message a user begins a conversation with\n\n\u003crules\u003e\n- ensure it is not more than 50 characters long\n- the title should be a summary of the user''s message\n- it should be one line long\n- do not use quotes or colons\n- the entire text you return will be used as the title\n- never return anything that is more than one sentence (one line) long\n\u003c/rules\u003e\n\n /no_think","type":"text"}],"stream":true}'
12+ headers:
13+ Accept:
14+ - application/json
15+ Content-Type:
16+ - application/json
17+ User-Agent:
18+ - Anthropic/Go 1.14.0
19+ url: https://api.anthropic.com/v1/messages
20+ method: POST
21+ response:
22+ proto: HTTP/2.0
23+ proto_major: 2
24+ proto_minor: 0
25+ content_length: -1
26+ body: |+
27+ event: message_start
28+ data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01WSfpakrUTZru3pucFjjWmQ","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":134,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
29+
30+ event: content_block_start
31+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
32+
33+ event: content_block_delta
34+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Rea"} }
35+
36+ event: content_block_delta
37+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d Go"} }
38+
39+ event: ping
40+ data: {"type": "ping"}
41+
42+ event: content_block_delta
43+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Module"} }
44+
45+ event: content_block_delta
46+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Dependencies"} }
47+
48+ event: content_block_stop
49+ data: {"type":"content_block_stop","index":0 }
50+
51+ event: message_delta
52+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":134,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":7} }
53+
54+ event: message_stop
55+ data: {"type":"message_stop" }
56+
57+ headers:
58+ Content-Type:
59+ - text/event-stream; charset=utf-8
60+ status: 200 OK
61+ code: 200
62+ duration: 987.366375ms
63+- id: 1
64+ request:
65+ proto: HTTP/1.1
66+ proto_major: 1
67+ proto_minor: 1
68+ content_length: 51822
69+ host: ""
70+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"},{\"text\":\"Read the go mod\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
71+ headers:
72+ Accept:
73+ - application/json
74+ Content-Type:
75+ - application/json
76+ User-Agent:
77+ - Anthropic/Go 1.14.0
78+ url: https://api.anthropic.com/v1/messages
79+ method: POST
80+ response:
81+ proto: HTTP/2.0
82+ proto_major: 2
83+ proto_minor: 0
84+ content_length: -1
85+ body: |+
86+ event: message_start
87+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01DoWU7sWGpfrv2pjP3CU8nB","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4391,"cache_read_input_tokens":9490,"cache_creation":{"ephemeral_5m_input_tokens":4391,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
88+
89+ event: content_block_start
90+ data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01JUD4pCdKUou4UkL33iZRSK","name":"view","input":{}} }
91+
92+ event: content_block_delta
93+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }
94+
95+ event: content_block_delta
96+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"file_"} }
97+
98+ event: content_block_delta
99+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"path\": \"/tmp"} }
100+
101+ event: content_block_delta
102+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"/crus"} }
103+
104+ event: content_block_delta
105+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"h-test/T"} }
106+
107+ event: content_block_delta
108+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"estCoderAgen"}}
109+
110+ event: content_block_delta
111+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"t/"} }
112+
113+ event: content_block_delta
114+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"anthropic-"} }
115+
116+ event: content_block_delta
117+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"sonne"} }
118+
119+ event: content_block_delta
120+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"t/read_a_fil"} }
121+
122+ event: content_block_delta
123+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"e/go.mo"} }
124+
125+ event: content_block_delta
126+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"d\"}"} }
127+
128+ event: content_block_stop
129+ data: {"type":"content_block_stop","index":0 }
130+
131+ event: message_delta
132+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":4391,"cache_read_input_tokens":9490,"output_tokens":79} }
133+
134+ event: message_stop
135+ data: {"type":"message_stop" }
136+
137+ headers:
138+ Content-Type:
139+ - text/event-stream; charset=utf-8
140+ status: 200 OK
141+ code: 200
142+ duration: 3.377161208s
143+- id: 2
144+ request:
145+ proto: HTTP/1.1
146+ proto_major: 1
147+ proto_minor: 1
148+ content_length: 52255
149+ host: ""
150+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"type\":\"text\"},{\"text\":\"Read the go mod\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01JUD4pCdKUou4UkL33iZRSK\",\"input\":{\"file_path\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/read_a_file/go.mod\"},\"name\":\"view\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01JUD4pCdKUou4UkL33iZRSK\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cfile\\u003e\\n 1|module example.com/testproject\\n 2|\\n 3|go 1.23\\n\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
151+ headers:
152+ Accept:
153+ - application/json
154+ Content-Type:
155+ - application/json
156+ User-Agent:
157+ - Anthropic/Go 1.14.0
158+ url: https://api.anthropic.com/v1/messages
159+ method: POST
160+ response:
161+ proto: HTTP/2.0
162+ proto_major: 2
163+ proto_minor: 0
164+ content_length: -1
165+ body: |+
166+ event: message_start
167+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01Jp7putCPeFuHZ3jtvEiQUS","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":120,"cache_read_input_tokens":13881,"cache_creation":{"ephemeral_5m_input_tokens":120,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
168+
169+ event: content_block_start
170+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
171+
172+ event: content_block_delta
173+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"The"} }
174+
175+ event: content_block_delta
176+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" go"} }
177+
178+ event: ping
179+ data: {"type": "ping"}
180+
181+ event: content_block_delta
182+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":".mod defines"} }
183+
184+ event: content_block_delta
185+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" a"} }
186+
187+ event: content_block_delta
188+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" module `"} }
189+
190+ event: content_block_delta
191+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"example.com/testproject` using"} }
192+
193+ event: content_block_delta
194+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Go"} }
195+
196+ event: content_block_delta
197+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" 1.23."} }
198+
199+ event: content_block_stop
200+ data: {"type":"content_block_stop","index":0}
201+
202+ event: message_delta
203+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":120,"cache_read_input_tokens":13881,"output_tokens":25} }
204+
205+ event: message_stop
206+ data: {"type":"message_stop" }
207+
208+ headers:
209+ Content-Type:
210+ - text/event-stream; charset=utf-8
211+ status: 200 OK
212+ code: 200
213+ duration: 2.556238792s
internal/agent/testdata/TestCoderAgent/anthropic-sonnet/simple_test.yamlnew file+121
@@ -0,0 +1,121 @@
1+---
2+version: 2
3+interactions:
4+- id: 0
5+ request:
6+ proto: HTTP/1.1
7+ proto_major: 1
8+ proto_minor: 1
9+ content_length: 713
10+ host: ""
11+ body: '{"max_tokens":40,"messages":[{"content":[{"text":"Generate a concise title for the following content:\n\nHello\n \u003cthink\u003e\n\n\u003c/think\u003e","type":"text"}],"role":"user"}],"model":"claude-3-5-haiku-20241022","system":[{"text":"you will generate a short title based on the first message a user begins a conversation with\n\n\u003crules\u003e\n- ensure it is not more than 50 characters long\n- the title should be a summary of the user''s message\n- it should be one line long\n- do not use quotes or colons\n- the entire text you return will be used as the title\n- never return anything that is more than one sentence (one line) long\n\u003c/rules\u003e\n\n /no_think","type":"text"}],"stream":true}'
12+ headers:
13+ Accept:
14+ - application/json
15+ Content-Type:
16+ - application/json
17+ User-Agent:
18+ - Anthropic/Go 1.14.0
19+ url: https://api.anthropic.com/v1/messages
20+ method: POST
21+ response:
22+ proto: HTTP/2.0
23+ proto_major: 2
24+ proto_minor: 0
25+ content_length: -1
26+ body: |+
27+ event: message_start
28+ data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01TxmeH5H2NGkxM58ZrqhuU1","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":131,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
29+
30+ event: content_block_start
31+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
32+
33+ event: content_block_delta
34+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Quick"} }
35+
36+ event: content_block_delta
37+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Greeting"} }
38+
39+ event: ping
40+ data: {"type": "ping"}
41+
42+ event: content_block_stop
43+ data: {"type":"content_block_stop","index":0 }
44+
45+ event: ping
46+ data: {"type": "ping"}
47+
48+ event: ping
49+ data: {"type": "ping"}
50+
51+ event: message_delta
52+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":131,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":6} }
53+
54+ event: message_stop
55+ data: {"type":"message_stop" }
56+
57+ headers:
58+ Content-Type:
59+ - text/event-stream; charset=utf-8
60+ status: 200 OK
61+ code: 200
62+ duration: 700.496625ms
63+- id: 1
64+ request:
65+ proto: HTTP/1.1
66+ proto_major: 1
67+ proto_minor: 1
68+ content_length: 51812
69+ host: ""
70+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"},{\"text\":\"Hello\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/simple_test\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
71+ headers:
72+ Accept:
73+ - application/json
74+ Content-Type:
75+ - application/json
76+ User-Agent:
77+ - Anthropic/Go 1.14.0
78+ url: https://api.anthropic.com/v1/messages
79+ method: POST
80+ response:
81+ proto: HTTP/2.0
82+ proto_major: 2
83+ proto_minor: 0
84+ content_length: -1
85+ body: |+
86+ event: message_start
87+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01SVJCdg52ty5fTHuSnTtDLx","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":13876,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":13876,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
88+
89+ event: content_block_start
90+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
91+
92+ event: content_block_delta
93+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Hello"} }
94+
95+ event: content_block_delta
96+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"! Ready"} }
97+
98+ event: ping
99+ data: {"type": "ping"}
100+
101+ event: content_block_delta
102+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" to help"} }
103+
104+ event: content_block_delta
105+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"."}}
106+
107+ event: content_block_stop
108+ data: {"type":"content_block_stop","index":0 }
109+
110+ event: message_delta
111+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":13876,"cache_read_input_tokens":0,"output_tokens":9} }
112+
113+ event: message_stop
114+ data: {"type":"message_stop" }
115+
116+ headers:
117+ Content-Type:
118+ - text/event-stream; charset=utf-8
119+ status: 200 OK
120+ code: 200
121+ duration: 2.547362167s
internal/agent/testdata/TestCoderAgent/anthropic-sonnet/sourcegraph_tool.yamlnew file+301
@@ -0,0 +1,301 @@
1+---
2+version: 2
3+interactions:
4+- id: 0
5+ request:
6+ proto: HTTP/1.1
7+ proto_major: 1
8+ proto_minor: 1
9+ content_length: 768
10+ host: ""
11+ body: '{"max_tokens":40,"messages":[{"content":[{"text":"Generate a concise title for the following content:\n\nuse sourcegraph to search for ''func main'' in Go repositories\n \u003cthink\u003e\n\n\u003c/think\u003e","type":"text"}],"role":"user"}],"model":"claude-3-5-haiku-20241022","system":[{"text":"you will generate a short title based on the first message a user begins a conversation with\n\n\u003crules\u003e\n- ensure it is not more than 50 characters long\n- the title should be a summary of the user''s message\n- it should be one line long\n- do not use quotes or colons\n- the entire text you return will be used as the title\n- never return anything that is more than one sentence (one line) long\n\u003c/rules\u003e\n\n /no_think","type":"text"}],"stream":true}'
12+ headers:
13+ Accept:
14+ - application/json
15+ Content-Type:
16+ - application/json
17+ User-Agent:
18+ - Anthropic/Go 1.14.0
19+ url: https://api.anthropic.com/v1/messages
20+ method: POST
21+ response:
22+ proto: HTTP/2.0
23+ proto_major: 2
24+ proto_minor: 0
25+ content_length: -1
26+ body: |+
27+ event: message_start
28+ data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_014dxeWmvWs82uYJw8q11pgi","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":145,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":3,"service_tier":"standard"}} }
29+
30+ event: content_block_start
31+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
32+
33+ event: content_block_delta
34+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Searching Go"} }
35+
36+ event: content_block_delta
37+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Repos"} }
38+
39+ event: ping
40+ data: {"type": "ping"}
41+
42+ event: content_block_delta
43+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" for Main"} }
44+
45+ event: content_block_delta
46+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Function"}}
47+
48+ event: content_block_stop
49+ data: {"type":"content_block_stop","index":0 }
50+
51+ event: message_delta
52+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":145,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":11} }
53+
54+ event: message_stop
55+ data: {"type":"message_stop" }
56+
57+ headers:
58+ Content-Type:
59+ - text/event-stream; charset=utf-8
60+ status: 200 OK
61+ code: 200
62+ duration: 720.76ms
63+- id: 1
64+ request:
65+ proto: HTTP/1.1
66+ proto_major: 1
67+ proto_minor: 1
68+ content_length: 51872
69+ host: ""
70+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"},{\"text\":\"use sourcegraph to search for 'func main' in Go repositories\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
71+ headers:
72+ Accept:
73+ - application/json
74+ Content-Type:
75+ - application/json
76+ User-Agent:
77+ - Anthropic/Go 1.14.0
78+ url: https://api.anthropic.com/v1/messages
79+ method: POST
80+ response:
81+ proto: HTTP/2.0
82+ proto_major: 2
83+ proto_minor: 0
84+ content_length: -1
85+ body: |+
86+ event: message_start
87+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01CvijWyeEpC2AqebBBEAAvq","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4402,"cache_read_input_tokens":9490,"cache_creation":{"ephemeral_5m_input_tokens":4402,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
88+
89+ event: content_block_start
90+ data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01NkusdWvdtsBEbkaTsPgTiA","name":"sourcegraph","input":{}} }
91+
92+ event: content_block_delta
93+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }
94+
95+ event: content_block_delta
96+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"query\": \""} }
97+
98+ event: content_block_delta
99+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"lang:g"} }
100+
101+ event: content_block_delta
102+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"o func main\""} }
103+
104+ event: content_block_delta
105+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"count\""} }
106+
107+ event: content_block_delta
108+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":": 10}"} }
109+
110+ event: content_block_stop
111+ data: {"type":"content_block_stop","index":0 }
112+
113+ event: message_delta
114+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":4402,"cache_read_input_tokens":9490,"output_tokens":74} }
115+
116+ event: message_stop
117+ data: {"type":"message_stop" }
118+
119+ headers:
120+ Content-Type:
121+ - text/event-stream; charset=utf-8
122+ status: 200 OK
123+ code: 200
124+ duration: 2.263150167s
125+- id: 2
126+ request:
127+ proto: HTTP/1.1
128+ proto_major: 1
129+ proto_minor: 1
130+ content_length: 424
131+ host: sourcegraph.com
132+ body: '{"query":"query Search($query: String!) { search(query: $query, version: V2, patternType: keyword ) { results { matchCount, limitHit, resultCount, approximateResultCount, missing { name }, timedout { name }, indexUnavailable, results { __typename, ... on FileMatch { repository { name }, file { path, url, content }, lineMatches { preview, lineNumber, offsetAndLengths } } } } } }","variables":{"query":"lang:go func main"}}'
133+ headers:
134+ Content-Type:
135+ - application/json
136+ User-Agent:
137+ - crush/1.0
138+ url: https://sourcegraph.com/.api/graphql
139+ method: POST
140+ response:
141+ proto: HTTP/2.0
142+ proto_major: 2
143+ proto_minor: 0
144+ content_length: -1
145+ uncompressed: true
146+ body: '{"data":{"search":{"results":{"matchCount":30,"limitHit":true,"resultCount":30,"approximateResultCount":"30+","missing":[],"timedout":[],"indexUnavailable":false,"results":[{"__typename":"FileMatch","repository":{"name":"github.com/jcalabro/uscope"},"file":{"path":"assets/gobacktrace/main.go","url":"/github.com/jcalabro/uscope/-/blob/assets/gobacktrace/main.go","content":"package main\n\nimport \"fmt\"\n\nfunc FuncE() {\n\tfmt.Println(\"FuncE\")\n}\n\nfunc FuncD() {\n\tFuncE()\n\tfmt.Println(\"FuncD\")\n}\n\nfunc FuncC() {\n\tFuncD()\n\tfmt.Println(\"FuncC\")\n}\n\nfunc FuncB() {\n\tFuncC()\n\tfmt.Println(\"FuncB\")\n}\n\nfunc FuncA() {\n\tFuncB()\n\tfmt.Println(\"FuncA\")\n}\n\nfunc FuncF() {\n\tfmt.Println(\"FuncF\")\n\tFuncE()\n}\n\nfunc main() {\n\tFuncA()\n\tFuncB()\n\tFuncC()\n\tFuncD()\n\tFuncE()\n\tFuncF()\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":33,"offsetAndLengths":[[0,9]]},{"preview":"\tFuncA()","lineNumber":34,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncB()","lineNumber":35,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncC()","lineNumber":36,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncD()","lineNumber":37,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncE()","lineNumber":38,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncF()","lineNumber":39,"offsetAndLengths":[[1,4]]},{"preview":"func FuncE() {","lineNumber":4,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tfmt.Println(\"FuncE\")","lineNumber":5,"offsetAndLengths":[[14,4]]},{"preview":"func FuncD() {","lineNumber":8,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tFuncE()","lineNumber":9,"offsetAndLengths":[[1,4]]},{"preview":"\tfmt.Println(\"FuncD\")","lineNumber":10,"offsetAndLengths":[[14,4]]},{"preview":"func FuncC() {","lineNumber":13,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tFuncD()","lineNumber":14,"offsetAndLengths":[[1,4]]},{"preview":"\tfmt.Println(\"FuncC\")","lineNumber":15,"offsetAndLengths":[[14,4]]},{"preview":"func FuncB() {","lineNumber":18,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tFuncC()","lineNumber":19,"offsetAndLengths":[[1,4]]},{"preview":"\tfmt.Println(\"FuncB\")","lineNumber":20,"offsetAndLengths":[[14,4]]},{"preview":"func FuncA() {","lineNumber":23,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tFuncB()","lineNumber":24,"offsetAndLengths":[[1,4]]},{"preview":"\tfmt.Println(\"FuncA\")","lineNumber":25,"offsetAndLengths":[[14,4]]},{"preview":"func FuncF() {","lineNumber":28,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tfmt.Println(\"FuncF\")","lineNumber":29,"offsetAndLengths":[[14,4]]},{"preview":"\tFuncE()","lineNumber":30,"offsetAndLengths":[[1,4]]}]}]}}}}'
147+ headers:
148+ Content-Type:
149+ - application/json
150+ status: 200 OK
151+ code: 200
152+ duration: 1.368927167s
153+- id: 3
154+ request:
155+ proto: HTTP/1.1
156+ proto_major: 1
157+ proto_minor: 1
158+ content_length: 59710
159+ host: ""
160+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"type\":\"text\"},{\"text\":\"use sourcegraph to search for 'func main' in Go repositories\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01NkusdWvdtsBEbkaTsPgTiA\",\"input\":{\"count\":10,\"query\":\"lang:go func main\"},\"name\":\"sourcegraph\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01NkusdWvdtsBEbkaTsPgTiA\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"# Sourcegraph Search Results\\n\\nFound 30 matches across 30 results\\n(Result limit reached, try a more specific query)\\n\\n## Result 1: github.com/jcalabro/uscope/assets/gobacktrace/main.go\\n\\nURL: /github.com/jcalabro/uscope/-/blob/assets/gobacktrace/main.go\\n\\n```\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| func main() {\\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| \\tFuncA()\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncB()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncC()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncD()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncE()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncF()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| func FuncE() {\\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| \\tfmt.Println(\\\"FuncE\\\")\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| func FuncD() {\\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| \\tFuncE()\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tfmt.Println(\\\"FuncD\\\")\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n```\\n\\n```\\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| func FuncC() {\\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n```\\n\\n```\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| \\tFuncD()\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n```\\n\\n```\\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tfmt.Println(\\\"FuncC\\\")\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n```\\n\\n```\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| func FuncB() {\\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n```\\n\\n```\\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| \\tFuncC()\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n```\\n\\n```\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tfmt.Println(\\\"FuncB\\\")\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n```\\n\\n```\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| func FuncA() {\\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n```\\n\\n```\\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| \\tFuncB()\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n```\\n\\n```\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tfmt.Println(\\\"FuncA\\\")\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n```\\n\\n```\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| func FuncF() {\\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n```\\n\\n```\\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| \\tfmt.Println(\\\"FuncF\\\")\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n```\\n\\n```\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tFuncE()\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n```\\n\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
161+ headers:
162+ Accept:
163+ - application/json
164+ Content-Type:
165+ - application/json
166+ User-Agent:
167+ - Anthropic/Go 1.14.0
168+ url: https://api.anthropic.com/v1/messages
169+ method: POST
170+ response:
171+ proto: HTTP/2.0
172+ proto_major: 2
173+ proto_minor: 0
174+ content_length: -1
175+ body: |+
176+ event: message_start
177+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01112HtWJkJNk1dZh9TCpGdW","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":3890,"cache_read_input_tokens":13892,"cache_creation":{"ephemeral_5m_input_tokens":3890,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}}}
178+
179+ event: content_block_start
180+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
181+
182+ event: content_block_delta
183+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Foun"} }
184+
185+ event: content_block_delta
186+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d "}}
187+
188+ event: ping
189+ data: {"type": "ping"}
190+
191+ event: content_block_delta
192+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"30 matches across"} }
193+
194+ event: content_block_delta
195+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Go"} }
196+
197+ event: content_block_delta
198+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" repositories"} }
199+
200+ event: content_block_delta
201+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":". The search"} }
202+
203+ event: content_block_delta
204+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" returne"} }
205+
206+ event: content_block_delta
207+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d examples"} }
208+
209+ event: content_block_delta
210+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" of"} }
211+
212+ event: content_block_delta
213+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" `"} }
214+
215+ event: content_block_delta
216+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"func main()` declarations"} }
217+
218+ event: content_block_delta
219+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" from"} }
220+
221+ event: content_block_delta
222+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" various projects"} }
223+
224+ event: content_block_delta
225+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":", with"} }
226+
227+ event: content_block_delta
228+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" the"} }
229+
230+ event: content_block_delta
231+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" result"} }
232+
233+ event: content_block_delta
234+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" limit"} }
235+
236+ event: content_block_delta
237+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" reache"} }
238+
239+ event: content_block_delta
240+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d."} }
241+
242+ event: content_block_delta
243+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Most"} }
244+
245+ event: content_block_delta
246+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" matches"} }
247+
248+ event: content_block_delta
249+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" are from"}}
250+
251+ event: content_block_delta
252+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" github"} }
253+
254+ event: content_block_delta
255+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":".com/jcalabro"} }
256+
257+ event: content_block_delta
258+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"/uscope/assets/go"} }
259+
260+ event: content_block_delta
261+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"backtrace/main.go showing"} }
262+
263+ event: content_block_delta
264+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" a"} }
265+
266+ event: content_block_delta
267+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" simple"} }
268+
269+ event: content_block_delta
270+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" main function that"} }
271+
272+ event: content_block_delta
273+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" calls multiple"} }
274+
275+ event: content_block_delta
276+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" helper"} }
277+
278+ event: content_block_delta
279+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" functions ("} }
280+
281+ event: content_block_delta
282+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"FuncA through"} }
283+
284+ event: content_block_delta
285+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" FuncF)."} }
286+
287+ event: content_block_stop
288+ data: {"type":"content_block_stop","index":0 }
289+
290+ event: message_delta
291+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":3890,"cache_read_input_tokens":13892,"output_tokens":80} }
292+
293+ event: message_stop
294+ data: {"type":"message_stop" }
295+
296+ headers:
297+ Content-Type:
298+ - text/event-stream; charset=utf-8
299+ status: 200 OK
300+ code: 200
301+ duration: 2.432020375s
internal/agent/testdata/TestCoderAgent/anthropic-sonnet/update_a_file.yamlnew file+305
@@ -0,0 +1,305 @@
1+---
2+version: 2
3+interactions:
4+- id: 0
5+ request:
6+ proto: HTTP/1.1
7+ proto_major: 1
8+ proto_minor: 1
9+ content_length: 777
10+ host: ""
11+ body: '{"max_tokens":40,"messages":[{"content":[{"text":"Generate a concise title for the following content:\n\nupdate the main.go file by changing the print to say hello from crush\n \u003cthink\u003e\n\n\u003c/think\u003e","type":"text"}],"role":"user"}],"model":"claude-3-5-haiku-20241022","system":[{"text":"you will generate a short title based on the first message a user begins a conversation with\n\n\u003crules\u003e\n- ensure it is not more than 50 characters long\n- the title should be a summary of the user''s message\n- it should be one line long\n- do not use quotes or colons\n- the entire text you return will be used as the title\n- never return anything that is more than one sentence (one line) long\n\u003c/rules\u003e\n\n /no_think","type":"text"}],"stream":true}'
12+ headers:
13+ Accept:
14+ - application/json
15+ Content-Type:
16+ - application/json
17+ User-Agent:
18+ - Anthropic/Go 1.14.0
19+ url: https://api.anthropic.com/v1/messages
20+ method: POST
21+ response:
22+ proto: HTTP/2.0
23+ proto_major: 2
24+ proto_minor: 0
25+ content_length: -1
26+ body: |+
27+ event: message_start
28+ data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_018Kk1bqYYWgiDzM5DRrtHhL","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":145,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
29+
30+ event: content_block_start
31+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
32+
33+ event: content_block_delta
34+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Update"} }
35+
36+ event: content_block_delta
37+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" main"} }
38+
39+ event: ping
40+ data: {"type": "ping"}
41+
42+ event: content_block_delta
43+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":".go Hello"} }
44+
45+ event: content_block_delta
46+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Print"} }
47+
48+ event: content_block_stop
49+ data: {"type":"content_block_stop","index":0 }
50+
51+ event: message_delta
52+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":145,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":9} }
53+
54+ event: message_stop
55+ data: {"type":"message_stop" }
56+
57+ headers:
58+ Content-Type:
59+ - text/event-stream; charset=utf-8
60+ status: 200 OK
61+ code: 200
62+ duration: 694.563833ms
63+- id: 1
64+ request:
65+ proto: HTTP/1.1
66+ proto_major: 1
67+ proto_minor: 1
68+ content_length: 51878
69+ host: ""
70+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"},{\"text\":\"update the main.go file by changing the print to say hello from crush\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
71+ headers:
72+ Accept:
73+ - application/json
74+ Content-Type:
75+ - application/json
76+ User-Agent:
77+ - Anthropic/Go 1.14.0
78+ url: https://api.anthropic.com/v1/messages
79+ method: POST
80+ response:
81+ proto: HTTP/2.0
82+ proto_major: 2
83+ proto_minor: 0
84+ content_length: -1
85+ body: |+
86+ event: message_start
87+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01NnP68tiieRLUeqHFYM9d1x","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4402,"cache_read_input_tokens":9490,"cache_creation":{"ephemeral_5m_input_tokens":4402,"ephemeral_1h_input_tokens":0},"output_tokens":8,"service_tier":"standard"}} }
88+
89+ event: content_block_start
90+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
91+
92+ event: content_block_delta
93+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"I'll update the main.go file"} }
94+
95+ event: content_block_delta
96+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" to change"} }
97+
98+ event: ping
99+ data: {"type": "ping"}
100+
101+ event: content_block_delta
102+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" the print statement to say \"hello"} }
103+
104+ event: content_block_delta
105+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" from crush\"."} }
106+
107+ event: content_block_stop
108+ data: {"type":"content_block_stop","index":0 }
109+
110+ event: content_block_start
111+ data: {"type":"content_block_start","index":1,"content_block":{"type":"tool_use","id":"toolu_018Si5tyoNCpgSPmmnox9nPA","name":"view","input":{}} }
112+
113+ event: content_block_delta
114+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":""} }
115+
116+ event: content_block_delta
117+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"{\"f"} }
118+
119+ event: content_block_delta
120+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"ile_path\""} }
121+
122+ event: content_block_delta
123+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":": "} }
124+
125+ event: content_block_delta
126+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"\"main.go\"}"} }
127+
128+ event: content_block_stop
129+ data: {"type":"content_block_stop","index":1 }
130+
131+ event: message_delta
132+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":4402,"cache_read_input_tokens":9490,"output_tokens":76}}
133+
134+ event: message_stop
135+ data: {"type":"message_stop" }
136+
137+ headers:
138+ Content-Type:
139+ - text/event-stream; charset=utf-8
140+ status: 200 OK
141+ code: 200
142+ duration: 2.146467334s
143+- id: 2
144+ request:
145+ proto: HTTP/1.1
146+ proto_major: 1
147+ proto_minor: 1
148+ content_length: 52436
149+ host: ""
150+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"type\":\"text\"},{\"text\":\"update the main.go file by changing the print to say hello from crush\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"text\":\"I'll update the main.go file to change the print statement to say \\\"hello from crush\\\".\",\"type\":\"text\"},{\"id\":\"toolu_018Si5tyoNCpgSPmmnox9nPA\",\"input\":{\"file_path\":\"main.go\"},\"name\":\"view\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_018Si5tyoNCpgSPmmnox9nPA\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cfile\\u003e\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
151+ headers:
152+ Accept:
153+ - application/json
154+ Content-Type:
155+ - application/json
156+ User-Agent:
157+ - Anthropic/Go 1.14.0
158+ url: https://api.anthropic.com/v1/messages
159+ method: POST
160+ response:
161+ proto: HTTP/2.0
162+ proto_major: 2
163+ proto_minor: 0
164+ content_length: -1
165+ body: |+
166+ event: message_start
167+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01NthBKRMKB2CywucN3VqWTz","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":140,"cache_read_input_tokens":13892,"cache_creation":{"ephemeral_5m_input_tokens":140,"ephemeral_1h_input_tokens":0},"output_tokens":18,"service_tier":"standard"}} }
168+
169+ event: content_block_start
170+ data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01EZmEG6RVLRQCxSvDa18Att","name":"edit","input":{}} }
171+
172+ event: content_block_delta
173+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }
174+
175+ event: content_block_delta
176+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"file_pat"} }
177+
178+ event: content_block_delta
179+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"h\""} }
180+
181+ event: content_block_delta
182+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":": \"main."} }
183+
184+ event: content_block_delta
185+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"go\""} }
186+
187+ event: content_block_delta
188+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"old_strin"} }
189+
190+ event: content_block_delta
191+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"g\": \"f"} }
192+
193+ event: content_block_delta
194+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"un"} }
195+
196+ event: content_block_delta
197+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"c main() {\\n"} }
198+
199+ event: content_block_delta
200+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\\tfmt.Prin"} }
201+
202+ event: content_block_delta
203+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tln(\\\"Hel"} }
204+
205+ event: content_block_delta
206+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"lo, W"} }
207+
208+ event: content_block_delta
209+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"orld!\\\")\\"} }
210+
211+ event: content_block_delta
212+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"n}\""} }
213+
214+ event: content_block_delta
215+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"new_str"} }
216+
217+ event: content_block_delta
218+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ing\": \""} }
219+
220+ event: content_block_delta
221+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"fun"} }
222+
223+ event: content_block_delta
224+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"c m"} }
225+
226+ event: content_block_delta
227+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ain() {"} }
228+
229+ event: content_block_delta
230+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\\n\\tfmt.Pr"} }
231+
232+ event: content_block_delta
233+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"intln(\\"} }
234+
235+ event: content_block_delta
236+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"hello from"} }
237+
238+ event: content_block_delta
239+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" cru"} }
240+
241+ event: content_block_delta
242+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"sh\\\")\\n}\"}"} }
243+
244+ event: content_block_stop
245+ data: {"type":"content_block_stop","index":0 }
246+
247+ event: message_delta
248+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":140,"cache_read_input_tokens":13892,"output_tokens":123} }
249+
250+ event: message_stop
251+ data: {"type":"message_stop" }
252+
253+ headers:
254+ Content-Type:
255+ - text/event-stream; charset=utf-8
256+ status: 200 OK
257+ code: 200
258+ duration: 2.421450125s
259+- id: 3
260+ request:
261+ proto: HTTP/1.1
262+ proto_major: 1
263+ proto_minor: 1
264+ content_length: 52982
265+ host: ""
266+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"type\":\"text\"},{\"text\":\"update the main.go file by changing the print to say hello from crush\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"text\":\"I'll update the main.go file to change the print statement to say \\\"hello from crush\\\".\",\"type\":\"text\"},{\"id\":\"toolu_018Si5tyoNCpgSPmmnox9nPA\",\"input\":{\"file_path\":\"main.go\"},\"name\":\"view\",\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_018Si5tyoNCpgSPmmnox9nPA\",\"content\":[{\"text\":\"\\u003cfile\\u003e\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01EZmEG6RVLRQCxSvDa18Att\",\"input\":{\"file_path\":\"main.go\",\"new_string\":\"func main() {\\n\\tfmt.Println(\\\"hello from crush\\\")\\n}\",\"old_string\":\"func main() {\\n\\tfmt.Println(\\\"Hello, World!\\\")\\n}\"},\"name\":\"edit\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01EZmEG6RVLRQCxSvDa18Att\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cresult\\u003e\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file/main.go\\n\\u003c/result\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
267+ headers:
268+ Accept:
269+ - application/json
270+ Content-Type:
271+ - application/json
272+ User-Agent:
273+ - Anthropic/Go 1.14.0
274+ url: https://api.anthropic.com/v1/messages
275+ method: POST
276+ response:
277+ proto: HTTP/2.0
278+ proto_major: 2
279+ proto_minor: 0
280+ content_length: -1
281+ body: |+
282+ event: message_start
283+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01W1Etzg5mEgGDXkqHFqza4x","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":175,"cache_read_input_tokens":14032,"cache_creation":{"ephemeral_5m_input_tokens":175,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
284+
285+ event: content_block_start
286+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
287+
288+ event: content_block_delta
289+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Done"} }
290+
291+ event: content_block_stop
292+ data: {"type":"content_block_stop","index":0 }
293+
294+ event: message_delta
295+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":175,"cache_read_input_tokens":14032,"output_tokens":4} }
296+
297+ event: message_stop
298+ data: {"type":"message_stop" }
299+
300+ headers:
301+ Content-Type:
302+ - text/event-stream; charset=utf-8
303+ status: 200 OK
304+ code: 200
305+ duration: 5.010124916s
internal/agent/testdata/TestCoderAgent/anthropic-sonnet/write_tool.yamlnew file+228
@@ -0,0 +1,228 @@
1+---
2+version: 2
3+interactions:
4+- id: 0
5+ request:
6+ proto: HTTP/1.1
7+ proto_major: 1
8+ proto_minor: 1
9+ content_length: 51915
10+ host: ""
11+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"},{\"text\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/write_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
12+ headers:
13+ Accept:
14+ - application/json
15+ Content-Type:
16+ - application/json
17+ User-Agent:
18+ - Anthropic/Go 1.14.0
19+ url: https://api.anthropic.com/v1/messages
20+ method: POST
21+ response:
22+ proto: HTTP/2.0
23+ proto_major: 2
24+ proto_minor: 0
25+ content_length: -1
26+ body: |+
27+ event: message_start
28+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01EU4nWu2YGh9eeRAuWsZV1d","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4416,"cache_read_input_tokens":9490,"cache_creation":{"ephemeral_5m_input_tokens":4416,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
29+
30+ event: content_block_start
31+ data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01RRLkwW4DxPSzksuQPsoLY2","name":"write","input":{}}}
32+
33+ event: content_block_delta
34+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }
35+
36+ event: content_block_delta
37+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"file_pa"} }
38+
39+ event: content_block_delta
40+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"th\": \"/"} }
41+
42+ event: content_block_delta
43+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tm"} }
44+
45+ event: content_block_delta
46+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"p/crush-"} }
47+
48+ event: content_block_delta
49+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"test/Test"}}
50+
51+ event: content_block_delta
52+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"Code"} }
53+
54+ event: content_block_delta
55+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"rAgent/a"} }
56+
57+ event: content_block_delta
58+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"nthr"} }
59+
60+ event: content_block_delta
61+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"opic-sonn"} }
62+
63+ event: content_block_delta
64+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"et/write_"} }
65+
66+ event: content_block_delta
67+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tool/c"}}
68+
69+ event: content_block_delta
70+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"on"} }
71+
72+ event: content_block_delta
73+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"fig.json\""} }
74+
75+ event: content_block_delta
76+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"co"} }
77+
78+ event: content_block_delta
79+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ntent"}}
80+
81+ event: content_block_delta
82+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\": "} }
83+
84+ event: content_block_delta
85+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"{\\\"name\\\""} }
86+
87+ event: content_block_delta
88+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":": \\\"test\\"} }
89+
90+ event: content_block_delta
91+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\", \\\"versi"} }
92+
93+ event: content_block_delta
94+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"on"} }
95+
96+ event: content_block_delta
97+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\\\": "} }
98+
99+ event: content_block_delta
100+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\\\"1"} }
101+
102+ event: content_block_delta
103+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".0"} }
104+
105+ event: content_block_delta
106+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".0\\\"}\"}"} }
107+
108+ event: content_block_stop
109+ data: {"type":"content_block_stop","index":0 }
110+
111+ event: message_delta
112+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":4416,"cache_read_input_tokens":9490,"output_tokens":109} }
113+
114+ event: message_stop
115+ data: {"type":"message_stop" }
116+
117+ headers:
118+ Content-Type:
119+ - text/event-stream; charset=utf-8
120+ status: 200 OK
121+ code: 200
122+ duration: 2.502714167s
123+- id: 1
124+ request:
125+ proto: HTTP/1.1
126+ proto_major: 1
127+ proto_minor: 1
128+ content_length: 817
129+ host: ""
130+ body: '{"max_tokens":40,"messages":[{"content":[{"text":"Generate a concise title for the following content:\n\nuse write to create a new file called config.json with content ''{\"name\": \"test\", \"version\": \"1.0.0\"}''\n \u003cthink\u003e\n\n\u003c/think\u003e","type":"text"}],"role":"user"}],"model":"claude-3-5-haiku-20241022","system":[{"text":"you will generate a short title based on the first message a user begins a conversation with\n\n\u003crules\u003e\n- ensure it is not more than 50 characters long\n- the title should be a summary of the user''s message\n- it should be one line long\n- do not use quotes or colons\n- the entire text you return will be used as the title\n- never return anything that is more than one sentence (one line) long\n\u003c/rules\u003e\n\n /no_think","type":"text"}],"stream":true}'
131+ headers:
132+ Accept:
133+ - application/json
134+ Content-Type:
135+ - application/json
136+ User-Agent:
137+ - Anthropic/Go 1.14.0
138+ url: https://api.anthropic.com/v1/messages
139+ method: POST
140+ response:
141+ proto: HTTP/2.0
142+ proto_major: 2
143+ proto_minor: 0
144+ content_length: -1
145+ body: |+
146+ event: message_start
147+ data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01UXnLVmCRU6XCSfGYTXbA1w","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":161,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
148+
149+ event: content_block_start
150+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
151+
152+ event: content_block_delta
153+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Create"} }
154+
155+ event: content_block_delta
156+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" config"} }
157+
158+ event: ping
159+ data: {"type": "ping"}
160+
161+ event: content_block_delta
162+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":".json file with JSON"} }
163+
164+ event: content_block_delta
165+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" data"} }
166+
167+ event: content_block_stop
168+ data: {"type":"content_block_stop","index":0 }
169+
170+ event: message_delta
171+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":161,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":11} }
172+
173+ event: message_stop
174+ data: {"type":"message_stop" }
175+
176+ headers:
177+ Content-Type:
178+ - text/event-stream; charset=utf-8
179+ status: 200 OK
180+ code: 200
181+ duration: 6.654356666s
182+- id: 2
183+ request:
184+ proto: HTTP/1.1
185+ proto_major: 1
186+ proto_minor: 1
187+ content_length: 52447
188+ host: ""
189+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"\\u003csystem_reminder\\u003eThis is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.\\u003c/system_reminder\\u003e\",\"type\":\"text\"},{\"text\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01RRLkwW4DxPSzksuQPsoLY2\",\"input\":{\"content\":\"{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}\",\"file_path\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/write_tool/config.json\"},\"name\":\"write\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01RRLkwW4DxPSzksuQPsoLY2\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cresult\\u003e\\nFile successfully written: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/write_tool/config.json\\n\\u003c/result\\u003e\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default \\u003c4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\".\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003ctask_completion\\u003e\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n\\u003c/task_completion\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/write_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands with automatic background conversion for long-running tasks.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cbackground_execution\\u003e\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `\\u0026` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n\\u003c/background_execution\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- PARTIAL SUCCESS: If some edits fail, successful edits are still applied. Failed edits are returned in the response.\\n- File is modified if at least one edit succeeds.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are applied in order; successful edits are kept even if later edits fail.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n5. Check the response for failed edits and retry them if needed.\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation continues even if some edits fail; check response for failed edits.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf some edits fail:\\n1. Check the response metadata for the list of failed edits with their error messages.\\n2. View the file again to see the current state after successful edits.\\n3. Adjust the failed edits based on the new file content.\\n4. Retry the failed edits with corrected old_string values.\\n5. Consider breaking complex batches into smaller, independent operations.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don't leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you're certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Review failed edits in the response and retry with corrections.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n✅ Correct: Handling partial success\\n\\n```\\n// If edit 2 fails, edit 1 is still applied\\n// Response will indicate:\\n// - edits_applied: 1\\n// - edits_failed: [{index: 2, error: \\\"...\\\", edit: {...}}]\\n// You can then retry edit 2 with corrected context\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches raw content from URL and returns it in specified format without any AI processing.\\n\\n\\u003cwhen_to_use\\u003e\\nUse this tool when you need:\\n- Raw, unprocessed content from a URL\\n- Direct access to API responses or JSON data\\n- HTML/text/markdown content without interpretation\\n- Simple, fast content retrieval without analysis\\n- To save tokens by avoiding AI processing\\n\\nDO NOT use this tool when you need to:\\n- Extract specific information from a webpage (use agentic_fetch instead)\\n- Answer questions about web content (use agentic_fetch instead)\\n- Analyze or summarize web pages (use agentic_fetch instead)\\n\\u003c/when_to_use\\u003e\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Fast and lightweight - no AI processing\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Returns raw content only - no analysis or extraction\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n- If the user asks to analyze or extract from a page, use agentic_fetch instead\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n- Supports image files (PNG, JPEG, GIF, BMP, SVG, WebP)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n- Renders image files directly in terminal\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 5MB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Binary files (except images) cannot be displayed\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n- View tool automatically detects and renders image files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
190+ headers:
191+ Accept:
192+ - application/json
193+ Content-Type:
194+ - application/json
195+ User-Agent:
196+ - Anthropic/Go 1.14.0
197+ url: https://api.anthropic.com/v1/messages
198+ method: POST
199+ response:
200+ proto: HTTP/2.0
201+ proto_major: 2
202+ proto_minor: 0
203+ content_length: -1
204+ body: |+
205+ event: message_start
206+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01Lcun1BxRxcbqd6RQxtBmLz","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":155,"cache_read_input_tokens":13906,"cache_creation":{"ephemeral_5m_input_tokens":155,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }
207+
208+ event: content_block_start
209+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
210+
211+ event: content_block_delta
212+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Done"} }
213+
214+ event: content_block_stop
215+ data: {"type":"content_block_stop","index":0 }
216+
217+ event: message_delta
218+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":4,"cache_creation_input_tokens":155,"cache_read_input_tokens":13906,"output_tokens":4} }
219+
220+ event: message_stop
221+ data: {"type":"message_stop" }
222+
223+ headers:
224+ Content-Type:
225+ - text/event-stream; charset=utf-8
226+ status: 200 OK
227+ code: 200
228+ duration: 3.788904042s
internal/agent/testdata/TestCoderAgent/glm-5.1/bash_tool.yamldeleted−425
@@ -1,425 +0,0 @@
1−---
2−version: 2
3−interactions:
4−- id: 0
5− request:
6− proto: HTTP/1.1
7− proto_major: 1
8− proto_minor: 1
9− content_length: 853
10− host: ""
11− body: '{"messages":[{"content":"You will generate a short title based on the first message a user begins a conversation with.\n\n<rules>\n- Keep the title in the same language that the user wrote their message in.\n- Ensure it is not more than 50 characters long.\n- The title should be a summary of the user''s message.\n- It should be one line long.\n- Do not use quotes or colons.\n- The entire text you return will be used as the title.\n- Never return anything that is more than one sentence (one line) long.\n</rules>\n\n /no_think","role":"system"},{"content":"Generate a concise title for the following content:\n\nuse bash to create a file named test.txt with content ''hello bash''. do not print its timestamp\n <think>\n\n</think>","role":"user"}],"model":"gpt-oss-120b","max_completion_tokens":40,"stream_options":{"include_usage":true},"stream":true}'
12− headers:
13− Accept:
14− - application/json
15− Content-Type:
16− - application/json
17− User-Agent:
18− - Charm-Crush/devel (https://charm.land/crush)
19− url: https://hyper.charm.land/v1/chat/completions
20− method: POST
21− response:
22− proto: HTTP/2.0
23− proto_major: 2
24− proto_minor: 0
25− content_length: -1
26− uncompressed: true
27− body: |+
28− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
29−
30− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"We"},"finish_reason":null}]}
31−
32− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" need"},"finish_reason":null}]}
33−
34− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
35−
36− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" generate"},"finish_reason":null}]}
37−
38− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
39−
40− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" short"},"finish_reason":null}]}
41−
42− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
43−
44− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" based"},"finish_reason":null}]}
45−
46− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" on"},"finish_reason":null}]}
47−
48− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
49−
50− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" user's"},"finish_reason":null}]}
51−
52− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" first"},"finish_reason":null}]}
53−
54− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" message"},"finish_reason":null}]}
55−
56− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
57−
58− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" The"},"finish_reason":null}]}
59−
60− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
61−
62− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" wrote"},"finish_reason":null}]}
63−
64− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
65−
66− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" English"},"finish_reason":null}]}
67−
68− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
69−
70− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Title"},"finish_reason":null}]}
71−
72− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" must"},"finish_reason":null}]}
73−
74− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
75−
76− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \u003c="},"finish_reason":null}]}
77−
78− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
79−
80− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
81−
82− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
83−
84− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" no"},"finish_reason":null}]}
85−
86− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
87−
88− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"/"},"finish_reason":null}]}
89−
90− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"col"},"finish_reason":null}]}
91−
92− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ons"},"finish_reason":null}]}
93−
94− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
95−
96− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" one"},"finish_reason":null}]}
97−
98− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
99−
100− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
101−
102− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" no"},"finish_reason":null}]}
103−
104− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" more"},"finish_reason":null}]}
105−
106− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" than"},"finish_reason":null}]}
107−
108− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" one"},"finish_reason":null}]}
109−
110− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" sentence"},"finish_reason":null}]}
111−
112− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
113−
114− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Summ"},"finish_reason":null}]}
115−
116− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ar"},"finish_reason":null}]}
117−
118− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ize"},"finish_reason":null}]}
119−
120− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
121−
122− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
123−
124− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"bash"},"finish_reason":null}]}
125−
126− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" create"},"finish_reason":null}]}
127−
128− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" test"},"finish_reason":null}]}
129−
130− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".txt"},"finish_reason":null}]}
131−
132− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
133−
134− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" hello"},"finish_reason":null}]}
135−
136− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" bash"},"finish_reason":null}]}
137−
138− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" without"},"finish_reason":null}]}
139−
140− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" timestamp"},"finish_reason":null}]}
141−
142− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
143−
144− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Let's"},"finish_reason":null}]}
145−
146− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" craft"},"finish_reason":null}]}
147−
148− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
149−
150− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
151−
152− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Create"},"finish_reason":null}]}
153−
154− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" test"},"finish_reason":null}]}
155−
156− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".txt"},"finish_reason":null}]}
157−
158− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
159−
160− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" hello"},"finish_reason":null}]}
161−
162− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" bash"},"finish_reason":null}]}
163−
164− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" using"},"finish_reason":null}]}
165−
166− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Bash"},"finish_reason":null}]}
167−
168− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
169−
170− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
171−
172− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" under"},"finish_reason":null}]}
173−
174− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
175−
176− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
177−
178− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
179−
180− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
181−
182− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
183−
184− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
185−
186− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Create"},"finish_reason":null}]}
187−
188− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" test"},"finish_reason":null}]}
189−
190− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".txt"},"finish_reason":null}]}
191−
192− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
193−
194− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" hello"},"finish_reason":null}]}
195−
196− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" bash"},"finish_reason":null}]}
197−
198− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" using"},"finish_reason":null}]}
199−
200− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Bash"},"finish_reason":null}]}
201−
202− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
203−
204− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ="},"finish_reason":null}]}
205−
206− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
207−
208− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"38"},"finish_reason":null}]}
209−
210− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
211−
212− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
213−
214− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" No"},"finish_reason":null}]}
215−
216− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
217−
218− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
219−
220− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Good"},"finish_reason":null}]}
221−
222− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
223−
224− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Create"},"finish_reason":null}]}
225−
226− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" test"},"finish_reason":null}]}
227−
228− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":".txt"},"finish_reason":null}]}
229−
230− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" with"},"finish_reason":null}]}
231−
232− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" hello"},"finish_reason":null}]}
233−
234− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" bash"},"finish_reason":null}]}
235−
236− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" using"},"finish_reason":null}]}
237−
238− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Bash"},"finish_reason":null}]}
239−
240− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
241−
242− data: {"id":"chatcmpl-9b4429c7811fb2c7070cc503","object":"chat.completion.chunk","created":1782413792,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":224,"completion_tokens":115,"total_tokens":339,"completion_tokens_details":{"reasoning_tokens":98},"cost":{"usd":0.00015733800000000003,"hypercredits":0.0031467600000000006},"remaining":{"hypercredits":0}}}
243−
244− data: [DONE]
245−
246− headers:
247− Content-Type:
248− - text/event-stream
249− status: 200 OK
250− code: 200
251− duration: 700.546792ms
252−- id: 1
253− request:
254− proto: HTTP/1.1
255− proto_major: 1
256− proto_minor: 1
257− content_length: 35672
258− host: ""
259− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ THE RELEVANT CONTEXT BEFORE EDITING**: Never edit a file you haven't already read the relevant context for in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\". When committing, follow the `<git_commits>` format from the bash tool description exactly, including any configured attribution lines.\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **TOOL CONSTRAINTS**: Only use documented tools. Never attempt 'apply_patch' or 'apply_diff' - they don't exist. Use 'edit' or 'multiedit' instead.\\n14. **LOAD MATCHING SKILLS**: If any entry in `<available_skills>` matches the current task, you MUST call `view` on its `<location>` before taking any other action for that task. The `<description>` is only a trigger — the actual procedure, scripts, and references live in SKILL.md. Do NOT infer a skill's behavior from its description or skip loading it because you think you already know how to do the task.\\n15. **LIMIT FILE READS**: Avoid reading entire files, as they can be very large. Read only the sections you need using 'offset' and 'limit' parameters.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- ALWAYS think and respond in the same spoken language the prompt was written in.\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\n**Available edit tools:**\\n- `edit` - Single find/replace in a file\\n- `multiedit` - Multiple find/replace operations in one file\\n- `write` - Create/overwrite entire file\\n\\nNever use `apply_patch` or similar - those tools don't exist.\\n\\nCritical: ALWAYS read the relevant context of files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the relevant context first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</editing_files>\\n\\n<whitespace_and_exact_matching>\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n</whitespace_and_exact_matching>\\n\\n<task_completion>\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n</task_completion>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences\\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n<bash_commands>\\n**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/glm-5.1/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n<available_skills>\\n <skill>\\n <name>crush-hooks</name>\\n <description>Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.</description>\\n <location>crush://skills/crush-hooks/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n <skill>\\n <name>jq</name>\\n <description>Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.</description>\\n <location>crush://skills/jq/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n</available_skills>\\n\\n<skills_usage>\\nThe `<description>` of each skill is a TRIGGER — it tells you *when* a skill applies. It is NOT a specification of what the skill does or how to do it. The procedure, scripts, commands, references, and required flags live only in the SKILL.md body. You do not know what a skill actually does until you have read its SKILL.md.\\n\\nMANDATORY activation flow:\\n1. Scan `<available_skills>` against the current user task.\\n2. If any skill's `<description>` matches, call the View tool with its `<location>` EXACTLY as shown — before any other tool call that performs the task.\\n3. Read the entire SKILL.md and follow its instructions.\\n4. Only then execute the task, using the skill's prescribed commands/tools.\\n\\nDo NOT skip step 2 because you think you already know how to do the task. Do NOT infer a skill's behavior from its name or description. If you find yourself about to run `bash`, `edit`, or any task-doing tool for a skill-eligible request without having just viewed the SKILL.md, stop and load the skill first.\\n\\nBuiltin skills (type=builtin) use virtual `crush://skills/...` location identifiers. The \\\"crush://\\\" prefix is NOT a URL, network address, or MCP resource — it is a special internal identifier the View tool understands natively. Pass the `<location>` verbatim to View.\\n\\nDo not use MCP tools (including read_mcp_resource) to load skills.\\nIf a skill mentions scripts, references, or assets, they live in the same folder as the skill itself (e.g., scripts/, references/, assets/ subdirectories within the skill's folder).\\n</skills_usage>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"<system_reminder>This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.</system_reminder>\",\"role\":\"user\"},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'. do not print its timestamp\",\"role\":\"user\"}],\"model\":\"glm-5.1\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Execute shell commands; long-running commands automatically move to background and return a shell ID.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute (default, configurable via `auto_background_after`) automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<background_execution>\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `&` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n</background_execution>\\n\\n<git_message_quality>\\nThese rules apply whenever creating or updating commit messages, PR titles, or PR bodies:\\n\\n- Messages MUST be understandable to someone unfamiliar with the codebase.\\n- Before creating or updating a message, verify this litmus test: a new contributor reading only the commit message or PR title/body should understand what problem this solves, why it matters, and the impact without opening files, reading the diff, or knowing internal code names.\\n- Avoid code identifiers, filenames, function names, and implementation details unless they are necessary for understanding the user-facing impact.\\n- Bad: \\\"Add NameFromHex with sync.Once lazy init\\\"\\n- Good: \\\"Improve color name lookup performance while keeping startup fast\\\"\\n</git_message_quality>\\n\\n<commit_messages>\\nCommit messages are for future readers scanning history. Before committing:\\n\\n- Follow <git_message_quality>.\\n- Draft a concise 1-2 sentence message focusing on why the change exists and what outcome it enables, not a list of files or implementation details.\\n- Use clear, accurate verbs (\\\"add\\\"=new capability, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix) and avoid generic messages.\\n- The first line MUST be under 72 characters.\\n- Add a body only when it is needed to explain the reasoning, tradeoffs, or important context; wrap body lines at 72 characters.\\n- If the change is internal-only, still describe the benefit or maintenance outcome rather than naming private code.\\n- Bad: \\\"fix: nil pointer in session.go\\\"\\n- Good: \\\"fix: prevent session loading from crashing on missing metadata\\\"\\n- Bad: \\\"refactor: move PromptBuilder into internal/agent\\\"\\n- Good: \\\"refactor: make prompt assembly easier to maintain\\\"\\n</commit_messages>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond the context of git\\n\\n4. Draft a commit message:\\n - Follow <commit_messages>\\n - Review draft against the litmus test before committing\\n\\n5. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\nCommit message here.\\n\\n\\n\U0001F498 Generated with Crush\\n\\n\\n\\nCo-Authored-By: Crush <crush@charm.land>\\n\\nEOF\\n)\\\"\\n\\n6. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n7. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m.\\n</git_commits>\\n\\n<pull_requests>\\n\\n\\nWhen user asks you to create or update a PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n\\n3. Commit changes if needed\\n\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n\\n6. Draft a PR message:\\n - Follow <git_message_quality>\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Use clear, concise language\\n - Provide an accurate reflection of changes and purpose\\n - Avoid generic summaries; messages should be thoughtful\\n - Review draft against the litmus test before creating or updating the PR\\n\\n7. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n<summary>\\n\\n\U0001F498 Generated with Crush\\n\\nEOF\\n)\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"auto_background_after\":{\"description\":\"Seconds to wait before automatically moving the command to a background job (default: 60)\",\"type\":\"integer\"},\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Download a URL directly to a local file (binary-safe, streaming, max 600s timeout); overwrites without warning. For reading content into context use fetch.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edit a file by exact find-and-replace; can also create or delete content. For renames/moves use bash. For large edits use write.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Apply multiple find-and-replace edits to a single file in one operation; edits run sequentially. Prefer over edit for multiple changes to the same file. Same exact-match rules as edit apply.\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetch raw content from a URL as text, markdown, or html (max 100KB); no AI processing. For analysis or extraction use agentic_fetch.\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Find files by name/pattern (glob syntax), sorted by modification time; max 100 results; skips hidden files. Use grep to search file contents.\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Search file contents by regex or literal text; returns matching file paths sorted by modification time (max 100); respects .gitignore. Use glob to filter by filename, not contents.\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"List files and directories as a tree; skips hidden files and common system dirs; max 1000 files. Use glob to find files by pattern, grep to search contents.\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public GitHub repositories via Sourcegraph; supports regex, language/repo/file filters, and symbol search (max 20 results). Only searches public repos.\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Read a file by path with line numbers; supports offset and line limit (default 200, max 200KB returned file content section); renders images (PNG, JPEG, GIF, WebP); use ls for directories.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 200)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Create or overwrite a file with given content; auto-creates parent dirs. Cannot append. Read the file first to avoid conflicts. For surgical changes use edit or multiedit.\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
260− headers:
261− Accept:
262− - application/json
263− Content-Type:
264− - application/json
265− User-Agent:
266− - Charm-Crush/devel (https://charm.land/crush)
267− url: https://hyper.charm.land/v1/chat/completions
268− method: POST
269− response:
270− proto: HTTP/2.0
271− proto_major: 2
272− proto_minor: 0
273− content_length: -1
274− uncompressed: true
275− body: |+
276− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
277−
278− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
279−
280− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
281−
282− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" wants"},"finish_reason":null}]}
283−
284− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" me"},"finish_reason":null}]}
285−
286− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
287−
288− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" create"},"finish_reason":null}]}
289−
290− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
291−
292− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" file"},"finish_reason":null}]}
293−
294− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" named"},"finish_reason":null}]}
295−
296− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" test"},"finish_reason":null}]}
297−
298− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":".txt"},"finish_reason":null}]}
299−
300− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
301−
302− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
303−
304− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
305−
306− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"hello"},"finish_reason":null}]}
307−
308− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" bash"},"finish_reason":null}]}
309−
310− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"'"},"finish_reason":null}]}
311−
312− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" using"},"finish_reason":null}]}
313−
314− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
315−
316− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" bash"},"finish_reason":null}]}
317−
318− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" tool"},"finish_reason":null}]}
319−
320− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
321−
322− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
323−
324− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" not"},"finish_reason":null}]}
325−
326− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" print"},"finish_reason":null}]}
327−
328− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" its"},"finish_reason":null}]}
329−
330− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" timestamp"},"finish_reason":null}]}
331−
332− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
333−
334− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_51c682620b31061c","type":"function","index":0,"function":{"name":"bash","arguments":""}}]},"finish_reason":null}]}
335−
336− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\"command\": \""}}]},"finish_reason":null}]}
337−
338− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"echo"}}]},"finish_reason":null}]}
339−
340− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" '"}}]},"finish_reason":null}]}
341−
342− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"hello"}}]},"finish_reason":null}]}
343−
344− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" bash"}}]},"finish_reason":null}]}
345−
346− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"'"}}]},"finish_reason":null}]}
347−
348− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \u003e"}}]},"finish_reason":null}]}
349−
350− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" test"}}]},"finish_reason":null}]}
351−
352− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".txt"}}]},"finish_reason":null}]}
353−
354− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\""}}]},"finish_reason":null}]}
355−
356− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":", \"description\": \""}}]},"finish_reason":null}]}
357−
358− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Create"}}]},"finish_reason":null}]}
359−
360− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" test"}}]},"finish_reason":null}]}
361−
362− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".txt"}}]},"finish_reason":null}]}
363−
364− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" with"}}]},"finish_reason":null}]}
365−
366− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" content"}}]},"finish_reason":null}]}
367−
368− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\""}}]},"finish_reason":null}]}
369−
370− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
371−
372− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
373−
374− data: {"id":"chatcmpl-5baef5f0d9ce99f46bc74840","object":"chat.completion.chunk","created":1782413793,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":686,"completion_tokens":56,"total_tokens":8221,"prompt_tokens_details":{"cached_tokens":7479},"completion_tokens_details":{"reasoning_tokens":32},"cost":{"usd":0.0013476,"hypercredits":0.026952},"remaining":{"hypercredits":0}}}
375−
376− data: [DONE]
377−
378− headers:
379− Content-Type:
380− - text/event-stream
381− status: 200 OK
382− code: 200
383− duration: 1.461643167s
384−- id: 2
385− request:
386− proto: HTTP/1.1
387− proto_major: 1
388− proto_minor: 1
389− content_length: 36122
390− host: ""
391− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ THE RELEVANT CONTEXT BEFORE EDITING**: Never edit a file you haven't already read the relevant context for in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\". When committing, follow the `<git_commits>` format from the bash tool description exactly, including any configured attribution lines.\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **TOOL CONSTRAINTS**: Only use documented tools. Never attempt 'apply_patch' or 'apply_diff' - they don't exist. Use 'edit' or 'multiedit' instead.\\n14. **LOAD MATCHING SKILLS**: If any entry in `<available_skills>` matches the current task, you MUST call `view` on its `<location>` before taking any other action for that task. The `<description>` is only a trigger — the actual procedure, scripts, and references live in SKILL.md. Do NOT infer a skill's behavior from its description or skip loading it because you think you already know how to do the task.\\n15. **LIMIT FILE READS**: Avoid reading entire files, as they can be very large. Read only the sections you need using 'offset' and 'limit' parameters.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- ALWAYS think and respond in the same spoken language the prompt was written in.\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\n**Available edit tools:**\\n- `edit` - Single find/replace in a file\\n- `multiedit` - Multiple find/replace operations in one file\\n- `write` - Create/overwrite entire file\\n\\nNever use `apply_patch` or similar - those tools don't exist.\\n\\nCritical: ALWAYS read the relevant context of files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the relevant context first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</editing_files>\\n\\n<whitespace_and_exact_matching>\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n</whitespace_and_exact_matching>\\n\\n<task_completion>\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n</task_completion>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences\\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n<bash_commands>\\n**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/glm-5.1/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n<available_skills>\\n <skill>\\n <name>crush-hooks</name>\\n <description>Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.</description>\\n <location>crush://skills/crush-hooks/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n <skill>\\n <name>jq</name>\\n <description>Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.</description>\\n <location>crush://skills/jq/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n</available_skills>\\n\\n<skills_usage>\\nThe `<description>` of each skill is a TRIGGER — it tells you *when* a skill applies. It is NOT a specification of what the skill does or how to do it. The procedure, scripts, commands, references, and required flags live only in the SKILL.md body. You do not know what a skill actually does until you have read its SKILL.md.\\n\\nMANDATORY activation flow:\\n1. Scan `<available_skills>` against the current user task.\\n2. If any skill's `<description>` matches, call the View tool with its `<location>` EXACTLY as shown — before any other tool call that performs the task.\\n3. Read the entire SKILL.md and follow its instructions.\\n4. Only then execute the task, using the skill's prescribed commands/tools.\\n\\nDo NOT skip step 2 because you think you already know how to do the task. Do NOT infer a skill's behavior from its name or description. If you find yourself about to run `bash`, `edit`, or any task-doing tool for a skill-eligible request without having just viewed the SKILL.md, stop and load the skill first.\\n\\nBuiltin skills (type=builtin) use virtual `crush://skills/...` location identifiers. The \\\"crush://\\\" prefix is NOT a URL, network address, or MCP resource — it is a special internal identifier the View tool understands natively. Pass the `<location>` verbatim to View.\\n\\nDo not use MCP tools (including read_mcp_resource) to load skills.\\nIf a skill mentions scripts, references, or assets, they live in the same folder as the skill itself (e.g., scripts/, references/, assets/ subdirectories within the skill's folder).\\n</skills_usage>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"<system_reminder>This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.</system_reminder>\",\"role\":\"user\"},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'. do not print its timestamp\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_51c682620b31061c\",\"function\":{\"arguments\":\"{\\\"command\\\": \\\"echo 'hello bash' > test.txt\\\", \\\"description\\\": \\\"Create test.txt with content\\\"}\",\"name\":\"bash\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"The user wants me to create a file named test.txt with content 'hello bash' using the bash tool, and not print its timestamp.\"},{\"content\":\"no output\",\"tool_call_id\":\"call_51c682620b31061c\",\"role\":\"tool\"}],\"model\":\"glm-5.1\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Execute shell commands; long-running commands automatically move to background and return a shell ID.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute (default, configurable via `auto_background_after`) automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<background_execution>\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `&` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n</background_execution>\\n\\n<git_message_quality>\\nThese rules apply whenever creating or updating commit messages, PR titles, or PR bodies:\\n\\n- Messages MUST be understandable to someone unfamiliar with the codebase.\\n- Before creating or updating a message, verify this litmus test: a new contributor reading only the commit message or PR title/body should understand what problem this solves, why it matters, and the impact without opening files, reading the diff, or knowing internal code names.\\n- Avoid code identifiers, filenames, function names, and implementation details unless they are necessary for understanding the user-facing impact.\\n- Bad: \\\"Add NameFromHex with sync.Once lazy init\\\"\\n- Good: \\\"Improve color name lookup performance while keeping startup fast\\\"\\n</git_message_quality>\\n\\n<commit_messages>\\nCommit messages are for future readers scanning history. Before committing:\\n\\n- Follow <git_message_quality>.\\n- Draft a concise 1-2 sentence message focusing on why the change exists and what outcome it enables, not a list of files or implementation details.\\n- Use clear, accurate verbs (\\\"add\\\"=new capability, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix) and avoid generic messages.\\n- The first line MUST be under 72 characters.\\n- Add a body only when it is needed to explain the reasoning, tradeoffs, or important context; wrap body lines at 72 characters.\\n- If the change is internal-only, still describe the benefit or maintenance outcome rather than naming private code.\\n- Bad: \\\"fix: nil pointer in session.go\\\"\\n- Good: \\\"fix: prevent session loading from crashing on missing metadata\\\"\\n- Bad: \\\"refactor: move PromptBuilder into internal/agent\\\"\\n- Good: \\\"refactor: make prompt assembly easier to maintain\\\"\\n</commit_messages>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond the context of git\\n\\n4. Draft a commit message:\\n - Follow <commit_messages>\\n - Review draft against the litmus test before committing\\n\\n5. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\nCommit message here.\\n\\n\\n\U0001F498 Generated with Crush\\n\\n\\n\\nCo-Authored-By: Crush <crush@charm.land>\\n\\nEOF\\n)\\\"\\n\\n6. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n7. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m.\\n</git_commits>\\n\\n<pull_requests>\\n\\n\\nWhen user asks you to create or update a PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n\\n3. Commit changes if needed\\n\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n\\n6. Draft a PR message:\\n - Follow <git_message_quality>\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Use clear, concise language\\n - Provide an accurate reflection of changes and purpose\\n - Avoid generic summaries; messages should be thoughtful\\n - Review draft against the litmus test before creating or updating the PR\\n\\n7. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n<summary>\\n\\n\U0001F498 Generated with Crush\\n\\nEOF\\n)\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"auto_background_after\":{\"description\":\"Seconds to wait before automatically moving the command to a background job (default: 60)\",\"type\":\"integer\"},\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Download a URL directly to a local file (binary-safe, streaming, max 600s timeout); overwrites without warning. For reading content into context use fetch.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edit a file by exact find-and-replace; can also create or delete content. For renames/moves use bash. For large edits use write.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Apply multiple find-and-replace edits to a single file in one operation; edits run sequentially. Prefer over edit for multiple changes to the same file. Same exact-match rules as edit apply.\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetch raw content from a URL as text, markdown, or html (max 100KB); no AI processing. For analysis or extraction use agentic_fetch.\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Find files by name/pattern (glob syntax), sorted by modification time; max 100 results; skips hidden files. Use grep to search file contents.\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Search file contents by regex or literal text; returns matching file paths sorted by modification time (max 100); respects .gitignore. Use glob to filter by filename, not contents.\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"List files and directories as a tree; skips hidden files and common system dirs; max 1000 files. Use glob to find files by pattern, grep to search contents.\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public GitHub repositories via Sourcegraph; supports regex, language/repo/file filters, and symbol search (max 20 results). Only searches public repos.\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Read a file by path with line numbers; supports offset and line limit (default 200, max 200KB returned file content section); renders images (PNG, JPEG, GIF, WebP); use ls for directories.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 200)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Create or overwrite a file with given content; auto-creates parent dirs. Cannot append. Read the file first to avoid conflicts. For surgical changes use edit or multiedit.\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
392− headers:
393− Accept:
394− - application/json
395− Content-Type:
396− - application/json
397− User-Agent:
398− - Charm-Crush/devel (https://charm.land/crush)
399− url: https://hyper.charm.land/v1/chat/completions
400− method: POST
401− response:
402− proto: HTTP/2.0
403− proto_major: 2
404− proto_minor: 0
405− content_length: -1
406− uncompressed: true
407− body: |+
408− data: {"id":"chatcmpl-985f3df336cbf13a5d358129","object":"chat.completion.chunk","created":1782413794,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
409−
410− data: {"id":"chatcmpl-985f3df336cbf13a5d358129","object":"chat.completion.chunk","created":1782413794,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Done"},"finish_reason":null}]}
411−
412− data: {"id":"chatcmpl-985f3df336cbf13a5d358129","object":"chat.completion.chunk","created":1782413794,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"."},"finish_reason":null}]}
413−
414− data: {"id":"chatcmpl-985f3df336cbf13a5d358129","object":"chat.completion.chunk","created":1782413794,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
415−
416− data: {"id":"chatcmpl-985f3df336cbf13a5d358129","object":"chat.completion.chunk","created":1782413794,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":720,"completion_tokens":4,"total_tokens":8203,"prompt_tokens_details":{"cached_tokens":7479},"cost":{"usd":0.0010255999999999998,"hypercredits":0.020511999999999996},"remaining":{"hypercredits":0}}}
417−
418− data: [DONE]
419−
420− headers:
421− Content-Type:
422− - text/event-stream
423− status: 200 OK
424− code: 200
425− duration: 1.122182833s
internal/agent/testdata/TestCoderAgent/glm-5.1/download_tool.yamldeleted−483
@@ -1,483 +0,0 @@
1−---
2−version: 2
3−interactions:
4−- id: 0
5− request:
6− proto: HTTP/1.1
7− proto_major: 1
8− proto_minor: 1
9− content_length: 35697
10− host: ""
11− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ THE RELEVANT CONTEXT BEFORE EDITING**: Never edit a file you haven't already read the relevant context for in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\". When committing, follow the `<git_commits>` format from the bash tool description exactly, including any configured attribution lines.\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **TOOL CONSTRAINTS**: Only use documented tools. Never attempt 'apply_patch' or 'apply_diff' - they don't exist. Use 'edit' or 'multiedit' instead.\\n14. **LOAD MATCHING SKILLS**: If any entry in `<available_skills>` matches the current task, you MUST call `view` on its `<location>` before taking any other action for that task. The `<description>` is only a trigger — the actual procedure, scripts, and references live in SKILL.md. Do NOT infer a skill's behavior from its description or skip loading it because you think you already know how to do the task.\\n15. **LIMIT FILE READS**: Avoid reading entire files, as they can be very large. Read only the sections you need using 'offset' and 'limit' parameters.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- ALWAYS think and respond in the same spoken language the prompt was written in.\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\n**Available edit tools:**\\n- `edit` - Single find/replace in a file\\n- `multiedit` - Multiple find/replace operations in one file\\n- `write` - Create/overwrite entire file\\n\\nNever use `apply_patch` or similar - those tools don't exist.\\n\\nCritical: ALWAYS read the relevant context of files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the relevant context first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</editing_files>\\n\\n<whitespace_and_exact_matching>\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n</whitespace_and_exact_matching>\\n\\n<task_completion>\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n</task_completion>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences\\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n<bash_commands>\\n**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/glm-5.1/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n<available_skills>\\n <skill>\\n <name>crush-hooks</name>\\n <description>Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.</description>\\n <location>crush://skills/crush-hooks/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n <skill>\\n <name>jq</name>\\n <description>Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.</description>\\n <location>crush://skills/jq/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n</available_skills>\\n\\n<skills_usage>\\nThe `<description>` of each skill is a TRIGGER — it tells you *when* a skill applies. It is NOT a specification of what the skill does or how to do it. The procedure, scripts, commands, references, and required flags live only in the SKILL.md body. You do not know what a skill actually does until you have read its SKILL.md.\\n\\nMANDATORY activation flow:\\n1. Scan `<available_skills>` against the current user task.\\n2. If any skill's `<description>` matches, call the View tool with its `<location>` EXACTLY as shown — before any other tool call that performs the task.\\n3. Read the entire SKILL.md and follow its instructions.\\n4. Only then execute the task, using the skill's prescribed commands/tools.\\n\\nDo NOT skip step 2 because you think you already know how to do the task. Do NOT infer a skill's behavior from its name or description. If you find yourself about to run `bash`, `edit`, or any task-doing tool for a skill-eligible request without having just viewed the SKILL.md, stop and load the skill first.\\n\\nBuiltin skills (type=builtin) use virtual `crush://skills/...` location identifiers. The \\\"crush://\\\" prefix is NOT a URL, network address, or MCP resource — it is a special internal identifier the View tool understands natively. Pass the `<location>` verbatim to View.\\n\\nDo not use MCP tools (including read_mcp_resource) to load skills.\\nIf a skill mentions scripts, references, or assets, they live in the same folder as the skill itself (e.g., scripts/, references/, assets/ subdirectories within the skill's folder).\\n</skills_usage>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"<system_reminder>This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.</system_reminder>\",\"role\":\"user\"},{\"content\":\"download the file from https://example-files.online-convert.com/document/txt/example.txt and save it as example.txt\",\"role\":\"user\"}],\"model\":\"glm-5.1\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Execute shell commands; long-running commands automatically move to background and return a shell ID.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute (default, configurable via `auto_background_after`) automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<background_execution>\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `&` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n</background_execution>\\n\\n<git_message_quality>\\nThese rules apply whenever creating or updating commit messages, PR titles, or PR bodies:\\n\\n- Messages MUST be understandable to someone unfamiliar with the codebase.\\n- Before creating or updating a message, verify this litmus test: a new contributor reading only the commit message or PR title/body should understand what problem this solves, why it matters, and the impact without opening files, reading the diff, or knowing internal code names.\\n- Avoid code identifiers, filenames, function names, and implementation details unless they are necessary for understanding the user-facing impact.\\n- Bad: \\\"Add NameFromHex with sync.Once lazy init\\\"\\n- Good: \\\"Improve color name lookup performance while keeping startup fast\\\"\\n</git_message_quality>\\n\\n<commit_messages>\\nCommit messages are for future readers scanning history. Before committing:\\n\\n- Follow <git_message_quality>.\\n- Draft a concise 1-2 sentence message focusing on why the change exists and what outcome it enables, not a list of files or implementation details.\\n- Use clear, accurate verbs (\\\"add\\\"=new capability, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix) and avoid generic messages.\\n- The first line MUST be under 72 characters.\\n- Add a body only when it is needed to explain the reasoning, tradeoffs, or important context; wrap body lines at 72 characters.\\n- If the change is internal-only, still describe the benefit or maintenance outcome rather than naming private code.\\n- Bad: \\\"fix: nil pointer in session.go\\\"\\n- Good: \\\"fix: prevent session loading from crashing on missing metadata\\\"\\n- Bad: \\\"refactor: move PromptBuilder into internal/agent\\\"\\n- Good: \\\"refactor: make prompt assembly easier to maintain\\\"\\n</commit_messages>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond the context of git\\n\\n4. Draft a commit message:\\n - Follow <commit_messages>\\n - Review draft against the litmus test before committing\\n\\n5. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\nCommit message here.\\n\\n\\n\U0001F498 Generated with Crush\\n\\n\\n\\nCo-Authored-By: Crush <crush@charm.land>\\n\\nEOF\\n)\\\"\\n\\n6. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n7. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m.\\n</git_commits>\\n\\n<pull_requests>\\n\\n\\nWhen user asks you to create or update a PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n\\n3. Commit changes if needed\\n\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n\\n6. Draft a PR message:\\n - Follow <git_message_quality>\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Use clear, concise language\\n - Provide an accurate reflection of changes and purpose\\n - Avoid generic summaries; messages should be thoughtful\\n - Review draft against the litmus test before creating or updating the PR\\n\\n7. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n<summary>\\n\\n\U0001F498 Generated with Crush\\n\\nEOF\\n)\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"auto_background_after\":{\"description\":\"Seconds to wait before automatically moving the command to a background job (default: 60)\",\"type\":\"integer\"},\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Download a URL directly to a local file (binary-safe, streaming, max 600s timeout); overwrites without warning. For reading content into context use fetch.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edit a file by exact find-and-replace; can also create or delete content. For renames/moves use bash. For large edits use write.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Apply multiple find-and-replace edits to a single file in one operation; edits run sequentially. Prefer over edit for multiple changes to the same file. Same exact-match rules as edit apply.\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetch raw content from a URL as text, markdown, or html (max 100KB); no AI processing. For analysis or extraction use agentic_fetch.\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Find files by name/pattern (glob syntax), sorted by modification time; max 100 results; skips hidden files. Use grep to search file contents.\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Search file contents by regex or literal text; returns matching file paths sorted by modification time (max 100); respects .gitignore. Use glob to filter by filename, not contents.\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"List files and directories as a tree; skips hidden files and common system dirs; max 1000 files. Use glob to find files by pattern, grep to search contents.\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public GitHub repositories via Sourcegraph; supports regex, language/repo/file filters, and symbol search (max 20 results). Only searches public repos.\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Read a file by path with line numbers; supports offset and line limit (default 200, max 200KB returned file content section); renders images (PNG, JPEG, GIF, WebP); use ls for directories.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 200)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Create or overwrite a file with given content; auto-creates parent dirs. Cannot append. Read the file first to avoid conflicts. For surgical changes use edit or multiedit.\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
12− headers:
13− Accept:
14− - application/json
15− Content-Type:
16− - application/json
17− User-Agent:
18− - Charm-Crush/devel (https://charm.land/crush)
19− url: https://hyper.charm.land/v1/chat/completions
20− method: POST
21− response:
22− proto: HTTP/2.0
23− proto_major: 2
24− proto_minor: 0
25− content_length: -1
26− uncompressed: true
27− body: |+
28− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
29−
30− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
31−
32− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
33−
34− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" wants"},"finish_reason":null}]}
35−
36− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
37−
38− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" download"},"finish_reason":null}]}
39−
40− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
41−
42− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" file"},"finish_reason":null}]}
43−
44− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" from"},"finish_reason":null}]}
45−
46− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
47−
48− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" URL"},"finish_reason":null}]}
49−
50− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
51−
52− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" save"},"finish_reason":null}]}
53−
54− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" it"},"finish_reason":null}]}
55−
56− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" as"},"finish_reason":null}]}
57−
58− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" example"},"finish_reason":null}]}
59−
60− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":".txt"},"finish_reason":null}]}
61−
62− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
63−
64− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_4cbf337c01e5b47c","type":"function","index":0,"function":{"name":"download","arguments":""}}]},"finish_reason":null}]}
65−
66− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\"file_path\": \""}}]},"finish_reason":null}]}
67−
68− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/tmp"}}]},"finish_reason":null}]}
69−
70− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/c"}}]},"finish_reason":null}]}
71−
72− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"rush"}}]},"finish_reason":null}]}
73−
74− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}]}
75−
76− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}]}
77−
78− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}]}
79−
80− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}]}
81−
82− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/g"}}]},"finish_reason":null}]}
83−
84− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"lm"}}]},"finish_reason":null}]}
85−
86− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}]}
87−
88− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}]}
89−
90− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"."}}]},"finish_reason":null}]}
91−
92− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"1"}}]},"finish_reason":null}]}
93−
94− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/download"}}]},"finish_reason":null}]}
95−
96− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}]}
97−
98− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/example"}}]},"finish_reason":null}]}
99−
100− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".txt"}}]},"finish_reason":null}]}
101−
102− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\""}}]},"finish_reason":null}]}
103−
104− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":", \"url\": \""}}]},"finish_reason":null}]}
105−
106− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"https"}}]},"finish_reason":null}]}
107−
108− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"://"}}]},"finish_reason":null}]}
109−
110− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"example"}}]},"finish_reason":null}]}
111−
112− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-files"}}]},"finish_reason":null}]}
113−
114− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".online"}}]},"finish_reason":null}]}
115−
116− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}]}
117−
118− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"convert"}}]},"finish_reason":null}]}
119−
120− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".com"}}]},"finish_reason":null}]}
121−
122− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/document"}}]},"finish_reason":null}]}
123−
124− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/t"}}]},"finish_reason":null}]}
125−
126− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"xt"}}]},"finish_reason":null}]}
127−
128− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/example"}}]},"finish_reason":null}]}
129−
130− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".txt"}}]},"finish_reason":null}]}
131−
132− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\""}}]},"finish_reason":null}]}
133−
134− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
135−
136− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
137−
138− data: {"id":"chatcmpl-cc0c9ef25b702fedc808d605","object":"chat.completion.chunk","created":1782413796,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":689,"completion_tokens":63,"total_tokens":8231,"prompt_tokens_details":{"cached_tokens":7479},"completion_tokens_details":{"reasoning_tokens":18},"cost":{"usd":0.001321,"hypercredits":0.026419999999999996},"remaining":{"hypercredits":0}}}
139−
140− data: [DONE]
141−
142− headers:
143− Content-Type:
144− - text/event-stream
145− status: 200 OK
146− code: 200
147− duration: 936.027666ms
148−- id: 1
149− request:
150− proto: HTTP/1.1
151− proto_major: 1
152− proto_minor: 1
153− content_length: 874
154− host: ""
155− body: '{"messages":[{"content":"You will generate a short title based on the first message a user begins a conversation with.\n\n<rules>\n- Keep the title in the same language that the user wrote their message in.\n- Ensure it is not more than 50 characters long.\n- The title should be a summary of the user''s message.\n- It should be one line long.\n- Do not use quotes or colons.\n- The entire text you return will be used as the title.\n- Never return anything that is more than one sentence (one line) long.\n</rules>\n\n /no_think","role":"system"},{"content":"Generate a concise title for the following content:\n\ndownload the file from https://example-files.online-convert.com/document/txt/example.txt and save it as example.txt\n <think>\n\n</think>","role":"user"}],"model":"gpt-oss-120b","max_completion_tokens":40,"stream_options":{"include_usage":true},"stream":true}'
156− headers:
157− Accept:
158− - application/json
159− Content-Type:
160− - application/json
161− User-Agent:
162− - Charm-Crush/devel (https://charm.land/crush)
163− url: https://hyper.charm.land/v1/chat/completions
164− method: POST
165− response:
166− proto: HTTP/2.0
167− proto_major: 2
168− proto_minor: 0
169− content_length: -1
170− uncompressed: true
171− body: |+
172− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
173−
174− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
175−
176− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
177−
178− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" asks"},"finish_reason":null}]}
179−
180− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
181−
182− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
183−
184− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Generate"},"finish_reason":null}]}
185−
186− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
187−
188− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
189−
190− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
191−
192− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
193−
194− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
195−
196− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" following"},"finish_reason":null}]}
197−
198− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
199−
200− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
201−
202− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" download"},"finish_reason":null}]}
203−
204− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
205−
206− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" file"},"finish_reason":null}]}
207−
208− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" from"},"finish_reason":null}]}
209−
210− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" https"},"finish_reason":null}]}
211−
212− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"://"},"finish_reason":null}]}
213−
214− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"example"},"finish_reason":null}]}
215−
216− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"-files"},"finish_reason":null}]}
217−
218− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".online"},"finish_reason":null}]}
219−
220− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"-con"},"finish_reason":null}]}
221−
222− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"vert"},"finish_reason":null}]}
223−
224− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".com"},"finish_reason":null}]}
225−
226− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"/document"},"finish_reason":null}]}
227−
228− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"/t"},"finish_reason":null}]}
229−
230− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"xt"},"finish_reason":null}]}
231−
232− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"/example"},"finish_reason":null}]}
233−
234− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".txt"},"finish_reason":null}]}
235−
236− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
237−
238− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" save"},"finish_reason":null}]}
239−
240− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" it"},"finish_reason":null}]}
241−
242− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" as"},"finish_reason":null}]}
243−
244− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" example"},"finish_reason":null}]}
245−
246− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".txt"},"finish_reason":null}]}
247−
248− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
249−
250− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Need"},"finish_reason":null}]}
251−
252− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
253−
254− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" short"},"finish_reason":null}]}
255−
256− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
257−
258− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
259−
260− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" same"},"finish_reason":null}]}
261−
262− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" language"},"finish_reason":null}]}
263−
264− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
265−
266− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"English"},"finish_reason":null}]}
267−
268− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"),"},"finish_reason":null}]}
269−
270− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \u003c="},"finish_reason":null}]}
271−
272− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
273−
274− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
275−
276− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
277−
278− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" one"},"finish_reason":null}]}
279−
280− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
281−
282− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
283−
284− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" no"},"finish_reason":null}]}
285−
286− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
287−
288− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
289−
290− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" no"},"finish_reason":null}]}
291−
292− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" colon"},"finish_reason":null}]}
293−
294− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
295−
296− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Something"},"finish_reason":null}]}
297−
298− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" like"},"finish_reason":null}]}
299−
300− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
301−
302− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Download"},"finish_reason":null}]}
303−
304− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
305−
306− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Save"},"finish_reason":null}]}
307−
308− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" example"},"finish_reason":null}]}
309−
310− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".txt"},"finish_reason":null}]}
311−
312− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" from"},"finish_reason":null}]}
313−
314− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" URL"},"finish_reason":null}]}
315−
316− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
317−
318− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
319−
320− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
321−
322− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
323−
324− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
325−
326− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Download"},"finish_reason":null}]}
327−
328− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
329−
330− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Save"},"finish_reason":null}]}
331−
332− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" example"},"finish_reason":null}]}
333−
334− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".txt"},"finish_reason":null}]}
335−
336− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" from"},"finish_reason":null}]}
337−
338− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" URL"},"finish_reason":null}]}
339−
340− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
341−
342− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ="},"finish_reason":null}]}
343−
344− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
345−
346− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"38"},"finish_reason":null}]}
347−
348− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
349−
350− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
351−
352− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Good"},"finish_reason":null}]}
353−
354− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
355−
356− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Download"},"finish_reason":null}]}
357−
358− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" and"},"finish_reason":null}]}
359−
360− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Save"},"finish_reason":null}]}
361−
362− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" example"},"finish_reason":null}]}
363−
364− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":".txt"},"finish_reason":null}]}
365−
366− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" from"},"finish_reason":null}]}
367−
368− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" URL"},"finish_reason":null}]}
369−
370− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
371−
372− data: {"id":"chatcmpl-cacd42b690dbfa0c757a15f0","object":"chat.completion.chunk","created":1782413796,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":160,"completion_tokens":108,"total_tokens":336,"prompt_tokens_details":{"cached_tokens":68},"completion_tokens_details":{"reasoning_tokens":103},"cost":{"usd":0.000145462,"hypercredits":0.00290924},"remaining":{"hypercredits":0}}}
373−
374− data: [DONE]
375−
376− headers:
377− Content-Type:
378− - text/event-stream
379− status: 200 OK
380− code: 200
381− duration: 1.326897958s
382−- id: 2
383− request:
384− proto: HTTP/1.1
385− proto_major: 1
386− proto_minor: 1
387− content_length: 0
388− host: example-files.online-convert.com
389− headers:
390− User-Agent:
391− - crush/1.0
392− url: https://example-files.online-convert.com/document/txt/example.txt
393− method: GET
394− response:
395− proto: HTTP/2.0
396− proto_major: 2
397− proto_minor: 0
398− content_length: -1
399− uncompressed: true
400− body: |-
401− TXT test file
402− Purpose: Provide example of this file type
403− Document file type: TXT
404− Version: 1.0
405− Remark:
406−
407− Example content:
408− The names "John Doe" for males, "Jane Doe" or "Jane Roe" for females, or "Jonnie Doe" and "Janie Doe" for children, or just "Doe" non-gender-specifically are used as placeholder names for a party whose true identity is unknown or must be withheld in a legal action, case, or discussion. The names are also used to refer to acorpse or hospital patient whose identity is unknown. This practice is widely used in the United States and Canada, but is rarely used in other English-speaking countries including the United Kingdom itself, from where the use of "John Doe" in a legal context originates. The names Joe Bloggs or John Smith are used in the UK instead, as well as in Australia and New Zealand.
409−
410− John Doe is sometimes used to refer to a typical male in other contexts as well, in a similar manner to John Q. Public, known in Great Britain as Joe Public, John Smith or Joe Bloggs. For example, the first name listed on a form is often John Doe, along with a fictional address or other fictional information to provide an example of how to fill in the form. The name is also used frequently in popular culture, for example in the Frank Capra film Meet John Doe. John Doe was also the name of a 2002 American television series.
411−
412− Similarly, a child or baby whose identity is unknown may be referred to as Baby Doe. A notorious murder case in Kansas City, Missouri, referred to the baby victim as Precious Doe. Other unidentified female murder victims are Cali Doe and Princess Doe. Additional persons may be called James Doe, Judy Doe, etc. However, to avoid possible confusion, if two anonymous or unknown parties are cited in a specific case or action, the surnames Doe and Roe may be used simultaneously; for example, "John Doe v. Jane Roe". If several anonymous parties are referenced, they may simply be labelled John Doe #1, John Doe #2, etc. (the U.S. Operation Delego cited 21 (numbered) "John Doe"s) or labelled with other variants of Doe / Roe / Poe / etc. Other early alternatives such as John Stiles and Richard Miles are now rarely used, and Mary Major has been used in some American federal cases.
413−
414−
415−
416− File created by https://www.online-convert.com
417− More example files: https://www.online-convert.com/file-type
418− Text of Example content: Wikipedia (https://en.wikipedia.org/wiki/John_Doe)
419− License: Attribution-ShareAlike 4.0 (https://creativecommons.org/licenses/by-sa/4.0/)
420−
421− Feel free to use and share the file according to the license above.
422− headers:
423− Content-Type:
424− - text/plain; charset=UTF-8
425− status: 200 OK
426− code: 200
427− duration: 893.137459ms
428−- id: 3
429− request:
430− proto: HTTP/1.1
431− proto_major: 1
432− proto_minor: 1
433− content_length: 36247
434− host: ""
435− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ THE RELEVANT CONTEXT BEFORE EDITING**: Never edit a file you haven't already read the relevant context for in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\". When committing, follow the `<git_commits>` format from the bash tool description exactly, including any configured attribution lines.\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **TOOL CONSTRAINTS**: Only use documented tools. Never attempt 'apply_patch' or 'apply_diff' - they don't exist. Use 'edit' or 'multiedit' instead.\\n14. **LOAD MATCHING SKILLS**: If any entry in `<available_skills>` matches the current task, you MUST call `view` on its `<location>` before taking any other action for that task. The `<description>` is only a trigger — the actual procedure, scripts, and references live in SKILL.md. Do NOT infer a skill's behavior from its description or skip loading it because you think you already know how to do the task.\\n15. **LIMIT FILE READS**: Avoid reading entire files, as they can be very large. Read only the sections you need using 'offset' and 'limit' parameters.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- ALWAYS think and respond in the same spoken language the prompt was written in.\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\n**Available edit tools:**\\n- `edit` - Single find/replace in a file\\n- `multiedit` - Multiple find/replace operations in one file\\n- `write` - Create/overwrite entire file\\n\\nNever use `apply_patch` or similar - those tools don't exist.\\n\\nCritical: ALWAYS read the relevant context of files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the relevant context first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</editing_files>\\n\\n<whitespace_and_exact_matching>\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n</whitespace_and_exact_matching>\\n\\n<task_completion>\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n</task_completion>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences\\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n<bash_commands>\\n**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/glm-5.1/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n<available_skills>\\n <skill>\\n <name>crush-hooks</name>\\n <description>Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.</description>\\n <location>crush://skills/crush-hooks/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n <skill>\\n <name>jq</name>\\n <description>Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.</description>\\n <location>crush://skills/jq/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n</available_skills>\\n\\n<skills_usage>\\nThe `<description>` of each skill is a TRIGGER — it tells you *when* a skill applies. It is NOT a specification of what the skill does or how to do it. The procedure, scripts, commands, references, and required flags live only in the SKILL.md body. You do not know what a skill actually does until you have read its SKILL.md.\\n\\nMANDATORY activation flow:\\n1. Scan `<available_skills>` against the current user task.\\n2. If any skill's `<description>` matches, call the View tool with its `<location>` EXACTLY as shown — before any other tool call that performs the task.\\n3. Read the entire SKILL.md and follow its instructions.\\n4. Only then execute the task, using the skill's prescribed commands/tools.\\n\\nDo NOT skip step 2 because you think you already know how to do the task. Do NOT infer a skill's behavior from its name or description. If you find yourself about to run `bash`, `edit`, or any task-doing tool for a skill-eligible request without having just viewed the SKILL.md, stop and load the skill first.\\n\\nBuiltin skills (type=builtin) use virtual `crush://skills/...` location identifiers. The \\\"crush://\\\" prefix is NOT a URL, network address, or MCP resource — it is a special internal identifier the View tool understands natively. Pass the `<location>` verbatim to View.\\n\\nDo not use MCP tools (including read_mcp_resource) to load skills.\\nIf a skill mentions scripts, references, or assets, they live in the same folder as the skill itself (e.g., scripts/, references/, assets/ subdirectories within the skill's folder).\\n</skills_usage>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"<system_reminder>This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.</system_reminder>\",\"role\":\"user\"},{\"content\":\"download the file from https://example-files.online-convert.com/document/txt/example.txt and save it as example.txt\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_4cbf337c01e5b47c\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/download_tool/example.txt\\\", \\\"url\\\": \\\"https://example-files.online-convert.com/document/txt/example.txt\\\"}\",\"name\":\"download\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"The user wants to download a file from a URL and save it as example.txt.\"},{\"content\":\"Successfully downloaded 2574 bytes to example.txt (Content-Type: text/plain; charset=UTF-8)\",\"tool_call_id\":\"call_4cbf337c01e5b47c\",\"role\":\"tool\"}],\"model\":\"glm-5.1\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Execute shell commands; long-running commands automatically move to background and return a shell ID.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute (default, configurable via `auto_background_after`) automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<background_execution>\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `&` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n</background_execution>\\n\\n<git_message_quality>\\nThese rules apply whenever creating or updating commit messages, PR titles, or PR bodies:\\n\\n- Messages MUST be understandable to someone unfamiliar with the codebase.\\n- Before creating or updating a message, verify this litmus test: a new contributor reading only the commit message or PR title/body should understand what problem this solves, why it matters, and the impact without opening files, reading the diff, or knowing internal code names.\\n- Avoid code identifiers, filenames, function names, and implementation details unless they are necessary for understanding the user-facing impact.\\n- Bad: \\\"Add NameFromHex with sync.Once lazy init\\\"\\n- Good: \\\"Improve color name lookup performance while keeping startup fast\\\"\\n</git_message_quality>\\n\\n<commit_messages>\\nCommit messages are for future readers scanning history. Before committing:\\n\\n- Follow <git_message_quality>.\\n- Draft a concise 1-2 sentence message focusing on why the change exists and what outcome it enables, not a list of files or implementation details.\\n- Use clear, accurate verbs (\\\"add\\\"=new capability, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix) and avoid generic messages.\\n- The first line MUST be under 72 characters.\\n- Add a body only when it is needed to explain the reasoning, tradeoffs, or important context; wrap body lines at 72 characters.\\n- If the change is internal-only, still describe the benefit or maintenance outcome rather than naming private code.\\n- Bad: \\\"fix: nil pointer in session.go\\\"\\n- Good: \\\"fix: prevent session loading from crashing on missing metadata\\\"\\n- Bad: \\\"refactor: move PromptBuilder into internal/agent\\\"\\n- Good: \\\"refactor: make prompt assembly easier to maintain\\\"\\n</commit_messages>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond the context of git\\n\\n4. Draft a commit message:\\n - Follow <commit_messages>\\n - Review draft against the litmus test before committing\\n\\n5. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\nCommit message here.\\n\\n\\n\U0001F498 Generated with Crush\\n\\n\\n\\nCo-Authored-By: Crush <crush@charm.land>\\n\\nEOF\\n)\\\"\\n\\n6. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n7. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m.\\n</git_commits>\\n\\n<pull_requests>\\n\\n\\nWhen user asks you to create or update a PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n\\n3. Commit changes if needed\\n\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n\\n6. Draft a PR message:\\n - Follow <git_message_quality>\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Use clear, concise language\\n - Provide an accurate reflection of changes and purpose\\n - Avoid generic summaries; messages should be thoughtful\\n - Review draft against the litmus test before creating or updating the PR\\n\\n7. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n<summary>\\n\\n\U0001F498 Generated with Crush\\n\\nEOF\\n)\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"auto_background_after\":{\"description\":\"Seconds to wait before automatically moving the command to a background job (default: 60)\",\"type\":\"integer\"},\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Download a URL directly to a local file (binary-safe, streaming, max 600s timeout); overwrites without warning. For reading content into context use fetch.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edit a file by exact find-and-replace; can also create or delete content. For renames/moves use bash. For large edits use write.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Apply multiple find-and-replace edits to a single file in one operation; edits run sequentially. Prefer over edit for multiple changes to the same file. Same exact-match rules as edit apply.\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetch raw content from a URL as text, markdown, or html (max 100KB); no AI processing. For analysis or extraction use agentic_fetch.\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Find files by name/pattern (glob syntax), sorted by modification time; max 100 results; skips hidden files. Use grep to search file contents.\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Search file contents by regex or literal text; returns matching file paths sorted by modification time (max 100); respects .gitignore. Use glob to filter by filename, not contents.\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"List files and directories as a tree; skips hidden files and common system dirs; max 1000 files. Use glob to find files by pattern, grep to search contents.\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public GitHub repositories via Sourcegraph; supports regex, language/repo/file filters, and symbol search (max 20 results). Only searches public repos.\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Read a file by path with line numbers; supports offset and line limit (default 200, max 200KB returned file content section); renders images (PNG, JPEG, GIF, WebP); use ls for directories.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 200)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Create or overwrite a file with given content; auto-creates parent dirs. Cannot append. Read the file first to avoid conflicts. For surgical changes use edit or multiedit.\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
436− headers:
437− Accept:
438− - application/json
439− Content-Type:
440− - application/json
441− User-Agent:
442− - Charm-Crush/devel (https://charm.land/crush)
443− url: https://hyper.charm.land/v1/chat/completions
444− method: POST
445− response:
446− proto: HTTP/2.0
447− proto_major: 2
448− proto_minor: 0
449− content_length: -1
450− uncompressed: true
451− body: |+
452− data: {"id":"chatcmpl-4bda680be45220e2a1b071f0","object":"chat.completion.chunk","created":1782413799,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
453−
454− data: {"id":"chatcmpl-4bda680be45220e2a1b071f0","object":"chat.completion.chunk","created":1782413799,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Download"},"finish_reason":null}]}
455−
456− data: {"id":"chatcmpl-4bda680be45220e2a1b071f0","object":"chat.completion.chunk","created":1782413799,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"ed"},"finish_reason":null}]}
457−
458− data: {"id":"chatcmpl-4bda680be45220e2a1b071f0","object":"chat.completion.chunk","created":1782413799,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" and"},"finish_reason":null}]}
459−
460− data: {"id":"chatcmpl-4bda680be45220e2a1b071f0","object":"chat.completion.chunk","created":1782413799,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" saved"},"finish_reason":null}]}
461−
462− data: {"id":"chatcmpl-4bda680be45220e2a1b071f0","object":"chat.completion.chunk","created":1782413799,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" as"},"finish_reason":null}]}
463−
464− data: {"id":"chatcmpl-4bda680be45220e2a1b071f0","object":"chat.completion.chunk","created":1782413799,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `"},"finish_reason":null}]}
465−
466− data: {"id":"chatcmpl-4bda680be45220e2a1b071f0","object":"chat.completion.chunk","created":1782413799,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"example"},"finish_reason":null}]}
467−
468− data: {"id":"chatcmpl-4bda680be45220e2a1b071f0","object":"chat.completion.chunk","created":1782413799,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":".txt"},"finish_reason":null}]}
469−
470− data: {"id":"chatcmpl-4bda680be45220e2a1b071f0","object":"chat.completion.chunk","created":1782413799,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`."},"finish_reason":null}]}
471−
472− data: {"id":"chatcmpl-4bda680be45220e2a1b071f0","object":"chat.completion.chunk","created":1782413799,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
473−
474− data: {"id":"chatcmpl-4bda680be45220e2a1b071f0","object":"chat.completion.chunk","created":1782413799,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":73,"completion_tokens":11,"total_tokens":8251,"prompt_tokens_details":{"cached_tokens":8167},"cost":{"usd":0.0001506,"hypercredits":0.003012},"remaining":{"hypercredits":0}}}
475−
476− data: [DONE]
477−
478− headers:
479− Content-Type:
480− - text/event-stream
481− status: 200 OK
482− code: 200
483− duration: 1.486211917s
internal/agent/testdata/TestCoderAgent/glm-5.1/fetch_tool.yamldeleted−650
@@ -1,650 +0,0 @@
1−---
2−version: 2
3−interactions:
4−- id: 0
5− request:
6− proto: HTTP/1.1
7− proto_major: 1
8− proto_minor: 1
9− content_length: 35715
10− host: ""
11− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ THE RELEVANT CONTEXT BEFORE EDITING**: Never edit a file you haven't already read the relevant context for in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\". When committing, follow the `<git_commits>` format from the bash tool description exactly, including any configured attribution lines.\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **TOOL CONSTRAINTS**: Only use documented tools. Never attempt 'apply_patch' or 'apply_diff' - they don't exist. Use 'edit' or 'multiedit' instead.\\n14. **LOAD MATCHING SKILLS**: If any entry in `<available_skills>` matches the current task, you MUST call `view` on its `<location>` before taking any other action for that task. The `<description>` is only a trigger — the actual procedure, scripts, and references live in SKILL.md. Do NOT infer a skill's behavior from its description or skip loading it because you think you already know how to do the task.\\n15. **LIMIT FILE READS**: Avoid reading entire files, as they can be very large. Read only the sections you need using 'offset' and 'limit' parameters.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- ALWAYS think and respond in the same spoken language the prompt was written in.\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\n**Available edit tools:**\\n- `edit` - Single find/replace in a file\\n- `multiedit` - Multiple find/replace operations in one file\\n- `write` - Create/overwrite entire file\\n\\nNever use `apply_patch` or similar - those tools don't exist.\\n\\nCritical: ALWAYS read the relevant context of files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the relevant context first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</editing_files>\\n\\n<whitespace_and_exact_matching>\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n</whitespace_and_exact_matching>\\n\\n<task_completion>\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n</task_completion>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences\\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n<bash_commands>\\n**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/glm-5.1/fetch_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n<available_skills>\\n <skill>\\n <name>crush-hooks</name>\\n <description>Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.</description>\\n <location>crush://skills/crush-hooks/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n <skill>\\n <name>jq</name>\\n <description>Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.</description>\\n <location>crush://skills/jq/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n</available_skills>\\n\\n<skills_usage>\\nThe `<description>` of each skill is a TRIGGER — it tells you *when* a skill applies. It is NOT a specification of what the skill does or how to do it. The procedure, scripts, commands, references, and required flags live only in the SKILL.md body. You do not know what a skill actually does until you have read its SKILL.md.\\n\\nMANDATORY activation flow:\\n1. Scan `<available_skills>` against the current user task.\\n2. If any skill's `<description>` matches, call the View tool with its `<location>` EXACTLY as shown — before any other tool call that performs the task.\\n3. Read the entire SKILL.md and follow its instructions.\\n4. Only then execute the task, using the skill's prescribed commands/tools.\\n\\nDo NOT skip step 2 because you think you already know how to do the task. Do NOT infer a skill's behavior from its name or description. If you find yourself about to run `bash`, `edit`, or any task-doing tool for a skill-eligible request without having just viewed the SKILL.md, stop and load the skill first.\\n\\nBuiltin skills (type=builtin) use virtual `crush://skills/...` location identifiers. The \\\"crush://\\\" prefix is NOT a URL, network address, or MCP resource — it is a special internal identifier the View tool understands natively. Pass the `<location>` verbatim to View.\\n\\nDo not use MCP tools (including read_mcp_resource) to load skills.\\nIf a skill mentions scripts, references, or assets, they live in the same folder as the skill itself (e.g., scripts/, references/, assets/ subdirectories within the skill's folder).\\n</skills_usage>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"<system_reminder>This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.</system_reminder>\",\"role\":\"user\"},{\"content\":\"fetch the content from https://example-files.online-convert.com/website/html/example.html and tell me if it contains the word 'John Doe'\",\"role\":\"user\"}],\"model\":\"glm-5.1\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Execute shell commands; long-running commands automatically move to background and return a shell ID.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute (default, configurable via `auto_background_after`) automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<background_execution>\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `&` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n</background_execution>\\n\\n<git_message_quality>\\nThese rules apply whenever creating or updating commit messages, PR titles, or PR bodies:\\n\\n- Messages MUST be understandable to someone unfamiliar with the codebase.\\n- Before creating or updating a message, verify this litmus test: a new contributor reading only the commit message or PR title/body should understand what problem this solves, why it matters, and the impact without opening files, reading the diff, or knowing internal code names.\\n- Avoid code identifiers, filenames, function names, and implementation details unless they are necessary for understanding the user-facing impact.\\n- Bad: \\\"Add NameFromHex with sync.Once lazy init\\\"\\n- Good: \\\"Improve color name lookup performance while keeping startup fast\\\"\\n</git_message_quality>\\n\\n<commit_messages>\\nCommit messages are for future readers scanning history. Before committing:\\n\\n- Follow <git_message_quality>.\\n- Draft a concise 1-2 sentence message focusing on why the change exists and what outcome it enables, not a list of files or implementation details.\\n- Use clear, accurate verbs (\\\"add\\\"=new capability, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix) and avoid generic messages.\\n- The first line MUST be under 72 characters.\\n- Add a body only when it is needed to explain the reasoning, tradeoffs, or important context; wrap body lines at 72 characters.\\n- If the change is internal-only, still describe the benefit or maintenance outcome rather than naming private code.\\n- Bad: \\\"fix: nil pointer in session.go\\\"\\n- Good: \\\"fix: prevent session loading from crashing on missing metadata\\\"\\n- Bad: \\\"refactor: move PromptBuilder into internal/agent\\\"\\n- Good: \\\"refactor: make prompt assembly easier to maintain\\\"\\n</commit_messages>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond the context of git\\n\\n4. Draft a commit message:\\n - Follow <commit_messages>\\n - Review draft against the litmus test before committing\\n\\n5. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\nCommit message here.\\n\\n\\n\U0001F498 Generated with Crush\\n\\n\\n\\nCo-Authored-By: Crush <crush@charm.land>\\n\\nEOF\\n)\\\"\\n\\n6. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n7. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m.\\n</git_commits>\\n\\n<pull_requests>\\n\\n\\nWhen user asks you to create or update a PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n\\n3. Commit changes if needed\\n\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n\\n6. Draft a PR message:\\n - Follow <git_message_quality>\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Use clear, concise language\\n - Provide an accurate reflection of changes and purpose\\n - Avoid generic summaries; messages should be thoughtful\\n - Review draft against the litmus test before creating or updating the PR\\n\\n7. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n<summary>\\n\\n\U0001F498 Generated with Crush\\n\\nEOF\\n)\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"auto_background_after\":{\"description\":\"Seconds to wait before automatically moving the command to a background job (default: 60)\",\"type\":\"integer\"},\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Download a URL directly to a local file (binary-safe, streaming, max 600s timeout); overwrites without warning. For reading content into context use fetch.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edit a file by exact find-and-replace; can also create or delete content. For renames/moves use bash. For large edits use write.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Apply multiple find-and-replace edits to a single file in one operation; edits run sequentially. Prefer over edit for multiple changes to the same file. Same exact-match rules as edit apply.\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetch raw content from a URL as text, markdown, or html (max 100KB); no AI processing. For analysis or extraction use agentic_fetch.\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Find files by name/pattern (glob syntax), sorted by modification time; max 100 results; skips hidden files. Use grep to search file contents.\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Search file contents by regex or literal text; returns matching file paths sorted by modification time (max 100); respects .gitignore. Use glob to filter by filename, not contents.\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"List files and directories as a tree; skips hidden files and common system dirs; max 1000 files. Use glob to find files by pattern, grep to search contents.\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public GitHub repositories via Sourcegraph; supports regex, language/repo/file filters, and symbol search (max 20 results). Only searches public repos.\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Read a file by path with line numbers; supports offset and line limit (default 200, max 200KB returned file content section); renders images (PNG, JPEG, GIF, WebP); use ls for directories.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 200)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Create or overwrite a file with given content; auto-creates parent dirs. Cannot append. Read the file first to avoid conflicts. For surgical changes use edit or multiedit.\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
12− headers:
13− Accept:
14− - application/json
15− Content-Type:
16− - application/json
17− User-Agent:
18− - Charm-Crush/devel (https://charm.land/crush)
19− url: https://hyper.charm.land/v1/chat/completions
20− method: POST
21− response:
22− proto: HTTP/2.0
23− proto_major: 2
24− proto_minor: 0
25− content_length: -1
26− uncompressed: true
27− body: |+
28− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
29−
30− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
31−
32− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
33−
34− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" wants"},"finish_reason":null}]}
35−
36− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" me"},"finish_reason":null}]}
37−
38− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
39−
40− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" fetch"},"finish_reason":null}]}
41−
42− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
43−
44− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" from"},"finish_reason":null}]}
45−
46− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
47−
48− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" URL"},"finish_reason":null}]}
49−
50− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
51−
52− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" check"},"finish_reason":null}]}
53−
54− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" if"},"finish_reason":null}]}
55−
56− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" it"},"finish_reason":null}]}
57−
58− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" contains"},"finish_reason":null}]}
59−
60− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
61−
62− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" word"},"finish_reason":null}]}
63−
64− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
65−
66− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"John"},"finish_reason":null}]}
67−
68− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" Doe"},"finish_reason":null}]}
69−
70− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"'."},"finish_reason":null}]}
71−
72− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_60557666b1c79950","type":"function","index":0,"function":{"name":"fetch","arguments":""}}]},"finish_reason":null}]}
73−
74− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\"format\": \""}}]},"finish_reason":null}]}
75−
76− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"text"}}]},"finish_reason":null}]}
77−
78− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\""}}]},"finish_reason":null}]}
79−
80− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":", \"url\": \""}}]},"finish_reason":null}]}
81−
82− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"https"}}]},"finish_reason":null}]}
83−
84− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"://"}}]},"finish_reason":null}]}
85−
86− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"example"}}]},"finish_reason":null}]}
87−
88− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-files"}}]},"finish_reason":null}]}
89−
90− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".online"}}]},"finish_reason":null}]}
91−
92− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}]}
93−
94− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"convert"}}]},"finish_reason":null}]}
95−
96− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".com"}}]},"finish_reason":null}]}
97−
98− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/"}}]},"finish_reason":null}]}
99−
100− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"website"}}]},"finish_reason":null}]}
101−
102− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/html"}}]},"finish_reason":null}]}
103−
104− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/example"}}]},"finish_reason":null}]}
105−
106− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".html"}}]},"finish_reason":null}]}
107−
108− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\""}}]},"finish_reason":null}]}
109−
110− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
111−
112− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
113−
114− data: {"id":"chatcmpl-adf239d098d5e63d542c1773","object":"chat.completion.chunk","created":1782413801,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":696,"completion_tokens":50,"total_tokens":8225,"prompt_tokens_details":{"cached_tokens":7479},"completion_tokens_details":{"reasoning_tokens":23},"cost":{"usd":0.0012956,"hypercredits":0.025912},"remaining":{"hypercredits":0}}}
115−
116− data: [DONE]
117−
118− headers:
119− Content-Type:
120− - text/event-stream
121− status: 200 OK
122− code: 200
123− duration: 2.230852292s
124−- id: 1
125− request:
126− proto: HTTP/1.1
127− proto_major: 1
128− proto_minor: 1
129− content_length: 895
130− host: ""
131− body: '{"messages":[{"content":"You will generate a short title based on the first message a user begins a conversation with.\n\n<rules>\n- Keep the title in the same language that the user wrote their message in.\n- Ensure it is not more than 50 characters long.\n- The title should be a summary of the user''s message.\n- It should be one line long.\n- Do not use quotes or colons.\n- The entire text you return will be used as the title.\n- Never return anything that is more than one sentence (one line) long.\n</rules>\n\n /no_think","role":"system"},{"content":"Generate a concise title for the following content:\n\nfetch the content from https://example-files.online-convert.com/website/html/example.html and tell me if it contains the word ''John Doe''\n <think>\n\n</think>","role":"user"}],"model":"gpt-oss-120b","max_completion_tokens":40,"stream_options":{"include_usage":true},"stream":true}'
132− headers:
133− Accept:
134− - application/json
135− Content-Type:
136− - application/json
137− User-Agent:
138− - Charm-Crush/devel (https://charm.land/crush)
139− url: https://hyper.charm.land/v1/chat/completions
140− method: POST
141− response:
142− proto: HTTP/2.0
143− proto_major: 2
144− proto_minor: 0
145− content_length: -1
146− uncompressed: true
147− body: |+
148− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
149−
150− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" wants"},"finish_reason":null}]}
151−
152− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
153−
154− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" short"},"finish_reason":null}]}
155−
156− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
157−
158− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
159−
160− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" their"},"finish_reason":null}]}
161−
162− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" request"},"finish_reason":null}]}
163−
164− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
165−
166− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
167−
168− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Title"},"finish_reason":null}]}
169−
170− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
171−
172− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" English"},"finish_reason":null}]}
173−
174− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
175−
176− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Summ"},"finish_reason":null}]}
177−
178− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ar"},"finish_reason":null}]}
179−
180− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ize"},"finish_reason":null}]}
181−
182− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
183−
184− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
185−
186− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Check"},"finish_reason":null}]}
187−
188− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" example"},"finish_reason":null}]}
189−
190− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".html"},"finish_reason":null}]}
191−
192− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
193−
194− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" word"},"finish_reason":null}]}
195−
196− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
197−
198− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"John"},"finish_reason":null}]}
199−
200− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Doe"},"finish_reason":null}]}
201−
202− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'"},"finish_reason":null}]}
203−
204− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
205−
206− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Must"},"finish_reason":null}]}
207−
208− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
209−
210− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \u003c="},"finish_reason":null}]}
211−
212− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
213−
214− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
215−
216− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
217−
218− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Let's"},"finish_reason":null}]}
219−
220− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" craft"},"finish_reason":null}]}
221−
222− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
223−
224− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
225−
226− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Check"},"finish_reason":null}]}
227−
228− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" if"},"finish_reason":null}]}
229−
230− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" example"},"finish_reason":null}]}
231−
232− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".html"},"finish_reason":null}]}
233−
234− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" contains"},"finish_reason":null}]}
235−
236− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
237−
238− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"John"},"finish_reason":null}]}
239−
240− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Doe"},"finish_reason":null}]}
241−
242− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'"},"finish_reason":null}]}
243−
244− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
245−
246− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
247−
248− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
249−
250− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
251−
252− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
253−
254− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
255−
256− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
257−
258− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Check"},"finish_reason":null}]}
259−
260− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" if"},"finish_reason":null}]}
261−
262− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" example"},"finish_reason":null}]}
263−
264− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".html"},"finish_reason":null}]}
265−
266− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" contains"},"finish_reason":null}]}
267−
268− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
269−
270− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"John"},"finish_reason":null}]}
271−
272− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Doe"},"finish_reason":null}]}
273−
274− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'\""},"finish_reason":null}]}
275−
276− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that's"},"finish_reason":null}]}
277−
278− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
279−
280− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"41"},"finish_reason":null}]}
281−
282− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" maybe"},"finish_reason":null}]}
283−
284− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
285−
286− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Let's"},"finish_reason":null}]}
287−
288− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
289−
290− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
291−
292− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" C"},"finish_reason":null}]}
293−
294− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
295−
296− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
297−
298− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
299−
300− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"h"},"finish_reason":null}]}
301−
302− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
303−
304− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"e"},"finish_reason":null}]}
305−
306− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
307−
308− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"c"},"finish_reason":null}]}
309−
310− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
311−
312− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"k"},"finish_reason":null}]}
313−
314− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
315−
316− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
317−
318− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
319−
320− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" i"},"finish_reason":null}]}
321−
322− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
323−
324− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"f"},"finish_reason":null}]}
325−
326− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"8"},"finish_reason":null}]}
327−
328− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
329−
330− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"9"},"finish_reason":null}]}
331−
332− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" e"},"finish_reason":null}]}
333−
334− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"10"},"finish_reason":null}]}
335−
336− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"x"},"finish_reason":null}]}
337−
338− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"11"},"finish_reason":null}]}
339−
340− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"a"},"finish_reason":null}]}
341−
342− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"12"},"finish_reason":null}]}
343−
344− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"m"},"finish_reason":null}]}
345−
346− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"13"},"finish_reason":null}]}
347−
348− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"p"},"finish_reason":null}]}
349−
350− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"14"},"finish_reason":null}]}
351−
352− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"l"},"finish_reason":null}]}
353−
354− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"15"},"finish_reason":null}]}
355−
356− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"e"},"finish_reason":null}]}
357−
358− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"16"},"finish_reason":null}]}
359−
360− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
361−
362− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"17"},"finish_reason":null}]}
363−
364− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"h"},"finish_reason":null}]}
365−
366− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"18"},"finish_reason":null}]}
367−
368− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"t"},"finish_reason":null}]}
369−
370− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"19"},"finish_reason":null}]}
371−
372− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"m"},"finish_reason":null}]}
373−
374− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"20"},"finish_reason":null}]}
375−
376− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"l"},"finish_reason":null}]}
377−
378− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"21"},"finish_reason":null}]}
379−
380− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
381−
382− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"22"},"finish_reason":null}]}
383−
384− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" c"},"finish_reason":null}]}
385−
386− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"23"},"finish_reason":null}]}
387−
388− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"o"},"finish_reason":null}]}
389−
390− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"24"},"finish_reason":null}]}
391−
392− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"n"},"finish_reason":null}]}
393−
394− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"25"},"finish_reason":null}]}
395−
396− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"t"},"finish_reason":null}]}
397−
398− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"26"},"finish_reason":null}]}
399−
400− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"a"},"finish_reason":null}]}
401−
402− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"27"},"finish_reason":null}]}
403−
404− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"i"},"finish_reason":null}]}
405−
406− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"28"},"finish_reason":null}]}
407−
408− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"n"},"finish_reason":null}]}
409−
410− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"29"},"finish_reason":null}]}
411−
412− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"s"},"finish_reason":null}]}
413−
414− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"30"},"finish_reason":null}]}
415−
416− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
417−
418− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"31"},"finish_reason":null}]}
419−
420− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
421−
422− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"32"},"finish_reason":null}]}
423−
424− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"J"},"finish_reason":null}]}
425−
426− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"33"},"finish_reason":null}]}
427−
428− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"o"},"finish_reason":null}]}
429−
430− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"34"},"finish_reason":null}]}
431−
432− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"h"},"finish_reason":null}]}
433−
434− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"35"},"finish_reason":null}]}
435−
436− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"n"},"finish_reason":null}]}
437−
438− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"36"},"finish_reason":null}]}
439−
440− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
441−
442− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"37"},"finish_reason":null}]}
443−
444− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"D"},"finish_reason":null}]}
445−
446− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"38"},"finish_reason":null}]}
447−
448− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"o"},"finish_reason":null}]}
449−
450− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"39"},"finish_reason":null}]}
451−
452− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"e"},"finish_reason":null}]}
453−
454− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"40"},"finish_reason":null}]}
455−
456− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'"},"finish_reason":null}]}
457−
458− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"41"},"finish_reason":null}]}
459−
460− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
461−
462− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
463−
464− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
465−
466− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"41"},"finish_reason":null}]}
467−
468− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
469−
470− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
471−
472− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" within"},"finish_reason":null}]}
473−
474− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
475−
476− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
477−
478− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
479−
480− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Good"},"finish_reason":null}]}
481−
482− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
483−
484− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Check"},"finish_reason":null}]}
485−
486− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" if"},"finish_reason":null}]}
487−
488− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" example"},"finish_reason":null}]}
489−
490− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":".html"},"finish_reason":null}]}
491−
492− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" contains"},"finish_reason":null}]}
493−
494− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" '"},"finish_reason":null}]}
495−
496− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"John"},"finish_reason":null}]}
497−
498− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Doe"},"finish_reason":null}]}
499−
500− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"'"},"finish_reason":null}]}
501−
502− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
503−
504− data: {"id":"chatcmpl-2422745116026947d8ea8426","object":"chat.completion.chunk","created":1782413800,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":173,"completion_tokens":183,"total_tokens":420,"prompt_tokens_details":{"cached_tokens":64},"cost":{"usd":0.00013191,"hypercredits":0.0026382},"remaining":{"hypercredits":0}}}
505−
506− data: [DONE]
507−
508− headers:
509− Content-Type:
510− - text/event-stream
511− status: 200 OK
512− code: 200
513− duration: 1.005238292s
514−- id: 2
515− request:
516− proto: HTTP/1.1
517− proto_major: 1
518− proto_minor: 1
519− content_length: 0
520− host: example-files.online-convert.com
521− headers:
522− User-Agent:
523− - crush/1.0
524− url: https://example-files.online-convert.com/website/html/example.html
525− method: GET
526− response:
527− proto: HTTP/2.0
528− proto_major: 2
529− proto_minor: 0
530− content_length: -1
531− uncompressed: true
532− body: |-
533− <!DOCTYPE html>
534−
535− <html>
536− <body>
537−
538− <h1>HTML test file</h1>
539−
540− <p>Purpose: Provide example of this file type<br>
541− Document file type: HTML<br>
542− Version: 1.0<br>
543− Remark:</p>
544−
545− <p><img align="right" style="height:5.0551cm;width:7.62cm;" src="data:image/*;base64,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
546− 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
547− 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
548− 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
549− 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
550− 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
551− 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
552− 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
553− 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
554− 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
555− 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
556− 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"/>
557−
558− Example content:<br>
559− The names "<b>John Doe</b>" for males, "<b>Jane Doe</b>" or "<b>Jane Roe</b>" for females, or "<b>Jonnie Doe</b>" and "<b>Janie Doe</b>" for children, or just "<b>Doe</b>" non-gender-specifically are used as placeholder names for a party whose true identity is unknown or must be withheld in a legal action, case, or discussion. The names are also used to refer to acorpse or hospital patient whose identity is unknown. This practice is widely used in the United States and Canada, but is rarely used in other English-speaking countries including the United Kingdom itself, from where the use of "John Doe" in a legal context originates. The names Joe Bloggs or John Smith are used in the UK instead, as well as in Australia and New Zealand.</p>
560−
561− <p>John Doe is sometimes used to refer to a typical male in other contexts as well, in a similar manner to John Q. Public, known in Great Britain as Joe Public, John Smith or Joe Bloggs. For example, the first name listed on a form is often John Doe, along with a fictional address or other fictional information to provide an example of how to fill in the form. The name is also used frequently in popular culture, for example in the Frank Capra film <i>Meet John Doe</i>. John Doe was also the name of a 2002 American television series.</p>
562−
563− <p>Similarly, a child or baby whose identity is unknown may be referred to as <b>Baby Doe</b>. A notorious murder case in Kansas City, Missouri, referred to the baby victim as <b>Precious Doe</b>. Other unidentified female murder victims are Cali Doe and Princess Doe. Additional persons may be called James Doe, Judy Doe, etc. However, to avoid possible confusion, if two anonymous or unknown parties are cited in a specific case or action, the surnames Doe and Roe may be used simultaneously; for example, "John Doe v. Jane Roe". If several anonymous parties are referenced, they may simply be labelled John Doe #1, John Doe #2, etc. (the U.S. Operation Delego cited 21 (numbered) "John Doe"s) or labelled with other variants of Doe / Roe / Poe / etc. Other early alternatives such as <b>John Stiles</b> and <b>Richard Miles</b> are now rarely used, and <b>Mary Major</b> has been used in some American federal cases.</p>
564−
565− <p><img style="height:1.6881cm;width:1.6881cm;" align="left" src="data:image/*;base64,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
566− B1/bMVO7nYqfTdlIhfMUvxUd51lhy67Tyq1UqJI9Jew1tnpUt0B6+/rwB89+fbtcyp1Q+gRk7z/Gy9tfzMHyrrfpKG8eqVDetsaC8o5Juz6zqvKuz6GyvKtkeXn3fbDzOauVdwpGynvzd+wv64P1QRgMBZhAGAwFmEAYDAWYQBgMBZhAGAwFmEAYDAWYQBgMBZhAGAwFmEAYDAWYQBgMBZhAGAwFmEAYDAWYQBgMBf4/fQGdtWECNsgAAAAASUVORK5CYII="/>
567−
568− File created by <a href="https://www.online-convert.com" target="_blank">https://www.online-convert.com</a><br>
569− More example files: <a href="https://www.online-convert.com/file-type" target="_blank">https://www.online-convert.com/file-type</a><br>
570− Text of "Example content": <a href="https://en.wikipedia.org/wiki/John_Doe" target="_blank">Wikipedia</a><br>
571− License: <a href="https://creativecommons.org/licenses/by-sa/3.0/" target="_blank">Attribution-ShareAlike 3.0 Unported</a>
572−
573− <img style="height:0.6949cm;width:1.9741cm;" align="right" src="data:image/*;base64,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"/></p>
574−
575− <p>Feel free to use and share the file according to license above.</p>
576−
577− </body>
578− </html>
579− headers:
580− Content-Type:
581− - text/html; charset=UTF-8
582− status: 200 OK
583− code: 200
584− duration: 147.645375ms
585−- id: 3
586− request:
587− proto: HTTP/1.1
588− proto_major: 1
589− proto_minor: 1
590− content_length: 36231
591− host: ""
592− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ THE RELEVANT CONTEXT BEFORE EDITING**: Never edit a file you haven't already read the relevant context for in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\". When committing, follow the `<git_commits>` format from the bash tool description exactly, including any configured attribution lines.\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **TOOL CONSTRAINTS**: Only use documented tools. Never attempt 'apply_patch' or 'apply_diff' - they don't exist. Use 'edit' or 'multiedit' instead.\\n14. **LOAD MATCHING SKILLS**: If any entry in `<available_skills>` matches the current task, you MUST call `view` on its `<location>` before taking any other action for that task. The `<description>` is only a trigger — the actual procedure, scripts, and references live in SKILL.md. Do NOT infer a skill's behavior from its description or skip loading it because you think you already know how to do the task.\\n15. **LIMIT FILE READS**: Avoid reading entire files, as they can be very large. Read only the sections you need using 'offset' and 'limit' parameters.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- ALWAYS think and respond in the same spoken language the prompt was written in.\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\n**Available edit tools:**\\n- `edit` - Single find/replace in a file\\n- `multiedit` - Multiple find/replace operations in one file\\n- `write` - Create/overwrite entire file\\n\\nNever use `apply_patch` or similar - those tools don't exist.\\n\\nCritical: ALWAYS read the relevant context of files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the relevant context first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</editing_files>\\n\\n<whitespace_and_exact_matching>\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n</whitespace_and_exact_matching>\\n\\n<task_completion>\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n</task_completion>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences\\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n<bash_commands>\\n**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/glm-5.1/fetch_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n<available_skills>\\n <skill>\\n <name>crush-hooks</name>\\n <description>Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.</description>\\n <location>crush://skills/crush-hooks/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n <skill>\\n <name>jq</name>\\n <description>Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.</description>\\n <location>crush://skills/jq/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n</available_skills>\\n\\n<skills_usage>\\nThe `<description>` of each skill is a TRIGGER — it tells you *when* a skill applies. It is NOT a specification of what the skill does or how to do it. The procedure, scripts, commands, references, and required flags live only in the SKILL.md body. You do not know what a skill actually does until you have read its SKILL.md.\\n\\nMANDATORY activation flow:\\n1. Scan `<available_skills>` against the current user task.\\n2. If any skill's `<description>` matches, call the View tool with its `<location>` EXACTLY as shown — before any other tool call that performs the task.\\n3. Read the entire SKILL.md and follow its instructions.\\n4. Only then execute the task, using the skill's prescribed commands/tools.\\n\\nDo NOT skip step 2 because you think you already know how to do the task. Do NOT infer a skill's behavior from its name or description. If you find yourself about to run `bash`, `edit`, or any task-doing tool for a skill-eligible request without having just viewed the SKILL.md, stop and load the skill first.\\n\\nBuiltin skills (type=builtin) use virtual `crush://skills/...` location identifiers. The \\\"crush://\\\" prefix is NOT a URL, network address, or MCP resource — it is a special internal identifier the View tool understands natively. Pass the `<location>` verbatim to View.\\n\\nDo not use MCP tools (including read_mcp_resource) to load skills.\\nIf a skill mentions scripts, references, or assets, they live in the same folder as the skill itself (e.g., scripts/, references/, assets/ subdirectories within the skill's folder).\\n</skills_usage>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"<system_reminder>This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.</system_reminder>\",\"role\":\"user\"},{\"content\":\"fetch the content from https://example-files.online-convert.com/website/html/example.html and tell me if it contains the word 'John Doe'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_60557666b1c79950\",\"function\":{\"arguments\":\"{\\\"format\\\": \\\"text\\\", \\\"url\\\": \\\"https://example-files.online-convert.com/website/html/example.html\\\"}\",\"name\":\"fetch\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"The user wants me to fetch content from a URL and check if it contains the word 'John Doe'.\"},{\"content\":\"HTML test file Purpose: Provide example of this file type Document file type: HTML Version: 1.0 Remark:\",\"tool_call_id\":\"call_60557666b1c79950\",\"role\":\"tool\"}],\"model\":\"glm-5.1\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Execute shell commands; long-running commands automatically move to background and return a shell ID.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute (default, configurable via `auto_background_after`) automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<background_execution>\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `&` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n</background_execution>\\n\\n<git_message_quality>\\nThese rules apply whenever creating or updating commit messages, PR titles, or PR bodies:\\n\\n- Messages MUST be understandable to someone unfamiliar with the codebase.\\n- Before creating or updating a message, verify this litmus test: a new contributor reading only the commit message or PR title/body should understand what problem this solves, why it matters, and the impact without opening files, reading the diff, or knowing internal code names.\\n- Avoid code identifiers, filenames, function names, and implementation details unless they are necessary for understanding the user-facing impact.\\n- Bad: \\\"Add NameFromHex with sync.Once lazy init\\\"\\n- Good: \\\"Improve color name lookup performance while keeping startup fast\\\"\\n</git_message_quality>\\n\\n<commit_messages>\\nCommit messages are for future readers scanning history. Before committing:\\n\\n- Follow <git_message_quality>.\\n- Draft a concise 1-2 sentence message focusing on why the change exists and what outcome it enables, not a list of files or implementation details.\\n- Use clear, accurate verbs (\\\"add\\\"=new capability, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix) and avoid generic messages.\\n- The first line MUST be under 72 characters.\\n- Add a body only when it is needed to explain the reasoning, tradeoffs, or important context; wrap body lines at 72 characters.\\n- If the change is internal-only, still describe the benefit or maintenance outcome rather than naming private code.\\n- Bad: \\\"fix: nil pointer in session.go\\\"\\n- Good: \\\"fix: prevent session loading from crashing on missing metadata\\\"\\n- Bad: \\\"refactor: move PromptBuilder into internal/agent\\\"\\n- Good: \\\"refactor: make prompt assembly easier to maintain\\\"\\n</commit_messages>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond the context of git\\n\\n4. Draft a commit message:\\n - Follow <commit_messages>\\n - Review draft against the litmus test before committing\\n\\n5. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\nCommit message here.\\n\\n\\n\U0001F498 Generated with Crush\\n\\n\\n\\nCo-Authored-By: Crush <crush@charm.land>\\n\\nEOF\\n)\\\"\\n\\n6. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n7. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m.\\n</git_commits>\\n\\n<pull_requests>\\n\\n\\nWhen user asks you to create or update a PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n\\n3. Commit changes if needed\\n\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n\\n6. Draft a PR message:\\n - Follow <git_message_quality>\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Use clear, concise language\\n - Provide an accurate reflection of changes and purpose\\n - Avoid generic summaries; messages should be thoughtful\\n - Review draft against the litmus test before creating or updating the PR\\n\\n7. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n<summary>\\n\\n\U0001F498 Generated with Crush\\n\\nEOF\\n)\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"auto_background_after\":{\"description\":\"Seconds to wait before automatically moving the command to a background job (default: 60)\",\"type\":\"integer\"},\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Download a URL directly to a local file (binary-safe, streaming, max 600s timeout); overwrites without warning. For reading content into context use fetch.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edit a file by exact find-and-replace; can also create or delete content. For renames/moves use bash. For large edits use write.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Apply multiple find-and-replace edits to a single file in one operation; edits run sequentially. Prefer over edit for multiple changes to the same file. Same exact-match rules as edit apply.\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetch raw content from a URL as text, markdown, or html (max 100KB); no AI processing. For analysis or extraction use agentic_fetch.\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Find files by name/pattern (glob syntax), sorted by modification time; max 100 results; skips hidden files. Use grep to search file contents.\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Search file contents by regex or literal text; returns matching file paths sorted by modification time (max 100); respects .gitignore. Use glob to filter by filename, not contents.\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"List files and directories as a tree; skips hidden files and common system dirs; max 1000 files. Use glob to find files by pattern, grep to search contents.\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public GitHub repositories via Sourcegraph; supports regex, language/repo/file filters, and symbol search (max 20 results). Only searches public repos.\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Read a file by path with line numbers; supports offset and line limit (default 200, max 200KB returned file content section); renders images (PNG, JPEG, GIF, WebP); use ls for directories.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 200)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Create or overwrite a file with given content; auto-creates parent dirs. Cannot append. Read the file first to avoid conflicts. For surgical changes use edit or multiedit.\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
593− headers:
594− Accept:
595− - application/json
596− Content-Type:
597− - application/json
598− User-Agent:
599− - Charm-Crush/devel (https://charm.land/crush)
600− url: https://hyper.charm.land/v1/chat/completions
601− method: POST
602− response:
603− proto: HTTP/2.0
604− proto_major: 2
605− proto_minor: 0
606− content_length: -1
607− uncompressed: true
608− body: |+
609− data: {"id":"chatcmpl-cd7a3a1eb813288fd5e12324","object":"chat.completion.chunk","created":1782413803,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
610−
611− data: {"id":"chatcmpl-cd7a3a1eb813288fd5e12324","object":"chat.completion.chunk","created":1782413803,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"No"},"finish_reason":null}]}
612−
613− data: {"id":"chatcmpl-cd7a3a1eb813288fd5e12324","object":"chat.completion.chunk","created":1782413803,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":","},"finish_reason":null}]}
614−
615− data: {"id":"chatcmpl-cd7a3a1eb813288fd5e12324","object":"chat.completion.chunk","created":1782413803,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" the"},"finish_reason":null}]}
616−
617− data: {"id":"chatcmpl-cd7a3a1eb813288fd5e12324","object":"chat.completion.chunk","created":1782413803,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" fetched"},"finish_reason":null}]}
618−
619− data: {"id":"chatcmpl-cd7a3a1eb813288fd5e12324","object":"chat.completion.chunk","created":1782413803,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" content"},"finish_reason":null}]}
620−
621− data: {"id":"chatcmpl-cd7a3a1eb813288fd5e12324","object":"chat.completion.chunk","created":1782413803,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" does"},"finish_reason":null}]}
622−
623− data: {"id":"chatcmpl-cd7a3a1eb813288fd5e12324","object":"chat.completion.chunk","created":1782413803,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" not"},"finish_reason":null}]}
624−
625− data: {"id":"chatcmpl-cd7a3a1eb813288fd5e12324","object":"chat.completion.chunk","created":1782413803,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" contain"},"finish_reason":null}]}
626−
627− data: {"id":"chatcmpl-cd7a3a1eb813288fd5e12324","object":"chat.completion.chunk","created":1782413803,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" the"},"finish_reason":null}]}
628−
629− data: {"id":"chatcmpl-cd7a3a1eb813288fd5e12324","object":"chat.completion.chunk","created":1782413803,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" word"},"finish_reason":null}]}
630−
631− data: {"id":"chatcmpl-cd7a3a1eb813288fd5e12324","object":"chat.completion.chunk","created":1782413803,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" \""},"finish_reason":null}]}
632−
633− data: {"id":"chatcmpl-cd7a3a1eb813288fd5e12324","object":"chat.completion.chunk","created":1782413803,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"John"},"finish_reason":null}]}
634−
635− data: {"id":"chatcmpl-cd7a3a1eb813288fd5e12324","object":"chat.completion.chunk","created":1782413803,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" Doe"},"finish_reason":null}]}
636−
637− data: {"id":"chatcmpl-cd7a3a1eb813288fd5e12324","object":"chat.completion.chunk","created":1782413803,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"\"."},"finish_reason":null}]}
638−
639− data: {"id":"chatcmpl-cd7a3a1eb813288fd5e12324","object":"chat.completion.chunk","created":1782413803,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
640−
641− data: {"id":"chatcmpl-cd7a3a1eb813288fd5e12324","object":"chat.completion.chunk","created":1782413803,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":753,"completion_tokens":16,"total_tokens":8248,"prompt_tokens_details":{"cached_tokens":7479},"cost":{"usd":0.0011246000000000001,"hypercredits":0.022492},"remaining":{"hypercredits":0}}}
642−
643− data: [DONE]
644−
645− headers:
646− Content-Type:
647− - text/event-stream
648− status: 200 OK
649− code: 200
650− duration: 977.248916ms
internal/agent/testdata/TestCoderAgent/glm-5.1/glob_tool.yamldeleted−737
@@ -1,737 +0,0 @@
1−---
2−version: 2
3−interactions:
4−- id: 0
5− request:
6− proto: HTTP/1.1
7− proto_major: 1
8− proto_minor: 1
9− content_length: 35633
10− host: ""
11− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ THE RELEVANT CONTEXT BEFORE EDITING**: Never edit a file you haven't already read the relevant context for in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\". When committing, follow the `<git_commits>` format from the bash tool description exactly, including any configured attribution lines.\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **TOOL CONSTRAINTS**: Only use documented tools. Never attempt 'apply_patch' or 'apply_diff' - they don't exist. Use 'edit' or 'multiedit' instead.\\n14. **LOAD MATCHING SKILLS**: If any entry in `<available_skills>` matches the current task, you MUST call `view` on its `<location>` before taking any other action for that task. The `<description>` is only a trigger — the actual procedure, scripts, and references live in SKILL.md. Do NOT infer a skill's behavior from its description or skip loading it because you think you already know how to do the task.\\n15. **LIMIT FILE READS**: Avoid reading entire files, as they can be very large. Read only the sections you need using 'offset' and 'limit' parameters.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- ALWAYS think and respond in the same spoken language the prompt was written in.\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\n**Available edit tools:**\\n- `edit` - Single find/replace in a file\\n- `multiedit` - Multiple find/replace operations in one file\\n- `write` - Create/overwrite entire file\\n\\nNever use `apply_patch` or similar - those tools don't exist.\\n\\nCritical: ALWAYS read the relevant context of files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the relevant context first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</editing_files>\\n\\n<whitespace_and_exact_matching>\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n</whitespace_and_exact_matching>\\n\\n<task_completion>\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n</task_completion>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences\\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n<bash_commands>\\n**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/glm-5.1/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n<available_skills>\\n <skill>\\n <name>crush-hooks</name>\\n <description>Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.</description>\\n <location>crush://skills/crush-hooks/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n <skill>\\n <name>jq</name>\\n <description>Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.</description>\\n <location>crush://skills/jq/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n</available_skills>\\n\\n<skills_usage>\\nThe `<description>` of each skill is a TRIGGER — it tells you *when* a skill applies. It is NOT a specification of what the skill does or how to do it. The procedure, scripts, commands, references, and required flags live only in the SKILL.md body. You do not know what a skill actually does until you have read its SKILL.md.\\n\\nMANDATORY activation flow:\\n1. Scan `<available_skills>` against the current user task.\\n2. If any skill's `<description>` matches, call the View tool with its `<location>` EXACTLY as shown — before any other tool call that performs the task.\\n3. Read the entire SKILL.md and follow its instructions.\\n4. Only then execute the task, using the skill's prescribed commands/tools.\\n\\nDo NOT skip step 2 because you think you already know how to do the task. Do NOT infer a skill's behavior from its name or description. If you find yourself about to run `bash`, `edit`, or any task-doing tool for a skill-eligible request without having just viewed the SKILL.md, stop and load the skill first.\\n\\nBuiltin skills (type=builtin) use virtual `crush://skills/...` location identifiers. The \\\"crush://\\\" prefix is NOT a URL, network address, or MCP resource — it is a special internal identifier the View tool understands natively. Pass the `<location>` verbatim to View.\\n\\nDo not use MCP tools (including read_mcp_resource) to load skills.\\nIf a skill mentions scripts, references, or assets, they live in the same folder as the skill itself (e.g., scripts/, references/, assets/ subdirectories within the skill's folder).\\n</skills_usage>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"<system_reminder>This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.</system_reminder>\",\"role\":\"user\"},{\"content\":\"use glob to find all .go files in the current directory\",\"role\":\"user\"}],\"model\":\"glm-5.1\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Execute shell commands; long-running commands automatically move to background and return a shell ID.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute (default, configurable via `auto_background_after`) automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<background_execution>\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `&` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n</background_execution>\\n\\n<git_message_quality>\\nThese rules apply whenever creating or updating commit messages, PR titles, or PR bodies:\\n\\n- Messages MUST be understandable to someone unfamiliar with the codebase.\\n- Before creating or updating a message, verify this litmus test: a new contributor reading only the commit message or PR title/body should understand what problem this solves, why it matters, and the impact without opening files, reading the diff, or knowing internal code names.\\n- Avoid code identifiers, filenames, function names, and implementation details unless they are necessary for understanding the user-facing impact.\\n- Bad: \\\"Add NameFromHex with sync.Once lazy init\\\"\\n- Good: \\\"Improve color name lookup performance while keeping startup fast\\\"\\n</git_message_quality>\\n\\n<commit_messages>\\nCommit messages are for future readers scanning history. Before committing:\\n\\n- Follow <git_message_quality>.\\n- Draft a concise 1-2 sentence message focusing on why the change exists and what outcome it enables, not a list of files or implementation details.\\n- Use clear, accurate verbs (\\\"add\\\"=new capability, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix) and avoid generic messages.\\n- The first line MUST be under 72 characters.\\n- Add a body only when it is needed to explain the reasoning, tradeoffs, or important context; wrap body lines at 72 characters.\\n- If the change is internal-only, still describe the benefit or maintenance outcome rather than naming private code.\\n- Bad: \\\"fix: nil pointer in session.go\\\"\\n- Good: \\\"fix: prevent session loading from crashing on missing metadata\\\"\\n- Bad: \\\"refactor: move PromptBuilder into internal/agent\\\"\\n- Good: \\\"refactor: make prompt assembly easier to maintain\\\"\\n</commit_messages>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond the context of git\\n\\n4. Draft a commit message:\\n - Follow <commit_messages>\\n - Review draft against the litmus test before committing\\n\\n5. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\nCommit message here.\\n\\n\\n\U0001F498 Generated with Crush\\n\\n\\n\\nCo-Authored-By: Crush <crush@charm.land>\\n\\nEOF\\n)\\\"\\n\\n6. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n7. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m.\\n</git_commits>\\n\\n<pull_requests>\\n\\n\\nWhen user asks you to create or update a PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n\\n3. Commit changes if needed\\n\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n\\n6. Draft a PR message:\\n - Follow <git_message_quality>\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Use clear, concise language\\n - Provide an accurate reflection of changes and purpose\\n - Avoid generic summaries; messages should be thoughtful\\n - Review draft against the litmus test before creating or updating the PR\\n\\n7. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n<summary>\\n\\n\U0001F498 Generated with Crush\\n\\nEOF\\n)\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"auto_background_after\":{\"description\":\"Seconds to wait before automatically moving the command to a background job (default: 60)\",\"type\":\"integer\"},\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Download a URL directly to a local file (binary-safe, streaming, max 600s timeout); overwrites without warning. For reading content into context use fetch.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edit a file by exact find-and-replace; can also create or delete content. For renames/moves use bash. For large edits use write.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Apply multiple find-and-replace edits to a single file in one operation; edits run sequentially. Prefer over edit for multiple changes to the same file. Same exact-match rules as edit apply.\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetch raw content from a URL as text, markdown, or html (max 100KB); no AI processing. For analysis or extraction use agentic_fetch.\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Find files by name/pattern (glob syntax), sorted by modification time; max 100 results; skips hidden files. Use grep to search file contents.\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Search file contents by regex or literal text; returns matching file paths sorted by modification time (max 100); respects .gitignore. Use glob to filter by filename, not contents.\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"List files and directories as a tree; skips hidden files and common system dirs; max 1000 files. Use glob to find files by pattern, grep to search contents.\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public GitHub repositories via Sourcegraph; supports regex, language/repo/file filters, and symbol search (max 20 results). Only searches public repos.\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Read a file by path with line numbers; supports offset and line limit (default 200, max 200KB returned file content section); renders images (PNG, JPEG, GIF, WebP); use ls for directories.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 200)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Create or overwrite a file with given content; auto-creates parent dirs. Cannot append. Read the file first to avoid conflicts. For surgical changes use edit or multiedit.\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
12− headers:
13− Accept:
14− - application/json
15− Content-Type:
16− - application/json
17− User-Agent:
18− - Charm-Crush/devel (https://charm.land/crush)
19− url: https://hyper.charm.land/v1/chat/completions
20− method: POST
21− response:
22− proto: HTTP/2.0
23− proto_major: 2
24− proto_minor: 0
25− content_length: -1
26− uncompressed: true
27− body: |+
28− data: {"id":"chatcmpl-680977ab8e48dc961b5a65b4","object":"chat.completion.chunk","created":1782413805,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
29−
30− data: {"id":"chatcmpl-680977ab8e48dc961b5a65b4","object":"chat.completion.chunk","created":1782413805,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_ad74b69d4b477328","type":"function","index":0,"function":{"name":"glob","arguments":""}}]},"finish_reason":null}]}
31−
32− data: {"id":"chatcmpl-680977ab8e48dc961b5a65b4","object":"chat.completion.chunk","created":1782413805,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\"pattern\": \""}}]},"finish_reason":null}]}
33−
34− data: {"id":"chatcmpl-680977ab8e48dc961b5a65b4","object":"chat.completion.chunk","created":1782413805,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"**"}}]},"finish_reason":null}]}
35−
36− data: {"id":"chatcmpl-680977ab8e48dc961b5a65b4","object":"chat.completion.chunk","created":1782413805,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/*."}}]},"finish_reason":null}]}
37−
38− data: {"id":"chatcmpl-680977ab8e48dc961b5a65b4","object":"chat.completion.chunk","created":1782413805,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go"}}]},"finish_reason":null}]}
39−
40− data: {"id":"chatcmpl-680977ab8e48dc961b5a65b4","object":"chat.completion.chunk","created":1782413805,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\""}}]},"finish_reason":null}]}
41−
42− data: {"id":"chatcmpl-680977ab8e48dc961b5a65b4","object":"chat.completion.chunk","created":1782413805,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
43−
44− data: {"id":"chatcmpl-680977ab8e48dc961b5a65b4","object":"chat.completion.chunk","created":1782413805,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
45−
46− data: {"id":"chatcmpl-680977ab8e48dc961b5a65b4","object":"chat.completion.chunk","created":1782413805,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":679,"completion_tokens":13,"total_tokens":8171,"prompt_tokens_details":{"cached_tokens":7479},"cost":{"usd":0.0010077999999999999,"hypercredits":0.020155999999999997},"remaining":{"hypercredits":0}}}
47−
48− data: [DONE]
49−
50− headers:
51− Content-Type:
52− - text/event-stream
53− status: 200 OK
54− code: 200
55− duration: 2.191829958s
56−- id: 1
57− request:
58− proto: HTTP/1.1
59− proto_major: 1
60− proto_minor: 1
61− content_length: 35910
62− host: ""
63− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ THE RELEVANT CONTEXT BEFORE EDITING**: Never edit a file you haven't already read the relevant context for in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\". When committing, follow the `<git_commits>` format from the bash tool description exactly, including any configured attribution lines.\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **TOOL CONSTRAINTS**: Only use documented tools. Never attempt 'apply_patch' or 'apply_diff' - they don't exist. Use 'edit' or 'multiedit' instead.\\n14. **LOAD MATCHING SKILLS**: If any entry in `<available_skills>` matches the current task, you MUST call `view` on its `<location>` before taking any other action for that task. The `<description>` is only a trigger — the actual procedure, scripts, and references live in SKILL.md. Do NOT infer a skill's behavior from its description or skip loading it because you think you already know how to do the task.\\n15. **LIMIT FILE READS**: Avoid reading entire files, as they can be very large. Read only the sections you need using 'offset' and 'limit' parameters.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- ALWAYS think and respond in the same spoken language the prompt was written in.\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\n**Available edit tools:**\\n- `edit` - Single find/replace in a file\\n- `multiedit` - Multiple find/replace operations in one file\\n- `write` - Create/overwrite entire file\\n\\nNever use `apply_patch` or similar - those tools don't exist.\\n\\nCritical: ALWAYS read the relevant context of files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the relevant context first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</editing_files>\\n\\n<whitespace_and_exact_matching>\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n</whitespace_and_exact_matching>\\n\\n<task_completion>\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n</task_completion>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences\\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n<bash_commands>\\n**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/glm-5.1/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n<available_skills>\\n <skill>\\n <name>crush-hooks</name>\\n <description>Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.</description>\\n <location>crush://skills/crush-hooks/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n <skill>\\n <name>jq</name>\\n <description>Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.</description>\\n <location>crush://skills/jq/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n</available_skills>\\n\\n<skills_usage>\\nThe `<description>` of each skill is a TRIGGER — it tells you *when* a skill applies. It is NOT a specification of what the skill does or how to do it. The procedure, scripts, commands, references, and required flags live only in the SKILL.md body. You do not know what a skill actually does until you have read its SKILL.md.\\n\\nMANDATORY activation flow:\\n1. Scan `<available_skills>` against the current user task.\\n2. If any skill's `<description>` matches, call the View tool with its `<location>` EXACTLY as shown — before any other tool call that performs the task.\\n3. Read the entire SKILL.md and follow its instructions.\\n4. Only then execute the task, using the skill's prescribed commands/tools.\\n\\nDo NOT skip step 2 because you think you already know how to do the task. Do NOT infer a skill's behavior from its name or description. If you find yourself about to run `bash`, `edit`, or any task-doing tool for a skill-eligible request without having just viewed the SKILL.md, stop and load the skill first.\\n\\nBuiltin skills (type=builtin) use virtual `crush://skills/...` location identifiers. The \\\"crush://\\\" prefix is NOT a URL, network address, or MCP resource — it is a special internal identifier the View tool understands natively. Pass the `<location>` verbatim to View.\\n\\nDo not use MCP tools (including read_mcp_resource) to load skills.\\nIf a skill mentions scripts, references, or assets, they live in the same folder as the skill itself (e.g., scripts/, references/, assets/ subdirectories within the skill's folder).\\n</skills_usage>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"<system_reminder>This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.</system_reminder>\",\"role\":\"user\"},{\"content\":\"use glob to find all .go files in the current directory\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_ad74b69d4b477328\",\"function\":{\"arguments\":\"{\\\"pattern\\\": \\\"**/*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/glm-5.1/glob_tool/main.go\",\"tool_call_id\":\"call_ad74b69d4b477328\",\"role\":\"tool\"}],\"model\":\"glm-5.1\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Execute shell commands; long-running commands automatically move to background and return a shell ID.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute (default, configurable via `auto_background_after`) automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<background_execution>\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `&` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n</background_execution>\\n\\n<git_message_quality>\\nThese rules apply whenever creating or updating commit messages, PR titles, or PR bodies:\\n\\n- Messages MUST be understandable to someone unfamiliar with the codebase.\\n- Before creating or updating a message, verify this litmus test: a new contributor reading only the commit message or PR title/body should understand what problem this solves, why it matters, and the impact without opening files, reading the diff, or knowing internal code names.\\n- Avoid code identifiers, filenames, function names, and implementation details unless they are necessary for understanding the user-facing impact.\\n- Bad: \\\"Add NameFromHex with sync.Once lazy init\\\"\\n- Good: \\\"Improve color name lookup performance while keeping startup fast\\\"\\n</git_message_quality>\\n\\n<commit_messages>\\nCommit messages are for future readers scanning history. Before committing:\\n\\n- Follow <git_message_quality>.\\n- Draft a concise 1-2 sentence message focusing on why the change exists and what outcome it enables, not a list of files or implementation details.\\n- Use clear, accurate verbs (\\\"add\\\"=new capability, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix) and avoid generic messages.\\n- The first line MUST be under 72 characters.\\n- Add a body only when it is needed to explain the reasoning, tradeoffs, or important context; wrap body lines at 72 characters.\\n- If the change is internal-only, still describe the benefit or maintenance outcome rather than naming private code.\\n- Bad: \\\"fix: nil pointer in session.go\\\"\\n- Good: \\\"fix: prevent session loading from crashing on missing metadata\\\"\\n- Bad: \\\"refactor: move PromptBuilder into internal/agent\\\"\\n- Good: \\\"refactor: make prompt assembly easier to maintain\\\"\\n</commit_messages>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond the context of git\\n\\n4. Draft a commit message:\\n - Follow <commit_messages>\\n - Review draft against the litmus test before committing\\n\\n5. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\nCommit message here.\\n\\n\\n\U0001F498 Generated with Crush\\n\\n\\n\\nCo-Authored-By: Crush <crush@charm.land>\\n\\nEOF\\n)\\\"\\n\\n6. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n7. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m.\\n</git_commits>\\n\\n<pull_requests>\\n\\n\\nWhen user asks you to create or update a PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n\\n3. Commit changes if needed\\n\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n\\n6. Draft a PR message:\\n - Follow <git_message_quality>\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Use clear, concise language\\n - Provide an accurate reflection of changes and purpose\\n - Avoid generic summaries; messages should be thoughtful\\n - Review draft against the litmus test before creating or updating the PR\\n\\n7. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n<summary>\\n\\n\U0001F498 Generated with Crush\\n\\nEOF\\n)\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"auto_background_after\":{\"description\":\"Seconds to wait before automatically moving the command to a background job (default: 60)\",\"type\":\"integer\"},\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Download a URL directly to a local file (binary-safe, streaming, max 600s timeout); overwrites without warning. For reading content into context use fetch.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edit a file by exact find-and-replace; can also create or delete content. For renames/moves use bash. For large edits use write.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Apply multiple find-and-replace edits to a single file in one operation; edits run sequentially. Prefer over edit for multiple changes to the same file. Same exact-match rules as edit apply.\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetch raw content from a URL as text, markdown, or html (max 100KB); no AI processing. For analysis or extraction use agentic_fetch.\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Find files by name/pattern (glob syntax), sorted by modification time; max 100 results; skips hidden files. Use grep to search file contents.\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Search file contents by regex or literal text; returns matching file paths sorted by modification time (max 100); respects .gitignore. Use glob to filter by filename, not contents.\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"List files and directories as a tree; skips hidden files and common system dirs; max 1000 files. Use glob to find files by pattern, grep to search contents.\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public GitHub repositories via Sourcegraph; supports regex, language/repo/file filters, and symbol search (max 20 results). Only searches public repos.\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Read a file by path with line numbers; supports offset and line limit (default 200, max 200KB returned file content section); renders images (PNG, JPEG, GIF, WebP); use ls for directories.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 200)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Create or overwrite a file with given content; auto-creates parent dirs. Cannot append. Read the file first to avoid conflicts. For surgical changes use edit or multiedit.\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
64− headers:
65− Accept:
66− - application/json
67− Content-Type:
68− - application/json
69− User-Agent:
70− - Charm-Crush/devel (https://charm.land/crush)
71− url: https://hyper.charm.land/v1/chat/completions
72− method: POST
73− response:
74− proto: HTTP/2.0
75− proto_major: 2
76− proto_minor: 0
77− content_length: -1
78− uncompressed: true
79− body: |+
80− data: {"id":"chatcmpl-85e120b7a3fdf21599aee1ba","object":"chat.completion.chunk","created":1782413807,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
81−
82− data: {"id":"chatcmpl-85e120b7a3fdf21599aee1ba","object":"chat.completion.chunk","created":1782413807,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Found"},"finish_reason":null}]}
83−
84− data: {"id":"chatcmpl-85e120b7a3fdf21599aee1ba","object":"chat.completion.chunk","created":1782413807,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" "},"finish_reason":null}]}
85−
86− data: {"id":"chatcmpl-85e120b7a3fdf21599aee1ba","object":"chat.completion.chunk","created":1782413807,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"1"},"finish_reason":null}]}
87−
88− data: {"id":"chatcmpl-85e120b7a3fdf21599aee1ba","object":"chat.completion.chunk","created":1782413807,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `."},"finish_reason":null}]}
89−
90− data: {"id":"chatcmpl-85e120b7a3fdf21599aee1ba","object":"chat.completion.chunk","created":1782413807,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"go"},"finish_reason":null}]}
91−
92− data: {"id":"chatcmpl-85e120b7a3fdf21599aee1ba","object":"chat.completion.chunk","created":1782413807,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`"},"finish_reason":null}]}
93−
94− data: {"id":"chatcmpl-85e120b7a3fdf21599aee1ba","object":"chat.completion.chunk","created":1782413807,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" file"},"finish_reason":null}]}
95−
96− data: {"id":"chatcmpl-85e120b7a3fdf21599aee1ba","object":"chat.completion.chunk","created":1782413807,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}]}
97−
98− data: {"id":"chatcmpl-85e120b7a3fdf21599aee1ba","object":"chat.completion.chunk","created":1782413807,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `"},"finish_reason":null}]}
99−
100− data: {"id":"chatcmpl-85e120b7a3fdf21599aee1ba","object":"chat.completion.chunk","created":1782413807,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"main"},"finish_reason":null}]}
101−
102− data: {"id":"chatcmpl-85e120b7a3fdf21599aee1ba","object":"chat.completion.chunk","created":1782413807,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}]}
103−
104− data: {"id":"chatcmpl-85e120b7a3fdf21599aee1ba","object":"chat.completion.chunk","created":1782413807,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`"},"finish_reason":null}]}
105−
106− data: {"id":"chatcmpl-85e120b7a3fdf21599aee1ba","object":"chat.completion.chunk","created":1782413807,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
107−
108− data: {"id":"chatcmpl-85e120b7a3fdf21599aee1ba","object":"chat.completion.chunk","created":1782413807,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":36,"completion_tokens":14,"total_tokens":8207,"prompt_tokens_details":{"cached_tokens":8157},"cost":{"usd":0.00011200000000000001,"hypercredits":0.0022400000000000002},"remaining":{"hypercredits":0}}}
109−
110− data: [DONE]
111−
112− headers:
113− Content-Type:
114− - text/event-stream
115− status: 200 OK
116− code: 200
117− duration: 1.449032542s
118−- id: 2
119− request:
120− proto: HTTP/1.1
121− proto_major: 1
122− proto_minor: 1
123− content_length: 814
124− host: ""
125− body: '{"messages":[{"content":"You will generate a short title based on the first message a user begins a conversation with.\n\n<rules>\n- Keep the title in the same language that the user wrote their message in.\n- Ensure it is not more than 50 characters long.\n- The title should be a summary of the user''s message.\n- It should be one line long.\n- Do not use quotes or colons.\n- The entire text you return will be used as the title.\n- Never return anything that is more than one sentence (one line) long.\n</rules>\n\n /no_think","role":"system"},{"content":"Generate a concise title for the following content:\n\nuse glob to find all .go files in the current directory\n <think>\n\n</think>","role":"user"}],"model":"gpt-oss-120b","max_completion_tokens":40,"stream_options":{"include_usage":true},"stream":true}'
126− headers:
127− Accept:
128− - application/json
129− Content-Type:
130− - application/json
131− User-Agent:
132− - Charm-Crush/devel (https://charm.land/crush)
133− url: https://hyper.charm.land/v1/chat/completions
134− method: POST
135− response:
136− proto: HTTP/2.0
137− proto_major: 2
138− proto_minor: 0
139− content_length: -1
140− uncompressed: true
141− body: |+
142− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
143−
144− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
145−
146− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" wants"},"finish_reason":null}]}
147−
148− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
149−
150− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
151−
152− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
153−
154− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
155−
156− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
157−
158− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
159−
160− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
161−
162− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
163−
164− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"use"},"finish_reason":null}]}
165−
166− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" glob"},"finish_reason":null}]}
167−
168− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
169−
170− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" find"},"finish_reason":null}]}
171−
172− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" all"},"finish_reason":null}]}
173−
174− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ."},"finish_reason":null}]}
175−
176− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"go"},"finish_reason":null}]}
177−
178− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
179−
180− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
181−
182− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
183−
184− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" current"},"finish_reason":null}]}
185−
186− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" directory"},"finish_reason":null}]}
187−
188− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
189−
190− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Title"},"finish_reason":null}]}
191−
192− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
193−
194− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" English"},"finish_reason":null}]}
195−
196− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
197−
198− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \u003c="},"finish_reason":null}]}
199−
200− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
201−
202− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
203−
204− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
205−
206− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" one"},"finish_reason":null}]}
207−
208− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
209−
210− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
211−
212− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" no"},"finish_reason":null}]}
213−
214− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
215−
216− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" or"},"finish_reason":null}]}
217−
218− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" col"},"finish_reason":null}]}
219−
220− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ons"},"finish_reason":null}]}
221−
222− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
223−
224− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Something"},"finish_reason":null}]}
225−
226− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" like"},"finish_reason":null}]}
227−
228− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
229−
230− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Finding"},"finish_reason":null}]}
231−
232− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ."},"finish_reason":null}]}
233−
234− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"go"},"finish_reason":null}]}
235−
236− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Files"},"finish_reason":null}]}
237−
238− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
239−
240− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Glob"},"finish_reason":null}]}
241−
242− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
243−
244− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Current"},"finish_reason":null}]}
245−
246− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Directory"},"finish_reason":null}]}
247−
248− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
249−
250− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
251−
252− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" under"},"finish_reason":null}]}
253−
254− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
255−
256− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
257−
258− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
259−
260− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
261−
262− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
263−
264− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
265−
266− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
267−
268− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Finding"},"finish_reason":null}]}
269−
270− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ."},"finish_reason":null}]}
271−
272− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"go"},"finish_reason":null}]}
273−
274− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Files"},"finish_reason":null}]}
275−
276− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
277−
278− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Glob"},"finish_reason":null}]}
279−
280− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
281−
282− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Current"},"finish_reason":null}]}
283−
284− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Directory"},"finish_reason":null}]}
285−
286− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
287−
288− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ="},"finish_reason":null}]}
289−
290− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" let's"},"finish_reason":null}]}
291−
292− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
293−
294− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
295−
296− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Finding"},"finish_reason":null}]}
297−
298− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
299−
300− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
301−
302− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
303−
304− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" +"},"finish_reason":null}]}
305−
306− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
307−
308− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
309−
310− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
311−
312− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
313−
314− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ="},"finish_reason":null}]}
315−
316− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"8"},"finish_reason":null}]}
317−
318− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
319−
320− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ."},"finish_reason":null}]}
321−
322− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"go"},"finish_reason":null}]}
323−
324− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
325−
326− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
327−
328− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
329−
330− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" =\u003e"},"finish_reason":null}]}
331−
332− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" total"},"finish_reason":null}]}
333−
334− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
335−
336− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"11"},"finish_reason":null}]}
337−
338− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
339−
340− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
341−
342− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
343−
344− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"12"},"finish_reason":null}]}
345−
346− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
347−
348− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Files"},"finish_reason":null}]}
349−
350− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
351−
352− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
353−
354− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
355−
356− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"17"},"finish_reason":null}]}
357−
358− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
359−
360− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
361−
362− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
363−
364− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"18"},"finish_reason":null}]}
365−
366− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
367−
368− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
369−
370− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
371−
372− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
373−
374− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
375−
376− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"22"},"finish_reason":null}]}
377−
378− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
379−
380− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
381−
382− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
383−
384− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"23"},"finish_reason":null}]}
385−
386− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
387−
388− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Glob"},"finish_reason":null}]}
389−
390− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
391−
392− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
393−
394− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
395−
396− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"27"},"finish_reason":null}]}
397−
398− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
399−
400− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
401−
402− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
403−
404− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"28"},"finish_reason":null}]}
405−
406− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
407−
408− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
409−
410− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
411−
412− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
413−
414− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
415−
416− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"30"},"finish_reason":null}]}
417−
418− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
419−
420− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
421−
422− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
423−
424− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"31"},"finish_reason":null}]}
425−
426− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
427−
428− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Current"},"finish_reason":null}]}
429−
430− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
431−
432− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
433−
434− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
435−
436− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"38"},"finish_reason":null}]}
437−
438− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
439−
440− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
441−
442− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
443−
444− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"39"},"finish_reason":null}]}
445−
446− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
447−
448− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Directory"},"finish_reason":null}]}
449−
450− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
451−
452− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"9"},"finish_reason":null}]}
453−
454− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
455−
456− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"48"},"finish_reason":null}]}
457−
458− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
459−
460− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" So"},"finish_reason":null}]}
461−
462− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
463−
464− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"48"},"finish_reason":null}]}
465−
466− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
467−
468− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
469−
470− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" okay"},"finish_reason":null}]}
471−
472− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
473−
474− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Or"},"finish_reason":null}]}
475−
476− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
477−
478− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Use"},"finish_reason":null}]}
479−
480− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" glob"},"finish_reason":null}]}
481−
482− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
483−
484− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" locate"},"finish_reason":null}]}
485−
486− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ."},"finish_reason":null}]}
487−
488− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"go"},"finish_reason":null}]}
489−
490− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
491−
492− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
493−
494− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" current"},"finish_reason":null}]}
495−
496− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" dir"},"finish_reason":null}]}
497−
498− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
499−
500− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Let's"},"finish_reason":null}]}
501−
502− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
503−
504− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
505−
506− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Use"},"finish_reason":null}]}
507−
508− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
509−
510− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
511−
512− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")+"},"finish_reason":null}]}
513−
514− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"space"},"finish_reason":null}]}
515−
516− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
517−
518− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
519−
520− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
521−
522− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" glob"},"finish_reason":null}]}
523−
524− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
525−
526− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
527−
528− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
529−
530− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"8"},"finish_reason":null}]}
531−
532− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
533−
534− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
535−
536− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
537−
538− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"9"},"finish_reason":null}]}
539−
540− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
541−
542− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
543−
544− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
545−
546− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
547−
548− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
549−
550− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"11"},"finish_reason":null}]}
551−
552− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
553−
554− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
555−
556− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
557−
558− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"12"},"finish_reason":null}]}
559−
560− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
561−
562− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" locate"},"finish_reason":null}]}
563−
564− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
565−
566− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
567−
568− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
569−
570− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"18"},"finish_reason":null}]}
571−
572− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
573−
574− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
575−
576− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
577−
578− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"19"},"finish_reason":null}]}
579−
580− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
581−
582− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ."},"finish_reason":null}]}
583−
584− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"go"},"finish_reason":null}]}
585−
586− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
587−
588− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
589−
590− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
591−
592− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"22"},"finish_reason":null}]}
593−
594− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
595−
596− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
597−
598− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
599−
600− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"23"},"finish_reason":null}]}
601−
602− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
603−
604− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
605−
606− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
607−
608− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
609−
610− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
611−
612− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"28"},"finish_reason":null}]}
613−
614− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
615−
616− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
617−
618− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
619−
620− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"29"},"finish_reason":null}]}
621−
622− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
623−
624− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
625−
626− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
627−
628− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
629−
630− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
631−
632− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"31"},"finish_reason":null}]}
633−
634− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
635−
636− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
637−
638− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
639−
640− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"32"},"finish_reason":null}]}
641−
642− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
643−
644− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" current"},"finish_reason":null}]}
645−
646− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
647−
648− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
649−
650− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
651−
652− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"39"},"finish_reason":null}]}
653−
654− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
655−
656− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
657−
658− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
659−
660− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"40"},"finish_reason":null}]}
661−
662− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
663−
664− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" dir"},"finish_reason":null}]}
665−
666− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
667−
668− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
669−
670− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
671−
672− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"43"},"finish_reason":null}]}
673−
674− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
675−
676− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
677−
678− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
679−
680− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"43"},"finish_reason":null}]}
681−
682− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
683−
684− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Both"},"finish_reason":null}]}
685−
686− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" fine"},"finish_reason":null}]}
687−
688− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
689−
690− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Let's"},"finish_reason":null}]}
691−
692− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" output"},"finish_reason":null}]}
693−
694− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" one"},"finish_reason":null}]}
695−
696− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
697−
698− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
699−
700− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" no"},"finish_reason":null}]}
701−
702− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
703−
704− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
705−
706− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Use"},"finish_reason":null}]}
707−
708− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" glob"},"finish_reason":null}]}
709−
710− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" to"},"finish_reason":null}]}
711−
712− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" locate"},"finish_reason":null}]}
713−
714− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" ."},"finish_reason":null}]}
715−
716− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"go"},"finish_reason":null}]}
717−
718− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" files"},"finish_reason":null}]}
719−
720− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" in"},"finish_reason":null}]}
721−
722− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" current"},"finish_reason":null}]}
723−
724− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" directory"},"finish_reason":null}]}
725−
726− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
727−
728− data: {"id":"chatcmpl-eb1b020a610e9fa7da88e894","object":"chat.completion.chunk","created":1782413804,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":157,"completion_tokens":298,"total_tokens":519,"prompt_tokens_details":{"cached_tokens":64},"cost":{"usd":0.00019385200000000003,"hypercredits":0.0038770400000000004},"remaining":{"hypercredits":0}}}
729−
730− data: [DONE]
731−
732− headers:
733− Content-Type:
734− - text/event-stream
735− status: 200 OK
736− code: 200
737− duration: 648.718041ms
internal/agent/testdata/TestCoderAgent/glm-5.1/grep_tool.yamldeleted−499
@@ -1,499 +0,0 @@
1−---
2−version: 2
3−interactions:
4−- id: 0
5− request:
6− proto: HTTP/1.1
7− proto_major: 1
8− proto_minor: 1
9− content_length: 35631
10− host: ""
11− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ THE RELEVANT CONTEXT BEFORE EDITING**: Never edit a file you haven't already read the relevant context for in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\". When committing, follow the `<git_commits>` format from the bash tool description exactly, including any configured attribution lines.\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **TOOL CONSTRAINTS**: Only use documented tools. Never attempt 'apply_patch' or 'apply_diff' - they don't exist. Use 'edit' or 'multiedit' instead.\\n14. **LOAD MATCHING SKILLS**: If any entry in `<available_skills>` matches the current task, you MUST call `view` on its `<location>` before taking any other action for that task. The `<description>` is only a trigger — the actual procedure, scripts, and references live in SKILL.md. Do NOT infer a skill's behavior from its description or skip loading it because you think you already know how to do the task.\\n15. **LIMIT FILE READS**: Avoid reading entire files, as they can be very large. Read only the sections you need using 'offset' and 'limit' parameters.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- ALWAYS think and respond in the same spoken language the prompt was written in.\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\n**Available edit tools:**\\n- `edit` - Single find/replace in a file\\n- `multiedit` - Multiple find/replace operations in one file\\n- `write` - Create/overwrite entire file\\n\\nNever use `apply_patch` or similar - those tools don't exist.\\n\\nCritical: ALWAYS read the relevant context of files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the relevant context first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</editing_files>\\n\\n<whitespace_and_exact_matching>\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n</whitespace_and_exact_matching>\\n\\n<task_completion>\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n</task_completion>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences\\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n<bash_commands>\\n**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/glm-5.1/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n<available_skills>\\n <skill>\\n <name>crush-hooks</name>\\n <description>Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.</description>\\n <location>crush://skills/crush-hooks/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n <skill>\\n <name>jq</name>\\n <description>Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.</description>\\n <location>crush://skills/jq/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n</available_skills>\\n\\n<skills_usage>\\nThe `<description>` of each skill is a TRIGGER — it tells you *when* a skill applies. It is NOT a specification of what the skill does or how to do it. The procedure, scripts, commands, references, and required flags live only in the SKILL.md body. You do not know what a skill actually does until you have read its SKILL.md.\\n\\nMANDATORY activation flow:\\n1. Scan `<available_skills>` against the current user task.\\n2. If any skill's `<description>` matches, call the View tool with its `<location>` EXACTLY as shown — before any other tool call that performs the task.\\n3. Read the entire SKILL.md and follow its instructions.\\n4. Only then execute the task, using the skill's prescribed commands/tools.\\n\\nDo NOT skip step 2 because you think you already know how to do the task. Do NOT infer a skill's behavior from its name or description. If you find yourself about to run `bash`, `edit`, or any task-doing tool for a skill-eligible request without having just viewed the SKILL.md, stop and load the skill first.\\n\\nBuiltin skills (type=builtin) use virtual `crush://skills/...` location identifiers. The \\\"crush://\\\" prefix is NOT a URL, network address, or MCP resource — it is a special internal identifier the View tool understands natively. Pass the `<location>` verbatim to View.\\n\\nDo not use MCP tools (including read_mcp_resource) to load skills.\\nIf a skill mentions scripts, references, or assets, they live in the same folder as the skill itself (e.g., scripts/, references/, assets/ subdirectories within the skill's folder).\\n</skills_usage>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"<system_reminder>This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.</system_reminder>\",\"role\":\"user\"},{\"content\":\"use grep to search for the word 'package' in go files\",\"role\":\"user\"}],\"model\":\"glm-5.1\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Execute shell commands; long-running commands automatically move to background and return a shell ID.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute (default, configurable via `auto_background_after`) automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<background_execution>\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `&` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n</background_execution>\\n\\n<git_message_quality>\\nThese rules apply whenever creating or updating commit messages, PR titles, or PR bodies:\\n\\n- Messages MUST be understandable to someone unfamiliar with the codebase.\\n- Before creating or updating a message, verify this litmus test: a new contributor reading only the commit message or PR title/body should understand what problem this solves, why it matters, and the impact without opening files, reading the diff, or knowing internal code names.\\n- Avoid code identifiers, filenames, function names, and implementation details unless they are necessary for understanding the user-facing impact.\\n- Bad: \\\"Add NameFromHex with sync.Once lazy init\\\"\\n- Good: \\\"Improve color name lookup performance while keeping startup fast\\\"\\n</git_message_quality>\\n\\n<commit_messages>\\nCommit messages are for future readers scanning history. Before committing:\\n\\n- Follow <git_message_quality>.\\n- Draft a concise 1-2 sentence message focusing on why the change exists and what outcome it enables, not a list of files or implementation details.\\n- Use clear, accurate verbs (\\\"add\\\"=new capability, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix) and avoid generic messages.\\n- The first line MUST be under 72 characters.\\n- Add a body only when it is needed to explain the reasoning, tradeoffs, or important context; wrap body lines at 72 characters.\\n- If the change is internal-only, still describe the benefit or maintenance outcome rather than naming private code.\\n- Bad: \\\"fix: nil pointer in session.go\\\"\\n- Good: \\\"fix: prevent session loading from crashing on missing metadata\\\"\\n- Bad: \\\"refactor: move PromptBuilder into internal/agent\\\"\\n- Good: \\\"refactor: make prompt assembly easier to maintain\\\"\\n</commit_messages>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond the context of git\\n\\n4. Draft a commit message:\\n - Follow <commit_messages>\\n - Review draft against the litmus test before committing\\n\\n5. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\nCommit message here.\\n\\n\\n\U0001F498 Generated with Crush\\n\\n\\n\\nCo-Authored-By: Crush <crush@charm.land>\\n\\nEOF\\n)\\\"\\n\\n6. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n7. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m.\\n</git_commits>\\n\\n<pull_requests>\\n\\n\\nWhen user asks you to create or update a PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n\\n3. Commit changes if needed\\n\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n\\n6. Draft a PR message:\\n - Follow <git_message_quality>\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Use clear, concise language\\n - Provide an accurate reflection of changes and purpose\\n - Avoid generic summaries; messages should be thoughtful\\n - Review draft against the litmus test before creating or updating the PR\\n\\n7. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n<summary>\\n\\n\U0001F498 Generated with Crush\\n\\nEOF\\n)\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"auto_background_after\":{\"description\":\"Seconds to wait before automatically moving the command to a background job (default: 60)\",\"type\":\"integer\"},\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Download a URL directly to a local file (binary-safe, streaming, max 600s timeout); overwrites without warning. For reading content into context use fetch.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edit a file by exact find-and-replace; can also create or delete content. For renames/moves use bash. For large edits use write.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Apply multiple find-and-replace edits to a single file in one operation; edits run sequentially. Prefer over edit for multiple changes to the same file. Same exact-match rules as edit apply.\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetch raw content from a URL as text, markdown, or html (max 100KB); no AI processing. For analysis or extraction use agentic_fetch.\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Find files by name/pattern (glob syntax), sorted by modification time; max 100 results; skips hidden files. Use grep to search file contents.\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Search file contents by regex or literal text; returns matching file paths sorted by modification time (max 100); respects .gitignore. Use glob to filter by filename, not contents.\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"List files and directories as a tree; skips hidden files and common system dirs; max 1000 files. Use glob to find files by pattern, grep to search contents.\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public GitHub repositories via Sourcegraph; supports regex, language/repo/file filters, and symbol search (max 20 results). Only searches public repos.\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Read a file by path with line numbers; supports offset and line limit (default 200, max 200KB returned file content section); renders images (PNG, JPEG, GIF, WebP); use ls for directories.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 200)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Create or overwrite a file with given content; auto-creates parent dirs. Cannot append. Read the file first to avoid conflicts. For surgical changes use edit or multiedit.\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
12− headers:
13− Accept:
14− - application/json
15− Content-Type:
16− - application/json
17− User-Agent:
18− - Charm-Crush/devel (https://charm.land/crush)
19− url: https://hyper.charm.land/v1/chat/completions
20− method: POST
21− response:
22− proto: HTTP/2.0
23− proto_major: 2
24− proto_minor: 0
25− content_length: -1
26− uncompressed: true
27− body: |+
28− data: {"id":"chatcmpl-8110189342807f502f916f95","object":"chat.completion.chunk","created":1782413815,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
29−
30− data: {"id":"chatcmpl-8110189342807f502f916f95","object":"chat.completion.chunk","created":1782413815,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_a57bfe141bf85225","type":"function","index":0,"function":{"name":"grep","arguments":""}}]},"finish_reason":null}]}
31−
32− data: {"id":"chatcmpl-8110189342807f502f916f95","object":"chat.completion.chunk","created":1782413815,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\"include\": \""}}]},"finish_reason":null}]}
33−
34− data: {"id":"chatcmpl-8110189342807f502f916f95","object":"chat.completion.chunk","created":1782413815,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"*."}}]},"finish_reason":null}]}
35−
36− data: {"id":"chatcmpl-8110189342807f502f916f95","object":"chat.completion.chunk","created":1782413815,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go"}}]},"finish_reason":null}]}
37−
38− data: {"id":"chatcmpl-8110189342807f502f916f95","object":"chat.completion.chunk","created":1782413815,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\""}}]},"finish_reason":null}]}
39−
40− data: {"id":"chatcmpl-8110189342807f502f916f95","object":"chat.completion.chunk","created":1782413815,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":", \"pattern\": \""}}]},"finish_reason":null}]}
41−
42− data: {"id":"chatcmpl-8110189342807f502f916f95","object":"chat.completion.chunk","created":1782413815,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"package"}}]},"finish_reason":null}]}
43−
44− data: {"id":"chatcmpl-8110189342807f502f916f95","object":"chat.completion.chunk","created":1782413815,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\""}}]},"finish_reason":null}]}
45−
46− data: {"id":"chatcmpl-8110189342807f502f916f95","object":"chat.completion.chunk","created":1782413815,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
47−
48− data: {"id":"chatcmpl-8110189342807f502f916f95","object":"chat.completion.chunk","created":1782413815,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
49−
50− data: {"id":"chatcmpl-8110189342807f502f916f95","object":"chat.completion.chunk","created":1782413815,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":680,"completion_tokens":18,"total_tokens":8177,"prompt_tokens_details":{"cached_tokens":7479},"cost":{"usd":0.0010312,"hypercredits":0.020623999999999997},"remaining":{"hypercredits":0}}}
51−
52− data: [DONE]
53−
54− headers:
55− Content-Type:
56− - text/event-stream
57− status: 200 OK
58− code: 200
59− duration: 1.505379s
60−- id: 1
61− request:
62− proto: HTTP/1.1
63− proto_major: 1
64− proto_minor: 1
65− content_length: 812
66− host: ""
67− body: '{"messages":[{"content":"You will generate a short title based on the first message a user begins a conversation with.\n\n<rules>\n- Keep the title in the same language that the user wrote their message in.\n- Ensure it is not more than 50 characters long.\n- The title should be a summary of the user''s message.\n- It should be one line long.\n- Do not use quotes or colons.\n- The entire text you return will be used as the title.\n- Never return anything that is more than one sentence (one line) long.\n</rules>\n\n /no_think","role":"system"},{"content":"Generate a concise title for the following content:\n\nuse grep to search for the word ''package'' in go files\n <think>\n\n</think>","role":"user"}],"model":"gpt-oss-120b","max_completion_tokens":40,"stream_options":{"include_usage":true},"stream":true}'
68− headers:
69− Accept:
70− - application/json
71− Content-Type:
72− - application/json
73− User-Agent:
74− - Charm-Crush/devel (https://charm.land/crush)
75− url: https://hyper.charm.land/v1/chat/completions
76− method: POST
77− response:
78− proto: HTTP/2.0
79− proto_major: 2
80− proto_minor: 0
81− content_length: -1
82− uncompressed: true
83− body: |+
84− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
85−
86− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
87−
88− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
89−
90− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" wants"},"finish_reason":null}]}
91−
92− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
93−
94− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
95−
96− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
97−
98− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
99−
100− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" They"},"finish_reason":null}]}
101−
102− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" gave"},"finish_reason":null}]}
103−
104− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
105−
106− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" phrase"},"finish_reason":null}]}
107−
108− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
109−
110− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
111−
112− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"use"},"finish_reason":null}]}
113−
114− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" grep"},"finish_reason":null}]}
115−
116− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
117−
118− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" search"},"finish_reason":null}]}
119−
120− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
121−
122− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
123−
124− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" word"},"finish_reason":null}]}
125−
126− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
127−
128− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"package"},"finish_reason":null}]}
129−
130− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'"},"finish_reason":null}]}
131−
132− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
133−
134− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" go"},"finish_reason":null}]}
135−
136− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
137−
138− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
139−
140− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Need"},"finish_reason":null}]}
141−
142− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
143−
144− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" produce"},"finish_reason":null}]}
145−
146− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
147−
148− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
149−
150− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
151−
152− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" same"},"finish_reason":null}]}
153−
154− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" language"},"finish_reason":null}]}
155−
156− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
157−
158− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"English"},"finish_reason":null}]}
159−
160− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")."},"finish_reason":null}]}
161−
162− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Under"},"finish_reason":null}]}
163−
164− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
165−
166− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
167−
168− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
169−
170− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
171−
172− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" one"},"finish_reason":null}]}
173−
174− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
175−
176− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
177−
178− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Something"},"finish_reason":null}]}
179−
180− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" like"},"finish_reason":null}]}
181−
182− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
183−
184− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
185−
186− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"G"},"finish_reason":null}]}
187−
188− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"rep"},"finish_reason":null}]}
189−
190− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
191−
192− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
193−
194− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"package"},"finish_reason":null}]}
195−
196− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'"},"finish_reason":null}]}
197−
198− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
199−
200− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Go"},"finish_reason":null}]}
201−
202− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
203−
204− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
205−
206− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
207−
208− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" within"},"finish_reason":null}]}
209−
210− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" limit"},"finish_reason":null}]}
211−
212− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
213−
214− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Title"},"finish_reason":null}]}
215−
216− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" length"},"finish_reason":null}]}
217−
218− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"?"},"finish_reason":null}]}
219−
220− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
221−
222− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
223−
224− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
225−
226− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
227−
228− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"G"},"finish_reason":null}]}
229−
230− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"rep"},"finish_reason":null}]}
231−
232− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
233−
234− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
235−
236− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"package"},"finish_reason":null}]}
237−
238− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'"},"finish_reason":null}]}
239−
240− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
241−
242− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Go"},"finish_reason":null}]}
243−
244− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
245−
246− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
247−
248− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ="},"finish_reason":null}]}
249−
250− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" let's"},"finish_reason":null}]}
251−
252− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
253−
254− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
255−
256− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" G"},"finish_reason":null}]}
257−
258− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
259−
260− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
261−
262− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
263−
264− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" r"},"finish_reason":null}]}
265−
266− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
267−
268− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" e"},"finish_reason":null}]}
269−
270− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
271−
272− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" p"},"finish_reason":null}]}
273−
274− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
275−
276− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
277−
278− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
279−
280− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" f"},"finish_reason":null}]}
281−
282− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
283−
284− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" o"},"finish_reason":null}]}
285−
286− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
287−
288− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" r"},"finish_reason":null}]}
289−
290− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"8"},"finish_reason":null}]}
291−
292− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
293−
294− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"9"},"finish_reason":null}]}
295−
296− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
297−
298− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"10"},"finish_reason":null}]}
299−
300− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" p"},"finish_reason":null}]}
301−
302− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"11"},"finish_reason":null}]}
303−
304− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
305−
306− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"12"},"finish_reason":null}]}
307−
308− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" c"},"finish_reason":null}]}
309−
310− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"13"},"finish_reason":null}]}
311−
312− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" k"},"finish_reason":null}]}
313−
314− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"14"},"finish_reason":null}]}
315−
316− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
317−
318− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"15"},"finish_reason":null}]}
319−
320− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" g"},"finish_reason":null}]}
321−
322− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"16"},"finish_reason":null}]}
323−
324− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" e"},"finish_reason":null}]}
325−
326− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"17"},"finish_reason":null}]}
327−
328− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
329−
330− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"18"},"finish_reason":null}]}
331−
332− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
333−
334− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"19"},"finish_reason":null}]}
335−
336− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" i"},"finish_reason":null}]}
337−
338− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"20"},"finish_reason":null}]}
339−
340− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" n"},"finish_reason":null}]}
341−
342− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"21"},"finish_reason":null}]}
343−
344− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
345−
346− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"22"},"finish_reason":null}]}
347−
348− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" G"},"finish_reason":null}]}
349−
350− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"23"},"finish_reason":null}]}
351−
352− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" o"},"finish_reason":null}]}
353−
354− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"24"},"finish_reason":null}]}
355−
356− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
357−
358− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"25"},"finish_reason":null}]}
359−
360− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" f"},"finish_reason":null}]}
361−
362− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"26"},"finish_reason":null}]}
363−
364− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" i"},"finish_reason":null}]}
365−
366− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"27"},"finish_reason":null}]}
367−
368− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" l"},"finish_reason":null}]}
369−
370− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"28"},"finish_reason":null}]}
371−
372− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" e"},"finish_reason":null}]}
373−
374− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"29"},"finish_reason":null}]}
375−
376− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" s"},"finish_reason":null}]}
377−
378− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"30"},"finish_reason":null}]}
379−
380− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
381−
382− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" So"},"finish_reason":null}]}
383−
384− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
385−
386− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"30"},"finish_reason":null}]}
387−
388− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
389−
390− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
391−
392− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" under"},"finish_reason":null}]}
393−
394− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
395−
396− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
397−
398− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
399−
400− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Provide"},"finish_reason":null}]}
401−
402− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that"},"finish_reason":null}]}
403−
404− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
405−
406− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"G"},"finish_reason":null}]}
407−
408− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"rep"},"finish_reason":null}]}
409−
410− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" for"},"finish_reason":null}]}
411−
412− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" '"},"finish_reason":null}]}
413−
414− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"package"},"finish_reason":null}]}
415−
416− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"'"},"finish_reason":null}]}
417−
418− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" in"},"finish_reason":null}]}
419−
420− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
421−
422− data: {"id":"chatcmpl-249484b499306e8f4f6345cf","object":"chat.completion.chunk","created":1782413814,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":201,"completion_tokens":179,"total_tokens":380,"completion_tokens_details":{"reasoning_tokens":129},"cost":{"usd":0.00020686400000000002,"hypercredits":0.00413728},"remaining":{"hypercredits":0}}}
423−
424− data: [DONE]
425−
426− headers:
427− Content-Type:
428− - text/event-stream
429− status: 200 OK
430− code: 200
431− duration: 541.974834ms
432−- id: 2
433− request:
434− proto: HTTP/1.1
435− proto_major: 1
436− proto_minor: 1
437− content_length: 35983
438− host: ""
439− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ THE RELEVANT CONTEXT BEFORE EDITING**: Never edit a file you haven't already read the relevant context for in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\". When committing, follow the `<git_commits>` format from the bash tool description exactly, including any configured attribution lines.\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **TOOL CONSTRAINTS**: Only use documented tools. Never attempt 'apply_patch' or 'apply_diff' - they don't exist. Use 'edit' or 'multiedit' instead.\\n14. **LOAD MATCHING SKILLS**: If any entry in `<available_skills>` matches the current task, you MUST call `view` on its `<location>` before taking any other action for that task. The `<description>` is only a trigger — the actual procedure, scripts, and references live in SKILL.md. Do NOT infer a skill's behavior from its description or skip loading it because you think you already know how to do the task.\\n15. **LIMIT FILE READS**: Avoid reading entire files, as they can be very large. Read only the sections you need using 'offset' and 'limit' parameters.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- ALWAYS think and respond in the same spoken language the prompt was written in.\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\n**Available edit tools:**\\n- `edit` - Single find/replace in a file\\n- `multiedit` - Multiple find/replace operations in one file\\n- `write` - Create/overwrite entire file\\n\\nNever use `apply_patch` or similar - those tools don't exist.\\n\\nCritical: ALWAYS read the relevant context of files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the relevant context first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</editing_files>\\n\\n<whitespace_and_exact_matching>\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n</whitespace_and_exact_matching>\\n\\n<task_completion>\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n</task_completion>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences\\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n<bash_commands>\\n**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/glm-5.1/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n<available_skills>\\n <skill>\\n <name>crush-hooks</name>\\n <description>Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.</description>\\n <location>crush://skills/crush-hooks/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n <skill>\\n <name>jq</name>\\n <description>Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.</description>\\n <location>crush://skills/jq/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n</available_skills>\\n\\n<skills_usage>\\nThe `<description>` of each skill is a TRIGGER — it tells you *when* a skill applies. It is NOT a specification of what the skill does or how to do it. The procedure, scripts, commands, references, and required flags live only in the SKILL.md body. You do not know what a skill actually does until you have read its SKILL.md.\\n\\nMANDATORY activation flow:\\n1. Scan `<available_skills>` against the current user task.\\n2. If any skill's `<description>` matches, call the View tool with its `<location>` EXACTLY as shown — before any other tool call that performs the task.\\n3. Read the entire SKILL.md and follow its instructions.\\n4. Only then execute the task, using the skill's prescribed commands/tools.\\n\\nDo NOT skip step 2 because you think you already know how to do the task. Do NOT infer a skill's behavior from its name or description. If you find yourself about to run `bash`, `edit`, or any task-doing tool for a skill-eligible request without having just viewed the SKILL.md, stop and load the skill first.\\n\\nBuiltin skills (type=builtin) use virtual `crush://skills/...` location identifiers. The \\\"crush://\\\" prefix is NOT a URL, network address, or MCP resource — it is a special internal identifier the View tool understands natively. Pass the `<location>` verbatim to View.\\n\\nDo not use MCP tools (including read_mcp_resource) to load skills.\\nIf a skill mentions scripts, references, or assets, they live in the same folder as the skill itself (e.g., scripts/, references/, assets/ subdirectories within the skill's folder).\\n</skills_usage>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"<system_reminder>This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.</system_reminder>\",\"role\":\"user\"},{\"content\":\"use grep to search for the word 'package' in go files\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_a57bfe141bf85225\",\"function\":{\"arguments\":\"{\\\"include\\\": \\\"*.go\\\", \\\"pattern\\\": \\\"package\\\"}\",\"name\":\"grep\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"Found 1 matches\\n/tmp/crush-test/TestCoderAgent/glm-5.1/grep_tool/main.go:\\n Line 1, Char 1: package main\\n\",\"tool_call_id\":\"call_a57bfe141bf85225\",\"role\":\"tool\"}],\"model\":\"glm-5.1\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Execute shell commands; long-running commands automatically move to background and return a shell ID.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute (default, configurable via `auto_background_after`) automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<background_execution>\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `&` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n</background_execution>\\n\\n<git_message_quality>\\nThese rules apply whenever creating or updating commit messages, PR titles, or PR bodies:\\n\\n- Messages MUST be understandable to someone unfamiliar with the codebase.\\n- Before creating or updating a message, verify this litmus test: a new contributor reading only the commit message or PR title/body should understand what problem this solves, why it matters, and the impact without opening files, reading the diff, or knowing internal code names.\\n- Avoid code identifiers, filenames, function names, and implementation details unless they are necessary for understanding the user-facing impact.\\n- Bad: \\\"Add NameFromHex with sync.Once lazy init\\\"\\n- Good: \\\"Improve color name lookup performance while keeping startup fast\\\"\\n</git_message_quality>\\n\\n<commit_messages>\\nCommit messages are for future readers scanning history. Before committing:\\n\\n- Follow <git_message_quality>.\\n- Draft a concise 1-2 sentence message focusing on why the change exists and what outcome it enables, not a list of files or implementation details.\\n- Use clear, accurate verbs (\\\"add\\\"=new capability, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix) and avoid generic messages.\\n- The first line MUST be under 72 characters.\\n- Add a body only when it is needed to explain the reasoning, tradeoffs, or important context; wrap body lines at 72 characters.\\n- If the change is internal-only, still describe the benefit or maintenance outcome rather than naming private code.\\n- Bad: \\\"fix: nil pointer in session.go\\\"\\n- Good: \\\"fix: prevent session loading from crashing on missing metadata\\\"\\n- Bad: \\\"refactor: move PromptBuilder into internal/agent\\\"\\n- Good: \\\"refactor: make prompt assembly easier to maintain\\\"\\n</commit_messages>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond the context of git\\n\\n4. Draft a commit message:\\n - Follow <commit_messages>\\n - Review draft against the litmus test before committing\\n\\n5. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\nCommit message here.\\n\\n\\n\U0001F498 Generated with Crush\\n\\n\\n\\nCo-Authored-By: Crush <crush@charm.land>\\n\\nEOF\\n)\\\"\\n\\n6. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n7. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m.\\n</git_commits>\\n\\n<pull_requests>\\n\\n\\nWhen user asks you to create or update a PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n\\n3. Commit changes if needed\\n\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n\\n6. Draft a PR message:\\n - Follow <git_message_quality>\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Use clear, concise language\\n - Provide an accurate reflection of changes and purpose\\n - Avoid generic summaries; messages should be thoughtful\\n - Review draft against the litmus test before creating or updating the PR\\n\\n7. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n<summary>\\n\\n\U0001F498 Generated with Crush\\n\\nEOF\\n)\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"auto_background_after\":{\"description\":\"Seconds to wait before automatically moving the command to a background job (default: 60)\",\"type\":\"integer\"},\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Download a URL directly to a local file (binary-safe, streaming, max 600s timeout); overwrites without warning. For reading content into context use fetch.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edit a file by exact find-and-replace; can also create or delete content. For renames/moves use bash. For large edits use write.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Apply multiple find-and-replace edits to a single file in one operation; edits run sequentially. Prefer over edit for multiple changes to the same file. Same exact-match rules as edit apply.\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetch raw content from a URL as text, markdown, or html (max 100KB); no AI processing. For analysis or extraction use agentic_fetch.\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Find files by name/pattern (glob syntax), sorted by modification time; max 100 results; skips hidden files. Use grep to search file contents.\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Search file contents by regex or literal text; returns matching file paths sorted by modification time (max 100); respects .gitignore. Use glob to filter by filename, not contents.\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"List files and directories as a tree; skips hidden files and common system dirs; max 1000 files. Use glob to find files by pattern, grep to search contents.\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public GitHub repositories via Sourcegraph; supports regex, language/repo/file filters, and symbol search (max 20 results). Only searches public repos.\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Read a file by path with line numbers; supports offset and line limit (default 200, max 200KB returned file content section); renders images (PNG, JPEG, GIF, WebP); use ls for directories.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 200)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Create or overwrite a file with given content; auto-creates parent dirs. Cannot append. Read the file first to avoid conflicts. For surgical changes use edit or multiedit.\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
440− headers:
441− Accept:
442− - application/json
443− Content-Type:
444− - application/json
445− User-Agent:
446− - Charm-Crush/devel (https://charm.land/crush)
447− url: https://hyper.charm.land/v1/chat/completions
448− method: POST
449− response:
450− proto: HTTP/2.0
451− proto_major: 2
452− proto_minor: 0
453− content_length: -1
454− uncompressed: true
455− body: |+
456− data: {"id":"chatcmpl-09dddfb926db7fdea7e49d0d","object":"chat.completion.chunk","created":1782413816,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
457−
458− data: {"id":"chatcmpl-09dddfb926db7fdea7e49d0d","object":"chat.completion.chunk","created":1782413816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"1"},"finish_reason":null}]}
459−
460− data: {"id":"chatcmpl-09dddfb926db7fdea7e49d0d","object":"chat.completion.chunk","created":1782413816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" match"},"finish_reason":null}]}
461−
462− data: {"id":"chatcmpl-09dddfb926db7fdea7e49d0d","object":"chat.completion.chunk","created":1782413816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" found"},"finish_reason":null}]}
463−
464− data: {"id":"chatcmpl-09dddfb926db7fdea7e49d0d","object":"chat.completion.chunk","created":1782413816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}]}
465−
466− data: {"id":"chatcmpl-09dddfb926db7fdea7e49d0d","object":"chat.completion.chunk","created":1782413816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `"},"finish_reason":null}]}
467−
468− data: {"id":"chatcmpl-09dddfb926db7fdea7e49d0d","object":"chat.completion.chunk","created":1782413816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"main"},"finish_reason":null}]}
469−
470− data: {"id":"chatcmpl-09dddfb926db7fdea7e49d0d","object":"chat.completion.chunk","created":1782413816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}]}
471−
472− data: {"id":"chatcmpl-09dddfb926db7fdea7e49d0d","object":"chat.completion.chunk","created":1782413816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}]}
473−
474− data: {"id":"chatcmpl-09dddfb926db7fdea7e49d0d","object":"chat.completion.chunk","created":1782413816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"1"},"finish_reason":null}]}
475−
476− data: {"id":"chatcmpl-09dddfb926db7fdea7e49d0d","object":"chat.completion.chunk","created":1782413816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`"},"finish_reason":null}]}
477−
478− data: {"id":"chatcmpl-09dddfb926db7fdea7e49d0d","object":"chat.completion.chunk","created":1782413816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" —"},"finish_reason":null}]}
479−
480− data: {"id":"chatcmpl-09dddfb926db7fdea7e49d0d","object":"chat.completion.chunk","created":1782413816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `"},"finish_reason":null}]}
481−
482− data: {"id":"chatcmpl-09dddfb926db7fdea7e49d0d","object":"chat.completion.chunk","created":1782413816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"package"},"finish_reason":null}]}
483−
484− data: {"id":"chatcmpl-09dddfb926db7fdea7e49d0d","object":"chat.completion.chunk","created":1782413816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" main"},"finish_reason":null}]}
485−
486− data: {"id":"chatcmpl-09dddfb926db7fdea7e49d0d","object":"chat.completion.chunk","created":1782413816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`"},"finish_reason":null}]}
487−
488− data: {"id":"chatcmpl-09dddfb926db7fdea7e49d0d","object":"chat.completion.chunk","created":1782413816,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
489−
490− data: {"id":"chatcmpl-09dddfb926db7fdea7e49d0d","object":"chat.completion.chunk","created":1782413816,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":59,"completion_tokens":17,"total_tokens":8234,"prompt_tokens_details":{"cached_tokens":8158},"cost":{"usd":0.0001574,"hypercredits":0.0031479999999999998},"remaining":{"hypercredits":0}}}
491−
492− data: [DONE]
493−
494− headers:
495− Content-Type:
496− - text/event-stream
497− status: 200 OK
498− code: 200
499− duration: 1.500804s
internal/agent/testdata/TestCoderAgent/glm-5.1/ls_tool.yamldeleted−485
@@ -1,485 +0,0 @@
1−---
2−version: 2
3−interactions:
4−- id: 0
5− request:
6− proto: HTTP/1.1
7− proto_major: 1
8− proto_minor: 1
9− content_length: 35625
10− host: ""
11− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ THE RELEVANT CONTEXT BEFORE EDITING**: Never edit a file you haven't already read the relevant context for in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\". When committing, follow the `<git_commits>` format from the bash tool description exactly, including any configured attribution lines.\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **TOOL CONSTRAINTS**: Only use documented tools. Never attempt 'apply_patch' or 'apply_diff' - they don't exist. Use 'edit' or 'multiedit' instead.\\n14. **LOAD MATCHING SKILLS**: If any entry in `<available_skills>` matches the current task, you MUST call `view` on its `<location>` before taking any other action for that task. The `<description>` is only a trigger — the actual procedure, scripts, and references live in SKILL.md. Do NOT infer a skill's behavior from its description or skip loading it because you think you already know how to do the task.\\n15. **LIMIT FILE READS**: Avoid reading entire files, as they can be very large. Read only the sections you need using 'offset' and 'limit' parameters.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- ALWAYS think and respond in the same spoken language the prompt was written in.\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\n**Available edit tools:**\\n- `edit` - Single find/replace in a file\\n- `multiedit` - Multiple find/replace operations in one file\\n- `write` - Create/overwrite entire file\\n\\nNever use `apply_patch` or similar - those tools don't exist.\\n\\nCritical: ALWAYS read the relevant context of files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the relevant context first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</editing_files>\\n\\n<whitespace_and_exact_matching>\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n</whitespace_and_exact_matching>\\n\\n<task_completion>\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n</task_completion>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences\\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n<bash_commands>\\n**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/glm-5.1/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n<available_skills>\\n <skill>\\n <name>crush-hooks</name>\\n <description>Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.</description>\\n <location>crush://skills/crush-hooks/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n <skill>\\n <name>jq</name>\\n <description>Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.</description>\\n <location>crush://skills/jq/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n</available_skills>\\n\\n<skills_usage>\\nThe `<description>` of each skill is a TRIGGER — it tells you *when* a skill applies. It is NOT a specification of what the skill does or how to do it. The procedure, scripts, commands, references, and required flags live only in the SKILL.md body. You do not know what a skill actually does until you have read its SKILL.md.\\n\\nMANDATORY activation flow:\\n1. Scan `<available_skills>` against the current user task.\\n2. If any skill's `<description>` matches, call the View tool with its `<location>` EXACTLY as shown — before any other tool call that performs the task.\\n3. Read the entire SKILL.md and follow its instructions.\\n4. Only then execute the task, using the skill's prescribed commands/tools.\\n\\nDo NOT skip step 2 because you think you already know how to do the task. Do NOT infer a skill's behavior from its name or description. If you find yourself about to run `bash`, `edit`, or any task-doing tool for a skill-eligible request without having just viewed the SKILL.md, stop and load the skill first.\\n\\nBuiltin skills (type=builtin) use virtual `crush://skills/...` location identifiers. The \\\"crush://\\\" prefix is NOT a URL, network address, or MCP resource — it is a special internal identifier the View tool understands natively. Pass the `<location>` verbatim to View.\\n\\nDo not use MCP tools (including read_mcp_resource) to load skills.\\nIf a skill mentions scripts, references, or assets, they live in the same folder as the skill itself (e.g., scripts/, references/, assets/ subdirectories within the skill's folder).\\n</skills_usage>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"<system_reminder>This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.</system_reminder>\",\"role\":\"user\"},{\"content\":\"use ls to list the files in the current directory\",\"role\":\"user\"}],\"model\":\"glm-5.1\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Execute shell commands; long-running commands automatically move to background and return a shell ID.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute (default, configurable via `auto_background_after`) automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<background_execution>\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `&` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n</background_execution>\\n\\n<git_message_quality>\\nThese rules apply whenever creating or updating commit messages, PR titles, or PR bodies:\\n\\n- Messages MUST be understandable to someone unfamiliar with the codebase.\\n- Before creating or updating a message, verify this litmus test: a new contributor reading only the commit message or PR title/body should understand what problem this solves, why it matters, and the impact without opening files, reading the diff, or knowing internal code names.\\n- Avoid code identifiers, filenames, function names, and implementation details unless they are necessary for understanding the user-facing impact.\\n- Bad: \\\"Add NameFromHex with sync.Once lazy init\\\"\\n- Good: \\\"Improve color name lookup performance while keeping startup fast\\\"\\n</git_message_quality>\\n\\n<commit_messages>\\nCommit messages are for future readers scanning history. Before committing:\\n\\n- Follow <git_message_quality>.\\n- Draft a concise 1-2 sentence message focusing on why the change exists and what outcome it enables, not a list of files or implementation details.\\n- Use clear, accurate verbs (\\\"add\\\"=new capability, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix) and avoid generic messages.\\n- The first line MUST be under 72 characters.\\n- Add a body only when it is needed to explain the reasoning, tradeoffs, or important context; wrap body lines at 72 characters.\\n- If the change is internal-only, still describe the benefit or maintenance outcome rather than naming private code.\\n- Bad: \\\"fix: nil pointer in session.go\\\"\\n- Good: \\\"fix: prevent session loading from crashing on missing metadata\\\"\\n- Bad: \\\"refactor: move PromptBuilder into internal/agent\\\"\\n- Good: \\\"refactor: make prompt assembly easier to maintain\\\"\\n</commit_messages>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond the context of git\\n\\n4. Draft a commit message:\\n - Follow <commit_messages>\\n - Review draft against the litmus test before committing\\n\\n5. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\nCommit message here.\\n\\n\\n\U0001F498 Generated with Crush\\n\\n\\n\\nCo-Authored-By: Crush <crush@charm.land>\\n\\nEOF\\n)\\\"\\n\\n6. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n7. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m.\\n</git_commits>\\n\\n<pull_requests>\\n\\n\\nWhen user asks you to create or update a PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n\\n3. Commit changes if needed\\n\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n\\n6. Draft a PR message:\\n - Follow <git_message_quality>\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Use clear, concise language\\n - Provide an accurate reflection of changes and purpose\\n - Avoid generic summaries; messages should be thoughtful\\n - Review draft against the litmus test before creating or updating the PR\\n\\n7. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n<summary>\\n\\n\U0001F498 Generated with Crush\\n\\nEOF\\n)\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"auto_background_after\":{\"description\":\"Seconds to wait before automatically moving the command to a background job (default: 60)\",\"type\":\"integer\"},\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Download a URL directly to a local file (binary-safe, streaming, max 600s timeout); overwrites without warning. For reading content into context use fetch.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edit a file by exact find-and-replace; can also create or delete content. For renames/moves use bash. For large edits use write.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Apply multiple find-and-replace edits to a single file in one operation; edits run sequentially. Prefer over edit for multiple changes to the same file. Same exact-match rules as edit apply.\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetch raw content from a URL as text, markdown, or html (max 100KB); no AI processing. For analysis or extraction use agentic_fetch.\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Find files by name/pattern (glob syntax), sorted by modification time; max 100 results; skips hidden files. Use grep to search file contents.\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Search file contents by regex or literal text; returns matching file paths sorted by modification time (max 100); respects .gitignore. Use glob to filter by filename, not contents.\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"List files and directories as a tree; skips hidden files and common system dirs; max 1000 files. Use glob to find files by pattern, grep to search contents.\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public GitHub repositories via Sourcegraph; supports regex, language/repo/file filters, and symbol search (max 20 results). Only searches public repos.\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Read a file by path with line numbers; supports offset and line limit (default 200, max 200KB returned file content section); renders images (PNG, JPEG, GIF, WebP); use ls for directories.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 200)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Create or overwrite a file with given content; auto-creates parent dirs. Cannot append. Read the file first to avoid conflicts. For surgical changes use edit or multiedit.\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
12− headers:
13− Accept:
14− - application/json
15− Content-Type:
16− - application/json
17− User-Agent:
18− - Charm-Crush/devel (https://charm.land/crush)
19− url: https://hyper.charm.land/v1/chat/completions
20− method: POST
21− response:
22− proto: HTTP/2.0
23− proto_major: 2
24− proto_minor: 0
25− content_length: -1
26− uncompressed: true
27− body: |+
28− data: {"id":"chatcmpl-edc9f684f6145a18378c95dd","object":"chat.completion.chunk","created":1782413818,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
29−
30− data: {"id":"chatcmpl-edc9f684f6145a18378c95dd","object":"chat.completion.chunk","created":1782413818,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_9fc14d4b22da05b9","type":"function","index":0,"function":{"name":"ls","arguments":""}}]},"finish_reason":null}]}
31−
32− data: {"id":"chatcmpl-edc9f684f6145a18378c95dd","object":"chat.completion.chunk","created":1782413818,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{}"}}]},"finish_reason":null}]}
33−
34− data: {"id":"chatcmpl-edc9f684f6145a18378c95dd","object":"chat.completion.chunk","created":1782413818,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
35−
36− data: {"id":"chatcmpl-edc9f684f6145a18378c95dd","object":"chat.completion.chunk","created":1782413818,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":677,"completion_tokens":5,"total_tokens":8161,"prompt_tokens_details":{"cached_tokens":7479},"cost":{"usd":0.0009697999999999999,"hypercredits":0.019395999999999997},"remaining":{"hypercredits":0}}}
37−
38− data: [DONE]
39−
40− headers:
41− Content-Type:
42− - text/event-stream
43− status: 200 OK
44− code: 200
45− duration: 1.511164s
46−- id: 1
47− request:
48− proto: HTTP/1.1
49− proto_major: 1
50− proto_minor: 1
51− content_length: 808
52− host: ""
53− body: '{"messages":[{"content":"You will generate a short title based on the first message a user begins a conversation with.\n\n<rules>\n- Keep the title in the same language that the user wrote their message in.\n- Ensure it is not more than 50 characters long.\n- The title should be a summary of the user''s message.\n- It should be one line long.\n- Do not use quotes or colons.\n- The entire text you return will be used as the title.\n- Never return anything that is more than one sentence (one line) long.\n</rules>\n\n /no_think","role":"system"},{"content":"Generate a concise title for the following content:\n\nuse ls to list the files in the current directory\n <think>\n\n</think>","role":"user"}],"model":"gpt-oss-120b","max_completion_tokens":40,"stream_options":{"include_usage":true},"stream":true}'
54− headers:
55− Accept:
56− - application/json
57− Content-Type:
58− - application/json
59− User-Agent:
60− - Charm-Crush/devel (https://charm.land/crush)
61− url: https://hyper.charm.land/v1/chat/completions
62− method: POST
63− response:
64− proto: HTTP/2.0
65− proto_major: 2
66− proto_minor: 0
67− content_length: -1
68− uncompressed: true
69− body: |+
70− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
71−
72− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
73−
74− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" asks"},"finish_reason":null}]}
75−
76− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
77−
78− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
79−
80− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Generate"},"finish_reason":null}]}
81−
82− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
83−
84− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
85−
86− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
87−
88− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
89−
90− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
91−
92− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" following"},"finish_reason":null}]}
93−
94− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
95−
96− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":\n\n"},"finish_reason":null}]}
97−
98− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"use"},"finish_reason":null}]}
99−
100− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ls"},"finish_reason":null}]}
101−
102− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
103−
104− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" list"},"finish_reason":null}]}
105−
106− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
107−
108− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
109−
110− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
111−
112− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
113−
114− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" current"},"finish_reason":null}]}
115−
116− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" directory"},"finish_reason":null}]}
117−
118− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"\n\n"},"finish_reason":null}]}
119−
120− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"We"},"finish_reason":null}]}
121−
122− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" need"},"finish_reason":null}]}
123−
124− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
125−
126− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" short"},"finish_reason":null}]}
127−
128− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
129−
130− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
131−
132− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" same"},"finish_reason":null}]}
133−
134− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" language"},"finish_reason":null}]}
135−
136− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
137−
138− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"English"},"finish_reason":null}]}
139−
140− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"),"},"finish_reason":null}]}
141−
142− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" max"},"finish_reason":null}]}
143−
144− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
145−
146− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
147−
148− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
149−
150− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
151−
152− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" one"},"finish_reason":null}]}
153−
154− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
155−
156− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
157−
158− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" no"},"finish_reason":null}]}
159−
160− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
161−
162− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" or"},"finish_reason":null}]}
163−
164− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" col"},"finish_reason":null}]}
165−
166− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ons"},"finish_reason":null}]}
167−
168− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
169−
170− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Something"},"finish_reason":null}]}
171−
172− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" like"},"finish_reason":null}]}
173−
174− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
175−
176− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"List"},"finish_reason":null}]}
177−
178− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
179−
180− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
181−
182− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" current"},"finish_reason":null}]}
183−
184− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" directory"},"finish_reason":null}]}
185−
186− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" using"},"finish_reason":null}]}
187−
188− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ls"},"finish_reason":null}]}
189−
190− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
191−
192− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
193−
194− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" within"},"finish_reason":null}]}
195−
196− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
197−
198− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
199−
200− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
201−
202− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"?"},"finish_reason":null}]}
203−
204− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
205−
206− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
207−
208− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" List"},"finish_reason":null}]}
209−
210− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
211−
212− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
213−
214− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
215−
216− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
217−
218− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
219−
220− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
221−
222− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
223−
224− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
225−
226− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
227−
228− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
229−
230− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
231−
232− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
233−
234− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
235−
236− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
237−
238− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
239−
240− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
241−
242− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
243−
244− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
245−
246− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
247−
248− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
249−
250− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
251−
252− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
253−
254− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
255−
256− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" current"},"finish_reason":null}]}
257−
258− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
259−
260− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
261−
262− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
263−
264− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
265−
266− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
267−
268− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
269−
270− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
271−
272− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" directory"},"finish_reason":null}]}
273−
274− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
275−
276− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"9"},"finish_reason":null}]}
277−
278− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
279−
280− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
281−
282− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
283−
284− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
285−
286− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
287−
288− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" using"},"finish_reason":null}]}
289−
290− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
291−
292− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
293−
294− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
295−
296− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
297−
298− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
299−
300− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
301−
302− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
303−
304− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ls"},"finish_reason":null}]}
305−
306− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
307−
308− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
309−
310− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
311−
312− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ="},"finish_reason":null}]}
313−
314− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" total"},"finish_reason":null}]}
315−
316− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
317−
318− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
319−
320− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
321−
322− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
323−
324− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
325−
326− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
327−
328− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
329−
330− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
331−
332− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
333−
334− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
335−
336− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
337−
338− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
339−
340− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
341−
342− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
343−
344− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
345−
346− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
347−
348− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
349−
350− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"9"},"finish_reason":null}]}
351−
352− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
353−
354− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
355−
356− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
357−
358− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
359−
360− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
361−
362− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
363−
364− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
365−
366− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
367−
368− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ="},"finish_reason":null}]}
369−
370− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
371−
372− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"41"},"finish_reason":null}]}
373−
374− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
375−
376− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
377−
378− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" OK"},"finish_reason":null}]}
379−
380− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".\n\n"},"finish_reason":null}]}
381−
382− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Return"},"finish_reason":null}]}
383−
384− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that"},"finish_reason":null}]}
385−
386− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
387−
388− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"List"},"finish_reason":null}]}
389−
390− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" files"},"finish_reason":null}]}
391−
392− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" in"},"finish_reason":null}]}
393−
394− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" current"},"finish_reason":null}]}
395−
396− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" directory"},"finish_reason":null}]}
397−
398− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" using"},"finish_reason":null}]}
399−
400− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" ls"},"finish_reason":null}]}
401−
402− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
403−
404− data: {"id":"chatcmpl-a1787c3e58fc5f4d633cd7f2","object":"chat.completion.chunk","created":1782413817,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":155,"completion_tokens":172,"total_tokens":391,"prompt_tokens_details":{"cached_tokens":64},"cost":{"usd":0.000122704,"hypercredits":0.00245408},"remaining":{"hypercredits":0}}}
405−
406− data: [DONE]
407−
408− headers:
409− Content-Type:
410− - text/event-stream
411− status: 200 OK
412− code: 200
413− duration: 531.140917ms
414−- id: 2
415− request:
416− proto: HTTP/1.1
417− proto_major: 1
418− proto_minor: 1
419− content_length: 35898
420− host: ""
421− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ THE RELEVANT CONTEXT BEFORE EDITING**: Never edit a file you haven't already read the relevant context for in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\". When committing, follow the `<git_commits>` format from the bash tool description exactly, including any configured attribution lines.\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **TOOL CONSTRAINTS**: Only use documented tools. Never attempt 'apply_patch' or 'apply_diff' - they don't exist. Use 'edit' or 'multiedit' instead.\\n14. **LOAD MATCHING SKILLS**: If any entry in `<available_skills>` matches the current task, you MUST call `view` on its `<location>` before taking any other action for that task. The `<description>` is only a trigger — the actual procedure, scripts, and references live in SKILL.md. Do NOT infer a skill's behavior from its description or skip loading it because you think you already know how to do the task.\\n15. **LIMIT FILE READS**: Avoid reading entire files, as they can be very large. Read only the sections you need using 'offset' and 'limit' parameters.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- ALWAYS think and respond in the same spoken language the prompt was written in.\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\n**Available edit tools:**\\n- `edit` - Single find/replace in a file\\n- `multiedit` - Multiple find/replace operations in one file\\n- `write` - Create/overwrite entire file\\n\\nNever use `apply_patch` or similar - those tools don't exist.\\n\\nCritical: ALWAYS read the relevant context of files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the relevant context first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</editing_files>\\n\\n<whitespace_and_exact_matching>\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n</whitespace_and_exact_matching>\\n\\n<task_completion>\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n</task_completion>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences\\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n<bash_commands>\\n**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/glm-5.1/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n<available_skills>\\n <skill>\\n <name>crush-hooks</name>\\n <description>Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.</description>\\n <location>crush://skills/crush-hooks/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n <skill>\\n <name>jq</name>\\n <description>Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.</description>\\n <location>crush://skills/jq/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n</available_skills>\\n\\n<skills_usage>\\nThe `<description>` of each skill is a TRIGGER — it tells you *when* a skill applies. It is NOT a specification of what the skill does or how to do it. The procedure, scripts, commands, references, and required flags live only in the SKILL.md body. You do not know what a skill actually does until you have read its SKILL.md.\\n\\nMANDATORY activation flow:\\n1. Scan `<available_skills>` against the current user task.\\n2. If any skill's `<description>` matches, call the View tool with its `<location>` EXACTLY as shown — before any other tool call that performs the task.\\n3. Read the entire SKILL.md and follow its instructions.\\n4. Only then execute the task, using the skill's prescribed commands/tools.\\n\\nDo NOT skip step 2 because you think you already know how to do the task. Do NOT infer a skill's behavior from its name or description. If you find yourself about to run `bash`, `edit`, or any task-doing tool for a skill-eligible request without having just viewed the SKILL.md, stop and load the skill first.\\n\\nBuiltin skills (type=builtin) use virtual `crush://skills/...` location identifiers. The \\\"crush://\\\" prefix is NOT a URL, network address, or MCP resource — it is a special internal identifier the View tool understands natively. Pass the `<location>` verbatim to View.\\n\\nDo not use MCP tools (including read_mcp_resource) to load skills.\\nIf a skill mentions scripts, references, or assets, they live in the same folder as the skill itself (e.g., scripts/, references/, assets/ subdirectories within the skill's folder).\\n</skills_usage>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"<system_reminder>This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.</system_reminder>\",\"role\":\"user\"},{\"content\":\"use ls to list the files in the current directory\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_9fc14d4b22da05b9\",\"function\":{\"arguments\":\"{}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/glm-5.1/ls_tool/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_9fc14d4b22da05b9\",\"role\":\"tool\"}],\"model\":\"glm-5.1\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Execute shell commands; long-running commands automatically move to background and return a shell ID.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute (default, configurable via `auto_background_after`) automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<background_execution>\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `&` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n</background_execution>\\n\\n<git_message_quality>\\nThese rules apply whenever creating or updating commit messages, PR titles, or PR bodies:\\n\\n- Messages MUST be understandable to someone unfamiliar with the codebase.\\n- Before creating or updating a message, verify this litmus test: a new contributor reading only the commit message or PR title/body should understand what problem this solves, why it matters, and the impact without opening files, reading the diff, or knowing internal code names.\\n- Avoid code identifiers, filenames, function names, and implementation details unless they are necessary for understanding the user-facing impact.\\n- Bad: \\\"Add NameFromHex with sync.Once lazy init\\\"\\n- Good: \\\"Improve color name lookup performance while keeping startup fast\\\"\\n</git_message_quality>\\n\\n<commit_messages>\\nCommit messages are for future readers scanning history. Before committing:\\n\\n- Follow <git_message_quality>.\\n- Draft a concise 1-2 sentence message focusing on why the change exists and what outcome it enables, not a list of files or implementation details.\\n- Use clear, accurate verbs (\\\"add\\\"=new capability, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix) and avoid generic messages.\\n- The first line MUST be under 72 characters.\\n- Add a body only when it is needed to explain the reasoning, tradeoffs, or important context; wrap body lines at 72 characters.\\n- If the change is internal-only, still describe the benefit or maintenance outcome rather than naming private code.\\n- Bad: \\\"fix: nil pointer in session.go\\\"\\n- Good: \\\"fix: prevent session loading from crashing on missing metadata\\\"\\n- Bad: \\\"refactor: move PromptBuilder into internal/agent\\\"\\n- Good: \\\"refactor: make prompt assembly easier to maintain\\\"\\n</commit_messages>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond the context of git\\n\\n4. Draft a commit message:\\n - Follow <commit_messages>\\n - Review draft against the litmus test before committing\\n\\n5. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\nCommit message here.\\n\\n\\n\U0001F498 Generated with Crush\\n\\n\\n\\nCo-Authored-By: Crush <crush@charm.land>\\n\\nEOF\\n)\\\"\\n\\n6. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n7. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m.\\n</git_commits>\\n\\n<pull_requests>\\n\\n\\nWhen user asks you to create or update a PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n\\n3. Commit changes if needed\\n\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n\\n6. Draft a PR message:\\n - Follow <git_message_quality>\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Use clear, concise language\\n - Provide an accurate reflection of changes and purpose\\n - Avoid generic summaries; messages should be thoughtful\\n - Review draft against the litmus test before creating or updating the PR\\n\\n7. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n<summary>\\n\\n\U0001F498 Generated with Crush\\n\\nEOF\\n)\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"auto_background_after\":{\"description\":\"Seconds to wait before automatically moving the command to a background job (default: 60)\",\"type\":\"integer\"},\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Download a URL directly to a local file (binary-safe, streaming, max 600s timeout); overwrites without warning. For reading content into context use fetch.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edit a file by exact find-and-replace; can also create or delete content. For renames/moves use bash. For large edits use write.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Apply multiple find-and-replace edits to a single file in one operation; edits run sequentially. Prefer over edit for multiple changes to the same file. Same exact-match rules as edit apply.\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetch raw content from a URL as text, markdown, or html (max 100KB); no AI processing. For analysis or extraction use agentic_fetch.\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Find files by name/pattern (glob syntax), sorted by modification time; max 100 results; skips hidden files. Use grep to search file contents.\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Search file contents by regex or literal text; returns matching file paths sorted by modification time (max 100); respects .gitignore. Use glob to filter by filename, not contents.\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"List files and directories as a tree; skips hidden files and common system dirs; max 1000 files. Use glob to find files by pattern, grep to search contents.\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public GitHub repositories via Sourcegraph; supports regex, language/repo/file filters, and symbol search (max 20 results). Only searches public repos.\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Read a file by path with line numbers; supports offset and line limit (default 200, max 200KB returned file content section); renders images (PNG, JPEG, GIF, WebP); use ls for directories.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 200)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Create or overwrite a file with given content; auto-creates parent dirs. Cannot append. Read the file first to avoid conflicts. For surgical changes use edit or multiedit.\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
422− headers:
423− Accept:
424− - application/json
425− Content-Type:
426− - application/json
427− User-Agent:
428− - Charm-Crush/devel (https://charm.land/crush)
429− url: https://hyper.charm.land/v1/chat/completions
430− method: POST
431− response:
432− proto: HTTP/2.0
433− proto_major: 2
434− proto_minor: 0
435− content_length: -1
436− uncompressed: true
437− body: |+
438− data: {"id":"chatcmpl-0df4ed5d1b2533d9447fa033","object":"chat.completion.chunk","created":1782413819,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
439−
440− data: {"id":"chatcmpl-0df4ed5d1b2533d9447fa033","object":"chat.completion.chunk","created":1782413819,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Two"},"finish_reason":null}]}
441−
442− data: {"id":"chatcmpl-0df4ed5d1b2533d9447fa033","object":"chat.completion.chunk","created":1782413819,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" files"},"finish_reason":null}]}
443−
444− data: {"id":"chatcmpl-0df4ed5d1b2533d9447fa033","object":"chat.completion.chunk","created":1782413819,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" in"},"finish_reason":null}]}
445−
446− data: {"id":"chatcmpl-0df4ed5d1b2533d9447fa033","object":"chat.completion.chunk","created":1782413819,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" the"},"finish_reason":null}]}
447−
448− data: {"id":"chatcmpl-0df4ed5d1b2533d9447fa033","object":"chat.completion.chunk","created":1782413819,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" current"},"finish_reason":null}]}
449−
450− data: {"id":"chatcmpl-0df4ed5d1b2533d9447fa033","object":"chat.completion.chunk","created":1782413819,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" directory"},"finish_reason":null}]}
451−
452− data: {"id":"chatcmpl-0df4ed5d1b2533d9447fa033","object":"chat.completion.chunk","created":1782413819,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":":\n"},"finish_reason":null}]}
453−
454− data: {"id":"chatcmpl-0df4ed5d1b2533d9447fa033","object":"chat.completion.chunk","created":1782413819,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}]}
455−
456− data: {"id":"chatcmpl-0df4ed5d1b2533d9447fa033","object":"chat.completion.chunk","created":1782413819,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `"},"finish_reason":null}]}
457−
458− data: {"id":"chatcmpl-0df4ed5d1b2533d9447fa033","object":"chat.completion.chunk","created":1782413819,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"go"},"finish_reason":null}]}
459−
460− data: {"id":"chatcmpl-0df4ed5d1b2533d9447fa033","object":"chat.completion.chunk","created":1782413819,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":".mod"},"finish_reason":null}]}
461−
462− data: {"id":"chatcmpl-0df4ed5d1b2533d9447fa033","object":"chat.completion.chunk","created":1782413819,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`\n"},"finish_reason":null}]}
463−
464− data: {"id":"chatcmpl-0df4ed5d1b2533d9447fa033","object":"chat.completion.chunk","created":1782413819,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}]}
465−
466− data: {"id":"chatcmpl-0df4ed5d1b2533d9447fa033","object":"chat.completion.chunk","created":1782413819,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `"},"finish_reason":null}]}
467−
468− data: {"id":"chatcmpl-0df4ed5d1b2533d9447fa033","object":"chat.completion.chunk","created":1782413819,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"main"},"finish_reason":null}]}
469−
470− data: {"id":"chatcmpl-0df4ed5d1b2533d9447fa033","object":"chat.completion.chunk","created":1782413819,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}]}
471−
472− data: {"id":"chatcmpl-0df4ed5d1b2533d9447fa033","object":"chat.completion.chunk","created":1782413819,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`"},"finish_reason":null}]}
473−
474− data: {"id":"chatcmpl-0df4ed5d1b2533d9447fa033","object":"chat.completion.chunk","created":1782413819,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
475−
476− data: {"id":"chatcmpl-0df4ed5d1b2533d9447fa033","object":"chat.completion.chunk","created":1782413819,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":8195,"completion_tokens":19,"total_tokens":8214,"cost":{"usd":0.0115566,"hypercredits":0.231132},"remaining":{"hypercredits":0}}}
477−
478− data: [DONE]
479−
480− headers:
481− Content-Type:
482− - text/event-stream
483− status: 200 OK
484− code: 200
485− duration: 1.065962584s
internal/agent/testdata/TestCoderAgent/glm-5.1/multiedit_tool.yamldeleted−1439
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/glm-5.1/parallel_tool_calls.yamldeleted−685
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/glm-5.1/read_a_file.yamldeleted−413
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/glm-5.1/simple_test.yamldeleted−277
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/glm-5.1/sourcegraph_tool.yamldeleted−1479
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/glm-5.1/update_a_file.yamldeleted−747
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/glm-5.1/write_tool.yamldeleted−547
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/openai-gpt-5/bash_tool.yamlnew file+184
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/openai-gpt-5/download_tool.yamlnew file+260
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/openai-gpt-5/fetch_tool.yamlnew file+257
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/openai-gpt-5/glob_tool.yamlnew file+148
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/openai-gpt-5/grep_tool.yamlnew file+214
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/openai-gpt-5/ls_tool.yamlnew file+188
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/openai-gpt-5/multiedit_tool.yamlnew file+593
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/openai-gpt-5/parallel_tool_calls.yamlnew file+246
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/openai-gpt-5/read_a_file.yamlnew file+281
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/openai-gpt-5/simple_test.yamlnew file+83
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/openai-gpt-5/sourcegraph_tool.yamlnew file+658
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/openai-gpt-5/update_a_file.yamlnew file+583
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/openai-gpt-5/write_tool.yamlnew file+214
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/bash_tool.yamlnew file+628
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/download_tool.yamlnew file+262
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/fetch_tool.yamlnew file+265
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/glob_tool.yamlnew file+251
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/grep_tool.yamlnew file+166
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/ls_tool.yamlnew file+186
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/multiedit_tool.yaml+678
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/parallel_tool_calls.yaml+196
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/read_a_file.yaml+245
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/simple_test.yaml+81
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/sourcegraph_tool.yaml+647
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/update_a_file.yaml+447
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/write_tool.yaml+220
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/zai-glm4.6/bash_tool.yaml+130
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/zai-glm4.6/download_tool.yaml+190
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/zai-glm4.6/fetch_tool.yaml+229
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/zai-glm4.6/glob_tool.yaml+142
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/zai-glm4.6/grep_tool.yaml+190
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/zai-glm4.6/ls_tool.yaml+134
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/zai-glm4.6/multiedit_tool.yaml+361
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/zai-glm4.6/parallel_tool_calls.yaml+162
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/zai-glm4.6/read_a_file.yaml+194
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/zai-glm4.6/simple_test.yaml+95
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/zai-glm4.6/sourcegraph_tool.yaml+382
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/zai-glm4.6/update_a_file.yaml+269
This diff is too big to show here.
internal/agent/testdata/TestCoderAgent/zai-glm4.6/write_tool.yaml+130
This diff is too big to show here.
internal/agent/tools/bash.go+52−50
This diff is too big to show here.
internal/agent/tools/bash.md.tpl−173
This diff is too big to show here.
internal/agent/tools/bash.tpl+142
This diff is too big to show here.
internal/agent/tools/bash_test.go−213
This diff is too big to show here.
internal/agent/tools/context_test.go−233
This diff is too big to show here.
internal/agent/tools/crush_info.go−487
This diff is too big to show here.
internal/agent/tools/crush_info.md−19
This diff is too big to show here.
internal/agent/tools/crush_info_test.go−505
This diff is too big to show here.
internal/agent/tools/crush_logs.go−514
This diff is too big to show here.
internal/agent/tools/crush_logs.md.tpl−13
This diff is too big to show here.
internal/agent/tools/crush_logs_test.go−529
This diff is too big to show here.
internal/agent/tools/diagnostics.go+20−100
This diff is too big to show here.
internal/agent/tools/diagnostics.md+24−1
This diff is too big to show here.
internal/agent/tools/download.go+16−37
This diff is too big to show here.
internal/agent/tools/download.md+28
This diff is too big to show here.
internal/agent/tools/download.md.tpl−1
This diff is too big to show here.
internal/agent/tools/edit.go+58−99
This diff is too big to show here.
internal/agent/tools/edit.md+147−1
This diff is too big to show here.
internal/agent/tools/fetch.go+38−64
This diff is too big to show here.
internal/agent/tools/fetch.md+45
This diff is too big to show here.
internal/agent/tools/fetch.md.tpl−2
This diff is too big to show here.
internal/agent/tools/fetch_helpers.go+2−3
This diff is too big to show here.
internal/agent/tools/file.go+53
This diff is too big to show here.
internal/agent/tools/glob.go+29−99
This diff is too big to show here.
internal/agent/tools/glob.md+40
This diff is too big to show here.
internal/agent/tools/glob.md.tpl−1
This diff is too big to show here.
internal/agent/tools/glob_test.go−74
This diff is too big to show here.
internal/agent/tools/grep.go+45−72
This diff is too big to show here.
internal/agent/tools/grep.md+49
This diff is too big to show here.
internal/agent/tools/grep.md.tpl−1
This diff is too big to show here.
internal/agent/tools/job_kill.go+3−4
This diff is too big to show here.
internal/agent/tools/job_kill.md+1−1
This diff is too big to show here.
internal/agent/tools/job_output.go+3−10
This diff is too big to show here.
internal/agent/tools/job_output.md+19−1
This diff is too big to show here.
internal/agent/tools/job_test.go−5
This diff is too big to show here.
internal/agent/tools/list_mcp_resources.go−100
This diff is too big to show here.
internal/agent/tools/list_mcp_resources.md−1
This diff is too big to show here.
internal/agent/tools/ls.go+13−40
This diff is too big to show here.
internal/agent/tools/ls.md+34
This diff is too big to show here.
internal/agent/tools/ls.md.tpl−1
This diff is too big to show here.
internal/agent/tools/lsp_restart.go−80
This diff is too big to show here.
internal/agent/tools/lsp_restart.md−1
This diff is too big to show here.
internal/agent/tools/mcp-tools.go+18−39
This diff is too big to show here.
internal/agent/tools/mcp/init.go+69−210
This diff is too big to show here.
internal/agent/tools/mcp/init_test.go−526
This diff is too big to show here.
internal/agent/tools/mcp/prompts.go+4−5
This diff is too big to show here.
internal/agent/tools/mcp/resources.go−109
This diff is too big to show here.
internal/agent/tools/mcp/tools.go+12−114
This diff is too big to show here.
internal/agent/tools/mcp/tools_test.go−117
This diff is too big to show here.
internal/agent/tools/multiedit.go+31−60
This diff is too big to show here.
internal/agent/tools/multiedit.md+125−1
This diff is too big to show here.
internal/agent/tools/multiedit_test.go+18−7
This diff is too big to show here.
internal/agent/tools/read_mcp_resource.go−103
This diff is too big to show here.
internal/agent/tools/read_mcp_resource.md−1
This diff is too big to show here.
internal/agent/tools/references.go+21−17
This diff is too big to show here.
internal/agent/tools/references.md+26−1
This diff is too big to show here.
internal/agent/tools/rg.go+1−10
This diff is too big to show here.
internal/agent/tools/safe.go+6−99
This diff is too big to show here.
internal/agent/tools/safe_test.go−74
This diff is too big to show here.
internal/agent/tools/search.go+77−107
This diff is too big to show here.
internal/agent/tools/sourcegraph.go+22−40
This diff is too big to show here.
internal/agent/tools/sourcegraph.md+55
This diff is too big to show here.
internal/agent/tools/sourcegraph.md.tpl−1
This diff is too big to show here.
internal/agent/tools/todos.go+3−4
This diff is too big to show here.
internal/agent/tools/todos.md+90−1
This diff is too big to show here.
internal/agent/tools/tools.go+33−64
This diff is too big to show here.
internal/agent/tools/view.go+121−300
This diff is too big to show here.
internal/agent/tools/view.md+38
This diff is too big to show here.
internal/agent/tools/view.md.tpl−1
This diff is too big to show here.
internal/agent/tools/view_test.go−356
This diff is too big to show here.
internal/agent/tools/web_fetch.go+17−25
This diff is too big to show here.
internal/agent/tools/web_fetch.md+28
This diff is too big to show here.
internal/agent/tools/web_fetch.md.tpl−2
This diff is too big to show here.
internal/agent/tools/web_search.go+11−22
This diff is too big to show here.
internal/agent/tools/web_search.md+18
This diff is too big to show here.
internal/agent/tools/web_search.md.tpl−2
This diff is too big to show here.
internal/agent/tools/write.go+43−50
This diff is too big to show here.
internal/agent/tools/write.md+30−1
This diff is too big to show here.
internal/agent/tools/write_test.go−49
This diff is too big to show here.
internal/agent/usage_fallback.go−167
This diff is too big to show here.
internal/agent/usage_fallback_test.go−339
This diff is too big to show here.
internal/app/app.go+85−423
This diff is too big to show here.
internal/app/app_test.go−183
This diff is too big to show here.
internal/app/lsp.go+80
This diff is too big to show here.
internal/app/lsp_events.go+2−3
This diff is too big to show here.
internal/app/provider.go−95
This diff is too big to show here.
internal/app/provider_test.go−210
This diff is too big to show here.
internal/app/resolve_session_test.go−174
This diff is too big to show here.
internal/app/testing.go−72
This diff is too big to show here.
internal/backend/accepted_run_integration_test.go−131
This diff is too big to show here.
internal/backend/agent.go−273
This diff is too big to show here.
internal/backend/agent_runcomplete_test.go−163
This diff is too big to show here.
internal/backend/agent_test.go−164
This diff is too big to show here.
internal/backend/backend.go−792
This diff is too big to show here.
internal/backend/backend_skills_test.go−167
This diff is too big to show here.
internal/backend/backend_test.go−1241
This diff is too big to show here.
internal/backend/config.go−307
This diff is too big to show here.
internal/backend/config_test.go−205
This diff is too big to show here.
internal/backend/events.go−109
This diff is too big to show here.
internal/backend/filetracker.go−37
This diff is too big to show here.
internal/backend/permission.go−60
This diff is too big to show here.
internal/backend/race_off_test.go−5
This diff is too big to show here.
internal/backend/race_on_test.go−5
This diff is too big to show here.
internal/backend/session.go−132
This diff is too big to show here.
internal/backend/shell_command_test.go−54
This diff is too big to show here.
internal/backend/testing.go−69
This diff is too big to show here.
internal/backend/util.go−22
This diff is too big to show here.
internal/client/client.go−213
This diff is too big to show here.
internal/client/config.go−345
This diff is too big to show here.
internal/client/config_test.go−101
This diff is too big to show here.
internal/client/dial_other.go−13
This diff is too big to show here.
internal/client/dial_windows.go−15
This diff is too big to show here.
internal/client/proto.go−861
This diff is too big to show here.
internal/client/proto_test.go−178
This diff is too big to show here.
internal/clipboard/clipboard.go−44
This diff is too big to show here.
internal/clipboard/clipboard_not_supported.go−13
This diff is too big to show here.
internal/clipboard/clipboard_supported.go−30
This diff is too big to show here.
internal/cmd/clientserverrace/race_test.go−361
This diff is too big to show here.
internal/cmd/dirs.go+37−62
This diff is too big to show here.
internal/cmd/dirs_test.go+46
This diff is too big to show here.
internal/cmd/gitignore/default−4
This diff is too big to show here.
internal/cmd/gitignore/old−1
This diff is too big to show here.
internal/cmd/login.go+95−56
This diff is too big to show here.
internal/cmd/login_test.go−21
This diff is too big to show here.
internal/cmd/logout.go−182
This diff is too big to show here.
internal/cmd/logout_test.go−41
This diff is too big to show here.
internal/cmd/logs.go+6−6
This diff is too big to show here.
internal/cmd/models.go−155
This diff is too big to show here.
internal/cmd/root.go+81−622
This diff is too big to show here.
internal/cmd/root_other.go−15
This diff is too big to show here.
internal/cmd/root_windows.go−18
This diff is too big to show here.
internal/cmd/run.go+19−609
This diff is too big to show here.
internal/cmd/run_stream_test.go−417
This diff is too big to show here.
internal/cmd/schema.go+1−35
This diff is too big to show here.
internal/cmd/schema_test.go−59
This diff is too big to show here.
internal/cmd/server.go−99
This diff is too big to show here.
internal/cmd/server_other.go−12
This diff is too big to show here.
internal/cmd/server_windows.go−10
This diff is too big to show here.
internal/cmd/session.go−728
This diff is too big to show here.
internal/cmd/stats.go−390
This diff is too big to show here.
internal/cmd/stats/AGENTS.md−3
This diff is too big to show here.
internal/cmd/stats/footer.svg−838
This diff is too big to show here.
internal/cmd/stats/header.svg−673
This diff is too big to show here.
internal/cmd/stats/heartbit.svg−43
This diff is too big to show here.
internal/cmd/stats/index.css−270
This diff is too big to show here.
internal/cmd/stats/index.html−136
This diff is too big to show here.
internal/cmd/stats/index.js−356
This diff is too big to show here.
internal/commands/commands.go−239
This diff is too big to show here.
internal/commands/commands_test.go−114
This diff is too big to show here.
internal/config/agent_id_test.go−29
This diff is too big to show here.
internal/config/atomicwrite.go−38
This diff is too big to show here.
internal/config/atomicwrite_test.go−43
This diff is too big to show here.
internal/config/attribution_migration_test.go+3−1
This diff is too big to show here.
internal/config/catwalk.go+2−2
This diff is too big to show here.
internal/config/catwalk_test.go+1−1
This diff is too big to show here.
internal/config/clone_test.go−46
This diff is too big to show here.
internal/config/config.go+331−428
This diff is too big to show here.
internal/config/copilot.go+47
This diff is too big to show here.
internal/config/docker_mcp.go−141
This diff is too big to show here.
internal/config/docker_mcp_test.go−195
This diff is too big to show here.
internal/config/hyper.go+2−2
This diff is too big to show here.
internal/config/hyper_test.go+1−1
This diff is too big to show here.
internal/config/init.go+25−17
This diff is too big to show here.
internal/config/load.go+127−686
This diff is too big to show here.
internal/config/load_bench_test.go−103
This diff is too big to show here.
internal/config/load_test.go+118−1161
This diff is too big to show here.
internal/config/mcp_resolved_url_test.go−105
This diff is too big to show here.
internal/config/merge.go+16
This diff is too big to show here.
internal/config/merge_test.go+27
This diff is too big to show here.
internal/config/provider.go+9−18
This diff is too big to show here.
internal/config/provider_empty_test.go+1−1
This diff is too big to show here.
internal/config/provider_test.go+1−1
This diff is too big to show here.
internal/config/recent_models_test.go+172−77
This diff is too big to show here.
internal/config/refresh_singleflight_test.go−175
This diff is too big to show here.
internal/config/reload_hooks_test.go−102
This diff is too big to show here.
internal/config/resolve.go+131−140
This diff is too big to show here.
internal/config/resolve_real_test.go−512
This diff is too big to show here.
internal/config/resolve_test.go+288−185
This diff is too big to show here.
internal/config/scope.go−29
This diff is too big to show here.
internal/config/scopeb_race_test.go−74
This diff is too big to show here.
internal/config/store.go−1078
This diff is too big to show here.
internal/config/store_test.go−784
This diff is too big to show here.
internal/config/update_model_bench_test.go−108
This diff is too big to show here.
internal/csync/maps.go+10−32
This diff is too big to show here.
internal/csync/maps_test.go+3−4
This diff is too big to show here.
internal/csync/slices.go+34−10
This diff is too big to show here.
internal/csync/slices_test.go+57
This diff is too big to show here.
internal/csync/value.go−44
This diff is too big to show here.
internal/csync/value_test.go−97
This diff is too big to show here.
internal/csync/versionedmap.go−5
This diff is too big to show here.
internal/db/connect.go+33−195
This diff is too big to show here.
internal/db/connect_modernc.go−31
This diff is too big to show here.
internal/db/connect_ncruces.go−33
This diff is too big to show here.
internal/db/connect_test.go−210
This diff is too big to show here.
internal/db/datadirlock.go−131
This diff is too big to show here.
internal/db/db.go+1−181
This diff is too big to show here.
internal/db/embed.go+6
This diff is too big to show here.
internal/db/files.sql.go+5−21
This diff is too big to show here.
internal/db/messages.sql.go+2−132
This diff is too big to show here.
internal/db/migrations/20260127000000_add_read_files_table.sql−20
This diff is too big to show here.
internal/db/migrations/20260701000000_add_composite_indexes.sql−12
This diff is too big to show here.
internal/db/migrations/20260702000000_add_hot_path_indexes.sql−14
This diff is too big to show here.
internal/db/models.go+1−7
This diff is too big to show here.
internal/db/querier.go+2−20
This diff is too big to show here.
internal/db/read_files.sql.go−79
This diff is too big to show here.
internal/db/sessions.sql.go+6−80
This diff is too big to show here.
internal/db/sql/files.sql+4−12
This diff is too big to show here.
internal/db/sql/messages.sql−19
This diff is too big to show here.
internal/db/sql/read_files.sql−20
This diff is too big to show here.
internal/db/sql/sessions.sql+3−18
This diff is too big to show here.
internal/db/sql/stats.sql−93
This diff is too big to show here.
internal/db/stats.sql.go−367
This diff is too big to show here.
internal/diffdetect/detect.go−36
This diff is too big to show here.
internal/diffdetect/detect_test.go−152
This diff is too big to show here.
internal/discover/discover.go−145
This diff is too big to show here.
internal/discover/discover_test.go−221
This diff is too big to show here.
internal/discover/enricher.go−60
This diff is too big to show here.
internal/discover/litellm.go−87
This diff is too big to show here.
internal/discover/litellm_test.go−173
This diff is too big to show here.
internal/discover/llamacpp.go−83
This diff is too big to show here.
internal/discover/llamacpp_test.go−135
This diff is too big to show here.
internal/discover/lmstudio.go−95
This diff is too big to show here.
internal/discover/lmstudio_test.go−154
This diff is too big to show here.
internal/discover/ollama.go−105
This diff is too big to show here.
internal/discover/ollama_test.go−131
This diff is too big to show here.
internal/discover/omlx.go−73
This diff is too big to show here.
internal/discover/omlx_test.go−92
This diff is too big to show here.
internal/dns/android.go−41
This diff is too big to show here.
internal/env/env.go+12−1
This diff is too big to show here.
internal/env/env_test.go+2−4
This diff is too big to show here.
internal/event/all.go−24
This diff is too big to show here.
internal/event/event.go+22−56
This diff is too big to show here.
internal/event/event_test.go−105
This diff is too big to show here.
internal/filepathext/filepath.go−25
This diff is too big to show here.
internal/filepathext/filepath_test.go−37
This diff is too big to show here.
internal/filetracker/service.go−110
This diff is too big to show here.
internal/filetracker/service_test.go−116
This diff is too big to show here.
internal/format/spinner.go+6−7
This diff is too big to show here.
internal/fsext/drive_other.go−16
This diff is too big to show here.
internal/fsext/drive_windows.go−26
This diff is too big to show here.
internal/fsext/fileutil.go+35−77
This diff is too big to show here.
internal/fsext/fileutil_dirtrim_test.go−32
This diff is too big to show here.
internal/fsext/fileutil_test.go+13−13
This diff is too big to show here.
internal/fsext/ignore_test.go+3−3
This diff is too big to show here.
internal/fsext/lookup.go+7−142
This diff is too big to show here.
internal/fsext/lookup_test.go−125
This diff is too big to show here.
internal/fsext/ls.go+124−187
This diff is too big to show here.
internal/fsext/ls_test.go+2−3
This diff is too big to show here.
internal/fsext/owner_others.go+5−8
This diff is too big to show here.
internal/fsext/owner_windows.go−7
This diff is too big to show here.
internal/fsext/paste.go−129
This diff is too big to show here.
internal/fsext/paste_test.go−149
This diff is too big to show here.
internal/herdr/client.go−405
This diff is too big to show here.
internal/herdr/client_test.go−158
This diff is too big to show here.
internal/herdr/translate.go−150
This diff is too big to show here.
internal/herdr/translate_test.go−145
This diff is too big to show here.
internal/history/file.go+15−27
This diff is too big to show here.
internal/home/home.go+1−10
This diff is too big to show here.
internal/hooks/hooks.go−193
This diff is too big to show here.
internal/hooks/hooks_test.go−757
This diff is too big to show here.
internal/hooks/input.go−211
This diff is too big to show here.
internal/hooks/runner.go−265
This diff is too big to show here.
internal/lock/lock.go−75
This diff is too big to show here.
internal/lock/lock_test.go−168
This diff is too big to show here.
internal/lock/lock_unix.go−45
This diff is too big to show here.
internal/lock/lock_windows.go−57
This diff is too big to show here.
internal/log/http.go+2−5
This diff is too big to show here.
internal/log/log.go+4−20
This diff is too big to show here.
internal/lsp/client.go+152−356
This diff is too big to show here.
internal/lsp/client_test.go+2−149
This diff is too big to show here.
internal/lsp/handlers.go+24−21
This diff is too big to show here.
internal/lsp/language.go+132
This diff is too big to show here.
internal/lsp/manager.go−412
This diff is too big to show here.
internal/lsp/manager_test.go−35
This diff is too big to show here.
internal/lsp/rootmarkers_test.go+37
This diff is too big to show here.
internal/lsp/util/edit.go+46−94
This diff is too big to show here.
internal/lsp/util/edit_test.go−376
This diff is too big to show here.
internal/message/attachment.go+3−14
This diff is too big to show here.
internal/message/content.go+39−140
This diff is too big to show here.
internal/message/content_test.go−142
This diff is too big to show here.
internal/message/message.go+65−461
This diff is too big to show here.
internal/message/message_test.go−695
This diff is too big to show here.
internal/oauth/claude/challenge.go+28
This diff is too big to show here.
internal/oauth/claude/oauth.go+126
This diff is too big to show here.
internal/oauth/copilot/client.go−94
This diff is too big to show here.
internal/oauth/copilot/client_test.go−70
This diff is too big to show here.
internal/oauth/token.go+4−33
This diff is too big to show here.
internal/permission/permission.go+91−175
This diff is too big to show here.
internal/permission/permission_test.go+9−377
This diff is too big to show here.
internal/projects/projects_test.go−6
This diff is too big to show here.
internal/proto/agent.go−82
This diff is too big to show here.
internal/proto/history.go−12
This diff is too big to show here.
internal/proto/mcp.go−172
This diff is too big to show here.
internal/proto/message.go−714
This diff is too big to show here.
internal/proto/permission.go−147
This diff is too big to show here.
internal/proto/permission_test.go−186
This diff is too big to show here.
internal/proto/proto.go−309
This diff is too big to show here.
internal/proto/requests.go−137
This diff is too big to show here.
internal/proto/requests_test.go−106
This diff is too big to show here.
internal/proto/server.go−6
This diff is too big to show here.
internal/proto/session.go−37
This diff is too big to show here.
internal/proto/skills.go−28
This diff is too big to show here.
internal/proto/tools.go−234
This diff is too big to show here.
internal/proto/version.go−10
This diff is too big to show here.
internal/pubsub/broker.go+21−186
This diff is too big to show here.
internal/pubsub/broker_test.go−117
This diff is too big to show here.
internal/pubsub/events.go+12−41
This diff is too big to show here.
internal/server/agent_cancel_test.go−227
This diff is too big to show here.
internal/server/config.go−525
This diff is too big to show here.
internal/server/e2e_agent_test.go−742
This diff is too big to show here.
internal/server/e2e_test.go−612
This diff is too big to show here.
internal/server/events.go−311
This diff is too big to show here.
internal/server/events_test.go−182
This diff is too big to show here.
internal/server/logging.go−53
This diff is too big to show here.
internal/server/multiclient_test.go−230
This diff is too big to show here.
internal/server/net_other.go−61
This diff is too big to show here.
internal/server/net_windows.go−37
This diff is too big to show here.
internal/server/proto.go−1129
This diff is too big to show here.
internal/server/recover.go−59
This diff is too big to show here.
internal/server/recover_test.go−94
This diff is too big to show here.
internal/server/server.go−286
This diff is too big to show here.
internal/server/sessions_isbusy_test.go−334
This diff is too big to show here.
internal/server/socket.go−10
This diff is too big to show here.
internal/server/socket_classify.go−27
This diff is too big to show here.
internal/server/socket_test.go−193
This diff is too big to show here.
internal/session/session.go+11−122
This diff is too big to show here.
internal/session/session_test.go−81
This diff is too big to show here.
internal/shell/background.go+19−63
This diff is too big to show here.
internal/shell/background_test.go+22−70
This diff is too big to show here.
internal/shell/dispatch.go−425
This diff is too big to show here.
internal/shell/dispatch_test.go−594
This diff is too big to show here.
internal/shell/dispatch_windows_test.go−40
This diff is too big to show here.
internal/shell/exec_unix.go−108
This diff is too big to show here.
internal/shell/exec_windows.go−23
This diff is too big to show here.
internal/shell/expand.go−162
This diff is too big to show here.
internal/shell/expand_test.go−241
This diff is too big to show here.
internal/shell/isolation_unix_test.go−143
This diff is too big to show here.
internal/shell/jq.go−342
This diff is too big to show here.
internal/shell/jq_test.go−212
This diff is too big to show here.
internal/shell/persist_message.go−44
This diff is too big to show here.
internal/shell/persist_message_test.go−69
This diff is too big to show here.
internal/shell/run.go−345
This diff is too big to show here.
internal/shell/run_test.go−364
This diff is too big to show here.
internal/shell/shell.go+50−47
This diff is too big to show here.
internal/shell/stream.go−52
This diff is too big to show here.
internal/skills/builtin/crush-config/SKILL.md−370
This diff is too big to show here.
internal/skills/builtin/crush-hooks/SKILL.md−209
This diff is too big to show here.
internal/skills/builtin/jq/SKILL.md−97
This diff is too big to show here.
internal/skills/catalog.go−154
This diff is too big to show here.
internal/skills/diagnostics_test.go−104
This diff is too big to show here.
internal/skills/embed.go−79
This diff is too big to show here.
internal/skills/manager.go−227
This diff is too big to show here.
internal/skills/manager_test.go−249
This diff is too big to show here.
internal/skills/skills.go−437
This diff is too big to show here.
internal/skills/skills_test.go−520
This diff is too big to show here.
internal/skills/tracker.go−86
This diff is too big to show here.
internal/skills/tracker_test.go−102
This diff is too big to show here.
internal/stringext/string.go+6−25
This diff is too big to show here.
internal/stringext/string_test.go−38
This diff is too big to show here.
internal/swagger/docs.go−3717
This diff is too big to show here.
internal/swagger/swagger.json−3692
This diff is too big to show here.
internal/swagger/swagger.yaml−2457
This diff is too big to show here.
internal/tui/components/anim/anim.go+447
This diff is too big to show here.
internal/tui/components/chat/chat.go+782
This diff is too big to show here.
internal/tui/components/chat/editor/editor.go+664
This diff is too big to show here.
internal/tui/components/chat/editor/keys.go+71
This diff is too big to show here.
internal/tui/components/chat/header/header.go+167
This diff is too big to show here.
internal/tui/components/chat/messages/messages.go+459
This diff is too big to show here.
internal/tui/components/chat/messages/renderer.go+1403
This diff is too big to show here.
internal/tui/components/chat/messages/tool.go+877
This diff is too big to show here.
internal/tui/components/chat/sidebar/sidebar.go+613
This diff is too big to show here.
internal/tui/components/chat/splash/keys.go+58
This diff is too big to show here.
internal/tui/components/chat/splash/splash.go+1072
This diff is too big to show here.
internal/tui/components/chat/todos/todos.go+67
This diff is too big to show here.
internal/tui/components/completions/completions.go+308
This diff is too big to show here.
internal/tui/components/completions/keys.go+72
This diff is too big to show here.
internal/tui/components/core/core.go+207
This diff is too big to show here.
internal/tui/components/core/layout/layout.go+27
This diff is too big to show here.
internal/tui/components/core/status/status.go+113
This diff is too big to show here.
internal/tui/components/core/status_test.go+144
This diff is too big to show here.
internal/tui/components/core/testdata/TestStatus/AllFieldsWithExtraContent.golden+1
This diff is too big to show here.
internal/tui/components/core/testdata/TestStatus/Default.golden+1
This diff is too big to show here.
internal/tui/components/core/testdata/TestStatus/EmptyDescription.golden+1
This diff is too big to show here.
internal/tui/components/core/testdata/TestStatus/LongDescription.golden+1
This diff is too big to show here.
internal/tui/components/core/testdata/TestStatus/NarrowWidth.golden+1
This diff is too big to show here.
internal/tui/components/core/testdata/TestStatus/NoIcon.golden+1
This diff is too big to show here.
internal/tui/components/core/testdata/TestStatus/VeryNarrowWidth.golden+1
This diff is too big to show here.
internal/tui/components/core/testdata/TestStatus/WithColors.golden+1
This diff is too big to show here.
internal/tui/components/core/testdata/TestStatus/WithCustomIcon.golden+1
This diff is too big to show here.
internal/tui/components/core/testdata/TestStatus/WithExtraContent.golden+1
This diff is too big to show here.
internal/tui/components/core/testdata/TestStatusTruncation/Width20.golden+1
This diff is too big to show here.
internal/tui/components/core/testdata/TestStatusTruncation/Width30.golden+1
This diff is too big to show here.
internal/tui/components/core/testdata/TestStatusTruncation/Width40.golden+1
This diff is too big to show here.
internal/tui/components/core/testdata/TestStatusTruncation/Width50.golden+1
This diff is too big to show here.
internal/tui/components/core/testdata/TestStatusTruncation/Width60.golden+1
This diff is too big to show here.
internal/tui/components/dialogs/claude/method.go+115
This diff is too big to show here.
internal/tui/components/dialogs/claude/oauth.go+267
This diff is too big to show here.
internal/tui/components/dialogs/commands/arguments.go+245
This diff is too big to show here.
internal/tui/components/dialogs/commands/commands.go+481
This diff is too big to show here.
internal/tui/components/dialogs/commands/keys.go+133
This diff is too big to show here.
internal/tui/components/dialogs/copilot/device_flow.go+281
This diff is too big to show here.
internal/tui/components/dialogs/dialogs.go+165
This diff is too big to show here.
internal/tui/components/dialogs/filepicker/filepicker.go+260
This diff is too big to show here.
internal/tui/components/dialogs/filepicker/keys.go+80
This diff is too big to show here.
internal/tui/components/dialogs/hyper/device_flow.go+267
This diff is too big to show here.
internal/tui/components/dialogs/keys.go+43
This diff is too big to show here.
internal/tui/components/dialogs/models/apikey.go+203
This diff is too big to show here.
internal/tui/components/dialogs/models/keys.go+177
This diff is too big to show here.
internal/tui/components/dialogs/models/list.go+335
This diff is too big to show here.
internal/tui/components/dialogs/models/list_recent_test.go+369
This diff is too big to show here.
internal/tui/components/dialogs/models/models.go+668
This diff is too big to show here.
internal/tui/components/dialogs/permissions/keys.go+113
This diff is too big to show here.
internal/tui/components/dialogs/permissions/permissions.go+899
This diff is too big to show here.
internal/tui/components/dialogs/quit/keys.go+75
This diff is too big to show here.
internal/tui/components/dialogs/quit/quit.go+120
This diff is too big to show here.
internal/tui/components/dialogs/reasoning/reasoning.go+264
This diff is too big to show here.
internal/tui/components/dialogs/sessions/keys.go+67
This diff is too big to show here.
internal/tui/components/dialogs/sessions/sessions.go+181
This diff is too big to show here.
internal/tui/components/files/files.go+146
This diff is too big to show here.
internal/tui/components/image/image.go+86
This diff is too big to show here.
internal/tui/components/image/load.go+169
This diff is too big to show here.
internal/tui/components/logo/logo.go+346
This diff is too big to show here.
internal/tui/components/logo/rand.go+24
This diff is too big to show here.
internal/tui/components/lsp/lsp.go+161
This diff is too big to show here.
internal/tui/components/mcp/mcp.go+138
This diff is too big to show here.
internal/tui/exp/diffview/Taskfile.yaml
This diff is too big to show here.
internal/tui/exp/diffview/chroma.go+57
This diff is too big to show here.
internal/tui/exp/diffview/diffview.go+6−55
This diff is too big to show here.
internal/tui/exp/diffview/diffview_test.go+19−1
This diff is too big to show here.
internal/tui/exp/diffview/split.go
This diff is too big to show here.
internal/tui/exp/diffview/style.go+124
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDefault.after
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDefault.before
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Split/CustomContextLines/DarkMode.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Split/CustomContextLines/LightMode.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Split/Default/DarkMode.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Split/Default/LightMode.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Split/LargeWidth/DarkMode.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Split/LargeWidth/LightMode.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Split/MultipleHunks/DarkMode.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Split/MultipleHunks/LightMode.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Split/Narrow/DarkMode.golden+4
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Split/Narrow/LightMode.golden+4
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Split/NoLineNumbers/DarkMode.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Split/NoLineNumbers/LightMode.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Split/NoSyntaxHighlight/DarkMode.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Split/NoSyntaxHighlight/LightMode.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Split/SmallWidth/DarkMode.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Split/SmallWidth/LightMode.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Unified/CustomContextLines/DarkMode.golden+17
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Unified/CustomContextLines/LightMode.golden+17
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Unified/Default/DarkMode.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Unified/Default/LightMode.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Unified/LargeWidth/DarkMode.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Unified/LargeWidth/LightMode.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Unified/MultipleHunks/DarkMode.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Unified/MultipleHunks/LightMode.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Unified/Narrow/DarkMode.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Unified/Narrow/LightMode.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Unified/NoLineNumbers/DarkMode.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Unified/NoLineNumbers/LightMode.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Unified/NoSyntaxHighlight/DarkMode.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Unified/NoSyntaxHighlight/LightMode.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Unified/SmallWidth/DarkMode.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffView/Unified/SmallWidth/LightMode.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Split/HeightOf001.golden
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Split/HeightOf002.golden+2
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Split/HeightOf003.golden+3
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Split/HeightOf004.golden+4
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Split/HeightOf005.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Split/HeightOf006.golden+6
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Split/HeightOf007.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Split/HeightOf008.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Split/HeightOf009.golden+9
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Split/HeightOf010.golden+10
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Split/HeightOf011.golden+11
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Split/HeightOf012.golden+12
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Split/HeightOf013.golden+13
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Split/HeightOf014.golden+14
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Split/HeightOf015.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Split/HeightOf016.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Split/HeightOf017.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Split/HeightOf018.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Split/HeightOf019.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Split/HeightOf020.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Unified/HeightOf001.golden
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Unified/HeightOf002.golden+2
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Unified/HeightOf003.golden+3
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Unified/HeightOf004.golden+4
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Unified/HeightOf005.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Unified/HeightOf006.golden+6
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Unified/HeightOf007.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Unified/HeightOf008.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Unified/HeightOf009.golden+9
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Unified/HeightOf010.golden+10
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Unified/HeightOf011.golden+11
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Unified/HeightOf012.golden+12
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Unified/HeightOf013.golden+13
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Unified/HeightOf014.golden+14
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Unified/HeightOf015.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Unified/HeightOf016.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Unified/HeightOf017.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Unified/HeightOf018.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Unified/HeightOf019.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewHeight/Unified/HeightOf020.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewLineBreakIssue/Split.golden+9
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewLineBreakIssue/Unified.golden+12
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewTabs/Split.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewTabs/Unified.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf001.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf002.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf003.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf004.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf005.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf006.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf007.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf008.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf009.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf010.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf011.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf012.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf013.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf014.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf015.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf016.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf017.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf018.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf019.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf020.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf021.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf022.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf023.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf024.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf025.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf026.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf027.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf028.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf029.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf030.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf031.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf032.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf033.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf034.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf035.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf036.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf037.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf038.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf039.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf040.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf041.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf042.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf043.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf044.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf045.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf046.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf047.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf048.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf049.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf050.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf051.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf052.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf053.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf054.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf055.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf056.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf057.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf058.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf059.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf060.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf061.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf062.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf063.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf064.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf065.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf066.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf067.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf068.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf069.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf070.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf071.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf072.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf073.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf074.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf075.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf076.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf077.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf078.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf079.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf080.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf081.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf082.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf083.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf084.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf085.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf086.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf087.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf088.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf089.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf090.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf091.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf092.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf093.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf094.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf095.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf096.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf097.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf098.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf099.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf100.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf101.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf102.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf103.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf104.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf105.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf106.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf107.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf108.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf109.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Split/WidthOf110.golden+15
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf001.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf002.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf003.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf004.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf005.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf006.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf007.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf008.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf009.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf010.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf011.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf012.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf013.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf014.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf015.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf016.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf017.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf018.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf019.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf020.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf021.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf022.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf023.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf024.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf025.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf026.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf027.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf028.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf029.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf030.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf031.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf032.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf033.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf034.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf035.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf036.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf037.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf038.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf039.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf040.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf041.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf042.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf043.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf044.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf045.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf046.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf047.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf048.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf049.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf050.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf051.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf052.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf053.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf054.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf055.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf056.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf057.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf058.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf059.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewWidth/Unified/WidthOf060.golden+16
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf00.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf01.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf02.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf03.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf04.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf05.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf06.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf07.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf08.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf09.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf10.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf11.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf12.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf13.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf14.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf15.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf16.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf17.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf18.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf19.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf20.golden+7
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf00.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf01.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf02.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf03.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf04.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf05.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf06.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf07.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf08.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf09.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf10.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf11.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf12.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf13.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf14.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf15.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf16.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf17.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf18.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf19.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf20.golden+8
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf00.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf01.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf02.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf03.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf04.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf05.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf06.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf07.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf08.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf09.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf10.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf11.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf12.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf13.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf14.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf15.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf16.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf00.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf01.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf02.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf03.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf04.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf05.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf06.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf07.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf08.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf09.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf10.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf11.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf12.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf13.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf14.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf15.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf16.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf00.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf01.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf02.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf03.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf04.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf05.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf06.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf07.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf08.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf09.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf10.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf11.golden+4
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf12.golden+3
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf13.golden+2
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf14.golden+1
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf15.golden
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf16.golden
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf00.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf01.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf02.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf03.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf04.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf05.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf06.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf07.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf08.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf09.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf10.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf11.golden+5
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf12.golden+4
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf13.golden+3
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf14.golden+2
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf15.golden+1
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf16.golden
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestLineBreakIssue.after
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestLineBreakIssue.before
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestMultipleHunks.after
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestMultipleHunks.before
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestNarrow.after
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestNarrow.before
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestTabs.after
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestTabs.before
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestUdiff/ToUnifiedDiff/DefaultContextLines/Content.golden
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestUdiff/ToUnifiedDiff/DefaultContextLines/JSON.golden
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestUdiff/ToUnifiedDiff/DefaultContextLinesPlusOne/Content.golden
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestUdiff/ToUnifiedDiff/DefaultContextLinesPlusOne/JSON.golden
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestUdiff/ToUnifiedDiff/DefaultContextLinesPlusTwo/Content.golden
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestUdiff/ToUnifiedDiff/DefaultContextLinesPlusTwo/JSON.golden
This diff is too big to show here.
internal/tui/exp/diffview/testdata/TestUdiff/Unified.golden
This diff is too big to show here.
internal/tui/exp/diffview/udiff_test.go+1−1
This diff is too big to show here.
internal/tui/exp/diffview/util.go+39
This diff is too big to show here.
internal/tui/exp/diffview/util_test.go
This diff is too big to show here.
internal/tui/exp/list/filterable.go+329
This diff is too big to show here.
internal/tui/exp/list/filterable_group.go+315
This diff is too big to show here.
internal/tui/exp/list/filterable_test.go+68
This diff is too big to show here.
internal/tui/exp/list/grouped.go+100
This diff is too big to show here.
internal/tui/exp/list/items.go+399
This diff is too big to show here.
internal/tui/exp/list/keys.go+76
This diff is too big to show here.
internal/tui/exp/list/list.go+1775
This diff is too big to show here.
internal/tui/exp/list/list_test.go+653
This diff is too big to show here.
internal/tui/exp/list/testdata/TestFilterableList/should_create_simple_filterable_list.golden+10
This diff is too big to show here.
internal/tui/exp/list/testdata/TestList/should_go_to_selected_item_at_the_beginning.golden+10
This diff is too big to show here.
internal/tui/exp/list/testdata/TestList/should_go_to_selected_item_at_the_beginning_backwards.golden+10
This diff is too big to show here.
internal/tui/exp/list/testdata/TestList/should_have_correct_positions_in_list_that_does_not_fits_the_items.golden+10
This diff is too big to show here.
internal/tui/exp/list/testdata/TestList/should_have_correct_positions_in_list_that_does_not_fits_the_items_and_has_multi_line_items.golden+10
This diff is too big to show here.
internal/tui/exp/list/testdata/TestList/should_have_correct_positions_in_list_that_does_not_fits_the_items_and_has_multi_line_items_backwards.golden+10
This diff is too big to show here.
internal/tui/exp/list/testdata/TestList/should_have_correct_positions_in_list_that_does_not_fits_the_items_backwards.golden+10
This diff is too big to show here.
internal/tui/exp/list/testdata/TestList/should_have_correct_positions_in_list_that_fits_the_items.golden+20
This diff is too big to show here.
internal/tui/exp/list/testdata/TestList/should_have_correct_positions_in_list_that_fits_the_items_backwards.golden+20
This diff is too big to show here.
internal/tui/exp/list/testdata/TestListMovement/should_move_viewport_down.golden+10
This diff is too big to show here.
internal/tui/exp/list/testdata/TestListMovement/should_move_viewport_down_and_up.golden+10
This diff is too big to show here.
internal/tui/exp/list/testdata/TestListMovement/should_move_viewport_up.golden+10
This diff is too big to show here.
internal/tui/exp/list/testdata/TestListMovement/should_move_viewport_up_and_down.golden+10
This diff is too big to show here.
internal/tui/exp/list/testdata/TestListMovement/should_not_change_offset_when_new_items_are_appended_and_we_are_at_the_bottom_in_backwards_list.golden+10
This diff is too big to show here.
internal/tui/exp/list/testdata/TestListMovement/should_not_change_offset_when_new_items_are_prepended_and_we_are_at_the_top_in_forward_list.golden+10
This diff is too big to show here.
internal/tui/exp/list/testdata/TestListMovement/should_stay_at_the_position_it_is_if_an_item_is_appended_and_we_are_in_forward_list.golden+10
This diff is too big to show here.
internal/tui/exp/list/testdata/TestListMovement/should_stay_at_the_position_it_is_if_an_item_is_prepended_and_we_are_in_backwards_list.golden+10
This diff is too big to show here.
internal/tui/exp/list/testdata/TestListMovement/should_stay_at_the_position_it_is_when_new_items_are_added_but_we_moved_down_in_forward_list.golden+10
This diff is too big to show here.
internal/tui/exp/list/testdata/TestListMovement/should_stay_at_the_position_it_is_when_new_items_are_added_but_we_moved_up_in_backwards_list.golden+10
This diff is too big to show here.
internal/tui/exp/list/testdata/TestListMovement/should_stay_at_the_position_it_is_when_the_hight_of_an_item_above_is_decreases_in_forward_list.golden+10
This diff is too big to show here.
internal/tui/exp/list/testdata/TestListMovement/should_stay_at_the_position_it_is_when_the_hight_of_an_item_above_is_increased_in_backwards_list.golden+10
This diff is too big to show here.
internal/tui/exp/list/testdata/TestListMovement/should_stay_at_the_position_it_is_when_the_hight_of_an_item_above_is_increased_in_forward_list.golden+10
This diff is too big to show here.
internal/tui/exp/list/testdata/TestListMovement/should_stay_at_the_position_it_is_when_the_hight_of_an_item_below_is_decreases_in_backwards_list.golden+10
This diff is too big to show here.
internal/tui/exp/list/testdata/TestListMovement/should_stay_at_the_position_it_is_when_the_hight_of_an_item_below_is_increased_in_backwards_list.golden+10
This diff is too big to show here.
internal/tui/exp/list/testdata/TestListMovement/should_stay_at_the_position_it_is_when_the_hight_of_an_item_below_is_increased_in_forward_list.golden+10
This diff is too big to show here.
internal/tui/highlight/highlight.go+54
This diff is too big to show here.
internal/tui/keys.go+45
This diff is too big to show here.
internal/tui/page/chat/chat.go+1449
This diff is too big to show here.
internal/tui/page/chat/keys.go+53
This diff is too big to show here.
internal/tui/page/chat/pills.go+125
This diff is too big to show here.
internal/tui/page/page.go+8
This diff is too big to show here.
internal/tui/styles/charmtone.go+83
This diff is too big to show here.
internal/tui/styles/chroma.go+79
This diff is too big to show here.
internal/tui/styles/icons.go+48
This diff is too big to show here.
internal/tui/styles/markdown.go+205
This diff is too big to show here.
internal/tui/styles/theme.go+703
This diff is too big to show here.
internal/tui/tui.go+710
This diff is too big to show here.
internal/tui/util/shell.go+15
This diff is too big to show here.
internal/tui/util/util.go+45
This diff is too big to show here.
internal/ui/AGENTS.md−200
This diff is too big to show here.
internal/ui/anim/anim.go−494
This diff is too big to show here.
internal/ui/attachments/attachments.go−152
This diff is too big to show here.
internal/ui/chat/agent.go−393
This diff is too big to show here.
internal/ui/chat/applyhighlight_callback_test.go−207
This diff is too big to show here.
internal/ui/chat/assistant.go−904
This diff is too big to show here.
internal/ui/chat/assistant_render_test.go−78
This diff is too big to show here.
internal/ui/chat/assistant_section_cache_test.go−464
This diff is too big to show here.
internal/ui/chat/assistant_test.go−142
This diff is too big to show here.
internal/ui/chat/assistant_thinking_bench_test.go−69
This diff is too big to show here.
internal/ui/chat/assistant_thinking_bound_test.go−105
This diff is too big to show here.
internal/ui/chat/assistant_thinking_window_test.go−500
This diff is too big to show here.
internal/ui/chat/bash.go−251
This diff is too big to show here.
internal/ui/chat/diagnostics.go−68
This diff is too big to show here.
internal/ui/chat/docker_mcp.go−283
This diff is too big to show here.
internal/ui/chat/fetch.go−192
This diff is too big to show here.
internal/ui/chat/file.go−371
This diff is too big to show here.
internal/ui/chat/generic.go−73
This diff is too big to show here.
internal/ui/chat/incremental_glamour_test.go−981
This diff is too big to show here.
internal/ui/chat/lsp_restart.go−62
This diff is too big to show here.
internal/ui/chat/mcp.go−78
This diff is too big to show here.
internal/ui/chat/mcp_test.go−406
This diff is too big to show here.
internal/ui/chat/messages.go−440
This diff is too big to show here.
internal/ui/chat/prefix_cache_test.go−197
This diff is too big to show here.
internal/ui/chat/references.go−63
This diff is too big to show here.
internal/ui/chat/search.go−256
This diff is too big to show here.
internal/ui/chat/shell.go−358
This diff is too big to show here.
internal/ui/chat/shell_test.go−59
This diff is too big to show here.
internal/ui/chat/streaming_markdown.go−721
This diff is too big to show here.
internal/ui/chat/todos.go−192
This diff is too big to show here.
internal/ui/chat/tool_result_content.go−60
This diff is too big to show here.
internal/ui/chat/tool_result_content_test.go−116
This diff is too big to show here.
internal/ui/chat/tools.go−1751
This diff is too big to show here.
internal/ui/chat/unified_diff.go−170
This diff is too big to show here.
internal/ui/chat/user.go−181
This diff is too big to show here.
internal/ui/chat/version_bump_test.go−567
This diff is too big to show here.
internal/ui/common/ansi16.go−128
This diff is too big to show here.
internal/ui/common/ansi16_test.go−106
This diff is too big to show here.
internal/ui/common/button.go−69
This diff is too big to show here.
internal/ui/common/capabilities.go−131
This diff is too big to show here.
internal/ui/common/common.go−121
This diff is too big to show here.
internal/ui/common/diff.go−35
This diff is too big to show here.
internal/ui/common/elements.go−242
This diff is too big to show here.
internal/ui/common/elements_test.go−35
This diff is too big to show here.
internal/ui/common/highlight.go−106
This diff is too big to show here.
internal/ui/common/interface.go−20
This diff is too big to show here.
internal/ui/common/markdown.go−139
This diff is too big to show here.
internal/ui/common/scrollbar.go−48
This diff is too big to show here.
internal/ui/completions/completions.go−434
This diff is too big to show here.
internal/ui/completions/completions_test.go−108
This diff is too big to show here.
internal/ui/completions/item.go−225
This diff is too big to show here.
internal/ui/completions/keys.go−74
This diff is too big to show here.
internal/ui/completions/version_bump_test.go−85
This diff is too big to show here.
internal/ui/dialog/actions.go−187
This diff is too big to show here.
internal/ui/dialog/api_key_input.go−367
This diff is too big to show here.
internal/ui/dialog/arguments.go−406
This diff is too big to show here.
internal/ui/dialog/commands.go−453
This diff is too big to show here.
internal/ui/dialog/commands_item.go−136
This diff is too big to show here.
internal/ui/dialog/common.go−171
This diff is too big to show here.
internal/ui/dialog/dialog.go−296
This diff is too big to show here.
internal/ui/dialog/filepicker.go−321
This diff is too big to show here.
internal/ui/dialog/models.go−519
This diff is too big to show here.
internal/ui/dialog/models_item.go−157
This diff is too big to show here.
internal/ui/dialog/models_list.go−275
This diff is too big to show here.
internal/ui/dialog/notifications.go−310
This diff is too big to show here.
internal/ui/dialog/oauth.go−378
This diff is too big to show here.
internal/ui/dialog/oauth_copilot.go−78
This diff is too big to show here.
internal/ui/dialog/oauth_hyper.go−96
This diff is too big to show here.
internal/ui/dialog/overlay_test.go−189
This diff is too big to show here.
internal/ui/dialog/permissions.go−859
This diff is too big to show here.
internal/ui/dialog/permissions_test.go−99
This diff is too big to show here.
internal/ui/dialog/quit.go−133
This diff is too big to show here.
internal/ui/dialog/reasoning.go−318
This diff is too big to show here.
internal/ui/dialog/sessions.go−473
This diff is too big to show here.
internal/ui/dialog/sessions_item.go−294
This diff is too big to show here.
internal/ui/dialog/version_bump_test.go−219
This diff is too big to show here.
internal/ui/difftastic/difftastic.go−60
This diff is too big to show here.
internal/ui/diffview/style.go−143
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Split/CustomContextLines/DarkMode.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Split/CustomContextLines/LightMode.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Split/Default/DarkMode.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Split/Default/LightMode.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Split/LargeWidth/DarkMode.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Split/LargeWidth/LightMode.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Split/MultipleHunks/DarkMode.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Split/MultipleHunks/LightMode.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Split/Narrow/DarkMode.golden−4
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Split/Narrow/LightMode.golden−4
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Split/NoLineNumbers/DarkMode.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Split/NoLineNumbers/LightMode.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Split/NoSyntaxHighlight/DarkMode.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Split/NoSyntaxHighlight/LightMode.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Split/SmallWidth/DarkMode.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Split/SmallWidth/LightMode.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Unified/CustomContextLines/DarkMode.golden−17
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Unified/CustomContextLines/LightMode.golden−17
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Unified/Default/DarkMode.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Unified/Default/LightMode.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Unified/LargeWidth/DarkMode.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Unified/LargeWidth/LightMode.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Unified/MultipleHunks/DarkMode.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Unified/MultipleHunks/LightMode.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Unified/Narrow/DarkMode.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Unified/Narrow/LightMode.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Unified/NoLineNumbers/DarkMode.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Unified/NoLineNumbers/LightMode.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Unified/NoSyntaxHighlight/DarkMode.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Unified/NoSyntaxHighlight/LightMode.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Unified/SmallWidth/DarkMode.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffView/Unified/SmallWidth/LightMode.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Split/HeightOf002.golden−2
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Split/HeightOf003.golden−3
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Split/HeightOf004.golden−4
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Split/HeightOf005.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Split/HeightOf006.golden−6
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Split/HeightOf007.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Split/HeightOf008.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Split/HeightOf009.golden−9
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Split/HeightOf010.golden−10
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Split/HeightOf011.golden−11
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Split/HeightOf012.golden−12
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Split/HeightOf013.golden−13
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Split/HeightOf014.golden−14
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Split/HeightOf015.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Split/HeightOf016.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Split/HeightOf017.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Split/HeightOf018.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Split/HeightOf019.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Split/HeightOf020.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Unified/HeightOf002.golden−2
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Unified/HeightOf003.golden−3
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Unified/HeightOf004.golden−4
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Unified/HeightOf005.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Unified/HeightOf006.golden−6
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Unified/HeightOf007.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Unified/HeightOf008.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Unified/HeightOf009.golden−9
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Unified/HeightOf010.golden−10
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Unified/HeightOf011.golden−11
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Unified/HeightOf012.golden−12
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Unified/HeightOf013.golden−13
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Unified/HeightOf014.golden−14
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Unified/HeightOf015.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Unified/HeightOf016.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Unified/HeightOf017.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Unified/HeightOf018.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Unified/HeightOf019.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewHeight/Unified/HeightOf020.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewLineBreakIssue/Split.golden−9
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewLineBreakIssue/Unified.golden−12
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewTabs/Split.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewTabs/Unified.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf001.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf002.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf003.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf004.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf005.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf006.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf007.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf008.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf009.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf010.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf011.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf012.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf013.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf014.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf015.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf016.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf017.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf018.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf019.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf020.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf021.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf022.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf023.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf024.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf025.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf026.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf027.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf028.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf029.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf030.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf031.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf032.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf033.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf034.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf035.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf036.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf037.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf038.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf039.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf040.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf041.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf042.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf043.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf044.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf045.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf046.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf047.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf048.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf049.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf050.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf051.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf052.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf053.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf054.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf055.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf056.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf057.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf058.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf059.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf060.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf061.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf062.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf063.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf064.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf065.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf066.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf067.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf068.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf069.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf070.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf071.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf072.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf073.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf074.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf075.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf076.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf077.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf078.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf079.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf080.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf081.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf082.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf083.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf084.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf085.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf086.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf087.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf088.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf089.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf090.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf091.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf092.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf093.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf094.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf095.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf096.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf097.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf098.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf099.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf100.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf101.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf102.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf103.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf104.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf105.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf106.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf107.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf108.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf109.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Split/WidthOf110.golden−15
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf001.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf002.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf003.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf004.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf005.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf006.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf007.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf008.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf009.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf010.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf011.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf012.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf013.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf014.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf015.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf016.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf017.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf018.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf019.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf020.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf021.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf022.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf023.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf024.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf025.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf026.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf027.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf028.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf029.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf030.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf031.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf032.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf033.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf034.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf035.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf036.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf037.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf038.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf039.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf040.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf041.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf042.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf043.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf044.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf045.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf046.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf047.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf048.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf049.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf050.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf051.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf052.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf053.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf054.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf055.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf056.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf057.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf058.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf059.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewWidth/Unified/WidthOf060.golden−16
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf00.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf01.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf02.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf03.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf04.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf05.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf06.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf07.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf08.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf09.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf10.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf11.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf12.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf13.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf14.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf15.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf16.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf17.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf18.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf19.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Split/XOffsetOf20.golden−7
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf00.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf01.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf02.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf03.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf04.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf05.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf06.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf07.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf08.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf09.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf10.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf11.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf12.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf13.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf14.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf15.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf16.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf17.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf18.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf19.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewXOffset/Unified/XOffsetOf20.golden−8
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf00.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf01.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf02.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf03.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf04.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf05.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf06.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf07.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf08.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf09.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf10.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf11.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf12.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf13.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf14.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf15.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Split/YOffsetOf16.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf00.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf01.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf02.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf03.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf04.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf05.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf06.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf07.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf08.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf09.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf10.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf11.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf12.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf13.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf14.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf15.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffset/Unified/YOffsetOf16.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf00.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf01.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf02.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf03.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf04.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf05.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf06.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf07.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf08.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf09.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf10.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf11.golden−4
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf12.golden−3
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf13.golden−2
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Split/YOffsetOf14.golden−1
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf00.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf01.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf02.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf03.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf04.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf05.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf06.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf07.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf08.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf09.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf10.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf11.golden−5
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf12.golden−4
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf13.golden−3
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf14.golden−2
This diff is too big to show here.
internal/ui/diffview/testdata/TestDiffViewYOffsetInfinite/Unified/YOffsetOf15.golden−1
This diff is too big to show here.
internal/ui/diffview/util.go−46
This diff is too big to show here.
internal/ui/image/image.go−288
This diff is too big to show here.
internal/ui/image/image_test.go−46
This diff is too big to show here.
internal/ui/list/filterable.go−157
This diff is too big to show here.
internal/ui/list/focus.go−13
This diff is too big to show here.
internal/ui/list/highlight.go−212
This diff is too big to show here.
internal/ui/list/item.go−126
This diff is too big to show here.
internal/ui/list/list.go−928
This diff is too big to show here.
internal/ui/list/list_test.go−770
This diff is too big to show here.
internal/ui/logo/example/main.go−49
This diff is too big to show here.
internal/ui/logo/letterforms.go−419
This diff is too big to show here.
internal/ui/logo/logo.go−168
This diff is too big to show here.
internal/ui/logo/rand.go−24
This diff is too big to show here.
internal/ui/model/chat.go−1166
This diff is too big to show here.
internal/ui/model/chat_draw_cache_test.go−334
This diff is too big to show here.
internal/ui/model/chat_expand_test.go−55
This diff is too big to show here.
internal/ui/model/filter.go−108
This diff is too big to show here.
internal/ui/model/filter_test.go−162
This diff is too big to show here.
internal/ui/model/header.go−264
This diff is too big to show here.
internal/ui/model/history.go−200
This diff is too big to show here.
internal/ui/model/keys.go−285
This diff is too big to show here.
internal/ui/model/landing.go−126
This diff is too big to show here.
internal/ui/model/layout_test.go−228
This diff is too big to show here.
internal/ui/model/lsp.go−147
This diff is too big to show here.
internal/ui/model/mcp.go−114
This diff is too big to show here.
internal/ui/model/onboarding.go−116
This diff is too big to show here.
internal/ui/model/permission_test.go−96
This diff is too big to show here.
internal/ui/model/pills.go−363
This diff is too big to show here.
internal/ui/model/session.go−272
This diff is too big to show here.
internal/ui/model/session_test.go−142
This diff is too big to show here.
internal/ui/model/sidebar.go−369
This diff is too big to show here.
internal/ui/model/skills.go−155
This diff is too big to show here.
internal/ui/model/skills_test.go−81
This diff is too big to show here.
internal/ui/model/status.go−123
This diff is too big to show here.
internal/ui/model/ui.go−4564
This diff is too big to show here.
internal/ui/model/ui_test.go−95
This diff is too big to show here.
internal/ui/notification/bell.go−27
This diff is too big to show here.
internal/ui/notification/crush-icon-solo.png
This diff is too big to show here.
internal/ui/notification/crush-icon.png
This diff is too big to show here.
internal/ui/notification/icon_darwin.go−11
This diff is too big to show here.
internal/ui/notification/icon_other.go−10
This diff is too big to show here.
internal/ui/notification/native.go−52
This diff is too big to show here.
internal/ui/notification/noop.go−12
This diff is too big to show here.
internal/ui/notification/notification.go−35
This diff is too big to show here.
internal/ui/notification/notification_test.go−213
This diff is too big to show here.
internal/ui/notification/osc.go−135
This diff is too big to show here.
internal/ui/styles/grad.go−119
This diff is too big to show here.
internal/ui/styles/quickstyle.go−989
This diff is too big to show here.
internal/ui/styles/styles.go−649
This diff is too big to show here.
internal/ui/styles/themes.go−235
This diff is too big to show here.
internal/ui/util/util.go−96
This diff is too big to show here.
internal/ui/xchroma/chroma.go−70
This diff is too big to show here.
internal/uicmd/uicmd.go+313
This diff is too big to show here.
internal/uiutil/uiutil.go+82
This diff is too big to show here.
internal/update/update.go+1−1
This diff is too big to show here.
internal/version/version.go+8−39
This diff is too big to show here.
internal/workspace/app_workspace.go−464
This diff is too big to show here.
internal/workspace/client_workspace.go−964
This diff is too big to show here.
internal/workspace/client_workspace_test.go−213
This diff is too big to show here.
internal/workspace/export_test.go−14
This diff is too big to show here.
internal/workspace/multiclient_integration_test.go−176
This diff is too big to show here.
internal/workspace/workspace.go−171
This diff is too big to show here.
main.go−11
This diff is too big to show here.
schema.json+29−194
This diff is too big to show here.
scripts/check_log_capitalization.sh−5
This diff is too big to show here.
vendor/charm.land/bubbles/v2/LICENSE−21
This diff is too big to show here.
vendor/charm.land/bubbles/v2/cursor/cursor.go−241
This diff is too big to show here.
vendor/charm.land/bubbles/v2/filepicker/filepicker.go−529
This diff is too big to show here.
vendor/charm.land/bubbles/v2/filepicker/hidden_unix.go−11
This diff is too big to show here.
vendor/charm.land/bubbles/v2/filepicker/hidden_windows.go−21
This diff is too big to show here.
vendor/charm.land/bubbles/v2/help/help.go−253
This diff is too big to show here.
vendor/charm.land/bubbles/v2/internal/memoization/memoization.go−125
This diff is too big to show here.
vendor/charm.land/bubbles/v2/internal/runeutil/runeutil.go−102
This diff is too big to show here.
vendor/charm.land/bubbles/v2/key/key.go−140
This diff is too big to show here.
vendor/charm.land/bubbles/v2/spinner/spinner.go−211
This diff is too big to show here.
vendor/charm.land/bubbles/v2/textarea/textarea.go−1897
This diff is too big to show here.
vendor/charm.land/bubbles/v2/textinput/styles.go−96
This diff is too big to show here.
vendor/charm.land/bubbles/v2/textinput/textinput.go−968
This diff is too big to show here.
vendor/charm.land/bubbles/v2/viewport/highlight.go−141
This diff is too big to show here.
vendor/charm.land/bubbles/v2/viewport/keymap.go−58
This diff is too big to show here.
vendor/charm.land/bubbles/v2/viewport/viewport.go−765
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/.gitattributes−1
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/.gitignore−23
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/.golangci.yml−47
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/.goreleaser.yml−5
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/LICENSE−21
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/README.md−402
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/Taskfile.yaml−38
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/UPGRADE_GUIDE_V2.md−573
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/clipboard.go−70
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/color.go−91
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/commands.go−175
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/cursed_renderer.go−860
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/cursor.go−28
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/environ.go−34
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/exec.go−129
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/focus.go−9
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/input.go−54
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/key.go−371
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/keyboard.go−59
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/logging.go−53
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/mod.go−27
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/mouse.go−144
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/nil_renderer.go−53
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/options.go−168
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/paste.go−20
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/profile.go−15
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/raw.go−37
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/renderer.go−104
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/screen.go−68
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/signals_unix.go−33
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/signals_windows.go−10
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/tea.go−1439
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/termcap.go−48
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/termios_bsd.go−13
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/termios_other.go−8
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/termios_unix.go−14
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/termios_windows.go−11
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/tty.go−136
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/tty_unix.go−47
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/tty_windows.go−64
This diff is too big to show here.
vendor/charm.land/bubbletea/v2/xterm.go−22
This diff is too big to show here.
vendor/charm.land/catwalk/LICENSE−21
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/aihubmix.json−3746
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/alibaba-singapore.json−141
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/alibaba-united-states.json−45
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/anthropic.json−183
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/avian.json−125
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/azure.json−225
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/baseten.json−187
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/bedrock-europe.json−115
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/bedrock-united-states.json−143
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/cerebras.json−42
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/chutes.json−227
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/copilot.json−310
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/cortecs.json−1697
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/deepseek.json−45
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/fireworks.json−171
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/gemini.json−91
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/groq.json−36
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/huggingface.json−267
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/ionet.json−335
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/kimi.json−23
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/minimax-china.json−91
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/minimax.json−91
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/moonshot.json−131
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/nebius.json−419
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/neuralwatt.json−155
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/openai.json−352
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/opencode-go.json−351
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/opencode-zen.json−908
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/openrouter.json−3831
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/qiniucloud.json−179
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/scaleway.json−141
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/synthetic.json−197
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/venice.json−1173
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/vercel.json−3072
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/vertexai.json−170
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/xai.json−59
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/zai.json−136
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/zhipu-coding.json−136
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/configs/zhipu.json−120
This diff is too big to show here.
vendor/charm.land/catwalk/internal/providers/providers.go−349
This diff is too big to show here.
vendor/charm.land/catwalk/pkg/catwalk/client.go−79
This diff is too big to show here.
vendor/charm.land/catwalk/pkg/catwalk/pkg.go−2
This diff is too big to show here.
vendor/charm.land/catwalk/pkg/catwalk/provider.go−157
This diff is too big to show here.
vendor/charm.land/catwalk/pkg/embedded/embedded.go−13
This diff is too big to show here.
vendor/charm.land/fang/v2/.gitignore−3
This diff is too big to show here.
vendor/charm.land/fang/v2/.golangci.yml−47
This diff is too big to show here.
vendor/charm.land/fang/v2/.goreleaser.yml−5
This diff is too big to show here.
vendor/charm.land/fang/v2/LICENSE.md−21
This diff is too big to show here.
vendor/charm.land/fang/v2/README.md−92
This diff is too big to show here.
vendor/charm.land/fang/v2/Taskfile.yml−7
This diff is too big to show here.
vendor/charm.land/fang/v2/UPGRADE_GUIDE_V2.md−127
This diff is too big to show here.
vendor/charm.land/fang/v2/fang.go−208
This diff is too big to show here.
vendor/charm.land/fang/v2/fang_other.go−10
This diff is too big to show here.
vendor/charm.land/fang/v2/fang_windows.go−30
This diff is too big to show here.
vendor/charm.land/fang/v2/help.go−482
This diff is too big to show here.
vendor/charm.land/fang/v2/theme.go−222
This diff is too big to show here.
vendor/charm.land/fantasy/.editorconfig−18
This diff is too big to show here.
vendor/charm.land/fantasy/.gitattributes−1
This diff is too big to show here.
vendor/charm.land/fantasy/.gitignore−42
This diff is too big to show here.
vendor/charm.land/fantasy/.golangci.yml−44
This diff is too big to show here.
vendor/charm.land/fantasy/.goreleaser.yml−6
This diff is too big to show here.
vendor/charm.land/fantasy/AGENTS.md−29
This diff is too big to show here.
vendor/charm.land/fantasy/LICENSE−177
This diff is too big to show here.
vendor/charm.land/fantasy/NOTICE−13
This diff is too big to show here.
vendor/charm.land/fantasy/README.md−95
This diff is too big to show here.
vendor/charm.land/fantasy/Taskfile.yaml−45
This diff is too big to show here.
vendor/charm.land/fantasy/agent.go−1702
This diff is too big to show here.
vendor/charm.land/fantasy/content.go−625
This diff is too big to show here.
vendor/charm.land/fantasy/content_json.go−1046
This diff is too big to show here.
vendor/charm.land/fantasy/crush.json−6
This diff is too big to show here.
vendor/charm.land/fantasy/cspell.json−1
This diff is too big to show here.
vendor/charm.land/fantasy/doc.go−2
This diff is too big to show here.
vendor/charm.land/fantasy/errors.go−155
This diff is too big to show here.
vendor/charm.land/fantasy/jsonrepair/jsonrepair.go−1648
This diff is too big to show here.
vendor/charm.land/fantasy/model.go−261
This diff is too big to show here.
vendor/charm.land/fantasy/model_json.go−156
This diff is too big to show here.
vendor/charm.land/fantasy/object.go−236
This diff is too big to show here.
vendor/charm.land/fantasy/object/object.go−620
This diff is too big to show here.
vendor/charm.land/fantasy/provider.go−11
This diff is too big to show here.
vendor/charm.land/fantasy/provider_registry.go−106
This diff is too big to show here.
vendor/charm.land/fantasy/providers/anthropic/anthropic.go−1707
This diff is too big to show here.
vendor/charm.land/fantasy/providers/anthropic/bedrock.go−15
This diff is too big to show here.
vendor/charm.land/fantasy/providers/anthropic/call_useragent.go−14
This diff is too big to show here.
vendor/charm.land/fantasy/providers/anthropic/computer_use.go−427
This diff is too big to show here.
vendor/charm.land/fantasy/providers/anthropic/error.go−67
This diff is too big to show here.
vendor/charm.land/fantasy/providers/anthropic/google.go−11
This diff is too big to show here.
vendor/charm.land/fantasy/providers/anthropic/provider_options.go−283
This diff is too big to show here.
vendor/charm.land/fantasy/providers/anthropic/sanitize.go−33
This diff is too big to show here.
vendor/charm.land/fantasy/providers/azure/README.md−6
This diff is too big to show here.
vendor/charm.land/fantasy/providers/azure/azure.go−125
This diff is too big to show here.
vendor/charm.land/fantasy/providers/bedrock/README.md−10
This diff is too big to show here.
vendor/charm.land/fantasy/providers/bedrock/bedrock.go−87
This diff is too big to show here.
vendor/charm.land/fantasy/providers/google/README.md−63
This diff is too big to show here.
vendor/charm.land/fantasy/providers/google/auth.go−15
This diff is too big to show here.
vendor/charm.land/fantasy/providers/google/call_useragent.go−53
This diff is too big to show here.
vendor/charm.land/fantasy/providers/google/error.go−51
This diff is too big to show here.
vendor/charm.land/fantasy/providers/google/google.go−1488
This diff is too big to show here.
vendor/charm.land/fantasy/providers/google/provider_options.go−146
This diff is too big to show here.
vendor/charm.land/fantasy/providers/google/slice.go−11
This diff is too big to show here.
vendor/charm.land/fantasy/providers/internal/httpheaders/httpheaders.go−60
This diff is too big to show here.
vendor/charm.land/fantasy/providers/openai/call_useragent.go−31
This diff is too big to show here.
vendor/charm.land/fantasy/providers/openai/error.go−92
This diff is too big to show here.
vendor/charm.land/fantasy/providers/openai/language_model.go−990
This diff is too big to show here.
vendor/charm.land/fantasy/providers/openai/language_model_hooks.go−668
This diff is too big to show here.
vendor/charm.land/fantasy/providers/openai/openai.go−220
This diff is too big to show here.
vendor/charm.land/fantasy/providers/openai/provider_options.go−217
This diff is too big to show here.
vendor/charm.land/fantasy/providers/openai/responses_language_model.go−1678
This diff is too big to show here.
vendor/charm.land/fantasy/providers/openai/responses_options.go−395
This diff is too big to show here.
vendor/charm.land/fantasy/providers/openaicompat/language_model_hooks.go−516
This diff is too big to show here.
vendor/charm.land/fantasy/providers/openaicompat/openaicompat.go−140
This diff is too big to show here.
vendor/charm.land/fantasy/providers/openaicompat/provider_options.go−161
This diff is too big to show here.
vendor/charm.land/fantasy/providers/openrouter/language_model_hooks.go−1063
This diff is too big to show here.
vendor/charm.land/fantasy/providers/openrouter/openrouter.go−121
This diff is too big to show here.
vendor/charm.land/fantasy/providers/openrouter/provider_options.go−218
This diff is too big to show here.
vendor/charm.land/fantasy/providers/vercel/language_model_hooks.go−1074
This diff is too big to show here.
vendor/charm.land/fantasy/providers/vercel/provider_options.go−195
This diff is too big to show here.
vendor/charm.land/fantasy/providers/vercel/vercel.go−122
This diff is too big to show here.
vendor/charm.land/fantasy/retry.go−155
This diff is too big to show here.
vendor/charm.land/fantasy/schema/schema.go−442
This diff is too big to show here.
vendor/charm.land/fantasy/tool.go−176
This diff is too big to show here.
vendor/charm.land/fantasy/util.go−22
This diff is too big to show here.
vendor/charm.land/fantasy/version.go−12
This diff is too big to show here.
vendor/charm.land/fantasy/version.txt−1
This diff is too big to show here.
vendor/charm.land/glamour/v2/.editorconfig−18
This diff is too big to show here.
vendor/charm.land/glamour/v2/.gitattributes−2
This diff is too big to show here.
vendor/charm.land/glamour/v2/.gitignore−2
This diff is too big to show here.
vendor/charm.land/glamour/v2/.golangci.yml−44
This diff is too big to show here.
vendor/charm.land/glamour/v2/.goreleaser.yml−6
This diff is too big to show here.
vendor/charm.land/glamour/v2/CONTRIBUTING.md−23
This diff is too big to show here.
vendor/charm.land/glamour/v2/LICENSE−21
This diff is too big to show here.
vendor/charm.land/glamour/v2/README.md−129
This diff is too big to show here.
vendor/charm.land/glamour/v2/Taskfile.yml−25
This diff is too big to show here.
vendor/charm.land/glamour/v2/UPGRADE_GUIDE_V2.md−279
This diff is too big to show here.
vendor/charm.land/glamour/v2/ansi/ansi.go−3
This diff is too big to show here.
vendor/charm.land/glamour/v2/ansi/baseelement.go−157
This diff is too big to show here.
vendor/charm.land/glamour/v2/ansi/blockelement.go−66
This diff is too big to show here.
vendor/charm.land/glamour/v2/ansi/blockstack.go−95
This diff is too big to show here.
vendor/charm.land/glamour/v2/ansi/codeblock.go−151
This diff is too big to show here.
vendor/charm.land/glamour/v2/ansi/codespan.go−15
This diff is too big to show here.
vendor/charm.land/glamour/v2/ansi/context.go−38
This diff is too big to show here.
vendor/charm.land/glamour/v2/ansi/elements.go−481
This diff is too big to show here.
vendor/charm.land/glamour/v2/ansi/emphasis.go−47
This diff is too big to show here.
vendor/charm.land/glamour/v2/ansi/heading.go−80
This diff is too big to show here.
vendor/charm.land/glamour/v2/ansi/image.go−57
This diff is too big to show here.
vendor/charm.land/glamour/v2/ansi/link.go−112
This diff is too big to show here.
vendor/charm.land/glamour/v2/ansi/listitem.go−29
This diff is too big to show here.
vendor/charm.land/glamour/v2/ansi/margin.go−231
This diff is too big to show here.
vendor/charm.land/glamour/v2/ansi/paragraph.go−63
This diff is too big to show here.
vendor/charm.land/glamour/v2/ansi/renderer.go−166
This diff is too big to show here.
vendor/charm.land/glamour/v2/ansi/style.go−252
This diff is too big to show here.
vendor/charm.land/glamour/v2/ansi/table.go−206
This diff is too big to show here.
vendor/charm.land/glamour/v2/ansi/table_links.go−234
This diff is too big to show here.
vendor/charm.land/glamour/v2/ansi/task.go−27
This diff is too big to show here.
vendor/charm.land/glamour/v2/ansi/templatehelper.go−86
This diff is too big to show here.
vendor/charm.land/glamour/v2/examples.sh−19
This diff is too big to show here.
vendor/charm.land/glamour/v2/gallery.sh−23
This diff is too big to show here.
vendor/charm.land/glamour/v2/glamour.go−294
This diff is too big to show here.
vendor/charm.land/glamour/v2/internal/autolink/autolink.go−55
This diff is too big to show here.
vendor/charm.land/glamour/v2/styles/README.md−565
This diff is too big to show here.
vendor/charm.land/glamour/v2/styles/ascii.json−87
This diff is too big to show here.
vendor/charm.land/glamour/v2/styles/dark.json−191
This diff is too big to show here.
vendor/charm.land/glamour/v2/styles/dracula.go−216
This diff is too big to show here.
vendor/charm.land/glamour/v2/styles/dracula.json−188
This diff is too big to show here.
vendor/charm.land/glamour/v2/styles/light.json−190
This diff is too big to show here.
vendor/charm.land/glamour/v2/styles/notty.json−87
This diff is too big to show here.
vendor/charm.land/glamour/v2/styles/pink.json−90
This diff is too big to show here.
vendor/charm.land/glamour/v2/styles/styles.go−691
This diff is too big to show here.
vendor/charm.land/glamour/v2/styles/tokyo-night.go−209
This diff is too big to show here.
vendor/charm.land/glamour/v2/styles/tokyo-night.json−182
This diff is too big to show here.
vendor/charm.land/glamour/v2/styles/tokyo_night.json−182
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/.editorconfig−18
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/.gitattributes−1
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/.gitignore−3
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/.golangci.yml−50
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/.goreleaser.yml−5
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/LICENSE−21
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/README.md−996
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/Taskfile.yaml−24
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/UPGRADE_GUIDE_V2.md−504
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/align.go−82
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/ansi_unix.go−8
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/ansi_windows.go−30
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/blending.go−196
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/borders.go−587
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/canvas.go−88
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/color.go−359
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/get.go−657
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/join.go−175
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/layer.go−327
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/lipgloss.go−3
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/position.go−134
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/query.go−92
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/ranges.go−48
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/runes.go−43
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/set.go−932
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/size.go−40
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/style.go−637
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/table/resizing.go−489
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/table/rows.go−130
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/table/table.go−568
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/table/util.go−44
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/terminal.go−124
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/tree/children.go−100
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/tree/enumerator.go−74
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/tree/renderer.go−165
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/tree/tree.go−407
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/unset.go−359
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/whitespace.go−76
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/wrap.go−113
This diff is too big to show here.
vendor/charm.land/lipgloss/v2/writer.go−160
This diff is too big to show here.
vendor/charm.land/log/v2/.gitignore−17
This diff is too big to show here.
vendor/charm.land/log/v2/.golangci.yml−50
This diff is too big to show here.
vendor/charm.land/log/v2/.goreleaser.yml−6
This diff is too big to show here.
vendor/charm.land/log/v2/LICENSE−21
This diff is too big to show here.
vendor/charm.land/log/v2/README.md−367
This diff is too big to show here.
vendor/charm.land/log/v2/UPGRADE_GUIDE_V2.md−320
This diff is too big to show here.
vendor/charm.land/log/v2/context.go−23
This diff is too big to show here.
vendor/charm.land/log/v2/doc.go−3
This diff is too big to show here.
vendor/charm.land/log/v2/formatter.go−27
This diff is too big to show here.
vendor/charm.land/log/v2/json.go−157
This diff is too big to show here.
vendor/charm.land/log/v2/level.go−65
This diff is too big to show here.
vendor/charm.land/log/v2/logfmt.go−32
This diff is too big to show here.
vendor/charm.land/log/v2/logger.go−413
This diff is too big to show here.
vendor/charm.land/log/v2/logger_121.go−72
This diff is too big to show here.
vendor/charm.land/log/v2/logger_no121.go−69
This diff is too big to show here.
vendor/charm.land/log/v2/options.go−61
This diff is too big to show here.
vendor/charm.land/log/v2/pkg.go−248
This diff is too big to show here.
vendor/charm.land/log/v2/stdlog.go−67
This diff is too big to show here.
vendor/charm.land/log/v2/styles.go−83
This diff is too big to show here.
vendor/charm.land/log/v2/text.go−272
This diff is too big to show here.
vendor/charm.land/x/vcr/LICENSE−21
This diff is too big to show here.
vendor/charm.land/x/vcr/doc.go−3
This diff is too big to show here.
vendor/charm.land/x/vcr/hooks.go−33
This diff is too big to show here.
vendor/charm.land/x/vcr/marshaler.go−19
This diff is too big to show here.
vendor/charm.land/x/vcr/matcher.go−70
This diff is too big to show here.
vendor/charm.land/x/vcr/recorder.go−70
This diff is too big to show here.
vendor/cloud.google.com/go/LICENSE−202
This diff is too big to show here.
vendor/cloud.google.com/go/auth/CHANGES.md−483
This diff is too big to show here.
vendor/cloud.google.com/go/auth/LICENSE−202
This diff is too big to show here.
vendor/cloud.google.com/go/auth/README.md−40
This diff is too big to show here.
vendor/cloud.google.com/go/auth/auth.go−618
This diff is too big to show here.
vendor/cloud.google.com/go/auth/credentials/compute.go−102
This diff is too big to show here.
vendor/cloud.google.com/go/auth/credentials/detect.go−471
This diff is too big to show here.
vendor/cloud.google.com/go/auth/credentials/doc.go−45
This diff is too big to show here.
vendor/cloud.google.com/go/auth/credentials/filetypes.go−329
This diff is too big to show here.
vendor/cloud.google.com/go/auth/credentials/internal/externalaccount/aws_provider.go−531
This diff is too big to show here.
vendor/cloud.google.com/go/auth/credentials/internal/externalaccount/executable_provider.go−284
This diff is too big to show here.
vendor/cloud.google.com/go/auth/credentials/internal/externalaccount/externalaccount.go−431
This diff is too big to show here.
vendor/cloud.google.com/go/auth/credentials/internal/externalaccount/file_provider.go−78
This diff is too big to show here.
vendor/cloud.google.com/go/auth/credentials/internal/externalaccount/info.go−74
This diff is too big to show here.
vendor/cloud.google.com/go/auth/credentials/internal/externalaccount/programmatic_provider.go−30
This diff is too big to show here.
vendor/cloud.google.com/go/auth/credentials/internal/externalaccount/url_provider.go−93
This diff is too big to show here.
vendor/cloud.google.com/go/auth/credentials/internal/externalaccount/x509_provider.go−220
This diff is too big to show here.
vendor/cloud.google.com/go/auth/credentials/internal/externalaccountuser/externalaccountuser.go−115
This diff is too big to show here.
vendor/cloud.google.com/go/auth/credentials/internal/gdch/gdch.go−198
This diff is too big to show here.
vendor/cloud.google.com/go/auth/credentials/internal/impersonate/idtoken.go−105
This diff is too big to show here.
vendor/cloud.google.com/go/auth/credentials/internal/impersonate/impersonate.go−168
This diff is too big to show here.
vendor/cloud.google.com/go/auth/credentials/internal/stsexchange/sts_exchange.go−167
This diff is too big to show here.
vendor/cloud.google.com/go/auth/credentials/selfsignedjwt.go−89
This diff is too big to show here.
vendor/cloud.google.com/go/auth/grpctransport/dial_socketopt.go−62
This diff is too big to show here.
vendor/cloud.google.com/go/auth/grpctransport/directpath.go−177
This diff is too big to show here.
vendor/cloud.google.com/go/auth/grpctransport/grpctransport.go−675
This diff is too big to show here.
vendor/cloud.google.com/go/auth/grpctransport/pool.go−119
This diff is too big to show here.
vendor/cloud.google.com/go/auth/httptransport/httptransport.go−254
This diff is too big to show here.
vendor/cloud.google.com/go/auth/httptransport/transport.go−548
This diff is too big to show here.
vendor/cloud.google.com/go/auth/internal/compute/compute.go−65
This diff is too big to show here.
vendor/cloud.google.com/go/auth/internal/compute/manufacturer.go−22
This diff is too big to show here.
vendor/cloud.google.com/go/auth/internal/compute/manufacturer_linux.go−23
This diff is too big to show here.
vendor/cloud.google.com/go/auth/internal/compute/manufacturer_windows.go−46
This diff is too big to show here.
vendor/cloud.google.com/go/auth/internal/credsfile/credsfile.go−63
This diff is too big to show here.
vendor/cloud.google.com/go/auth/internal/credsfile/filetype.go−159
This diff is too big to show here.
vendor/cloud.google.com/go/auth/internal/credsfile/parse.go−99
This diff is too big to show here.
vendor/cloud.google.com/go/auth/internal/internal.go−285
This diff is too big to show here.
vendor/cloud.google.com/go/auth/internal/jwt/jwt.go−208
This diff is too big to show here.
vendor/cloud.google.com/go/auth/internal/retry/retry.go−117
This diff is too big to show here.
vendor/cloud.google.com/go/auth/internal/transport/cba.go−361
This diff is too big to show here.
vendor/cloud.google.com/go/auth/internal/transport/cert/default_cert.go−65
This diff is too big to show here.
vendor/cloud.google.com/go/auth/internal/transport/cert/enterprise_cert.go−54
This diff is too big to show here.
vendor/cloud.google.com/go/auth/internal/transport/cert/secureconnect_cert.go−124
This diff is too big to show here.
vendor/cloud.google.com/go/auth/internal/transport/cert/workload_cert.go−138
This diff is too big to show here.
vendor/cloud.google.com/go/auth/internal/transport/headers/headers.go−61
This diff is too big to show here.
vendor/cloud.google.com/go/auth/internal/transport/s2a.go−138
This diff is too big to show here.
vendor/cloud.google.com/go/auth/internal/transport/transport.go−137
This diff is too big to show here.
vendor/cloud.google.com/go/auth/internal/trustboundary/external_accounts_config_providers.go−100
This diff is too big to show here.
vendor/cloud.google.com/go/auth/internal/trustboundary/trust_boundary.go−392
This diff is too big to show here.
vendor/cloud.google.com/go/auth/internal/version.go−20
This diff is too big to show here.
vendor/cloud.google.com/go/auth/oauth2adapt/CHANGES.md−82
This diff is too big to show here.
vendor/cloud.google.com/go/auth/oauth2adapt/LICENSE−202
This diff is too big to show here.
vendor/cloud.google.com/go/auth/oauth2adapt/oauth2adapt.go−200
This diff is too big to show here.
vendor/cloud.google.com/go/auth/threelegged.go−382
This diff is too big to show here.
vendor/cloud.google.com/go/civil/civil.go−500
This diff is too big to show here.
vendor/cloud.google.com/go/compute/metadata/CHANGES.md−115
This diff is too big to show here.
vendor/cloud.google.com/go/compute/metadata/LICENSE−202
This diff is too big to show here.
vendor/cloud.google.com/go/compute/metadata/README.md−27
This diff is too big to show here.
vendor/cloud.google.com/go/compute/metadata/log.go−149
This diff is too big to show here.
vendor/cloud.google.com/go/compute/metadata/metadata.go−937
This diff is too big to show here.
vendor/cloud.google.com/go/compute/metadata/retry.go−117
This diff is too big to show here.
vendor/cloud.google.com/go/compute/metadata/retry_linux.go−31
This diff is too big to show here.
vendor/cloud.google.com/go/compute/metadata/syscheck.go−28
This diff is too big to show here.
vendor/cloud.google.com/go/compute/metadata/syscheck_linux.go−30
This diff is too big to show here.
vendor/cloud.google.com/go/compute/metadata/syscheck_windows.go−39
This diff is too big to show here.
vendor/git.sr.ht/~jackmordaunt/go-toast/.gitignore−1
This diff is too big to show here.
vendor/git.sr.ht/~jackmordaunt/go-toast/ARCHITECTURE.md−244
This diff is too big to show here.
vendor/git.sr.ht/~jackmordaunt/go-toast/LICENSE−61
This diff is too big to show here.
vendor/git.sr.ht/~jackmordaunt/go-toast/README.md−86
This diff is too big to show here.
vendor/git.sr.ht/~jackmordaunt/go-toast/constants.go−65
This diff is too big to show here.
vendor/git.sr.ht/~jackmordaunt/go-toast/internal/winrt/data/xml/dom/xmldocument.go−73
This diff is too big to show here.
vendor/git.sr.ht/~jackmordaunt/go-toast/internal/winrt/ui/notifications/toastnotification.go−88
This diff is too big to show here.
vendor/git.sr.ht/~jackmordaunt/go-toast/internal/winrt/ui/notifications/toastnotificationmanager.go−53
This diff is too big to show here.
vendor/git.sr.ht/~jackmordaunt/go-toast/internal/winrt/ui/notifications/toastnotificationmanagerforuser.go−68
This diff is too big to show here.
vendor/git.sr.ht/~jackmordaunt/go-toast/internal/winrt/ui/notifications/toastnotifier.go−64
This diff is too big to show here.
vendor/git.sr.ht/~jackmordaunt/go-toast/tmpl/powershell.go.tmpl−14
This diff is too big to show here.
vendor/git.sr.ht/~jackmordaunt/go-toast/tmpl/tmpl.go−28
This diff is too big to show here.
vendor/git.sr.ht/~jackmordaunt/go-toast/tmpl/xml.go.tmpl−34
This diff is too big to show here.
vendor/git.sr.ht/~jackmordaunt/go-toast/toast.go−225
This diff is too big to show here.
vendor/git.sr.ht/~jackmordaunt/go-toast/wintoast/bind.go−86
This diff is too big to show here.
vendor/git.sr.ht/~jackmordaunt/go-toast/wintoast/bind_noop.go−19
This diff is too big to show here.
vendor/git.sr.ht/~jackmordaunt/go-toast/wintoast/bind_windows.go−174
This diff is too big to show here.
vendor/git.sr.ht/~jackmordaunt/go-toast/wintoast/impl.go−179
This diff is too big to show here.
vendor/git.sr.ht/~jackmordaunt/go-toast/wintoast/procs.go−37
This diff is too big to show here.
vendor/git.sr.ht/~jackmordaunt/go-toast/wintoast/registry.go−110
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/CHANGELOG.md−849
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/LICENSE.txt−21
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/README.md−39
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/ci.yml−29
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/cloud/cloud.go−44
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/cloud/doc.go−53
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/core.go−173
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/doc.go−264
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/errors.go−17
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/etag.go−57
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/internal/exported/exported.go−175
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/internal/exported/pipeline.go−77
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/internal/exported/request.go−260
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/internal/exported/response_error.go−201
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/internal/log/log.go−50
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/internal/pollers/async/async.go−159
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/internal/pollers/body/body.go−135
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/internal/pollers/fake/fake.go−133
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/internal/pollers/loc/loc.go−123
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/internal/pollers/op/op.go−148
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/internal/pollers/poller.go−24
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/internal/pollers/util.go−212
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/internal/shared/constants.go−44
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/internal/shared/shared.go−149
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/log/doc.go−10
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/log/log.go−55
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/policy/doc.go−10
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/policy/policy.go−198
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/runtime/doc.go−10
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/runtime/errors.go−27
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/runtime/pager.go−138
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/runtime/pipeline.go−94
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/runtime/policy_api_version.go−75
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/runtime/policy_bearer_token.go−236
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/runtime/policy_body_download.go−72
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/runtime/policy_http_header.go−40
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/runtime/policy_http_trace.go−154
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/runtime/policy_include_response.go−35
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/runtime/policy_key_credential.go−64
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/runtime/policy_logging.go−264
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/runtime/policy_request_id.go−34
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/runtime/policy_retry.go−276
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/runtime/policy_sas_credential.go−55
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/runtime/policy_telemetry.go−83
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/runtime/poller.go−396
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/runtime/request.go−281
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/runtime/response.go−109
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/runtime/transport_default_dialer_other.go−15
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/runtime/transport_default_dialer_wasm.go−15
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/runtime/transport_default_http_client.go−48
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/streaming/doc.go−9
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/streaming/progress.go−89
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/tracing/constants.go−41
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/tracing/tracing.go−191
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/internal/LICENSE.txt−21
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/internal/diag/diag.go−51
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/internal/diag/doc.go−7
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/internal/errorinfo/doc.go−7
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/internal/errorinfo/errorinfo.go−46
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/internal/exported/exported.go−129
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/internal/log/doc.go−7
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/internal/log/log.go−104
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/internal/poller/util.go−155
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/internal/temporal/resource.go−123
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/internal/uuid/doc.go−7
This diff is too big to show here.
vendor/github.com/Azure/azure-sdk-for-go/sdk/internal/uuid/uuid.go−76
This diff is too big to show here.
vendor/github.com/JohannesKaufmann/html-to-markdown/.gitignore−14
This diff is too big to show here.
vendor/github.com/JohannesKaufmann/html-to-markdown/CONTRIBUTING.md
This diff is too big to show here.
vendor/github.com/JohannesKaufmann/html-to-markdown/LICENSE−21
This diff is too big to show here.
vendor/github.com/JohannesKaufmann/html-to-markdown/README.md−242
This diff is too big to show here.
vendor/github.com/JohannesKaufmann/html-to-markdown/SECURITY.md−6
This diff is too big to show here.
vendor/github.com/JohannesKaufmann/html-to-markdown/commonmark.go−393
This diff is too big to show here.
vendor/github.com/JohannesKaufmann/html-to-markdown/escape/escape.go−65
This diff is too big to show here.
vendor/github.com/JohannesKaufmann/html-to-markdown/from.go−464
This diff is too big to show here.
vendor/github.com/JohannesKaufmann/html-to-markdown/logo_five_years.png
This diff is too big to show here.
vendor/github.com/JohannesKaufmann/html-to-markdown/markdown.go−212
This diff is too big to show here.
vendor/github.com/JohannesKaufmann/html-to-markdown/utils.go−533
This diff is too big to show here.
vendor/github.com/KyleBanks/depth/.gitignore−16
This diff is too big to show here.
vendor/github.com/KyleBanks/depth/.travis.yml−9
This diff is too big to show here.
vendor/github.com/KyleBanks/depth/LICENSE−21
This diff is too big to show here.
vendor/github.com/KyleBanks/depth/Makefile−32
This diff is too big to show here.
vendor/github.com/KyleBanks/depth/README.md−232
This diff is too big to show here.
vendor/github.com/KyleBanks/depth/depth.go−129
This diff is too big to show here.
vendor/github.com/KyleBanks/depth/pkg.go−184
This diff is too big to show here.
vendor/github.com/MakeNowJust/heredoc/LICENSE−21
This diff is too big to show here.
vendor/github.com/MakeNowJust/heredoc/README.md−52
This diff is too big to show here.
vendor/github.com/MakeNowJust/heredoc/heredoc.go−105
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/.gitattributes−1
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/.gitignore−10
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/.golangci.yml−147
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/CODEOWNERS−1
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/LICENSE−22
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/README.md−89
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/SECURITY.md−41
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/backup.go−287
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/doc.go−22
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/ea.go−137
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/file.go−320
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/fileinfo.go−106
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/hvsock.go−582
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/internal/fs/doc.go−2
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/internal/fs/fs.go−262
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/internal/fs/security.go−12
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/internal/fs/zsyscall_windows.go−61
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/internal/socket/rawaddr.go−20
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/internal/socket/socket.go−177
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/internal/socket/zsyscall_windows.go−69
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/internal/stringbuffer/wstring.go−132
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/pipe.go−586
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/pkg/guid/guid.go−232
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/pkg/guid/guid_nonwindows.go−16
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/pkg/guid/guid_windows.go−13
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/pkg/guid/variant_string.go−27
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/privilege.go−196
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/reparse.go−131
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/sd.go−133
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/syscall.go−5
This diff is too big to show here.
vendor/github.com/Microsoft/go-winio/zsyscall_windows.go−378
This diff is too big to show here.
vendor/github.com/PuerkitoBio/goquery/.gitattributes−1
This diff is too big to show here.
vendor/github.com/PuerkitoBio/goquery/.gitignore−16
This diff is too big to show here.
vendor/github.com/PuerkitoBio/goquery/LICENSE−12
This diff is too big to show here.
vendor/github.com/PuerkitoBio/goquery/README.md−218
This diff is too big to show here.
vendor/github.com/PuerkitoBio/goquery/array.go−124
This diff is too big to show here.
vendor/github.com/PuerkitoBio/goquery/doc.go−123
This diff is too big to show here.
vendor/github.com/PuerkitoBio/goquery/expand.go−70
This diff is too big to show here.
vendor/github.com/PuerkitoBio/goquery/filter.go−163
This diff is too big to show here.
vendor/github.com/PuerkitoBio/goquery/iteration.go−61
This diff is too big to show here.
vendor/github.com/PuerkitoBio/goquery/manipulation.go−679
This diff is too big to show here.
vendor/github.com/PuerkitoBio/goquery/property.go−275
This diff is too big to show here.
vendor/github.com/PuerkitoBio/goquery/query.go−49
This diff is too big to show here.
vendor/github.com/PuerkitoBio/goquery/traversal.go−704
This diff is too big to show here.
vendor/github.com/PuerkitoBio/goquery/type.go−203
This diff is too big to show here.
vendor/github.com/PuerkitoBio/goquery/utilities.go−177
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/.editorconfig−17
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/.gitignore−28
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/.golangci.yml−122
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/.goreleaser.yml−34
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/AGENTS.md−11
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/BUILD.bit−93
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/COPYING−118
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/Dockerfile−64
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/Justfile−59
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/README.md−309
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/biome.json−6
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/chroma.jpg
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/coalesce.go−35
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/colour.go−192
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/delegate.go−161
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/doc.go−7
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/emitters.go−233
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/formatter.go−43
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/formatters/api.go−57
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/formatters/html/html.go−692
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/formatters/json.go−39
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/formatters/svg/font_liberation_mono.go−51
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/formatters/svg/svg.go−222
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/formatters/tokens.go−18
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/formatters/tty_indexed.go−284
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/formatters/tty_truecolour.go−76
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/iterator.go−93
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexer.go−179
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/README.md−46
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/caddyfile.go−275
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/cl.go−243
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/dns.go−17
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/emacs.go−533
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/abap.xml−154
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/abnf.xml−66
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/actionscript.xml−68
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/actionscript_3.xml−163
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/ada.xml−321
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/agda.xml−66
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/al.xml−75
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/alloy.xml−58
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/ampl.xml−98
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/angular2.xml−109
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/antlr.xml−317
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/apacheconf.xml−74
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/apl.xml−59
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/applescript.xml−151
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/arangodb_aql.xml−174
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/arduino.xml−322
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/armasm.xml−126
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/arturo.xml−119
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/atl.xml−165
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/autohotkey.xml−78
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/autoit.xml−70
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/awk.xml−95
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/ballerina.xml−97
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/bash.xml−222
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/bash_session.xml−25
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/batchfile.xml−660
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/beef.xml−120
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/bibtex.xml−152
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/bicep.xml−84
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/blitzbasic.xml−141
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/bnf.xml−28
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/bqn.xml−83
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/brainfuck.xml−51
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/c#.xml−121
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/c++.xml−331
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/c.xml−260
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/c3.xml−374
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/cap_n_proto.xml−122
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/cassandra_cql.xml−137
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/ceylon.xml−151
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/cfengine3.xml−197
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/cfstatement.xml−92
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/chaiscript.xml−134
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/chapel.xml−143
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/cheetah.xml−55
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/clojure.xml−71
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/cmake.xml−90
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/cobol.xml−90
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/coffeescript.xml−210
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/common_lisp.xml−184
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/coq.xml−136
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/core.xml−79
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/crystal.xml−762
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/css.xml−323
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/csv.xml−53
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/cue.xml−85
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/cython.xml−372
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/d.xml−133
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/dart.xml−213
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/dax.xml−39
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/desktop_entry.xml−17
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/devicetree.xml−251
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/diff.xml−52
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/django_jinja.xml−153
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/dns.xml−44
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/docker.xml−68
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/dtd.xml−168
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/dylan.xml−176
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/ebnf.xml−90
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/elixir.xml−744
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/elm.xml−119
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/emacslisp.xml−132
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/erb.xml−37
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/erlang.xml−166
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/factor.xml−412
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/fennel.xml−68
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/fish.xml−159
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/forth.xml−78
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/fortran.xml−102
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/fortranfixed.xml−71
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/fsharp.xml−245
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/gas.xml−150
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/gdscript.xml−259
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/gdscript3.xml−270
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/gemfile_lock.xml−81
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/gettext.xml−24
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/gherkin.xml−263
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/gleam.xml−100
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/glsl.xml−65
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/gnuplot.xml−289
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/go_template.xml−114
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/graphql.xml−92
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/groff.xml−90
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/groovy.xml−135
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/handlebars.xml−147
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/hare.xml−98
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/haskell.xml−275
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/hcl.xml−143
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/hexdump.xml−189
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/hlb.xml−131
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/hlsl.xml−110
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/holyc.xml−252
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/html.xml−159
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/hy.xml−104
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/idris.xml−216
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/igor.xml−47
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/ini.xml−52
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/io.xml−71
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/iscdhcpd.xml−96
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/j.xml−157
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/janet.xml−48
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/java.xml−206
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/javascript.xml−160
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/json.xml−117
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/jsonata.xml−83
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/jsonnet.xml−138
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/julia.xml−400
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/jungle.xml−98
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/kakoune.xml−96
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/kdl.xml−75
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/kotlin.xml−234
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/lateralus.xml−184
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/lean.xml−56
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/lighttpd_configuration_file.xml−42
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/lilypond.xml−133
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/llvm.xml−73
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/lox.xml−78
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/lua.xml−158
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/luau.xml−173
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/makefile.xml−131
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/mako.xml−120
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/mason.xml−89
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/materialize_sql_dialect.xml−155
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/mathematica.xml−60
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/matlab.xml−114
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/mcfunction.xml−138
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/meson.xml−86
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/metal.xml−270
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/microcad.xml−139
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/minizinc.xml−82
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/mlir.xml−73
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/modelica.xml−106
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/modula-2.xml−245
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/mojo.xml−228
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/monkeyc.xml−153
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/moonbit.xml−75
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/moonscript.xml−83
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/morrowindscript.xml−90
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/myghty.xml−77
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/mysql.xml−121
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/nasm.xml−126
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/natural.xml−143
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/ndisasm.xml−123
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/newspeak.xml−121
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/nginx_configuration_file.xml−101
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/nim.xml−211
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/nix.xml−258
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/nsis.xml−59
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/nu.xml−126
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/objective-c.xml−510
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/objectpascal.xml−142
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/ocaml.xml−153
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/octave.xml−101
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/odin.xml−127
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/onesenterprise.xml−92
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/openedge_abl.xml−101
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/openscad.xml−96
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/org_mode.xml−329
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/pacmanconf.xml−37
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/perl.xml−400
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/php.xml−258
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/pig.xml−105
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/pkgconfig.xml−73
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/pl_pgsql.xml−119
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/plaintext.xml−21
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/plutus_core.xml−105
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/pony.xml−135
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/postgresql_sql_dialect.xml−155
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/postscript.xml−93
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/povray.xml−58
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/powerquery.xml−51
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/powershell.xml−230
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/prolog.xml−115
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/promela.xml−119
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/promql.xml−123
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/properties.xml−45
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/protocol_buffer.xml−124
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/prql.xml−161
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/psl.xml−213
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/puppet.xml−100
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/python.xml−595
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/python_2.xml−356
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/qbasic.xml−173
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/qml.xml−113
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/r.xml−128
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/racket.xml−260
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/ragel.xml−149
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/react.xml−236
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/reasonml.xml−147
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/reg.xml−68
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/rego.xml−94
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/rexx.xml−127
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/rgbasm.xml−239
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/ring.xml−74
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/rpgle.xml−176
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/rpm_spec.xml−58
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/ruby.xml−728
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/rust.xml−375
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/sas.xml−191
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/sass.xml−362
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/scala.xml−274
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/scdoc.xml−115
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/scheme.xml−106
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/scilab.xml−98
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/scss.xml−373
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/sed.xml−92
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/sieve.xml−61
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/smali.xml−73
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/smalltalk.xml−294
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/smarty.xml−79
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/snbt.xml−58
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/snobol.xml−95
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/solidity.xml−291
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/sourcepawn.xml−59
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/spade.xml−292
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/sparql.xml−160
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/sql.xml−90
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/squidconf.xml−63
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/standard_ml.xml−548
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/stas.xml−85
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/stylus.xml−132
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/swift.xml−207
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/systemd.xml−63
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/systemverilog.xml−181
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/tablegen.xml−69
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/tal.xml−43
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/tasm.xml−135
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/tcl.xml−272
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/tcsh.xml−121
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/templ.xml−315
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/termcap.xml−75
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/terminfo.xml−84
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/terraform.xml−149
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/tex.xml−113
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/thrift.xml−154
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/toml.xml−45
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/tradingview.xml−81
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/transact-sql.xml−137
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/turing.xml−82
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/turtle.xml−170
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/twig.xml−155
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/txtpb.xml−162
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/typescript.xml−302
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/typoscript.xml−178
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/typoscriptcssdata.xml−52
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/typoscripthtmldata.xml−52
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/typst.xml−108
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/ucode.xml−147
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/v.xml−355
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/v_shell.xml−365
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/vala.xml−72
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/vb_net.xml−162
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/verilog.xml−158
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/vhdl.xml−171
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/vhs.xml−48
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/viml.xml−85
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/vue.xml−295
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/wat.xml−149
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/wdte.xml−43
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/webgpu_shading_language.xml−142
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/webvtt.xml−283
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/whiley.xml−57
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/xml.xml−96
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/xorg.xml−35
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/yaml.xml−132
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/yang.xml−99
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/z80_assembly.xml−74
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/zed.xml−51
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/embedded/zig.xml−187
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/erb.go−29
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/gemtext.go−37
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/genshi.go−118
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/go.go−81
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/haxe.go−647
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/html.go−8
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/http.go−131
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/lexers.go−85
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/markdown.go−107
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/markless.go−168
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/mysql.go−33
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/php.go−37
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/raku.go−1710
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/rst.go−89
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/svelte.go−70
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/typoscript.go−85
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/yaml_jinja.go−20
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/lexers/zed.go−24
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/mutators.go−201
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/pygments-lexers.txt−605
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/quick/quick.go−44
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/regexp.go−533
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/registry.go−228
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/remap.go−94
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/renovate.json5−25
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/serialise.go−483
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/style.go−530
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/abap.xml−11
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/algol.xml−18
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/algol_nu.xml−18
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/api.go−95
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/arduino.xml−18
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/ashen.xml−69
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/aura-theme-dark-soft.xml−107
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/aura-theme-dark.xml−107
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/autumn.xml−36
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/average.xml−74
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/base16-snazzy.xml−74
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/borland.xml−26
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/bw.xml−23
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/catppuccin-frappe.xml−83
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/catppuccin-latte.xml−83
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/catppuccin-macchiato.xml−83
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/catppuccin-mocha.xml−83
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/colorful.xml−52
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/compat.go−69
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/darcula.xml−83
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/doom-one.xml−51
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/doom-one2.xml−64
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/dracula.xml−74
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/emacs.xml−44
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/evergarden.xml−33
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/friendly.xml−44
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/fruity.xml−19
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/github-dark.xml−46
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/github.xml−39
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/gruvbox-light.xml−34
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/gruvbox.xml−34
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/hr_high_contrast.xml−12
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/hrdark.xml−10
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/igor.xml−9
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/kanagawa-dragon.xml−83
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/kanagawa-lotus.xml−83
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/kanagawa-wave.xml−83
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/lovelace.xml−53
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/manni.xml−44
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/modus-operandi.xml−13
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/modus-vivendi.xml−13
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/monokai.xml−29
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/monokailight.xml−26
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/murphy.xml−52
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/native.xml−35
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/nord.xml−46
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/nordic.xml−46
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/onedark.xml−25
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/onesenterprise.xml−10
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/paraiso-dark.xml−37
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/paraiso-light.xml−37
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/pastie.xml−45
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/perldoc.xml−37
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/pygments.xml−42
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/rainbow_dash.xml−40
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/rose-pine-dawn.xml−29
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/rose-pine-moon.xml−29
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/rose-pine.xml−29
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/rpgle.xml−30
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/rrt.xml−19
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/solarized-dark.xml−39
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/solarized-dark256.xml−41
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/solarized-light.xml−17
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/swapoff.xml−18
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/tango.xml−72
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/tokyonight-day.xml−83
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/tokyonight-moon.xml−83
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/tokyonight-night.xml−83
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/tokyonight-storm.xml−83
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/trac.xml−35
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/vim.xml−29
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/vs.xml−16
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/vulcan.xml−74
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/witchhazel.xml−31
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/xcode-dark.xml−31
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/styles/xcode.xml−22
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/table.py−31
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/test.jsonl−2
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/tokentype_enumer.go−588
This diff is too big to show here.
vendor/github.com/alecthomas/chroma/v2/types.go−357
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/.gitignore−2
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/LICENSE−19
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/README.md−19
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/backward_references.go−185
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/backward_references_hq.go−796
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/bit_cost.go−436
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/bit_reader.go−266
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/bitwriter.go−56
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/block_splitter.go−144
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/block_splitter_command.go−434
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/block_splitter_distance.go−433
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/block_splitter_literal.go−433
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/brotli_bit_stream.go−1435
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/cluster.go−30
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/cluster_command.go−164
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/cluster_distance.go−326
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/cluster_literal.go−326
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/command.go−254
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/compress_fragment.go−834
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/compress_fragment_two_pass.go−775
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/constants.go−77
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/context.go−2176
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/decode.go−2581
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/dictionary.go−122890
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/dictionary_hash.go−32779
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/encode.go−1220
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/encoder.go−177
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/encoder_dict.go−22
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/encoder_fast.go−197
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/entropy_encode.go−592
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/entropy_encode_static.go−4399
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/fast_log.go−290
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/find_match_length.go−45
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/flate/LICENSE−27
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/flate/README.md−2
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/flate/gzip.go−65
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/flate/huffman_bit_writer.go−517
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/flate/huffman_code.go−346
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/flate/token.go−80
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/flate/writer.go−66
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/h10.go−287
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/h5.go−214
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/h6.go−216
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/hash.go−342
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/hash_composite.go−93
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/hash_forgetful_chain.go−252
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/hash_longest_match_quickly.go−214
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/hash_rolling.go−168
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/histogram.go−226
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/http.go−189
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/huffman.go−653
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/literal_cost.go−182
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/matchfinder/bargain1.go−212
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/matchfinder/bargain2.go−248
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/matchfinder/bargain3.go−278
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/matchfinder/emitter.go−34
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/matchfinder/m0.go−175
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/matchfinder/m4.go−339
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/matchfinder/matchfinder.go−103
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/matchfinder/pathfinder.go−328
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/matchfinder/textencoder.go−53
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/matchfinder/trio.go−326
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/matchfinder/zdfast.go−258
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/matchfinder/zfast.go−206
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/matchfinder/zm.go−301
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/memory.go−66
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/metablock.go−574
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/metablock_command.go−165
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/metablock_distance.go−165
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/metablock_literal.go−165
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/params.go−37
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/platform.go−103
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/prefix.go−30
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/prefix_dec.go−723
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/quality.go−196
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/reader.go−111
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/ringbuffer.go−134
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/state.go−294
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/static_dict.go−662
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/static_dict_lut.go−75094
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/symbol_list.go−22
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/transform.go−641
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/utf8_util.go−70
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/util.go−7
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/write_bits.go−52
This diff is too big to show here.
vendor/github.com/andybalholm/brotli/writer.go−162
This diff is too big to show here.
vendor/github.com/andybalholm/cascadia/.travis.yml−14
This diff is too big to show here.
vendor/github.com/andybalholm/cascadia/LICENSE−24
This diff is too big to show here.
vendor/github.com/andybalholm/cascadia/README.md−144
This diff is too big to show here.
vendor/github.com/andybalholm/cascadia/parser.go−889
This diff is too big to show here.
vendor/github.com/andybalholm/cascadia/pseudo_classes.go−458
This diff is too big to show here.
vendor/github.com/andybalholm/cascadia/selector.go−586
This diff is too big to show here.
vendor/github.com/andybalholm/cascadia/serialize.go−176
This diff is too big to show here.
vendor/github.com/andybalholm/cascadia/specificity.go−26
This diff is too big to show here.
vendor/github.com/atotto/clipboard/.travis.yml−22
This diff is too big to show here.
vendor/github.com/atotto/clipboard/LICENSE−27
This diff is too big to show here.
vendor/github.com/atotto/clipboard/README.md−48
This diff is too big to show here.
vendor/github.com/atotto/clipboard/clipboard.go−20
This diff is too big to show here.
vendor/github.com/atotto/clipboard/clipboard_darwin.go−52
This diff is too big to show here.
vendor/github.com/atotto/clipboard/clipboard_plan9.go−42
This diff is too big to show here.
vendor/github.com/atotto/clipboard/clipboard_unix.go−149
This diff is too big to show here.
vendor/github.com/atotto/clipboard/clipboard_windows.go−157
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/LICENSE.txt−202
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/NOTICE.txt−3
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/accountid_endpoint_mode.go−18
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/checksum.go−33
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/config.go−254
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/context.go−22
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/credential_cache.go−235
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/credentials.go−234
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/defaults/auto.go−38
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/defaults/configuration.go−43
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/defaults/defaults.go−50
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/defaults/doc.go−2
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/defaultsmode.go−95
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/doc.go−62
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/endpoints.go−247
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/errors.go−9
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/from_ptr.go−365
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/go_module_metadata.go−6
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/logging.go−119
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/logging_generate.go−95
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/middleware/metadata.go−213
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/middleware/middleware.go−168
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/middleware/osname.go−24
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/middleware/osname_go115.go−24
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/middleware/recursion_detection.go−94
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/middleware/request_id.go−27
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/middleware/request_id_retriever.go−57
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/middleware/user_agent.go−398
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream/CHANGELOG.md−203
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream/LICENSE.txt−202
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream/debug.go−144
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream/decode.go−218
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream/encode.go−167
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream/error.go−23
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream/eventstreamapi/headers.go−24
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream/eventstreamapi/middleware.go−71
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream/eventstreamapi/transport.go−13
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream/eventstreamapi/transport_go117.go−12
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream/go_module_metadata.go−6
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream/header.go−175
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream/header_value.go−521
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream/message.go−99
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/protocol/query/array.go−61
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/protocol/query/encoder.go−80
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/protocol/query/map.go−78
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/protocol/query/middleware.go−62
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/protocol/query/object.go−68
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/protocol/query/value.go−117
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/protocol/restjson/decoder_util.go−85
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/protocol/xml/error_utils.go−48
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/ratelimit/none.go−20
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/ratelimit/token_bucket.go−96
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/ratelimit/token_rate_limit.go−83
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/request.go−25
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/restrict_file_permissions.go−21
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/retry/adaptive.go−156
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/retry/adaptive_ratelimit.go−158
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/retry/adaptive_token_bucket.go−83
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/retry/attempt_metrics.go−51
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/retry/doc.go−80
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/retry/errors.go−20
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/retry/jitter_backoff.go−124
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/retry/metadata.go−52
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/retry/middleware.go−487
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/retry/retry.go−103
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/retry/retryable_error.go−228
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/retry/standard.go−343
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/retry/throttle_error.go−60
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/retry/timeout_error.go−52
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/retryer.go−127
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/runtime.go−14
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/signer/internal/v4/cache.go−115
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/signer/internal/v4/const.go−40
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/signer/internal/v4/header_rules.go−82
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/signer/internal/v4/headers.go−70
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/signer/internal/v4/hmac.go−13
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/signer/internal/v4/host.go−75
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/signer/internal/v4/scope.go−13
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/signer/internal/v4/time.go−36
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/signer/internal/v4/util.go−80
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/signer/v4/middleware.go−420
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/signer/v4/presign_middleware.go−127
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/signer/v4/stream.go−86
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/signer/v4/v4.go−564
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/to_ptr.go−297
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/transport/http/client.go−355
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/transport/http/content_type.go−42
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/transport/http/response_error.go−33
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/transport/http/response_error_middleware.go−56
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/transport/http/timeout_read_closer.go−109
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/types.go−42
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/aws/version.go−8
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/config/CHANGELOG.md−1097
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/config/LICENSE.txt−202
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/config/auth_scheme_preference.go−19
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/config/config.go−237
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/config/defaultsmode.go−47
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/config/doc.go−20
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/config/env_config.go−966
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/config/generate.go−4
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/config/go_module_metadata.go−6
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/config/internal/ini/errors.go−22
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/config/internal/ini/ini.go−56
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/config/internal/ini/parse.go−109
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/config/internal/ini/sections.go−157
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/config/internal/ini/strings.go−89
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/config/internal/ini/token.go−32
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/config/internal/ini/tokenize.go−92
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/config/internal/ini/value.go−93
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/config/load_options.go−1371
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/config/local.go−51
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/config/provider.go−802
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/config/resolve.go−458
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/config/resolve_bearer_token.go−122
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/config/resolve_credentials.go−650
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/config/shared_config.go−1704
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/credentials/CHANGELOG.md−990
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/credentials/LICENSE.txt−202
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/credentials/doc.go−4
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/credentials/ec2rolecreds/doc.go−58
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/credentials/ec2rolecreds/provider.go−241
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/credentials/endpointcreds/internal/client/auth.go−48
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/credentials/endpointcreds/internal/client/client.go−165
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/credentials/endpointcreds/internal/client/endpoints.go−20
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/credentials/endpointcreds/internal/client/middleware.go−164
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/credentials/endpointcreds/provider.go−207
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/credentials/go_module_metadata.go−6
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/credentials/logincreds/dpop.go−150
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/credentials/logincreds/file.go−14
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/credentials/logincreds/provider.go−184
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/credentials/logincreds/token.go−110
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/credentials/processcreds/doc.go−92
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/credentials/processcreds/provider.go−296
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/credentials/ssocreds/doc.go−81
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/credentials/ssocreds/sso_cached_token.go−232
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/credentials/ssocreds/sso_credentials_provider.go−165
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/credentials/ssocreds/sso_token_provider.go−147
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/credentials/static_provider.go−63
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/credentials/stscreds/assume_role_provider.go−338
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/credentials/stscreds/web_identity_provider.go−181
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/feature/ec2/imds/CHANGELOG.md−584
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/feature/ec2/imds/LICENSE.txt−202
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/feature/ec2/imds/api_client.go−358
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/feature/ec2/imds/api_op_GetDynamicData.go−77
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/feature/ec2/imds/api_op_GetIAMInfo.go−103
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/feature/ec2/imds/api_op_GetInstanceIdentityDocument.go−110
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/feature/ec2/imds/api_op_GetMetadata.go−77
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/feature/ec2/imds/api_op_GetRegion.go−73
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/feature/ec2/imds/api_op_GetToken.go−119
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/feature/ec2/imds/api_op_GetUserData.go−61
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/feature/ec2/imds/auth.go−48
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/feature/ec2/imds/doc.go−12
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/feature/ec2/imds/endpoints.go−20
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/feature/ec2/imds/go_module_metadata.go−6
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/feature/ec2/imds/internal/config/resolvers.go−114
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/feature/ec2/imds/request_middleware.go−313
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/feature/ec2/imds/token_provider.go−261
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/auth/auth.go−45
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/auth/scheme.go−191
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/auth/smithy/bearer_token_adapter.go−43
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/auth/smithy/bearer_token_signer_adapter.go−35
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/auth/smithy/credentials_adapter.go−46
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/auth/smithy/smithy.go−2
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/auth/smithy/v4signer_adapter.go−57
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/auth/smithy/v4signer_adapter_eventstream.go−51
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/configsources/CHANGELOG.md−544
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/configsources/LICENSE.txt−202
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/configsources/config.go−65
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/configsources/endpoints.go−57
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/configsources/go_module_metadata.go−6
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/context/context.go−65
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/endpoints/awsrulesfn/arn.go−94
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/endpoints/awsrulesfn/doc.go−3
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/endpoints/awsrulesfn/generate.go−7
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/endpoints/awsrulesfn/host.go−51
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/endpoints/awsrulesfn/partition.go−76
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/endpoints/awsrulesfn/partitions.go−496
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/endpoints/awsrulesfn/partitions.json−267
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/endpoints/endpoints.go−201
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/endpoints/v2/CHANGELOG.md−519
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/endpoints/v2/LICENSE.txt−202
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/endpoints/v2/endpoints.go−302
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/endpoints/v2/go_module_metadata.go−6
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/rand/rand.go−33
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/sdk/interfaces.go−9
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/sdk/time.go−74
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/sdkio/byte.go−12
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/shareddefaults/shared_config.go−47
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/strings/strings.go−11
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/sync/singleflight/LICENSE−28
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/sync/singleflight/docs.go−7
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/sync/singleflight/singleflight.go−210
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/timeconv/duration.go−13
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/v4a/CHANGELOG.md−486
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/v4a/LICENSE.txt−202
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/v4a/credentials.go−141
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/v4a/error.go−17
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/v4a/go_module_metadata.go−6
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/v4a/internal/crypto/compare.go−30
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/v4a/internal/crypto/ecc.go−113
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/v4a/internal/v4/const.go−36
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/v4a/internal/v4/header_rules.go−82
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/v4a/internal/v4/headers.go−68
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/v4a/internal/v4/hmac.go−13
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/v4a/internal/v4/host.go−75
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/v4a/internal/v4/time.go−36
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/v4a/internal/v4/util.go−64
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/v4a/middleware.go−118
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/v4a/presign_middleware.go−117
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/v4a/smithy.go−92
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/internal/v4a/v4a.go−520
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding/CHANGELOG.md−220
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding/LICENSE.txt−202
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding/accept_encoding_gzip.go−176
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding/doc.go−22
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding/go_module_metadata.go−6
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/internal/presigned-url/CHANGELOG.md−571
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/internal/presigned-url/LICENSE.txt−202
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/internal/presigned-url/context.go−56
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/internal/presigned-url/doc.go−3
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/internal/presigned-url/go_module_metadata.go−6
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/internal/presigned-url/middleware.go−110
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/signin/CHANGELOG.md−85
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/signin/LICENSE.txt−202
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/signin/api_client.go−945
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/signin/api_op_CreateOAuth2Token.go−212
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/signin/api_op_DeleteConsoleAuthorizationConfiguration.go−168
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/signin/api_op_DeleteResourcePermissionStatement.go−196
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/signin/api_op_GetConsoleAuthorizationConfiguration.go−168
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/signin/api_op_GetResourcePolicy.go−155
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/signin/api_op_ListResourcePermissionStatements.go−261
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/signin/api_op_PutConsoleAuthorizationConfiguration.go−168
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/signin/api_op_PutResourcePermissionStatement.go−216
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/signin/auth.go−361
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/signin/deserializers.go−2474
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/signin/doc.go−9
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/signin/endpoints.go−854
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/signin/generated.json−40
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/signin/go_module_metadata.go−6
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/signin/internal/endpoints/endpoints.go−333
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/signin/options.go−242
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/signin/serializers.go−724
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/signin/types/enums.go−46
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/signin/types/errors.go−247
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/signin/types/types.go−162
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/signin/validators.go−111
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sso/CHANGELOG.md−792
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sso/LICENSE.txt−202
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sso/api_client.go−929
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sso/api_op_GetRoleCredentials.go−165
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sso/api_op_ListAccountRoles.go−263
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sso/api_op_ListAccounts.go−261
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sso/api_op_Logout.go−164
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sso/auth.go−379
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sso/deserializers.go−1171
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sso/doc.go−27
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sso/endpoints.go−570
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sso/generated.json−35
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sso/go_module_metadata.go−6
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sso/internal/endpoints/endpoints.go−628
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sso/options.go−238
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sso/serializers.go−309
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sso/types/errors.go−115
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sso/types/types.go−63
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sso/validators.go−175
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/ssooidc/CHANGELOG.md−790
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/ssooidc/LICENSE.txt−202
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/ssooidc/api_client.go−929
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/ssooidc/api_op_CreateToken.go−235
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/ssooidc/api_op_CreateTokenWithIAM.go−282
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/ssooidc/api_op_RegisterClient.go−206
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/ssooidc/api_op_StartDeviceAuthorization.go−188
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/ssooidc/auth.go−373
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/ssooidc/deserializers.go−2244
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/ssooidc/doc.go−49
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/ssooidc/endpoints.go−570
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/ssooidc/generated.json−36
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/ssooidc/go_module_metadata.go−6
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/ssooidc/internal/endpoints/endpoints.go−628
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/ssooidc/options.go−238
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/ssooidc/serializers.go−512
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/ssooidc/types/enums.go−44
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/ssooidc/types/errors.go−430
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/ssooidc/types/types.go−25
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/ssooidc/validators.go−184
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sts/CHANGELOG.md−832
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sts/LICENSE.txt−202
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sts/api_client.go−1115
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sts/api_op_AssumeRole.go−544
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sts/api_op_AssumeRoleWithSAML.go−455
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sts/api_op_AssumeRoleWithWebIdentity.go−472
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sts/api_op_AssumeRoot.go−229
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sts/api_op_DecodeAuthorizationMessage.go−189
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sts/api_op_GetAccessKeyInfo.go−180
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sts/api_op_GetCallerIdentity.go−192
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sts/api_op_GetDelegatedAccessToken.go−169
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sts/api_op_GetFederationToken.go−393
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sts/api_op_GetSessionToken.go−239
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sts/api_op_GetWebIdentityToken.go−192
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sts/auth.go−377
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sts/deserializers.go−3456
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sts/doc.go−13
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sts/endpoints.go−683
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sts/generated.json−45
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sts/go_module_metadata.go−6
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sts/internal/endpoints/endpoints.go−585
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sts/options.go−286
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sts/serializers.go−1198
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sts/types/errors.go−363
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sts/types/types.go−144
This diff is too big to show here.
vendor/github.com/aws/aws-sdk-go-v2/service/sts/validators.go−433
This diff is too big to show here.
vendor/github.com/aws/smithy-go/.gitignore−29
This diff is too big to show here.
vendor/github.com/aws/smithy-go/.travis.yml−28
This diff is too big to show here.
vendor/github.com/aws/smithy-go/AGENTS.md−172
This diff is too big to show here.
vendor/github.com/aws/smithy-go/CHANGELOG.md−454
This diff is too big to show here.
vendor/github.com/aws/smithy-go/CODE_OF_CONDUCT.md−4
This diff is too big to show here.
vendor/github.com/aws/smithy-go/CONTRIBUTING.md−90
This diff is too big to show here.
vendor/github.com/aws/smithy-go/LICENSE−175
This diff is too big to show here.
vendor/github.com/aws/smithy-go/Makefile−130
This diff is too big to show here.
vendor/github.com/aws/smithy-go/NOTICE−1
This diff is too big to show here.
vendor/github.com/aws/smithy-go/README.md−107
This diff is too big to show here.
vendor/github.com/aws/smithy-go/auth/auth.go−3
This diff is too big to show here.
vendor/github.com/aws/smithy-go/auth/bearer/docs.go−3
This diff is too big to show here.
vendor/github.com/aws/smithy-go/auth/bearer/middleware.go−104
This diff is too big to show here.
vendor/github.com/aws/smithy-go/auth/bearer/token.go−50
This diff is too big to show here.
vendor/github.com/aws/smithy-go/auth/bearer/token_cache.go−208
This diff is too big to show here.
vendor/github.com/aws/smithy-go/auth/identity.go−47
This diff is too big to show here.
vendor/github.com/aws/smithy-go/auth/option.go−25
This diff is too big to show here.
vendor/github.com/aws/smithy-go/auth/scheme_id.go−20
This diff is too big to show here.
vendor/github.com/aws/smithy-go/changelog-template.json−9
This diff is too big to show here.
vendor/github.com/aws/smithy-go/context/suppress_expired.go−81
This diff is too big to show here.
vendor/github.com/aws/smithy-go/doc.go−2
This diff is too big to show here.
vendor/github.com/aws/smithy-go/document.go−10
This diff is too big to show here.
vendor/github.com/aws/smithy-go/document/doc.go−12
This diff is too big to show here.
vendor/github.com/aws/smithy-go/document/document.go−239
This diff is too big to show here.
vendor/github.com/aws/smithy-go/document/errors.go−75
This diff is too big to show here.
vendor/github.com/aws/smithy-go/encoding/doc.go−4
This diff is too big to show here.
vendor/github.com/aws/smithy-go/encoding/encoding.go−40
This diff is too big to show here.
vendor/github.com/aws/smithy-go/encoding/httpbinding/encode.go−123
This diff is too big to show here.
vendor/github.com/aws/smithy-go/encoding/httpbinding/header.go−122
This diff is too big to show here.
vendor/github.com/aws/smithy-go/encoding/httpbinding/path_replace.go−108
This diff is too big to show here.
vendor/github.com/aws/smithy-go/encoding/httpbinding/query.go−107
This diff is too big to show here.
vendor/github.com/aws/smithy-go/encoding/httpbinding/uri.go−111
This diff is too big to show here.
vendor/github.com/aws/smithy-go/encoding/json/array.go−35
This diff is too big to show here.
vendor/github.com/aws/smithy-go/encoding/json/constants.go−15
This diff is too big to show here.
vendor/github.com/aws/smithy-go/encoding/json/decoder_util.go−139
This diff is too big to show here.
vendor/github.com/aws/smithy-go/encoding/json/encoder.go−30
This diff is too big to show here.
vendor/github.com/aws/smithy-go/encoding/json/escape.go−198
This diff is too big to show here.
vendor/github.com/aws/smithy-go/encoding/json/object.go−40
This diff is too big to show here.
vendor/github.com/aws/smithy-go/encoding/json/value.go−154
This diff is too big to show here.
vendor/github.com/aws/smithy-go/encoding/xml/array.go−49
This diff is too big to show here.
vendor/github.com/aws/smithy-go/encoding/xml/constants.go−10
This diff is too big to show here.
vendor/github.com/aws/smithy-go/encoding/xml/doc.go−49
This diff is too big to show here.
vendor/github.com/aws/smithy-go/encoding/xml/element.go−91
This diff is too big to show here.
vendor/github.com/aws/smithy-go/encoding/xml/encoder.go−51
This diff is too big to show here.
vendor/github.com/aws/smithy-go/encoding/xml/error_utils.go−51
This diff is too big to show here.
vendor/github.com/aws/smithy-go/encoding/xml/escape.go−137
This diff is too big to show here.
vendor/github.com/aws/smithy-go/encoding/xml/map.go−53
This diff is too big to show here.
vendor/github.com/aws/smithy-go/encoding/xml/value.go−302
This diff is too big to show here.
vendor/github.com/aws/smithy-go/encoding/xml/xml_decoder.go−154
This diff is too big to show here.
vendor/github.com/aws/smithy-go/endpoints/endpoint.go−23
This diff is too big to show here.
vendor/github.com/aws/smithy-go/endpoints/private/bdd/evaluate.go−35
This diff is too big to show here.
vendor/github.com/aws/smithy-go/endpoints/private/rulesfn/doc.go−4
This diff is too big to show here.
vendor/github.com/aws/smithy-go/endpoints/private/rulesfn/split.go−16
This diff is too big to show here.
vendor/github.com/aws/smithy-go/endpoints/private/rulesfn/string_slice.go−18
This diff is too big to show here.
vendor/github.com/aws/smithy-go/endpoints/private/rulesfn/strings.go−25
This diff is too big to show here.
vendor/github.com/aws/smithy-go/endpoints/private/rulesfn/uri.go−133
This diff is too big to show here.
vendor/github.com/aws/smithy-go/errors.go−137
This diff is too big to show here.
vendor/github.com/aws/smithy-go/eventstream/const.go−24
This diff is too big to show here.
vendor/github.com/aws/smithy-go/eventstream/debug.go−144
This diff is too big to show here.
vendor/github.com/aws/smithy-go/eventstream/decode.go−218
This diff is too big to show here.
vendor/github.com/aws/smithy-go/eventstream/deserializer.go−294
This diff is too big to show here.
vendor/github.com/aws/smithy-go/eventstream/encode.go−167
This diff is too big to show here.
vendor/github.com/aws/smithy-go/eventstream/error.go−23
This diff is too big to show here.
vendor/github.com/aws/smithy-go/eventstream/header.go−175
This diff is too big to show here.
vendor/github.com/aws/smithy-go/eventstream/header_value.go−521
This diff is too big to show here.
vendor/github.com/aws/smithy-go/eventstream/message.go−99
This diff is too big to show here.
vendor/github.com/aws/smithy-go/eventstream/serializer.go−228
This diff is too big to show here.
vendor/github.com/aws/smithy-go/eventstream/signer.go−82
This diff is too big to show here.
vendor/github.com/aws/smithy-go/eventstream/types.go−26
This diff is too big to show here.
vendor/github.com/aws/smithy-go/go_module_metadata.go−6
This diff is too big to show here.
vendor/github.com/aws/smithy-go/internal/sync/singleflight/LICENSE−28
This diff is too big to show here.
vendor/github.com/aws/smithy-go/internal/sync/singleflight/docs.go−8
This diff is too big to show here.
vendor/github.com/aws/smithy-go/internal/sync/singleflight/singleflight.go−210
This diff is too big to show here.
vendor/github.com/aws/smithy-go/io/byte.go−12
This diff is too big to show here.
vendor/github.com/aws/smithy-go/io/doc.go−2
This diff is too big to show here.
vendor/github.com/aws/smithy-go/io/reader.go−16
This diff is too big to show here.
vendor/github.com/aws/smithy-go/io/ringbuffer.go−94
This diff is too big to show here.
vendor/github.com/aws/smithy-go/local-mod-replace.sh−39
This diff is too big to show here.
vendor/github.com/aws/smithy-go/logging/logger.go−82
This diff is too big to show here.
vendor/github.com/aws/smithy-go/metrics/metrics.go−136
This diff is too big to show here.
vendor/github.com/aws/smithy-go/metrics/nop.go−98
This diff is too big to show here.
vendor/github.com/aws/smithy-go/middleware/context.go−41
This diff is too big to show here.
vendor/github.com/aws/smithy-go/middleware/doc.go−67
This diff is too big to show here.
vendor/github.com/aws/smithy-go/middleware/eventstream_middleware.go−21
This diff is too big to show here.
vendor/github.com/aws/smithy-go/middleware/logging.go−46
This diff is too big to show here.
vendor/github.com/aws/smithy-go/middleware/metadata.go−65
This diff is too big to show here.
vendor/github.com/aws/smithy-go/middleware/middleware.go−71
This diff is too big to show here.
vendor/github.com/aws/smithy-go/middleware/ordered_group.go−270
This diff is too big to show here.
vendor/github.com/aws/smithy-go/middleware/stack.go−209
This diff is too big to show here.
vendor/github.com/aws/smithy-go/middleware/stack_values.go−100
This diff is too big to show here.
vendor/github.com/aws/smithy-go/middleware/step_build.go−298
This diff is too big to show here.
vendor/github.com/aws/smithy-go/middleware/step_deserialize.go−300
This diff is too big to show here.
vendor/github.com/aws/smithy-go/middleware/step_finalize.go−298
This diff is too big to show here.
vendor/github.com/aws/smithy-go/middleware/step_initialize.go−299
This diff is too big to show here.
vendor/github.com/aws/smithy-go/middleware/step_serialize.go−305
This diff is too big to show here.
vendor/github.com/aws/smithy-go/modman.toml−9
This diff is too big to show here.
vendor/github.com/aws/smithy-go/private/requestcompression/gzip.go−30
This diff is too big to show here.
vendor/github.com/aws/smithy-go/private/requestcompression/middleware_capture_request_compression.go−52
This diff is too big to show here.
vendor/github.com/aws/smithy-go/private/requestcompression/request_compression.go−103
This diff is too big to show here.
vendor/github.com/aws/smithy-go/properties.go−69
This diff is too big to show here.
vendor/github.com/aws/smithy-go/ptr/doc.go−5
This diff is too big to show here.
vendor/github.com/aws/smithy-go/ptr/from_ptr.go−601
This diff is too big to show here.
vendor/github.com/aws/smithy-go/ptr/gen_scalars.go−83
This diff is too big to show here.
vendor/github.com/aws/smithy-go/ptr/to_ptr.go−499
This diff is too big to show here.
vendor/github.com/aws/smithy-go/rand/doc.go−3
This diff is too big to show here.
vendor/github.com/aws/smithy-go/rand/rand.go−31
This diff is too big to show here.
vendor/github.com/aws/smithy-go/rand/uuid.go−87
This diff is too big to show here.
vendor/github.com/aws/smithy-go/schema.go−328
This diff is too big to show here.
vendor/github.com/aws/smithy-go/schema_ext.go−37
This diff is too big to show here.
vendor/github.com/aws/smithy-go/serde.go−229
This diff is too big to show here.
vendor/github.com/aws/smithy-go/sync/error.go−53
This diff is too big to show here.
vendor/github.com/aws/smithy-go/time/time.go−134
This diff is too big to show here.
vendor/github.com/aws/smithy-go/tracing/context.go−96
This diff is too big to show here.
vendor/github.com/aws/smithy-go/tracing/nop.go−32
This diff is too big to show here.
vendor/github.com/aws/smithy-go/tracing/tracing.go−95
This diff is too big to show here.
vendor/github.com/aws/smithy-go/trait.go−21
This diff is too big to show here.
vendor/github.com/aws/smithy-go/traits/http.go−69
This diff is too big to show here.
vendor/github.com/aws/smithy-go/traits/index.go−107
This diff is too big to show here.
vendor/github.com/aws/smithy-go/traits/serde.go−56
This diff is too big to show here.
vendor/github.com/aws/smithy-go/traits/traits.go−72
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/auth.go−30
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/auth_schemes.go−45
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/checksum_middleware.go−70
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/client.go−161
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/doc.go−5
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/eventstream.go−209
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/eventstream_middleware.go−69
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/headerlist.go−163
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/host.go−89
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/interceptor.go−321
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/interceptor_middleware.go−325
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/internal/io/safe.go−75
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/md5_checksum.go−25
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/metrics.go−204
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/middleware_close_response_body.go−79
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/middleware_content_length.go−84
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/middleware_header_comment.go−81
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/middleware_headers.go−167
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/middleware_http_logging.go−75
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/middleware_metadata.go−51
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/middleware_min_proto.go−79
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/properties.go−80
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/protocol.go−27
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/request.go−188
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/response.go−34
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/time.go−13
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/url.go−44
This diff is too big to show here.
vendor/github.com/aws/smithy-go/transport/http/user_agent.go−37
This diff is too big to show here.
vendor/github.com/aws/smithy-go/type_registry.go−70
This diff is too big to show here.
vendor/github.com/aws/smithy-go/validation.go−140
This diff is too big to show here.
vendor/github.com/aymanbagabas/go-udiff/LICENSE-BSD−27
This diff is too big to show here.
vendor/github.com/aymanbagabas/go-udiff/LICENSE-MIT−21
This diff is too big to show here.
vendor/github.com/aymanbagabas/go-udiff/Makefile−4
This diff is too big to show here.
vendor/github.com/aymanbagabas/go-udiff/README.md−142
This diff is too big to show here.
vendor/github.com/aymanbagabas/go-udiff/diff.go−177
This diff is too big to show here.
vendor/github.com/aymanbagabas/go-udiff/export.go−16
This diff is too big to show here.
vendor/github.com/aymanbagabas/go-udiff/lcs/common.go−179
This diff is too big to show here.
vendor/github.com/aymanbagabas/go-udiff/lcs/doc.go−156
This diff is too big to show here.
vendor/github.com/aymanbagabas/go-udiff/lcs/export.go−11
This diff is too big to show here.
vendor/github.com/aymanbagabas/go-udiff/lcs/git.sh−33
This diff is too big to show here.
vendor/github.com/aymanbagabas/go-udiff/lcs/labels.go−55
This diff is too big to show here.
vendor/github.com/aymanbagabas/go-udiff/lcs/old.go−475
This diff is too big to show here.
vendor/github.com/aymanbagabas/go-udiff/lcs/sequence.go−70
This diff is too big to show here.
vendor/github.com/aymanbagabas/go-udiff/merge.go−81
This diff is too big to show here.
vendor/github.com/aymanbagabas/go-udiff/ndiff.go−118
This diff is too big to show here.
vendor/github.com/aymanbagabas/go-udiff/unified.go−314
This diff is too big to show here.
vendor/github.com/aymerick/douceur/LICENSE−22
This diff is too big to show here.
vendor/github.com/aymerick/douceur/css/declaration.go−60
This diff is too big to show here.
vendor/github.com/aymerick/douceur/css/rule.go−230
This diff is too big to show here.
vendor/github.com/aymerick/douceur/css/stylesheet.go−25
This diff is too big to show here.
vendor/github.com/aymerick/douceur/parser/parser.go−409
This diff is too big to show here.
vendor/github.com/bahlo/generic-list-go/LICENSE−27
This diff is too big to show here.
vendor/github.com/bahlo/generic-list-go/README.md−5
This diff is too big to show here.
vendor/github.com/bahlo/generic-list-go/list.go−235
This diff is too big to show here.
vendor/github.com/bmatcuk/doublestar/v4/.codecov.yml−10
This diff is too big to show here.
vendor/github.com/bmatcuk/doublestar/v4/.gitignore−32
This diff is too big to show here.
vendor/github.com/bmatcuk/doublestar/v4/LICENSE−22
This diff is too big to show here.
vendor/github.com/bmatcuk/doublestar/v4/README.md−495
This diff is too big to show here.
vendor/github.com/bmatcuk/doublestar/v4/UPGRADING.md−63
This diff is too big to show here.
vendor/github.com/bmatcuk/doublestar/v4/doublestar.go−13
This diff is too big to show here.
vendor/github.com/bmatcuk/doublestar/v4/glob.go−497
This diff is too big to show here.