0cb2b2c...main · crush

git.iko.soy/crush

on main help sign in

.agents/skills/builtin-skills/SKILL.mdnew file+42

since splitsnapshots

unifiedsplit

@@ -0,0 +1,42 @@

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+---

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.mdnew file+72

@@ -0,0 +1,72 @@

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+---

6+# Shell Builtins

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` |

.envrcnew file+1

@@ -0,0 +1 @@

1+use flake

.gitattributes+2

@@ -1,2 +1,4 @@

1*.golden linguist-generated=true -text

2.github/crush-schema.json linguist-generated=true

3+internal/agent/hyper/provider.json linguist-generated=true

4+internal/agent/testdata/**/*.yaml -diff linguist-generated=true

.github/CODEOWNERSdeleted−1

@@ -1 +0,0 @@

1−*.go @charmbracelet/everyone

.github/cla-signatures.json+1368

@@ -727,6 +727,1374 @@

727 "created_at": "2025-10-18T19:24:00Z",

728 "repoId": 987670088,

729 "pullRequestNo": 1254

730+ },

731+ {

732+ "name": "Jesssullivan",

733+ "id": 37297218,

734+ "comment_id": 3439361465,

735+ "created_at": "2025-10-23T21:50:17Z",

736+ "repoId": 987670088,

737+ "pullRequestNo": 1292

738+ },

739+ {

740+ "name": "mmangkad",

741+ "id": 176301910,

742+ "comment_id": 3440286180,

743+ "created_at": "2025-10-24T01:32:47Z",

744+ "repoId": 987670088,

745+ "pullRequestNo": 1294

746+ },

747+ {

748+ "name": "blouflab",

749+ "id": 227565774,

750+ "comment_id": 3444483981,

751+ "created_at": "2025-10-24T18:59:01Z",

752+ "repoId": 987670088,

753+ "pullRequestNo": 1296

754+ },

755+ {

756+ "name": "Supratim69",

757+ "id": 128067781,

758+ "comment_id": 3444891894,

759+ "created_at": "2025-10-24T20:58:01Z",

760+ "repoId": 987670088,

761+ "pullRequestNo": 1299

762+ },

763+ {

764+ "name": "plandem",

765+ "id": 1381366,

766+ "comment_id": 3446669312,

767+ "created_at": "2025-10-25T12:52:04Z",

768+ "repoId": 987670088,

769+ "pullRequestNo": 1302

770+ },

771+ {

772+ "name": "dawndiy",

773+ "id": 1512740,

774+ "comment_id": 3456210693,

775+ "created_at": "2025-10-28T12:24:21Z",

776+ "repoId": 987670088,

777+ "pullRequestNo": 1312

778+ },

779+ {

780+ "name": "bradflaugher",

781+ "id": 16511019,

782+ "comment_id": 3458922489,

783+ "created_at": "2025-10-28T23:13:15Z",

784+ "repoId": 987670088,

785+ "pullRequestNo": 1324

786+ },

787+ {

788+ "name": "teras",

789+ "id": 592568,

790+ "comment_id": 3465825058,

791+ "created_at": "2025-10-30T02:04:26Z",

792+ "repoId": 987670088,

793+ "pullRequestNo": 1335

794+ },

795+ {

796+ "name": "heynemann",

797+ "id": 60965,

798+ "comment_id": 3475594747,

799+ "created_at": "2025-11-01T03:21:03Z",

800+ "repoId": 987670088,

801+ "pullRequestNo": 1357

802+ },

803+ {

804+ "name": "niklasschaeffer",

805+ "id": 1948226,

806+ "comment_id": 3476119118,

807+ "created_at": "2025-11-01T10:06:05Z",

808+ "repoId": 987670088,

809+ "pullRequestNo": 1358

810+ },

811+ {

812+ "name": "LarsArtmann",

813+ "id": 23587853,

814+ "comment_id": 3488527230,

815+ "created_at": "2025-11-05T00:18:02Z",

816+ "repoId": 987670088,

817+ "pullRequestNo": 1384

818+ },

819+ {

820+ "name": "danielmerja",

821+ "id": 30878766,

822+ "comment_id": 3492618827,

823+ "created_at": "2025-11-05T17:59:51Z",

824+ "repoId": 987670088,

825+ "pullRequestNo": 1387

826+ },

827+ {

828+ "name": "nanvenomous",

829+ "id": 43622197,

830+ "comment_id": 3497693075,

831+ "created_at": "2025-11-06T15:05:00Z",

832+ "repoId": 987670088,

833+ "pullRequestNo": 1392

834+ },

835+ {

836+ "name": "novalis78",

837+ "id": 190390,

838+ "comment_id": 3506836115,

839+ "created_at": "2025-11-08T19:53:10Z",

840+ "repoId": 987670088,

841+ "pullRequestNo": 1408

842+ },

843+ {

844+ "name": "alewtschuk",

845+ "id": 19924911,

846+ "comment_id": 3520127241,

847+ "created_at": "2025-11-12T05:44:54Z",

848+ "repoId": 987670088,

849+ "pullRequestNo": 1429

850+ },

851+ {

852+ "name": "Iflgit",

853+ "id": 24231648,

854+ "comment_id": 3536325469,

855+ "created_at": "2025-11-15T10:46:24Z",

856+ "repoId": 987670088,

857+ "pullRequestNo": 1450

858+ },

859+ {

860+ "name": "iainlane",

861+ "id": 321014,

862+ "comment_id": 3539345738,

863+ "created_at": "2025-11-16T20:55:47Z",

864+ "repoId": 987670088,

865+ "pullRequestNo": 1457

866+ },

867+ {

868+ "name": "micahwalter",

869+ "id": 47419,

870+ "comment_id": 3553482361,

871+ "created_at": "2025-11-19T15:59:07Z",

872+ "repoId": 987670088,

873+ "pullRequestNo": 1478

874+ },

875+ {

876+ "name": "heimoshuiyu",

877+ "id": 22657774,

878+ "comment_id": 3565689668,

879+ "created_at": "2025-11-22T05:23:17Z",

880+ "repoId": 987670088,

881+ "pullRequestNo": 1496

882+ },

883+ {

884+ "name": "masroor-ahmad",

885+ "id": 75073229,

886+ "comment_id": 3592527587,

887+ "created_at": "2025-11-30T12:55:09Z",

888+ "repoId": 987670088,

889+ "pullRequestNo": 1532

890+ },

891+ {

892+ "name": "thezbm",

893+ "id": 24851999,

894+ "comment_id": 3595049411,

895+ "created_at": "2025-12-01T07:39:02Z",

896+ "repoId": 987670088,

897+ "pullRequestNo": 1534

898+ },

899+ {

900+ "name": "marifcelik",

901+ "id": 46600975,

902+ "comment_id": 3610641638,

903+ "created_at": "2025-12-04T07:17:10Z",

904+ "repoId": 987670088,

905+ "pullRequestNo": 1546

906+ },

907+ {

908+ "name": "mike1858",

909+ "id": 223734115,

910+ "comment_id": 3615055552,

911+ "created_at": "2025-12-05T02:26:29Z",

912+ "repoId": 987670088,

913+ "pullRequestNo": 1553

914+ },

915+ {

916+ "name": "Guxinpei",

917+ "id": 20122411,

918+ "comment_id": 3617461839,

919+ "created_at": "2025-12-05T15:51:04Z",

920+ "repoId": 987670088,

921+ "pullRequestNo": 1555

922+ },

923+ {

924+ "name": "mikluko",

925+ "id": 42915,

926+ "comment_id": 3620605876,

927+ "created_at": "2025-12-06T15:43:45Z",

928+ "repoId": 987670088,

929+ "pullRequestNo": 1558

930+ },

931+ {

932+ "name": "Gustave-241021",

933+ "id": 185743951,

934+ "comment_id": 3620851967,

935+ "created_at": "2025-12-06T18:13:11Z",

936+ "repoId": 987670088,

937+ "pullRequestNo": 1560

938+ },

939+ {

940+ "name": "mengwong",

941+ "id": 1480631,

942+ "comment_id": 3636765109,

943+ "created_at": "2025-12-10T12:04:50Z",

944+ "repoId": 987670088,

945+ "pullRequestNo": 1592

946+ },

947+ {

948+ "name": "nonsleepr",

949+ "id": 2337602,

950+ "comment_id": 3644171671,

951+ "created_at": "2025-12-11T23:09:21Z",

952+ "repoId": 987670088,

953+ "pullRequestNo": 1611

954+ },

955+ {

956+ "name": "strawberry-code",

957+ "id": 18684103,

958+ "comment_id": 3650628850,

959+ "created_at": "2025-12-14T09:41:12Z",

960+ "repoId": 987670088,

961+ "pullRequestNo": 1628

962+ },

963+ {

964+ "name": "flatsponge",

965+ "id": 104839509,

966+ "comment_id": 3673002560,

967+ "created_at": "2025-12-19T01:11:45Z",

968+ "repoId": 987670088,

969+ "pullRequestNo": 1668

970+ },

971+ {

972+ "name": "jonhoo",

973+ "id": 176295,

974+ "comment_id": 3674853134,

975+ "created_at": "2025-12-19T12:14:08Z",

976+ "repoId": 987670088,

977+ "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

730 }

2098 }

731 ]

2099 ]

732}

2100}

.github/dependabot.yml+1

@@ -24,6 +24,7 @@ updates:

24 - dependency-name: github.com/charmbracelet/lipgloss/v2

25 versions:

26 - v2.0.0-beta1

27+ - dependency-name: mvdan.cc/sh/moreinterp

28 - package-ecosystem: "github-actions"

29 - package-ecosystem: "github-actions"

29 directory: "/"

30 directory: "/"

.github/labeler.yml+14

@@ -3,6 +3,10 @@

4"area: ci":

5 - "/^ci: /i"

6+"area: crush run":

7+ - "/crush run/i"

8+ - "/headless/i"

9+ - "/non-interactive/i"

6"area: diff":

10"area: diff":

7 - "/diff/i"

11 - "/diff/i"

8"area: docs":

12"area: docs":

@@ -41,16 +45,24 @@

41 - "/(panic|crash|segfault)/i"

45 - "/(panic|crash|segfault)/i"

42"provider: anthropic claude":

46"provider: anthropic claude":

43 - "/(anthropic|claude)/i"

47 - "/(anthropic|claude)/i"

48+"provider: avian":

49+ - "/avian/i"

44"provider: aws bedrock":

50"provider: aws bedrock":

45 - "/(aws|bedrock)/i"

51 - "/(aws|bedrock)/i"

46"provider: azure":

52"provider: azure":

47 - "/azure/i"

53 - "/azure/i"

54+"provider: github copilot":

55+ - "/copilot/i"

48"provider: google gemini":

56"provider: google gemini":

49 - "/gemini/i"

57 - "/gemini/i"

50"provider: google vertex":

58"provider: google vertex":

51 - "/vertex/i"

59 - "/vertex/i"

60+"provider: hyper":

61+ - "/hyper/i"

52"provider: kimi":

62"provider: kimi":

53 - "/kimi/i"

63 - "/kimi/i"

64+"provider: minimax":

65+ - "/minimax/i"

54"provider: ollama":

66"provider: ollama":

55 - "/llama/i"

67 - "/llama/i"

56"provider: openai chatgpt":

68"provider: openai chatgpt":

@@ -59,6 +71,8 @@

59 - "/openrouter/i"

71 - "/openrouter/i"

60"provider: qwen":

72"provider: qwen":

61 - "/qwen/i"

73 - "/qwen/i"

74+"provider: vercel":

75+ - "/vercel/i"

62"provider: xai grok":

76"provider: xai grok":

63 - "/(xai|x\\.ai|grok)/i"

77 - "/(xai|x\\.ai|grok)/i"

64"security":

78"security":

.github/workflows/build.yml+26−7

@@ -1,11 +1,30 @@

1name: build

2−on: [push, pull_request]

2+on:

3+ push:

4+ branches: [main]

5+ pull_request:

7+permissions:

8+ contents: read

10+concurrency:

11+ group: build-${{ github.event.pull_request.number || github.ref }}

12+ cancel-in-progress: true

4jobs:

14jobs:

5 build:

15 build:

6− uses: charmbracelet/meta/.github/workflows/build.yml@main

16+ strategy:

7− with:

17+ matrix:

8− go-version: ""

18+ os: [ubuntu-latest, macos-latest, windows-latest]

9− go-version-file: ./go.mod

19+ runs-on: ${{ matrix.os }}

10− secrets:

20+ steps:

11− gh_pat: "${{ secrets.PERSONAL_ACCESS_TOKEN }}"

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 ./...

.github/workflows/cla.yml+2−2

@@ -22,14 +22,14 @@ jobs:

22 github.event.comment.body == 'recheck' ||

23 github.event.comment.body == 'I have read the Contributor License Agreement (CLA) and hereby sign the CLA.' ||

24 github.event_name == 'pull_request_target'

25− uses: contributor-assistant/github-action@ca4a40a7d1004f18d9960b404b97e5f30a505a08 # v2.6.1

25+ uses: contributor-assistant/github-action@58daaf842ac3e26d08c2bdf26770d6e9c5b965a9

26 env:

27 GITHUB_TOKEN: ${{ secrets.PERSONAL_ACCESS_TOKEN }}

28 with:

29 path-to-signatures: ".github/cla-signatures.json"

30 path-to-document: "https://github.com/charmbracelet/crush/blob/main/CLA.md"

31 branch: "main"

32− allowlist: charmcli,charmcrush,dependabot[bot]

32+ allowlist: charmcli,charmcrush,dependabot[bot],Copilot

33 custom-pr-sign-comment: "I have read the Contributor License Agreement (CLA) and hereby sign the CLA."

34 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."

35 lock-pullrequest-aftermerge: false

.github/workflows/labeler.yml+1−1

@@ -14,6 +14,7 @@ on:

15permissions:

16 issues: write

17+ pull-requests: write

17 contents: read

18 contents: read

19jobs:

20jobs:

@@ -26,5 +27,4 @@ jobs:

26 enable-versioned-regex: 0

27 enable-versioned-regex: 0

27 include-title: 1

28 include-title: 1

28 include-body: 0

29 include-body: 0

29− repo-token: ${{ secrets.PERSONAL_ACCESS_TOKEN }}

30 issue-number: ${{ github.event.inputs.issue-number || github.event.issue.number || github.event.pull_request.number }}

.github/workflows/lint.yml+2−1

@@ -1,6 +1,7 @@

1name: lint

2on:

3 push:

4+ branches: [main]

4 pull_request:

5 pull_request:

6jobs:

7jobs:

@@ -8,5 +9,5 @@ jobs:

8 uses: charmbracelet/meta/.github/workflows/lint.yml@main

9 uses: charmbracelet/meta/.github/workflows/lint.yml@main

9 with:

10 with:

10 golangci_path: .golangci.yml

11 golangci_path: .golangci.yml

11− golangci_version: v2.4

12+ golangci_version: v2.11

12 timeout: 10m

13 timeout: 10m

.github/workflows/nightly.yml+1−1

@@ -11,7 +11,7 @@ jobs:

11 outputs:

12 should_run: ${{ steps.check.outputs.should_run }}

13 steps:

14− - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0

14+ - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0

15 with:

16 fetch-depth: 1

17 - id: check

.github/workflows/release.yml+1−3

@@ -15,7 +15,7 @@ jobs:

15 goreleaser:

16 uses: charmbracelet/meta/.github/workflows/goreleaser.yml@main

17 with:

18− go_version: "1.25"

18+ go_version: "1.26"

19 macos_sign_entitlements: "./.github/entitlements.plist"

20 secrets:

21 docker_username: ${{ secrets.DOCKERHUB_USERNAME }}

@@ -25,8 +25,6 @@ jobs:

25 fury_token: ${{ secrets.FURY_TOKEN }}

26 nfpm_gpg_key: ${{ secrets.NFPM_GPG_KEY }}

27 nfpm_passphrase: ${{ secrets.NFPM_PASSPHRASE }}

28− npm_token: ${{ secrets.NPM_TOKEN }}

29− snapcraft_token: ${{ secrets.SNAPCRAFT_TOKEN }}

30 aur_key: ${{ secrets.AUR_KEY }}

28 aur_key: ${{ secrets.AUR_KEY }}

31 macos_sign_p12: ${{ secrets.MACOS_SIGN_P12 }}

29 macos_sign_p12: ${{ secrets.MACOS_SIGN_P12 }}

32 macos_sign_password: ${{ secrets.MACOS_SIGN_PASSWORD }}

30 macos_sign_password: ${{ secrets.MACOS_SIGN_PASSWORD }}

.github/workflows/schema-update.yml+11−8

@@ -1,26 +1,29 @@

1−name: Update Schema

1+name: Update files

3on:

4 push:

5 branches: [main]

6 paths:

7 - "internal/config/**"

8+ - "internal/agent/hyper/**"

9+ workflow_dispatch:

9jobs:

11jobs:

10 update-schema:

12 update-schema:

11 runs-on: ubuntu-latest

13 runs-on: ubuntu-latest

12 steps:

14 steps:

13− - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0

15+ - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0

14 with:

16 with:

15 token: ${{ secrets.PERSONAL_ACCESS_TOKEN }}

17 token: ${{ secrets.PERSONAL_ACCESS_TOKEN }}

16− - uses: actions/setup-go@44694675825211faa026b3c33043df3e48a5fa00 # v6.0.0

18+ - uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0

17 with:

19 with:

18 go-version-file: go.mod

20 go-version-file: go.mod

19 - run: go run . schema > ./schema.json

21 - run: go run . schema > ./schema.json

22+ - run: go generate ./internal/agent/hyper/...

20− - uses: stefanzweifel/git-auto-commit-action@28e16e81777b558cc906c8750092100bbb34c5e3 # v5

23+ - uses: stefanzweifel/git-auto-commit-action@4a55954c782fc1ea30b9056cd3e7a2b40ca8887d # v5

21 with:

24 with:

22− commit_message: "chore: auto-update generated files"

25+ commit_message: "chore: auto-update files"

23 branch: main

26 branch: main

24− commit_user_name: actions-user

27+ commit_user_name: Charm

25− commit_user_email: actions@github.com

28+ commit_user_email: 124303983+charmcli@users.noreply.github.com

26− commit_author: actions-user <actions@github.com>

29+ commit_author: Charm <124303983+charmcli@users.noreply.github.com>

.github/workflows/security.ymlnew file+92

@@ -0,0 +1,92 @@

1+name: "security"

3+on:

4+ pull_request:

5+ push:

6+ branches: [main]

7+ schedule:

8+ - cron: "0 2 * * *"

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.ymlnew file+34

@@ -0,0 +1,34 @@

1+name: snapshot

3+on:

4+ push:

5+ branches:

6+ - main

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+7−2

@@ -42,11 +42,16 @@ Thumbs.db

42.env

43.env.local

45+# Nix/direnv

46+.direnv/

47+/result

48+

45**/.crush/**

49**/.crush/**

47/crush

51/crush

52+/tmp/

49manpages/

54manpages/

50−completions/

55+completions/crush.*sh

51−!internal/tui/components/completions/

52.prettierignore

56.prettierignore

57+.task

.golangci.yml+16−4

@@ -2,6 +2,7 @@ version: "2"

2linters:

3 enable:

4 - bodyclose

5+ - errcheck

5 # - exhaustive

6 # - exhaustive

6 # - goconst

7 # - goconst

7 # - godot

8 # - godot

@@ -9,6 +10,7 @@ linters:

9 # - gomoddirectives

10 # - gomoddirectives

10 - goprintffuncname

11 - goprintffuncname

11 # - gosec

12 # - gosec

13+ - ineffassign

12 - misspell

14 - misspell

13 # - nakedret

15 # - nakedret

14 # - nestif

16 # - nestif

@@ -23,20 +25,30 @@ linters:

23 - tparallel

25 - tparallel

24 # - unconvert

26 # - unconvert

25 # - unparam

27 # - unparam

28+ - unused

26 - whitespace

29 - whitespace

27 # - wrapcheck

30 # - wrapcheck

28− disable:

29− - errcheck

30− - ineffassign

31− - unused

32 exclusions:

31 exclusions:

33 generated: lax

32 generated: lax

34 presets:

33 presets:

35 - common-false-positives

34 - 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

36 rules:

39 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

37 - text: '(slog|log)\.\w+'

45 - text: '(slog|log)\.\w+'

38 linters:

46 linters:

39 - noctx

47 - noctx

48+ - path: internal/shell/run.go

49+ text: "SA1019.*interp.ExecHandler"

50+ linters:

51+ - staticcheck

40issues:

52issues:

41 max-issues-per-linter: 0

53 max-issues-per-linter: 0

42 max-same-issues: 0

54 max-same-issues: 0

.goreleaser.yml+22−6

@@ -98,6 +98,7 @@ checksum:

99aur_sources:

100 - private_key: "{{ .Env.AUR_KEY }}"

101+ disable: "{{ with .Prerelease }}true{{ end }}"

101 git_url: "ssh://aur@aur.archlinux.org/crush.git"

102 git_url: "ssh://aur@aur.archlinux.org/crush.git"

102 commit_author:

103 commit_author:

103 name: "Charm"

104 name: "Charm"

@@ -115,7 +116,7 @@ aur_sources:

115 export CGO_CXXFLAGS="${CXXFLAGS}"

116 export CGO_CXXFLAGS="${CXXFLAGS}"

116 export CGO_LDFLAGS="${LDFLAGS}"

117 export CGO_LDFLAGS="${LDFLAGS}"

117 export GOFLAGS="-buildmode=pie -trimpath -mod=readonly -modcacherw"

118 export GOFLAGS="-buildmode=pie -trimpath -mod=readonly -modcacherw"

118− go build -ldflags="-w -s -buildid='' -linkmode=external -X main.version=v${pkgver}" .

119+ go build -ldflags="-w -s -buildid='' -linkmode=external -X github.com/charmbracelet/crush/internal/version.Version=v${pkgver}" .

119 ./crush completion bash >./completions/crush.bash

120 ./crush completion bash >./completions/crush.bash

120 ./crush completion zsh >./completions/crush.zsh

121 ./crush completion zsh >./completions/crush.zsh

121 ./crush completion fish >./completions/crush.fish

122 ./crush completion fish >./completions/crush.fish

@@ -141,6 +142,7 @@ aur_sources:

141

142

142aurs:

143aurs:

143 - private_key: "{{ .Env.AUR_KEY }}"

144 - private_key: "{{ .Env.AUR_KEY }}"

145+ disable: "{{ with .Prerelease }}true{{ end }}"

144 git_url: "ssh://aur@aur.archlinux.org/crush-bin.git"

146 git_url: "ssh://aur@aur.archlinux.org/crush-bin.git"

145 commit_author:

147 commit_author:

146 name: "Charm"

148 name: "Charm"

@@ -150,7 +152,14 @@ aurs:

150 conflicts:

152 conflicts:

151 - crush

153 - crush

152 package: |-

154 package: |-

155+ case "$CARCH" in

156+ aarch64)

157+ cd "${srcdir}/crush_${pkgver}_Linux_arm64"

158+ ;;

159+ *)

153− cd "${srcdir}/crush_${pkgver}_Linux_${CARCH}"

160+ cd "${srcdir}/crush_${pkgver}_Linux_${CARCH}"

161+ ;;

162+ esac

154 # bin

163 # bin

155 install -Dm755 "./crush" "${pkgdir}/usr/bin/crush"

164 install -Dm755 "./crush" "${pkgdir}/usr/bin/crush"

156 # license

165 # license

@@ -170,7 +179,7 @@ aurs:

170 install -Dm644 README* "${pkgdir}/usr/share/doc/crush/"

179 install -Dm644 README* "${pkgdir}/usr/share/doc/crush/"

171

180

172furies:

181furies:

173− - disable: "{{ .IsNightly }}"

182+ - disable: "{{ if (or .Prerelease .IsNightly) }}true{{ end }}"

174 account: "{{ with .Env.FURY_TOKEN }}charmcli{{ else }}{{ end }}"

183 account: "{{ with .Env.FURY_TOKEN }}charmcli{{ else }}{{ end }}"

175 secret_name: FURY_TOKEN

184 secret_name: FURY_TOKEN

176

185

@@ -179,6 +188,7 @@ brews:

179 owner: charmbracelet

188 owner: charmbracelet

180 name: homebrew-tap

189 name: homebrew-tap

181 token: "{{ .Env.HOMEBREW_TAP_GITHUB_TOKEN }}"

190 token: "{{ .Env.HOMEBREW_TAP_GITHUB_TOKEN }}"

191+ skip_upload: "{{ with .Prerelease }}true{{ end }}"

182 commit_author:

192 commit_author:

183 name: "Charm"

193 name: "Charm"

184 email: "charmcli@users.noreply.github.com"

194 email: "charmcli@users.noreply.github.com"

@@ -194,6 +204,7 @@ scoops:

194 owner: charmbracelet

204 owner: charmbracelet

195 name: scoop-bucket

205 name: scoop-bucket

196 token: "{{ .Env.HOMEBREW_TAP_GITHUB_TOKEN }}"

206 token: "{{ .Env.HOMEBREW_TAP_GITHUB_TOKEN }}"

207+ skip_upload: "{{ with .Prerelease }}true{{ end }}"

197 commit_author:

208 commit_author:

198 name: "Charm"

209 name: "Charm"

199 email: "charmcli@users.noreply.github.com"

210 email: "charmcli@users.noreply.github.com"

@@ -203,6 +214,7 @@ npms:

203 repository: "git+https://github.com/charmbracelet/crush.git"

214 repository: "git+https://github.com/charmbracelet/crush.git"

204 bugs: https://github.com/charmbracelet/crush/issues

215 bugs: https://github.com/charmbracelet/crush/issues

205 access: public

216 access: public

217+ disable: "{{ with .Prerelease }}true{{ end }}"

206

218

207nfpms:

219nfpms:

208 - formats:

220 - formats:

@@ -230,11 +242,10 @@ nfpms:

230

242

231signs:

243signs:

232 - cmd: cosign

244 - cmd: cosign

233− certificate: "${artifact}.pem"

245+ signature: "${artifact}.sigstore.json"

234 args:

246 args:

235 - sign-blob

247 - sign-blob

236− - "--output-certificate=${certificate}"

237− - "--output-signature=${signature}"

248+ - "--bundle=${signature}"

238 - "${artifact}"

249 - "${artifact}"

239 - "--yes"

250 - "--yes"

240 artifacts: checksum

251 artifacts: checksum

@@ -257,6 +268,8 @@ nix:

257 name: "Charm"

268 name: "Charm"

258 email: "charmcli@users.noreply.github.com"

269 email: "charmcli@users.noreply.github.com"

259 license: fsl11Mit

270 license: fsl11Mit

271+ formatter: nixfmt

272+ skip_upload: "{{ with .Prerelease }}true{{ end }}"

260 extra_install: |-

273 extra_install: |-

261 installManPage ./manpages/crush.1.gz

274 installManPage ./manpages/crush.1.gz

262 installShellCompletion ./completions/*

275 installShellCompletion ./completions/*

@@ -267,6 +280,7 @@ winget:

267 publisher_url: https://charm.land

280 publisher_url: https://charm.land

268 release_notes_url: "https://github.com/charmbracelet/crush/releases/tag/{{.Tag}}"

281 release_notes_url: "https://github.com/charmbracelet/crush/releases/tag/{{.Tag}}"

269 license_url: https://github.com/charmbracelet/crush/blob/main/LICENSE.md

282 license_url: https://github.com/charmbracelet/crush/blob/main/LICENSE.md

283+ skip_upload: "{{ with .Prerelease }}true{{ end }}"

270 commit_author:

284 commit_author:

271 name: "Charm"

285 name: "Charm"

272 email: "charmcli@users.noreply.github.com"

286 email: "charmcli@users.noreply.github.com"

@@ -283,6 +297,8 @@ winget:

283 owner: microsoft

297 owner: microsoft

284 name: winget-pkgs

298 name: winget-pkgs

285 branch: master

299 branch: master

300+ body: |

301+ /cc @andreynering

286

302

287changelog:

303changelog:

288 sort: asc

304 sort: asc

AGENTS.mdnew file+223

@@ -0,0 +1,223 @@

1+# Crush Development Guide

3+## Project Overview

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.mddeleted−65

@@ -1,65 +0,0 @@

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−## Committing

64−

65−- ALWAYS use semantic commits (`fix:`, `feat:`, `chore:`, `refactor:`, `docs:`, `sec:`, etc).

LICENSE.md+1−1

@@ -6,7 +6,7 @@ FSL-1.1-MIT

7## Notice

11## Terms and Conditions

README.md+399−76

@@ -1,13 +1,16 @@

1# Crush

3+> [!NOTE]

4+> This is a personal fork of [charmbracelet/crush](https://github.com/charmbracelet/crush) with UI/UX tweaks and performance improvements.

3

6

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>

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>

5 <a href="https://github.com/charmbracelet/crush/releases"><img src="https://img.shields.io/github/release/charmbracelet/crush" alt="Latest Release"></a>

8 <a href="https://github.com/charmbracelet/crush/releases"><img src="https://img.shields.io/github/release/charmbracelet/crush" alt="Latest Release"></a>

6 <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>

9 <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>

7

10

9Your new coding bestie, now available in your favourite terminal. Your tools, your code, and your workflows, wired into your LLM of choice.

12Your new coding bestie, now available in your favourite terminal. Your tools, your code, and your workflows, wired into your LLM of choice.

10−你的新编程伙伴，现在就在你最爱的终端中。 你的工具、代码和工作流，都与您选择的 LLM 模型紧密相连。

13+终端里的编程新搭档， 无缝接入你的工具、代码与工作流，全面兼容主流 LLM 模型。

12<img width="800" alt="Crush Demo" src="https://github.com/user-attachments/assets/58280caf-851b-470a-b6f7-d5c4ea8a1968" />

15<img width="800" alt="Crush Demo" src="https://github.com/user-attachments/assets/58280caf-851b-470a-b6f7-d5c4ea8a1968" />

@@ -18,7 +21,8 @@

18- **Session-Based:** maintain multiple work sessions and contexts per project

21- **Session-Based:** maintain multiple work sessions and contexts per project

19- **LSP-Enhanced:** Crush uses LSPs for additional context, just like you do

22- **LSP-Enhanced:** Crush uses LSPs for additional context, just like you do

20- **Extensible:** add capabilities via MCPs (`http`, `stdio`, and `sse`)

23- **Extensible:** add capabilities via MCPs (`http`, `stdio`, and `sse`)

21−- **Works Everywhere:** first-class support in every terminal on macOS, Linux, Windows (PowerShell and WSL), FreeBSD, OpenBSD, and NetBSD

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

23## Installation

27## Installation

@@ -36,6 +40,9 @@ yay -S crush-bin

37# Nix

41# Nix

38nix run github:numtide/nix-ai-tools#crush

42nix run github:numtide/nix-ai-tools#crush

43+

44+# FreeBSD

45+pkg install crush

39```

46```

41Windows users:

48Windows users:

@@ -52,9 +59,9 @@ scoop install crush

52<details>

59<details>

53<summary>Nix (NUR)</summary>

60<summary>Nix (NUR)</summary>

55−Crush is available via [NUR](https://github.com/nix-community/NUR) in `nur.repos.charmbracelet.crush`.

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.

57−You can also try out Crush via `nix-shell`:

64+You can also try out Crush via the NUR with `nix-shell`:

59```bash

66```bash

60# Add the NUR channel.

67# Add the NUR channel.

@@ -165,35 +172,56 @@ go install github.com/charmbracelet/crush@latest

165> [!WARNING]

172> [!WARNING]

166> Productivity may increase when using Crush and you may find yourself nerd

173> Productivity may increase when using Crush and you may find yourself nerd

167> sniped when first using the application. If the symptoms persist, join the

174> sniped when first using the application. If the symptoms persist, join the

168−> [Discord][discord] and nerd snipe the rest of us.

175+> [Slack][slack] or [Discord][discord] and nerd snipe the rest of us.

169

176

170## Getting Started

177## Getting Started

171

178

172The quickest way to get started is to grab an API key for your preferred

179The quickest way to get started is to grab an API key for your preferred

173−provider such as Anthropic, OpenAI, Groq, or OpenRouter and just start

180+provider such as Anthropic, OpenAI, Groq, OpenRouter, or Vercel AI Gateway and just start

174Crush. You'll be prompted to enter your API key.

181Crush. You'll be prompted to enter your API key.

175

182

176That said, you can also set environment variables for preferred providers.

183That said, you can also set environment variables for preferred providers.

177

184

178| Environment Variable | Provider |

185| Environment Variable | Provider |

179| --------------------------- | -------------------------------------------------- |

186| --------------------------- | -------------------------------------------------- |

187+| `HYPER_API_KEY` | Charm Hyper |

180| `ANTHROPIC_API_KEY` | Anthropic |

188| `ANTHROPIC_API_KEY` | Anthropic |

181| `OPENAI_API_KEY` | OpenAI |

189| `OPENAI_API_KEY` | OpenAI |

182−| `OPENROUTER_API_KEY` | OpenRouter |

190+| `VERCEL_API_KEY` | Vercel AI Gateway |

183| `GEMINI_API_KEY` | Google Gemini |

191| `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 |

184| `CEREBRAS_API_KEY` | Cerebras |

196| `CEREBRAS_API_KEY` | Cerebras |

185−| `HF_TOKEN` | Huggingface Inference |

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 |

186| `VERTEXAI_PROJECT` | Google Cloud VertexAI (Gemini) |

204| `VERTEXAI_PROJECT` | Google Cloud VertexAI (Gemini) |

187| `VERTEXAI_LOCATION` | Google Cloud VertexAI (Gemini) |

205| `VERTEXAI_LOCATION` | Google Cloud VertexAI (Gemini) |

188−| `GROQ_API_KEY` | Groq |

189−| `AWS_ACCESS_KEY_ID` | AWS Bedrock (Claude) |

206+| `AWS_ACCESS_KEY_ID` | Amazon Bedrock (Claude) |

190−| `AWS_SECRET_ACCESS_KEY` | AWS Bedrock (Claude) |

207+| `AWS_SECRET_ACCESS_KEY` | Amazon Bedrock (Claude) |

191−| `AWS_REGION` | AWS Bedrock (Claude) |

208+| `AWS_REGION` | Amazon Bedrock (Claude) |

192−| `AWS_PROFILE` | AWS Bedrock (Custom Profile) |

209+| `AWS_PROFILE` | Amazon Bedrock (Custom Profile) |

193−| `AWS_BEARER_TOKEN_BEDROCK` | AWS Bedrock |

210+| `AWS_BEARER_TOKEN_BEDROCK` | Amazon Bedrock |

194| `AZURE_OPENAI_API_ENDPOINT` | Azure OpenAI models |

211| `AZURE_OPENAI_API_ENDPOINT` | Azure OpenAI models |

195| `AZURE_OPENAI_API_KEY` | Azure OpenAI models (optional when using Entra ID) |

212| `AZURE_OPENAI_API_KEY` | Azure OpenAI models (optional when using Entra ID) |

196| `AZURE_OPENAI_API_VERSION` | Azure OpenAI models |

213| `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)

197

225

198### By the Way

226### By the Way

199

227

@@ -205,13 +233,17 @@ Crush’s default model listing is managed in [Catwalk](https://github.com/charm

205

233

206## Configuration

234## Configuration

207

235

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+

208Crush runs great with no configuration. That said, if you do need or want to

240Crush runs great with no configuration. That said, if you do need or want to

209customize Crush, configuration can be added either local to the project itself,

241customize Crush, configuration can be added either local to the project itself,

210or globally, with the following priority:

242or globally, with the following priority:

211

243

2121. `.crush.json`

2441. `.crush.json`

2132. `crush.json`

2452. `crush.json`

214−3. `$HOME/.config/crush/crush.json` (Windows: `%USERPROFILE%\AppData\Local\crush\crush.json`)

246+3. `$HOME/.config/crush/crush.json`

215

247

216Configuration itself is stored as a JSON object:

248Configuration itself is stored as a JSON object:

217

249

@@ -222,7 +254,8 @@ Configuration itself is stored as a JSON object:

222}

254}

223```

255```

224

256

225−As an additional note, Crush also stores ephemeral data, such as application state, in one additional location:

257+As an additional note, Crush also stores ephemeral data, such as application

258+state, in one additional location:

226

259

227```bash

260```bash

228# Unix

261# Unix

@@ -232,6 +265,12 @@ $HOME/.local/share/crush/crush.json

232%LOCALAPPDATA%\crush\crush.json

265%LOCALAPPDATA%\crush\crush.json

233```

266```

234

267

268+> [!TIP]

269+> You can override the user and data config locations by setting:

270+>

271+> - `CRUSH_GLOBAL_CONFIG`

272+> - `CRUSH_GLOBAL_DATA`

273+

235### LSPs

274### LSPs

236

275

237Crush can use LSPs for additional context to help inform its decisions, just

276Crush can use LSPs for additional context to help inform its decisions, just

@@ -260,10 +299,36 @@ like you would. LSPs can be added manually like so:

260

299

261### MCPs

300### MCPs

262

301

263−Crush also supports Model Context Protocol (MCP) servers through three

302+Crush also supports Model Context Protocol (MCP) servers through three transport

264−transport types: `stdio` for command-line servers, `http` for HTTP endpoints,

303+types: `stdio` for command-line servers, `http` for HTTP endpoints, and `sse`

265−and `sse` for Server-Sent Events. Environment variable expansion is supported

304+for Server-Sent Events.

266−using `$(echo $VAR)` syntax.

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.

267

332

268```json

333```json

269{

334{

@@ -275,17 +340,19 @@ using `$(echo $VAR)` syntax.

275 "args": ["/path/to/mcp-server.js"],

340 "args": ["/path/to/mcp-server.js"],

276 "timeout": 120,

341 "timeout": 120,

277 "disabled": false,

342 "disabled": false,

343+ "disabled_tools": ["some-tool-name"],

278 "env": {

344 "env": {

279 "NODE_ENV": "production"

345 "NODE_ENV": "production"

280 }

346 }

281 },

347 },

282 "github": {

348 "github": {

283 "type": "http",

349 "type": "http",

284− "url": "https://example.com/mcp/",

350+ "url": "https://api.githubcopilot.com/mcp/",

285 "timeout": 120,

351 "timeout": 120,

286 "disabled": false,

352 "disabled": false,

353+ "disabled_tools": ["create_issue", "create_pull_request"],

287 "headers": {

354 "headers": {

288− "Authorization": "$(echo Bearer $EXAMPLE_MCP_TOKEN)"

355+ "Authorization": "Bearer $GH_PAT"

289 }

356 }

290 },

357 },

291 "streaming-service": {

358 "streaming-service": {

@@ -301,6 +368,72 @@ using `$(echo $VAR)` syntax.

301}

368}

302```

369```

303

370

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+

304### Ignoring Files

437### Ignoring Files

305

438

306Crush respects `.gitignore` files by default, but you can also create a

439Crush respects `.gitignore` files by default, but you can also create a

@@ -335,79 +468,204 @@ permissions. Use this with care.

335You can also skip all permission prompts entirely by running Crush with the

468You can also skip all permission prompts entirely by running Crush with the

336`--yolo` flag. Be very, very careful with this feature.

469`--yolo` flag. Be very, very careful with this feature.

337

470

338−### Attribution Settings

471+### Disabling Built-In Tools

339

472

340−By default, Crush adds attribution information to Git commits and pull requests

473+If you'd like to prevent Crush from using certain built-in tools entirely, you

341−it creates. You can customize this behavior with the `attribution` option:

474+can disable them via the `options.disabled_tools` list. Disabled tools are

475+completely hidden from the agent.

342

476

343```json

477```json

344{

478{

345 "$schema": "https://charm.land/crush.json",

479 "$schema": "https://charm.land/crush.json",

346 "options": {

480 "options": {

347− "attribution": {

481+ "disabled_tools": ["bash", "sourcegraph"]

348− "co_authored_by": true,

349− "generated_with": true

350− }

351 }

482 }

352}

483}

353```

484```

354

485

355−- `co_authored_by`: When true (default), adds `Co-Authored-By: Crush <crush@charm.land>` to commit messages

486+To disable tools from MCP servers, see the [MCP config section](#mcps).

356−- `generated_with`: When true (default), adds `💘 Generated with Crush` line to commit messages and PR descriptions

357

487

358−### Local Models

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+```

359

588

360−Local models can also be configured via OpenAI-compatible API. Here are two common examples:

589+Skills with `disable-model-invocation` won't appear in the model's available skills list but can still be invoked manually by users.

361

590

362−#### Ollama

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+

610+### Initialization

611+

612+When you initialize a project, Crush analyzes your codebase and creates

613+a context file that helps it work more effectively in future sessions.

614+By default, this file is named `AGENTS.md`, but you can customize the

615+name and location with the `initialize_as` option:

363

616

364```json

617```json

365{

618{

366− "providers": {

619+ "$schema": "https://charm.land/crush.json",

367− "ollama": {

620+ "options": {

368− "name": "Ollama",

621+ "initialize_as": "AGENTS.md"

369− "base_url": "http://localhost:11434/v1/",

370− "type": "openai",

371− "models": [

372− {

373− "name": "Qwen 3 30B",

374− "id": "qwen3:30b",

375− "context_window": 256000,

376− "default_max_tokens": 20000

377− }

378− ]

379− }

380 }

622 }

381}

623}

382```

624```

383

625

384−#### LM Studio

626+This is useful if you prefer a different naming convention or want to

627+place the file in a specific directory (e.g., `CRUSH.md` or

628+`docs/LLMs.md`). Crush will fill the file with project-specific context

629+like build commands, code patterns, and conventions it discovered during

630+initialization.

631+

632+### Attribution Settings

633+

634+By default, Crush adds attribution information to Git commits and pull requests

635+it creates. You can customize this behavior with the `attribution` option:

385

636

386```json

637```json

387{

638{

388− "providers": {

639+ "$schema": "https://charm.land/crush.json",

389− "lmstudio": {

640+ "options": {

390− "name": "LM Studio",

641+ "attribution": {

391− "base_url": "http://localhost:1234/v1/",

642+ "trailer_style": "co-authored-by",

392− "type": "openai",

643+ "generated_with": true

393− "models": [

394− {

395− "name": "Qwen 3 30B",

396− "id": "qwen/qwen3-30b-a3b-2507",

397− "context_window": 256000,

398− "default_max_tokens": 20000

399− }

400− ]

401 }

644 }

402 }

645 }

403}

646}

404```

647```

405

648

649+- `trailer_style`: Controls the attribution trailer added to commit messages

650+ (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

654+- `generated_with`: When true (default), adds `💘 Generated with Crush` line to

655+ commit messages and PR descriptions

656+

406### Custom Providers

657### Custom Providers

407

658

408Crush supports custom provider configurations for both OpenAI-compatible and

659Crush supports custom provider configurations for both OpenAI-compatible and

409Anthropic-compatible APIs.

660Anthropic-compatible APIs.

410

661

662+> [!NOTE]

663+> Note that we support two "types" for OpenAI. Make sure to choose the right one

664+> 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.

668+

411#### OpenAI-Compatible APIs

669#### OpenAI-Compatible APIs

412

670

413Here’s an example configuration for Deepseek, which uses an OpenAI-compatible

671Here’s an example configuration for Deepseek, which uses an OpenAI-compatible

@@ -418,7 +676,7 @@ API. Don't forget to set `DEEPSEEK_API_KEY` in your environment.

418 "$schema": "https://charm.land/crush.json",

676 "$schema": "https://charm.land/crush.json",

419 "providers": {

677 "providers": {

420 "deepseek": {

678 "deepseek": {

421− "type": "openai",

679+ "type": "openai-compat",

422 "base_url": "https://api.deepseek.com/v1",

680 "base_url": "https://api.deepseek.com/v1",

423 "api_key": "$DEEPSEEK_API_KEY",

681 "api_key": "$DEEPSEEK_API_KEY",

424 "models": [

682 "models": [

@@ -515,6 +773,68 @@ To add specific models to the configuration, configure as such:

515}

773}

516```

774```

517

775

776+### Local Models

777+

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.

782+

783+```json

784+{

785+ "providers": {

786+ "ollama": {

787+ "name": "Ollama",

788+ "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"

804+ }

805+ }

806+}

807+```

808+

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.

816+

817+```json

818+{

819+ "providers": {

820+ "ollama": {

821+ "name": "Ollama",

822+ "base_url": "http://localhost:11434/v1/",

823+ "type": "ollama",

824+ "models": [

825+ {

826+ "name": "Qwen 3 30B",

827+ "id": "qwen3:30b",

828+ "context_window": 256000,

829+ "default_max_tokens": 20000

830+ }

831+ ],

832+ "discover_models": true

833+ }

834+ }

835+}

836+```

837+

518## Logging

838## Logging

519

839

520Sometimes you need to look at logs. Luckily, Crush logs all sorts of

840Sometimes you need to look at logs. Luckily, Crush logs all sorts of

@@ -627,19 +947,21 @@ Or by setting the following in your config:

627}

947}

628```

948```

629

949

630−Crush also respects the [`DO_NOT_TRACK`](https://consoledonottrack.com)

950+Crush also respects the [`DO_NOT_TRACK`](https://donottrack.sh/) convention

631−convention which can be enabled via `export DO_NOT_TRACK=1`.

951+which can be enabled via `export DO_NOT_TRACK=1`.

952+

953+## Q&A

632

954

633−## A Note on Claude Max and GitHub Copilot

955+### Why is clipboard copy and paste not working?

634

956

635−Crush only supports model providers through official, compliant APIs. We do not

957+Installing an extra tool might be needed on Unix-like environments.

636−support or endorse any methods that rely on personal Claude Max and GitHub

637−Copilot accounts or OAuth workarounds, which violate Anthropic and

638−Microsoft’s Terms of Service.

639

958

640−We’re committed to building sustainable, trusted integrations with model

959+| Environment | Tool |

641−providers. If you’re a provider interested in working with us,

960+| ------------------- | ------------------------ |

642−[reach out](mailto:vt100@charm.sh).

961+| Windows | Native support |

962+| macOS | Native support |

963+| Linux/BSD + Wayland | `wl-copy` and `wl-paste` |

964+| Linux/BSD + X11 | `xclip` or `xsel` |

643

965

644## Contributing

966## Contributing

645

967

@@ -650,11 +972,12 @@ See the [contributing guide](https://github.com/charmbracelet/crush?tab=contribu

650We’d love to hear your thoughts on this project. Need help? We gotchu. You can find us on:

972We’d love to hear your thoughts on this project. Need help? We gotchu. You can find us on:

651

973

652- [Twitter](https://twitter.com/charmcli)

974- [Twitter](https://twitter.com/charmcli)

653−- [Slack](https://charm.land/slack)

975+- [Slack][slack]

654- [Discord][discord]

976- [Discord][discord]

655- [The Fediverse](https://mastodon.social/@charmcli)

977- [The Fediverse](https://mastodon.social/@charmcli)

656- [Bluesky](https://bsky.app/profile/charm.land)

978- [Bluesky](https://bsky.app/profile/charm.land)

657

979

980+[slack]: https://charm.land/slack

658[discord]: https://charm.land/discord

981[discord]: https://charm.land/discord

659

982

660## License

983## License

@@ -665,7 +988,7 @@ We’d love to hear your thoughts on this project. Need help? We gotchu. You can

665

988

666Part of [Charm](https://charm.land).

989Part of [Charm](https://charm.land).

667

990

668−<a href="https://charm.land/"><img alt="The Charm logo" width="400" src="https://stuff.charm.sh/charm-banner-next.jpg" /></a>

991+<a href="https://charm.land/"><img alt="The Charm logo" width="400" src="https://stuff.charm.sh/charm-banner-softy.jpg" /></a>

669

992

670

993

671Charm热爱开源 • Charm loves open source

994Charm热爱开源 • Charm loves open source

Taskfile.yaml+102−4

@@ -5,6 +5,8 @@ version: "3"

5vars:

6 VERSION:

7 sh: git describe --long 2>/dev/null || echo ""

8+ RACE:

9+ sh: test -f race.log && echo "1" || echo ""

9env:

11env:

10 CGO_ENABLED: 0

12 CGO_ENABLED: 0

@@ -21,10 +23,16 @@ tasks:

21 lint:

23 lint:

22 desc: Run base linters

24 desc: Run base linters

23 cmds:

25 cmds:

26+ - task: lint:log

24 - golangci-lint run --path-mode=abs --config=".golangci.yml" --timeout=5m

27 - golangci-lint run --path-mode=abs --config=".golangci.yml" --timeout=5m

25 env:

28 env:

26 GOEXPERIMENT: null

29 GOEXPERIMENT: null

31+ lint:log:

32+ desc: Check that log messages start with capital letters

33+ cmds:

34+ - ./scripts/check_log_capitalization.sh

35+

28 lint:fix:

36 lint:fix:

29 desc: Run base linters and fix issues

37 desc: Run base linters and fix issues

30 cmds:

38 cmds:

@@ -37,25 +45,67 @@ tasks:

37 vars:

45 vars:

38 LDFLAGS: '{{if .VERSION}}-ldflags="-X github.com/charmbracelet/crush/internal/version.Version={{.VERSION}}"{{end}}'

46 LDFLAGS: '{{if .VERSION}}-ldflags="-X github.com/charmbracelet/crush/internal/version.Version={{.VERSION}}"{{end}}'

39 cmds:

47 cmds:

40− - go build {{.LDFLAGS}} .

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

41 generates:

55 generates:

42− - crush

56+ - crush{{exeExt}}

44 run:

58 run:

45 desc: Run build

59 desc: Run build

46 cmds:

60 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

47− - go run . {{.CLI_ARGS}}

80+ - ./crush{{exeExt}} {{.CLI_ARGS}}

49 test:

82 test:

50 desc: Run tests

83 desc: Run tests

51 cmds:

84 cmds:

52− - go test ./... {{.CLI_ARGS}}

85+ - go test -race -failfast ./... {{.CLI_ARGS}}

86+

87+ test:record:

88+ desc: Run tests and record all VCR cassettes again

89+ aliases: [record]

90+ cmds:

91+ - rm -r internal/agent/testdata

92+ - go test -v -count=1 -timeout=1h ./internal/agent

54 fmt:

94 fmt:

55 desc: Run gofumpt

95 desc: Run gofumpt

56 cmds:

96 cmds:

57 - gofumpt -w .

97 - gofumpt -w .

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+

59 dev:

109 dev:

60 desc: Run with profiling enabled

110 desc: Run with profiling enabled

61 env:

111 env:

@@ -68,7 +118,14 @@ tasks:

68 vars:

118 vars:

69 LDFLAGS: '{{if .VERSION}}-ldflags="-X github.com/charmbracelet/crush/internal/version.Version={{.VERSION}}"{{end}}'

119 LDFLAGS: '{{if .VERSION}}-ldflags="-X github.com/charmbracelet/crush/internal/version.Version={{.VERSION}}"{{end}}'

70 cmds:

120 cmds:

121+ - task: fetch-tags

71 - go install {{.LDFLAGS}} -v .

122 - 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

129

73 profile:cpu:

130 profile:cpu:

74 desc: 10s CPU profile

131 desc: 10s CPU profile

@@ -93,6 +150,13 @@ tasks:

93 generates:

150 generates:

94 - schema.json

151 - schema.json

152

153+ hyper:

154+ desc: Update Hyper embedded provider.json

155+ cmds:

156+ - go generate ./internal/agent/hyper/...

157+ generates:

158+ - ./internal/agent/hyper/provider.json

159+

96 release:

160 release:

97 desc: Create and push a new tag following semver

161 desc: Create and push a new tag following semver

98 vars:

162 vars:

@@ -104,6 +168,10 @@ tasks:

104 msg: Not on main branch

168 msg: Not on main branch

105 - sh: "[ $(git status --porcelain=2 | wc -l) = 0 ]"

169 - sh: "[ $(git status --porcelain=2 | wc -l) = 0 ]"

106 msg: "Git is dirty"

170 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"

107 cmds:

175 cmds:

108 - task: fetch-tags

176 - task: fetch-tags

109 - git commit --allow-empty -m "{{.NEXT}}"

177 - git commit --allow-empty -m "{{.NEXT}}"

@@ -115,3 +183,33 @@ tasks:

115 cmds:

183 cmds:

116 - git tag -d nightly || true

184 - git tag -d nightly || true

117 - git fetch --tags

185 - git fetch --tags

186+

187+ deps:

188+ 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/*

194+ cmds:

195+ - go get charm.land/fantasy@latest

196+ - go get charm.land/catwalk@latest

197+ - 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

crush.json+35−1

@@ -1,6 +1,40 @@

2 "$schema": "https://charm.land/crush.json",

3 "lsp": {

4− "gopls": {}

4+ "gopls": {

5+ "options": {

6+ "gofumpt": true,

7+ "codelenses": {

8+ "gc_details": true,

9+ "generate": true,

10+ "run_govulncheck": true,

11+ "test": true,

12+ "tidy": true,

13+ "upgrade_dependency": true

14+ },

15+ "hints": {

16+ "assignVariableTypes": true,

17+ "compositeLiteralFields": true,

18+ "compositeLiteralTypes": true,

19+ "constantValues": true,

20+ "functionTypeParameters": true,

21+ "parameterNames": true,

22+ "rangeVariableTypes": true

23+ },

24+ "analyses": {

25+ "nilness": true,

26+ "unusedparams": true,

27+ "unusedvariable": true,

28+ "unusedwrite": true,

29+ "useany": true

30+ },

31+ "staticcheck": true,

32+ "directoryFilters": [

33+ "-.git",

34+ "-node_modules"

35+ ],

36+ "semanticTokens": true

37+ }

38+ }

5 }

39 }

40}

cspell.jsondeleted−1

@@ -1 +0,0 @@

1−{"flagWords":[],"version":"0.2","language":"en","words":["afero","agentic","alecthomas","anthropics","aymanbagabas","azidentity","bmatcuk","bubbletea","charlievieth","charmbracelet","charmtone","Charple","chkconfig","crush","curlie","cursorrules","diffview","doas","Dockerfiles","doublestar","dpkg","Emph","fastwalk","fdisk","filepicker","Focusable","fseventsd","fsext","genai","goquery","GROQ","Guac","imageorient","Inex","jetta","jsons","jsonschema","jspm","Kaufmann","killall","Lanczos","lipgloss","LOCALAPPDATA","lsps","lucasb","makepkg","mcps","MSYS","mvdan","natefinch","nfnt","noctx","nohup","nolint","nslookup","oksvg","Oneshot","openrouter","opkg","pacman","paru","pfctl","postamble","postambles","preconfigured","Preproc","Proactiveness","Puerkito","pycache","pytest","qjebbs","rasterx","rivo","sabhiram","sess","shortlog","sjson","Sourcegraph","srwiley","SSEMCP","Streamable","stretchr","Strikethrough","substrs","Suscriber","systeminfo","tasklist","termenv","textinput","tidwall","timedout","trashhalo","udiff","uniseg","Unticked","urllib","USERPROFILE","VERTEXAI","webp","whatis","whereis","sahilm","csync"]}

docs/hooks/FUTURE.mdnew file+260

@@ -0,0 +1,260 @@

1+# Hooks: Future Work

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.

7+> [!NOTE]

8+> This document was largely LLM-generated.

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.mdnew file+759

@@ -0,0 +1,759 @@

1+# Hooks

3+> [!NOTE]

4+> This document was designed for both humans and agents.

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.

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.

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+

759+Charm热爱开源 • Charm loves open source

docs/hooks/examples/rtk-rewrite.shnew file+60

@@ -0,0 +1,60 @@

1+#!/usr/bin/env bash

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.locknew file+60

@@ -0,0 +1,60 @@

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.nixnew file+75

@@ -0,0 +1,75 @@

1+{

2+ description = "Crush development environment";

4+ inputs = {

5+ nixpkgs.url = "github:NixOS/nixpkgs";

6+ flake-utils.url = "github:numtide/flake-utils";

7+ };

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+162−111

@@ -1,119 +1,159 @@

1module github.com/charmbracelet/crush

3−go 1.25.0

3+go 1.26.4

5require (

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

6− charm.land/fantasy v0.0.0

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

14+ charm.land/x/vcr v0.1.1

7 github.com/JohannesKaufmann/html-to-markdown v1.6.0

15 github.com/JohannesKaufmann/html-to-markdown v1.6.0

8 github.com/MakeNowJust/heredoc v1.0.0

16 github.com/MakeNowJust/heredoc v1.0.0

17+ github.com/Microsoft/go-winio v0.6.2

9− github.com/PuerkitoBio/goquery v1.10.3

18+ github.com/PuerkitoBio/goquery v1.12.0

10− github.com/alecthomas/chroma/v2 v2.20.0

19+ github.com/alecthomas/chroma/v2 v2.27.0

11− github.com/atotto/clipboard v0.1.4

12− github.com/aymanbagabas/go-udiff v0.3.1

20+ github.com/aymanbagabas/go-udiff v0.4.1

13− github.com/bmatcuk/doublestar/v4 v4.9.1

21+ github.com/bmatcuk/doublestar/v4 v4.10.0

14 github.com/charlievieth/fastwalk v1.0.14

22 github.com/charlievieth/fastwalk v1.0.14

15− github.com/charmbracelet/bubbles/v2 v2.0.0-beta.1.0.20250820203609-601216f68ee2

23+ github.com/charmbracelet/colorprofile v0.4.3

16− github.com/charmbracelet/bubbletea/v2 v2.0.0-beta.4.0.20251011205917-3b687ffc1619

24+ github.com/charmbracelet/openai-go v0.0.0-20260617131321-5e4b9c18c4be

17− github.com/charmbracelet/catwalk v0.6.5-0.20251015124117-3bfe9eb6d20f

18− github.com/charmbracelet/fang v0.4.3

19− github.com/charmbracelet/glamour/v2 v2.0.0-20250811143442-a27abb32f018

20− github.com/charmbracelet/lipgloss/v2 v2.0.0-beta.3.0.20250917201909-41ff0bf215ea

21− github.com/charmbracelet/log/v2 v2.0.0-20250226163916-c379e29ff706

25+ github.com/charmbracelet/ultraviolet v0.0.0-20260703014108-f5a850f9c2b7

22− github.com/charmbracelet/x/ansi v0.10.2

26+ github.com/charmbracelet/x/ansi v0.11.7

27+ github.com/charmbracelet/x/editor v0.2.0

28+ github.com/charmbracelet/x/etag v0.2.0

23− github.com/charmbracelet/x/exp/charmtone v0.0.0-20250708181618-a60a724ba6c3

29+ github.com/charmbracelet/x/exp/charmtone v0.0.0-20260527151214-009e6338d40d

24− github.com/charmbracelet/x/exp/golden v0.0.0-20250207160936-21c02780d27a

30+ github.com/charmbracelet/x/exp/golden v0.0.0-20250806222409-83e3a29d542f

25 github.com/charmbracelet/x/exp/ordered v0.1.0

31 github.com/charmbracelet/x/exp/ordered v0.1.0

26− github.com/charmbracelet/x/powernap v0.0.0-20251015113943-25f979b54ad4

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

27− github.com/charmbracelet/x/term v0.2.1

35+ 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

38+ github.com/denisbrodbeck/machineid v1.0.1

28− github.com/disintegration/imageorient v0.0.0-20180920195336-8147d86e83ec

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

29 github.com/google/uuid v1.6.0

43 github.com/google/uuid v1.6.0

30− github.com/invopop/jsonschema v0.13.0

44+ github.com/invopop/jsonschema v0.14.0

45+ github.com/itchyny/gojq v0.12.19

31 github.com/joho/godotenv v1.5.1

46 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

32− github.com/modelcontextprotocol/go-sdk v1.0.0

50+ github.com/modelcontextprotocol/go-sdk v1.6.1

33− github.com/muesli/termenv v0.16.0

34− github.com/ncruces/go-sqlite3 v0.29.1

51+ github.com/ncruces/go-sqlite3 v0.35.1

35− github.com/nfnt/resize v0.0.0-20180221191011-83c6a9932646

36 github.com/nxadm/tail v1.4.11

52 github.com/nxadm/tail v1.4.11

53+ github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c

54+ github.com/posthog/posthog-go v1.17.5

37− github.com/pressly/goose/v3 v3.25.0

55+ github.com/pressly/goose/v3 v3.27.2

38− github.com/qjebbs/go-jsons v1.0.0-alpha.4

56+ github.com/qjebbs/go-jsons v1.0.0-alpha.6

39− github.com/sabhiram/go-gitignore v0.0.0-20210923224102-525f6e181f06

57+ github.com/rivo/uniseg v0.4.7

40− github.com/sahilm/fuzzy v0.1.1

58+ github.com/sahilm/fuzzy v0.1.3

59+ github.com/sourcegraph/jsonrpc2 v0.2.1

41− github.com/spf13/cobra v1.10.1

60+ github.com/spf13/cobra v1.10.2

42− github.com/srwiley/oksvg v0.0.0-20221011165216-be6e8873101c

43− github.com/srwiley/rasterx v0.0.0-20220730225603-2ab79fcdd4ef

44 github.com/stretchr/testify v1.11.1

61 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

45 github.com/tidwall/sjson v1.2.5

65 github.com/tidwall/sjson v1.2.5

46− github.com/zeebo/xxh3 v1.0.2

66+ github.com/zeebo/xxh3 v1.1.0

47− go.yaml.in/yaml/v4 v4.0.0-rc.2

67+ go.uber.org/goleak v1.3.0

48− gopkg.in/dnaeon/go-vcr.v4 v4.0.6-0.20250923044825-7b4892dd3117

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

49 gopkg.in/natefinch/lumberjack.v2 v2.2.1

73 gopkg.in/natefinch/lumberjack.v2 v2.2.1

74+ gopkg.in/yaml.v3 v3.0.1

75+ modernc.org/sqlite v1.53.0

50− mvdan.cc/sh/v3 v3.12.1-0.20250902163504-3cf4fd5717a5

76+ mvdan.cc/sh/moreinterp v0.0.0-20250902163504-3cf4fd5717a5

77+ mvdan.cc/sh/v3 v3.13.1

51)

78)

53−replace charm.land/fantasy => ../../fantasy/main/

54−

55require (

80require (

56− cloud.google.com/go v0.116.0 // indirect

81+ cloud.google.com/go v0.123.0 // indirect

57− cloud.google.com/go/auth v0.17.0 // indirect

82+ cloud.google.com/go/auth v0.20.0 // indirect

58 cloud.google.com/go/auth/oauth2adapt v0.2.8 // indirect

83 cloud.google.com/go/auth/oauth2adapt v0.2.8 // indirect

59− cloud.google.com/go/compute/metadata v0.8.0 // indirect

84+ cloud.google.com/go/compute/metadata v0.9.0 // indirect

85+ git.sr.ht/~jackmordaunt/go-toast v1.1.2 // indirect

60 github.com/Azure/azure-sdk-for-go/sdk/azcore v1.17.0 // indirect

86 github.com/Azure/azure-sdk-for-go/sdk/azcore v1.17.0 // indirect

61 github.com/Azure/azure-sdk-for-go/sdk/internal v1.10.0 // indirect

87 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

62 github.com/andybalholm/cascadia v1.3.3 // indirect

90 github.com/andybalholm/cascadia v1.3.3 // indirect

91+ github.com/atotto/clipboard v0.1.4 // indirect

63− github.com/aws/aws-sdk-go-v2 v1.39.3 // indirect

92+ github.com/aws/aws-sdk-go-v2 v1.42.0 // indirect

64− github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.6.3 // indirect

93+ github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.13 // indirect

65− github.com/aws/aws-sdk-go-v2/config v1.27.27 // indirect

94+ github.com/aws/aws-sdk-go-v2/config v1.32.25 // indirect

66− github.com/aws/aws-sdk-go-v2/credentials v1.17.27 // indirect

95+ github.com/aws/aws-sdk-go-v2/credentials v1.19.24 // indirect

67− github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.16.11 // indirect

96+ github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.29 // indirect

68− github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.15 // indirect

97+ github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.29 // indirect

69− github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.15 // indirect

98+ github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.29 // indirect

70− github.com/aws/aws-sdk-go-v2/internal/ini v1.8.0 // indirect

99+ github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.30 // indirect

71− github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.11.3 // indirect

100+ github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.12 // indirect

72− github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.11.17 // 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

73− github.com/aws/aws-sdk-go-v2/service/sso v1.22.4 // indirect

103+ github.com/aws/aws-sdk-go-v2/service/sso v1.31.3 // indirect

74− github.com/aws/aws-sdk-go-v2/service/ssooidc v1.26.4 // indirect

104+ github.com/aws/aws-sdk-go-v2/service/ssooidc v1.36.6 // indirect

75− github.com/aws/aws-sdk-go-v2/service/sts v1.30.3 // indirect

105+ github.com/aws/aws-sdk-go-v2/service/sts v1.43.3 // indirect

76− github.com/aws/smithy-go v1.23.1 // indirect

106+ github.com/aws/smithy-go v1.27.3 // indirect

77− github.com/aymanbagabas/go-osc52/v2 v2.0.1 // indirect

78 github.com/aymerick/douceur v0.2.0 // indirect

107 github.com/aymerick/douceur v0.2.0 // indirect

79 github.com/bahlo/generic-list-go v0.2.0 // indirect

108 github.com/bahlo/generic-list-go v0.2.0 // indirect

80− github.com/buger/jsonparser v1.1.1 // indirect

109+ github.com/buger/jsonparser v1.1.2 // indirect

110+ github.com/cespare/xxhash/v2 v2.3.0 // indirect

81− github.com/charmbracelet/anthropic-sdk-go v0.0.0-20251022202715-ec1499142678 // indirect

111+ github.com/charmbracelet/anthropic-sdk-go v0.0.0-20260223140439-63879b0b8dab // indirect

82− github.com/charmbracelet/colorprofile v0.3.2

83− github.com/charmbracelet/go-genai v0.0.0-20251021165952-9befde14ce97 // indirect

84− github.com/charmbracelet/ultraviolet v0.0.0-20250915111650-81d4262876ef

85− github.com/charmbracelet/x/cellbuf v0.0.14-0.20250811133356-e0c5dbe5ea4a // indirect

86− github.com/charmbracelet/x/exp/slice v0.0.0-20250904123553-b4e2667e5ad5

87− github.com/charmbracelet/x/json v0.2.0 // indirect

88 github.com/charmbracelet/x/termios v0.1.1 // indirect

112 github.com/charmbracelet/x/termios v0.1.1 // indirect

89 github.com/charmbracelet/x/windows v0.2.2 // indirect

113 github.com/charmbracelet/x/windows v0.2.2 // indirect

90− github.com/davecgh/go-spew v1.1.1 // indirect

114+ github.com/cyphar/filepath-securejoin v0.6.1 // indirect

91− github.com/denisbrodbeck/machineid v1.0.1

115+ github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect

92− github.com/disintegration/gift v1.1.2 // indirect

93− github.com/dlclark/regexp2 v1.11.5 // indirect

116+ github.com/dlclark/regexp2/v2 v2.2.1 // indirect

94− github.com/dustin/go-humanize v1.0.1 // indirect

117+ github.com/ebitengine/purego v0.10.1 // indirect

118+ github.com/esiqveland/notify v0.13.3 // indirect

95− github.com/felixge/httpsnoop v1.0.4 // indirect

119+ github.com/felixge/httpsnoop v1.1.0 // indirect

96 github.com/fsnotify/fsnotify v1.9.0 // indirect

120 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

97 github.com/go-logfmt/logfmt v0.6.0 // indirect

124 github.com/go-logfmt/logfmt v0.6.0 // indirect

98 github.com/go-logr/logr v1.4.3 // indirect

125 github.com/go-logr/logr v1.4.3 // indirect

99 github.com/go-logr/stdr v1.2.2 // indirect

126 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

100− github.com/go-viper/mapstructure/v2 v2.4.0 // 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

101 github.com/google/go-cmp v0.7.0 // indirect

137 github.com/google/go-cmp v0.7.0 // indirect

102− github.com/google/jsonschema-go v0.3.0 // indirect

138+ github.com/google/jsonschema-go v0.4.3 // indirect

103 github.com/google/s2a-go v0.1.9 // indirect

139 github.com/google/s2a-go v0.1.9 // indirect

104− github.com/googleapis/enterprise-certificate-proxy v0.3.6 // indirect

140+ github.com/googleapis/enterprise-certificate-proxy v0.3.17 // indirect

105− github.com/googleapis/gax-go/v2 v2.15.0 // indirect

141+ github.com/googleapis/gax-go/v2 v2.22.0 // indirect

106 github.com/gorilla/css v1.0.1 // indirect

142 github.com/gorilla/css v1.0.1 // indirect

107 github.com/gorilla/websocket v1.5.3 // indirect

143 github.com/gorilla/websocket v1.5.3 // indirect

108 github.com/hashicorp/golang-lru/v2 v2.0.7 // indirect

144 github.com/hashicorp/golang-lru/v2 v2.0.7 // indirect

109 github.com/inconshreveable/mousetrap v1.1.0 // indirect

145 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

110− github.com/klauspost/compress v1.18.0 // indirect

152+ github.com/klauspost/compress v1.18.6 // indirect

111− github.com/klauspost/cpuid/v2 v2.0.9 // indirect

153+ github.com/klauspost/cpuid/v2 v2.3.0 // indirect

112 github.com/klauspost/pgzip v1.2.6 // indirect

154 github.com/klauspost/pgzip v1.2.6 // indirect

113− github.com/lucasb-eyer/go-colorful v1.3.0

114 github.com/mailru/easyjson v0.7.7 // indirect

155 github.com/mailru/easyjson v0.7.7 // indirect

115− github.com/mattn/go-isatty v0.0.20 // indirect

116− github.com/mattn/go-runewidth v0.0.17 // indirect

156+ github.com/mattn/go-runewidth v0.0.24 // indirect

117 github.com/mfridman/interpolate v0.0.2 // indirect

157 github.com/mfridman/interpolate v0.0.2 // indirect

118 github.com/microcosm-cc/bluemonday v1.0.27 // indirect

158 github.com/microcosm-cc/bluemonday v1.0.27 // indirect

119 github.com/mitchellh/mapstructure v1.5.0 // indirect

159 github.com/mitchellh/mapstructure v1.5.0 // indirect

@@ -122,49 +162,60 @@ require (

122 github.com/muesli/mango-cobra v1.2.0 // indirect

162 github.com/muesli/mango-cobra v1.2.0 // indirect

123 github.com/muesli/mango-pflag v0.1.0 // indirect

163 github.com/muesli/mango-pflag v0.1.0 // indirect

124 github.com/muesli/roff v0.1.0 // indirect

164 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

125 github.com/ncruces/julianday v1.0.0 // indirect

167 github.com/ncruces/julianday v1.0.0 // indirect

126− github.com/openai/openai-go/v2 v2.7.1 // indirect

168+ github.com/nfnt/resize v0.0.0-20180221191011-83c6a9932646 // indirect

169+ github.com/pb33f/ordered-map/v2 v2.3.1 // indirect

127− github.com/pierrec/lz4/v4 v4.1.22 // indirect

170+ github.com/pierrec/lz4/v4 v4.1.26 // indirect

171+ github.com/pjbgf/sha1cd v0.6.0 // indirect

128− github.com/pmezard/go-difflib v1.0.0 // indirect

172+ github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect

129− github.com/posthog/posthog-go v1.6.11

173+ github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec // indirect

130− github.com/rivo/uniseg v0.4.7

174+ github.com/segmentio/asm v1.2.1 // indirect

131− github.com/sergi/go-diff v1.3.2-0.20230802210424-5b0b94c5c0d3 // 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

132 github.com/sethvargo/go-retry v0.3.0 // indirect

178 github.com/sethvargo/go-retry v0.3.0 // indirect

133− github.com/sourcegraph/jsonrpc2 v0.2.1 // indirect

134 github.com/spf13/pflag v1.0.9 // indirect

179 github.com/spf13/pflag v1.0.9 // indirect

135− github.com/tetratelabs/wazero v1.9.0 // indirect

180+ github.com/swaggo/files/v2 v2.0.0 // indirect

136− github.com/tidwall/gjson v1.18.0 // indirect

181+ github.com/tadvi/systray v0.0.0-20190226123456-11a2b8fa57af // indirect

137 github.com/tidwall/match v1.1.1 // indirect

182 github.com/tidwall/match v1.1.1 // indirect

138 github.com/tidwall/pretty v1.2.1 // indirect

183 github.com/tidwall/pretty v1.2.1 // indirect

139 github.com/u-root/u-root v0.14.1-0.20250807200646-5e7721023dc7 // indirect

184 github.com/u-root/u-root v0.14.1-0.20250807200646-5e7721023dc7 // indirect

140 github.com/u-root/uio v0.0.0-20240224005618-d2acac8f3701 // indirect

185 github.com/u-root/uio v0.0.0-20240224005618-d2acac8f3701 // indirect

141− github.com/wk8/go-ordered-map/v2 v2.1.8 // indirect

142 github.com/xo/terminfo v0.0.0-20220910002029-abceb7e1c41e // indirect

186 github.com/xo/terminfo v0.0.0-20220910002029-abceb7e1c41e // indirect

143 github.com/yosida95/uritemplate/v3 v3.0.2 // indirect

187 github.com/yosida95/uritemplate/v3 v3.0.2 // indirect

144 github.com/yuin/goldmark v1.7.8 // indirect

188 github.com/yuin/goldmark v1.7.8 // indirect

145 github.com/yuin/goldmark-emoji v1.0.5 // indirect

189 github.com/yuin/goldmark-emoji v1.0.5 // indirect

146− go.opentelemetry.io/auto/sdk v1.1.0 // indirect

190+ go.opentelemetry.io/auto/sdk v1.2.1 // indirect

147− go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.61.0 // indirect

191+ go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.69.0 // indirect

148− go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.61.0 // indirect

192+ go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.69.0 // indirect

149− go.opentelemetry.io/otel v1.37.0 // indirect

193+ go.opentelemetry.io/otel v1.44.0 // indirect

150− go.opentelemetry.io/otel/metric v1.37.0 // indirect

194+ go.opentelemetry.io/otel/metric v1.44.0 // indirect

151− go.opentelemetry.io/otel/trace v1.37.0 // indirect

195+ go.opentelemetry.io/otel/trace v1.44.0 // indirect

152 go.uber.org/multierr v1.11.0 // indirect

196 go.uber.org/multierr v1.11.0 // indirect

197+ go.yaml.in/yaml/v4 v4.0.0-rc.3 // indirect

198+ golang.design/x/x11 v0.2.0 // indirect

153− golang.org/x/crypto v0.42.0 // indirect

199+ golang.org/x/crypto v0.53.0 // indirect

154− golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b // indirect

200+ golang.org/x/exp v0.0.0-20260410095643-746e56fc9e2f // indirect

201+ golang.org/x/exp/shiny v0.0.0-20250606033433-dcc06ee1d476 // indirect

155− golang.org/x/image v0.27.0 // indirect

202+ golang.org/x/image v0.43.0 // indirect

156− golang.org/x/net v0.44.0 // indirect

203+ golang.org/x/mobile v0.0.0-20250606033058-a2a15c67f36f // indirect

204+ golang.org/x/mod v0.36.0 // indirect

157− golang.org/x/oauth2 v0.32.0 // indirect

205+ golang.org/x/oauth2 v0.36.0 // indirect

158− golang.org/x/sync v0.17.0 // indirect

159− golang.org/x/sys v0.37.0 // indirect

160− golang.org/x/term v0.35.0 // indirect

206+ golang.org/x/term v0.44.0 // indirect

161− golang.org/x/text v0.30.0

162− golang.org/x/time v0.12.0 // indirect

207+ golang.org/x/time v0.15.0 // indirect

208+ golang.org/x/tools v0.45.0 // indirect

163− google.golang.org/api v0.239.0 // indirect

209+ google.golang.org/api v0.286.0 // indirect

210+ google.golang.org/genai v1.62.0 // indirect

164− google.golang.org/genproto/googleapis/rpc v0.0.0-20250603155806-513f23925822 // indirect

211+ google.golang.org/genproto/googleapis/rpc v0.0.0-20260622175928-b703f567277d // indirect

165− google.golang.org/grpc v1.74.2 // indirect

212+ google.golang.org/grpc v1.81.1 // indirect

166− google.golang.org/protobuf v1.36.10 // indirect

213+ google.golang.org/protobuf v1.36.11 // indirect

214+ gopkg.in/dnaeon/go-vcr.v4 v4.0.6-0.20251110073552-01de4eb40290 // indirect

167 gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7 // indirect

215 gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7 // indirect

168− gopkg.in/yaml.v3 v3.0.1 // indirect

216+ gopkg.in/warnings.v0 v0.1.2 // indirect

169− mvdan.cc/sh/moreinterp v0.0.0-20250902163504-3cf4fd5717a5

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

170)

221)

go.sum+367−212

@@ -1,11 +1,31 @@

1−cloud.google.com/go v0.116.0 h1:B3fRrSDkLRt5qSHWe40ERJvhvnQwdZiHu0bJOpldweE=

1+charm.land/bubbles/v2 v2.1.1 h1:7r55WzBxpo/R3z98hGmY7KKPd3ET6vsf0Fb9sDHOV60=

2−cloud.google.com/go v0.116.0/go.mod h1:cEPSRWPzZEswwdr9BxE6ChEn01dWlTaF05LiC2Xs70U=

2+charm.land/bubbles/v2 v2.1.1/go.mod h1:GE6M31gaWZVXzGw73OeuTTgy4lX+OtkH0E5ymnNsHxo=

3−cloud.google.com/go/auth v0.17.0 h1:74yCm7hCj2rUyyAocqnFzsAYXgJhrG26XCFimrc/Kz4=

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=

17+charm.land/x/vcr v0.1.1 h1:PXCFMUG0rPtyk35rhfzYCJEduOzWXCIbrXTFq4OF/9Q=

18+charm.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=

4−cloud.google.com/go/auth v0.17.0/go.mod h1:6wv/t5/6rOPAX4fJiRjKkJCvswLwdet7G8+UGXt7nCQ=

22+cloud.google.com/go/auth v0.20.0/go.mod h1:942/yi/itH1SsmpyrbnTMDgGfdy2BUqIKyd0cyYLc5Q=

5cloud.google.com/go/auth/oauth2adapt v0.2.8 h1:keo8NaayQZ6wimpNSmW5OPc283g65QNIiLpZnkHRbnc=

23cloud.google.com/go/auth/oauth2adapt v0.2.8 h1:keo8NaayQZ6wimpNSmW5OPc283g65QNIiLpZnkHRbnc=

6cloud.google.com/go/auth/oauth2adapt v0.2.8/go.mod h1:XQ9y31RkqZCcwJWNSx2Xvric3RrU88hAYYbjDWYDL+c=

24cloud.google.com/go/auth/oauth2adapt v0.2.8/go.mod h1:XQ9y31RkqZCcwJWNSx2Xvric3RrU88hAYYbjDWYDL+c=

7−cloud.google.com/go/compute/metadata v0.8.0 h1:HxMRIbao8w17ZX6wBnjhcDkW6lTFpgcaobyVfZWqRLA=

25+cloud.google.com/go/compute/metadata v0.9.0 h1:pDUj4QMoPejqq20dK0Pg2N4yG9zIkYGdBtwLoEkH9Zs=

8−cloud.google.com/go/compute/metadata v0.8.0/go.mod h1:sYOGTp851OV9bOFJ9CH7elVvyzopvWQFNNghtDQ/Biw=

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=

9github.com/Azure/azure-sdk-for-go/sdk/azcore v1.17.0 h1:g0EZJwz7xkXQiZAI5xi9f3WWFYBlX1CPTrR+NDToRkQ=

29github.com/Azure/azure-sdk-for-go/sdk/azcore v1.17.0 h1:g0EZJwz7xkXQiZAI5xi9f3WWFYBlX1CPTrR+NDToRkQ=

10github.com/Azure/azure-sdk-for-go/sdk/azcore v1.17.0/go.mod h1:XCW7KnZet0Opnr7HccfUw1PLc4CjHqpcaxW8DHklNkQ=

30github.com/Azure/azure-sdk-for-go/sdk/azcore v1.17.0/go.mod h1:XCW7KnZet0Opnr7HccfUw1PLc4CjHqpcaxW8DHklNkQ=

11github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.7.0 h1:tfLQ34V6F7tVSwoTf/4lH5sE0o6eCJuNDTmH09nDpbc=

31github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.7.0 h1:tfLQ34V6F7tVSwoTf/4lH5sE0o6eCJuNDTmH09nDpbc=

@@ -16,129 +36,154 @@ github.com/AzureAD/microsoft-authentication-library-for-go v1.2.2 h1:XHOnouVk1mx

16github.com/AzureAD/microsoft-authentication-library-for-go v1.2.2/go.mod h1:wP83P5OoQ5p6ip3ScPr0BAq0BvuPAvacpEuSzyouqAI=

36github.com/AzureAD/microsoft-authentication-library-for-go v1.2.2/go.mod h1:wP83P5OoQ5p6ip3ScPr0BAq0BvuPAvacpEuSzyouqAI=

17github.com/JohannesKaufmann/html-to-markdown v1.6.0 h1:04VXMiE50YYfCfLboJCLcgqF5x+rHJnb1ssNmqpLH/k=

37github.com/JohannesKaufmann/html-to-markdown v1.6.0 h1:04VXMiE50YYfCfLboJCLcgqF5x+rHJnb1ssNmqpLH/k=

18github.com/JohannesKaufmann/html-to-markdown v1.6.0/go.mod h1:NUI78lGg/a7vpEJTz/0uOcYMaibytE4BUOQS8k78yPQ=

38github.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=

19github.com/MakeNowJust/heredoc v1.0.0 h1:cXCdzVdstXyiTqTvfqk9SDHpKNjxuom+DOlyEeQ4pzQ=

41github.com/MakeNowJust/heredoc v1.0.0 h1:cXCdzVdstXyiTqTvfqk9SDHpKNjxuom+DOlyEeQ4pzQ=

20github.com/MakeNowJust/heredoc v1.0.0/go.mod h1:mG5amYoWBHf8vpLOuehzbGGw0EHxpZZ6lCpQ4fNJ8LE=

42github.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=

21github.com/PuerkitoBio/goquery v1.9.2/go.mod h1:GHPCaP0ODyyxqcNoFGYlAprUFH81NuRPd0GX3Zu2Mvk=

45github.com/PuerkitoBio/goquery v1.9.2/go.mod h1:GHPCaP0ODyyxqcNoFGYlAprUFH81NuRPd0GX3Zu2Mvk=

22−github.com/PuerkitoBio/goquery v1.10.3 h1:pFYcNSqHxBD06Fpj/KsbStFRsgRATgnf3LeXiUkhzPo=

46+github.com/PuerkitoBio/goquery v1.12.0 h1:pAcL4g3WRXekcB9AU/y1mbKez2dbY2AajVhtkO8RIBo=

23−github.com/PuerkitoBio/goquery v1.10.3/go.mod h1:tMUX0zDMHXYlAQk6p35XxQMqMweEKB7iK7iLNd4RH4Y=

47+github.com/PuerkitoBio/goquery v1.12.0/go.mod h1:802ej+gV2y7bbIhOIoPY5sT183ZW0YFofScC4q/hIpQ=

24github.com/alecthomas/assert/v2 v2.11.0 h1:2Q9r3ki8+JYXvGsDyBXwH3LcJ+WK5D0gc5E8vS6K3D0=

48github.com/alecthomas/assert/v2 v2.11.0 h1:2Q9r3ki8+JYXvGsDyBXwH3LcJ+WK5D0gc5E8vS6K3D0=

25github.com/alecthomas/assert/v2 v2.11.0/go.mod h1:Bze95FyfUr7x34QZrjL+XP+0qgp/zg8yS+TtBj1WA3k=

49github.com/alecthomas/assert/v2 v2.11.0/go.mod h1:Bze95FyfUr7x34QZrjL+XP+0qgp/zg8yS+TtBj1WA3k=

26−github.com/alecthomas/chroma/v2 v2.20.0 h1:sfIHpxPyR07/Oylvmcai3X/exDlE8+FA820NTz+9sGw=

50+github.com/alecthomas/chroma/v2 v2.27.0 h1:FodwmyOBgJULFYmDqibcp9pvfDLWdtPRh9v/r5BXYZs=

27−github.com/alecthomas/chroma/v2 v2.20.0/go.mod h1:e7tViK0xh/Nf4BYHl00ycY6rV7b8iXBksI9E359yNmA=

51+github.com/alecthomas/chroma/v2 v2.27.0/go.mod h1:NjJ3ciIgrqBNeIkWZ4e46nseoLDslxU1LmfCoL+wcY8=

28−github.com/alecthomas/repr v0.5.1 h1:E3G4t2QbHTSNpPKBgMTln5KLkZHLOcU7r37J4pXBuIg=

52+github.com/alecthomas/repr v0.5.2 h1:SU73FTI9D1P5UNtvseffFSGmdNci/O6RsqzeXJtP0Qs=

29−github.com/alecthomas/repr v0.5.1/go.mod h1:Fr0507jx4eOXV7AlPV6AVZLYrLIuIeSOWtW57eE/O/4=

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=

30github.com/andybalholm/cascadia v1.3.2/go.mod h1:7gtRlve5FxPPgIgX36uWBX58OdBsSS6lUvCFb+h7KvU=

56github.com/andybalholm/cascadia v1.3.2/go.mod h1:7gtRlve5FxPPgIgX36uWBX58OdBsSS6lUvCFb+h7KvU=

31github.com/andybalholm/cascadia v1.3.3 h1:AG2YHrzJIm4BZ19iwJ/DAua6Btl3IwJX+VI4kktS1LM=

57github.com/andybalholm/cascadia v1.3.3 h1:AG2YHrzJIm4BZ19iwJ/DAua6Btl3IwJX+VI4kktS1LM=

32github.com/andybalholm/cascadia v1.3.3/go.mod h1:xNd9bqTn98Ln4DwST8/nG+H0yuB8Hmgu1YHNnWw0GeA=

58github.com/andybalholm/cascadia v1.3.3/go.mod h1:xNd9bqTn98Ln4DwST8/nG+H0yuB8Hmgu1YHNnWw0GeA=

33github.com/atotto/clipboard v0.1.4 h1:EH0zSVneZPSuFR11BlR9YppQTVDbh5+16AmcJi4g1z4=

59github.com/atotto/clipboard v0.1.4 h1:EH0zSVneZPSuFR11BlR9YppQTVDbh5+16AmcJi4g1z4=

34github.com/atotto/clipboard v0.1.4/go.mod h1:ZY9tmq7sm5xIbd9bOK4onWV4S6X0u6GY7Vn0Yu86PYI=

60github.com/atotto/clipboard v0.1.4/go.mod h1:ZY9tmq7sm5xIbd9bOK4onWV4S6X0u6GY7Vn0Yu86PYI=

35−github.com/aws/aws-sdk-go-v2 v1.39.3 h1:h7xSsanJ4EQJXG5iuW4UqgP7qBopLpj84mpkNx3wPjM=

61+github.com/aws/aws-sdk-go-v2 v1.42.0 h1:XvXMJTkFQtpBKIWZnmr9ZEOc2InWM2yldjXEJ/bymhA=

36−github.com/aws/aws-sdk-go-v2 v1.39.3/go.mod h1:yWSxrnioGUZ4WVv9TgMrNUeLV3PFESn/v+6T/Su8gnM=

62+github.com/aws/aws-sdk-go-v2 v1.42.0/go.mod h1:27+ACypSLljLAEKsCYOmrjKh83vuTRkuAe9Uv/3A4bg=

37−github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.6.3 h1:tW1/Rkad38LA15X4UQtjXZXNKsCgkshC3EbmcUmghTg=

63+github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.13 h1:p1BBrg/Hhp6uK7zpejeI8QFXHJeC/mynzi04Sl03k9g=

38−github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.6.3/go.mod h1:UbnqO+zjqk3uIt9yCACHJ9IVNhyhOCnYk8yA19SAWrM=

64+github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.13/go.mod h1:8cIfkE9MDhkRZGpQ22aV6/lkYeYSozpz16Smrs5x4Ls=

39−github.com/aws/aws-sdk-go-v2/config v1.27.27 h1:HdqgGt1OAP0HkEDDShEl0oSYa9ZZBSOmKpdpsDMdO90=

65+github.com/aws/aws-sdk-go-v2/config v1.32.25 h1:ACCejvStYoilgwrfegSt5ZntCbPrk52qfwyNcnl3omM=

40−github.com/aws/aws-sdk-go-v2/config v1.27.27/go.mod h1:MVYamCg76dFNINkZFu4n4RjDixhVr51HLj4ErWzrVwg=

66+github.com/aws/aws-sdk-go-v2/config v1.32.25/go.mod h1:LJyU8sDRbXUxFn8xMJIGP+v9QYYwveNLI8a/giAOiAs=

41−github.com/aws/aws-sdk-go-v2/credentials v1.17.27 h1:2raNba6gr2IfA0eqqiP2XiQ0UVOpGPgDSi0I9iAP+UI=

67+github.com/aws/aws-sdk-go-v2/credentials v1.19.24 h1:2hQqYCV9yqyePQ9o6dCrZc/zO8U3TwPr9mIKlZnPu/I=

42−github.com/aws/aws-sdk-go-v2/credentials v1.17.27/go.mod h1:gniiwbGahQByxan6YjQUMcW4Aov6bLC3m+evgcoN4r4=

68+github.com/aws/aws-sdk-go-v2/credentials v1.19.24/go.mod h1:IDwpACtwqHLISdzfwUUNq4P9DsB/h5BLg4FwJPNfqFY=

43−github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.16.11 h1:KreluoV8FZDEtI6Co2xuNk/UqI9iwMrOx/87PBNIKqw=

69+github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.29 h1:r6qZHbT+wxgWO/e9vYNUEtg7lv5+UN3pRqKhLXvnArg=

44−github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.16.11/go.mod h1:SeSUYBLsMYFoRvHE0Tjvn7kbxaUhl75CJi1sbfhMxkU=

70+github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.29/go.mod h1:QRnaRcTVGKPGRy8w78HMQtKUGRYcnMZAANATkeVA6Mo=

45−github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.15 h1:SoNJ4RlFEQEbtDcCEt+QG56MY4fm4W8rYirAmq+/DdU=

71+github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.29 h1:f3vKqSo13fhTYb+JEcXwXefZQE26I1FB5eTSniU67ko=

46−github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.15/go.mod h1:U9ke74k1n2bf+RIgoX1SXFed1HLs51OgUSs+Ph0KJP8=

72+github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.29/go.mod h1:MzoLFUArKGpGD+ukmPiTPG1X5x4o6M2kq4v2dr1FiEc=

47−github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.15 h1:C6WHdGnTDIYETAm5iErQUiVNsclNx9qbJVPIt03B6bI=

73+github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.29 h1:RdwIf/CuUsvJX3RgJagbOyotl/cxoLY4xviKuE7p2GY=

48−github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.15/go.mod h1:ZQLZqhcu+JhSrA9/NXRm8SkDvsycE+JkV3WGY41e+IM=

74+github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.29/go.mod h1:71wt8W2EgswdZy9Mf9KNnzxZ3TiZlv4caKghPktDOkA=

49−github.com/aws/aws-sdk-go-v2/internal/ini v1.8.0 h1:hT8rVHwugYE2lEfdFE0QWVo81lF7jMrYJVDWI+f+VxU=

75+github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.30 h1:VTGy885W5DKBxWRUJbym9hytNaYzsyaPkCHGRRMAOhU=

50−github.com/aws/aws-sdk-go-v2/internal/ini v1.8.0/go.mod h1:8tu/lYfQfFe6IGnaOdrpVgEL2IrrDOf6/m9RQum4NkY=

76+github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.30/go.mod h1:AS0HycUvJRFvTt613AYDOgO2jzw+00cVSMny8XB3yMY=

51−github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.11.3 h1:dT3MqvGhSoaIhRseqw2I0yH81l7wiR2vjs57O51EAm8=

77+github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.12 h1:ZD2+BSw9vFsNlKYIasSNt3uDbjqqXIBcM13UJv/Lx2k=

52−github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.11.3/go.mod h1:GlAeCkHwugxdHaueRr4nhPuY+WW+gR8UjlcqzPr1SPI=

78+github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.12/go.mod h1:Ms4zlcVBbXbiP7EVLhl+lgjvA/a7YphqQ3Ih3174EmI=

53−github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.11.17 h1:HGErhhrxZlQ044RiM+WdoZxp0p+EGM62y3L6pwA4olE=

79+github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.29 h1:DRebniUGZ2MqiiIVmQJ04vIXr918hubdHMnarSLEWyU=

54−github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.11.17/go.mod h1:RkZEx4l0EHYDJpWppMJ3nD9wZJAa8/0lq9aVC+r2UII=

80+github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.29/go.mod h1:LfRkPCD8YHDM2E5eTkos2UpwYeZnBcVarTa8L59bJHA=

55−github.com/aws/aws-sdk-go-v2/service/sso v1.22.4 h1:BXx0ZIxvrJdSgSvKTZ+yRBeSqqgPM89VPlulEcl37tM=

81+github.com/aws/aws-sdk-go-v2/service/signin v1.2.0 h1:3nXpRcFwRCW8n7HgO2QGy0Dc20eQNfBuUemGQhpF8m8=

56−github.com/aws/aws-sdk-go-v2/service/sso v1.22.4/go.mod h1:ooyCOXjvJEsUw7x+ZDHeISPMhtwI3ZCB7ggFMcFfWLU=

82+github.com/aws/aws-sdk-go-v2/service/signin v1.2.0/go.mod h1:LxYujSTLPRlp2vTtcUO/+1ilrew8ytt6SvQyOgejzFQ=

57−github.com/aws/aws-sdk-go-v2/service/ssooidc v1.26.4 h1:yiwVzJW2ZxZTurVbYWA7QOrAaCYQR72t0wrSBfoesUE=

83+github.com/aws/aws-sdk-go-v2/service/sso v1.31.3 h1:ey1XLTYXb9PcLt4535632o5kCGXNXEhNb620Dqwuylo=

58−github.com/aws/aws-sdk-go-v2/service/ssooidc v1.26.4/go.mod h1:0oxfLkpz3rQ/CHlx5hB7H69YUpFiI1tql6Q6Ne+1bCw=

84+github.com/aws/aws-sdk-go-v2/service/sso v1.31.3/go.mod h1:Lk7PlmoTYryQmyBG0EXqj5BcUbj3whXdU2s3yGI3EAc=

59−github.com/aws/aws-sdk-go-v2/service/sts v1.30.3 h1:ZsDKRLXGWHk8WdtyYMoGNO7bTudrvuKpDKgMVRlepGE=

85+github.com/aws/aws-sdk-go-v2/service/ssooidc v1.36.6 h1:yLr03zQE/5Eu5l3QU0Si+xMbLMbSDF2YXsigqXngs6g=

60−github.com/aws/aws-sdk-go-v2/service/sts v1.30.3/go.mod h1:zwySh8fpFyXp9yOr/KVzxOl8SRqgf/IDw5aUt9UKFcQ=

86+github.com/aws/aws-sdk-go-v2/service/ssooidc v1.36.6/go.mod h1:Q5N6icH+KJZDLh+ESNwzdv6cZ6vLFF/egy3IOxWhmz4=

61−github.com/aws/smithy-go v1.23.1 h1:sLvcH6dfAFwGkHLZ7dGiYF7aK6mg4CgKA/iDKjLDt9M=

87+github.com/aws/aws-sdk-go-v2/service/sts v1.43.3 h1:VrIhKRCSK1umelSgB9RghvA9RTUYeQffyAS5ApXehNI=

62−github.com/aws/smithy-go v1.23.1/go.mod h1:LEj2LM3rBRQJxPZTB4KuzZkaZYnZPnvgIhb4pu07mx0=

88+github.com/aws/aws-sdk-go-v2/service/sts v1.43.3/go.mod h1:r8wkDOuLaaMFqFiYAb8dGY2A3gJCOujMc6CFOVC4Zhc=

63−github.com/aymanbagabas/go-osc52/v2 v2.0.1 h1:HwpRHbFMcZLEVr42D4p7XBqjyuxQH5SMiErDT4WkJ2k=

89+github.com/aws/smithy-go v1.27.3 h1:F3Zb497UhhskkfpJmfkXswyo+t0sh9OTBnIHjogWbVY=

64−github.com/aymanbagabas/go-osc52/v2 v2.0.1/go.mod h1:uYgXzlJ7ZpABp8OJ+exZzJJhRNQ2ASbcXHWsFqH8hp8=

90+github.com/aws/smithy-go v1.27.3/go.mod h1:YE2RhdIuDbA5E5bTdciG9KrW3+TiEONeUWCqxX9i1Fc=

65−github.com/aymanbagabas/go-udiff v0.3.1 h1:LV+qyBQ2pqe0u42ZsUEtPiCaUoqgA9gYRDs3vj1nolY=

91+github.com/aymanbagabas/go-udiff v0.4.1 h1:OEIrQ8maEeDBXQDoGCbbTTXYJMYRCRO1fnodZ12Gv5o=

66−github.com/aymanbagabas/go-udiff v0.3.1/go.mod h1:G0fsKmG+P6ylD0r6N/KgQD/nWzgfnl8ZBcNLgcbrw8E=

92+github.com/aymanbagabas/go-udiff v0.4.1/go.mod h1:0L9PGwj20lrtmEMeyw4WKJ/TMyDtvAoK9bf2u/mNo3w=

67github.com/aymerick/douceur v0.2.0 h1:Mv+mAeH1Q+n9Fr+oyamOlAkUNPWPlA8PPGR0QAaYuPk=

93github.com/aymerick/douceur v0.2.0 h1:Mv+mAeH1Q+n9Fr+oyamOlAkUNPWPlA8PPGR0QAaYuPk=

68github.com/aymerick/douceur v0.2.0/go.mod h1:wlT5vV2O3h55X9m7iVYN0TBM0NH/MmbLnd30/FjWUq4=

94github.com/aymerick/douceur v0.2.0/go.mod h1:wlT5vV2O3h55X9m7iVYN0TBM0NH/MmbLnd30/FjWUq4=

69github.com/bahlo/generic-list-go v0.2.0 h1:5sz/EEAK+ls5wF+NeqDpk5+iNdMDXrh3z3nPnH1Wvgk=

95github.com/bahlo/generic-list-go v0.2.0 h1:5sz/EEAK+ls5wF+NeqDpk5+iNdMDXrh3z3nPnH1Wvgk=

70github.com/bahlo/generic-list-go v0.2.0/go.mod h1:2KvAjgMlE5NNynlg/5iLrrCCZ2+5xWbdbCW3pNTGyYg=

96github.com/bahlo/generic-list-go v0.2.0/go.mod h1:2KvAjgMlE5NNynlg/5iLrrCCZ2+5xWbdbCW3pNTGyYg=

71−github.com/bmatcuk/doublestar/v4 v4.9.1 h1:X8jg9rRZmJd4yRy7ZeNDRnM+T3ZfHv15JiBJ/avrEXE=

97+github.com/bmatcuk/doublestar/v4 v4.10.0 h1:zU9WiOla1YA122oLM6i4EXvGW62DvKZVxIe6TYWexEs=

72−github.com/bmatcuk/doublestar/v4 v4.9.1/go.mod h1:xBQ8jztBU6kakFMg+8WGxn0c6z1fTSPVIjEY1Wr7jzc=

98+github.com/bmatcuk/doublestar/v4 v4.10.0/go.mod h1:xBQ8jztBU6kakFMg+8WGxn0c6z1fTSPVIjEY1Wr7jzc=

73−github.com/buger/jsonparser v1.1.1 h1:2PnMjfWD7wBILjqQbt530v576A/cAbQvEW9gGIpYMUs=

99+github.com/buger/jsonparser v1.1.2 h1:frqHqw7otoVbk5M8LlE/L7HTnIq2v9RX6EJ48i9AxJk=

74−github.com/buger/jsonparser v1.1.1/go.mod h1:6RYKKt7H4d4+iWqouImQ9R2FZql3VbhNgx27UK13J/0=

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=

75github.com/charlievieth/fastwalk v1.0.14 h1:3Eh5uaFGwHZd8EGwTjJnSpBkfwfsak9h6ICgnWlhAyg=

103github.com/charlievieth/fastwalk v1.0.14 h1:3Eh5uaFGwHZd8EGwTjJnSpBkfwfsak9h6ICgnWlhAyg=

76github.com/charlievieth/fastwalk v1.0.14/go.mod h1:diVcUreiU1aQ4/Wu3NbxxH4/KYdKpLDojrQ1Bb2KgNY=

104github.com/charlievieth/fastwalk v1.0.14/go.mod h1:diVcUreiU1aQ4/Wu3NbxxH4/KYdKpLDojrQ1Bb2KgNY=

77−github.com/charmbracelet/anthropic-sdk-go v0.0.0-20251022202715-ec1499142678 h1:ruB8GXJ6K6lbuU+NhHKsqoHbU/+E+/+0kfUxhWPLvFs=

105+github.com/charmbracelet/anthropic-sdk-go v0.0.0-20260223140439-63879b0b8dab h1:J7XQLgl9sefgTnTGrmX3xqvp5o6MCiBzEjGv5igAlc4=

78−github.com/charmbracelet/anthropic-sdk-go v0.0.0-20251022202715-ec1499142678/go.mod h1:8TIYxZxsuCqqeJ0lga/b91tBwrbjoHDC66Sq5t8N2R4=

106+github.com/charmbracelet/anthropic-sdk-go v0.0.0-20260223140439-63879b0b8dab/go.mod h1:hqlYqR7uPKOKfnNeicUbZp0Ps0GeYFlKYtwh5HGDCx8=

79−github.com/charmbracelet/bubbles/v2 v2.0.0-beta.1.0.20250820203609-601216f68ee2 h1:973OHYuq2Jx9deyuPwe/6lsuQrDCatOsjP8uCd02URE=

107+github.com/charmbracelet/colorprofile v0.4.3 h1:QPa1IWkYI+AOB+fE+mg/5/4HRMZcaXex9t5KX76i20Q=

80−github.com/charmbracelet/bubbles/v2 v2.0.0-beta.1.0.20250820203609-601216f68ee2/go.mod h1:6HamsBKWqEC/FVHuQMHgQL+knPyvHH55HwJDHl/adMw=

108+github.com/charmbracelet/colorprofile v0.4.3/go.mod h1:/zT4BhpD5aGFpqQQqw7a+VtHCzu+zrQtt1zhMt9mR4Q=

81−github.com/charmbracelet/bubbletea/v2 v2.0.0-beta.4.0.20251011205917-3b687ffc1619 h1:hjOhtqsxa+LVuCAkzhfA43wtusOaUPyQdSTg/wbRscw=

109+github.com/charmbracelet/openai-go v0.0.0-20260617131321-5e4b9c18c4be h1:pg+OWlIkk9HOe/8P5J95aKe2wGDzFUiiyFOUpwR30B4=

82−github.com/charmbracelet/bubbletea/v2 v2.0.0-beta.4.0.20251011205917-3b687ffc1619/go.mod h1:5IzIGXU1n0foRc8bRAherC8ZuQCQURPlwx3ANLq1138=

110+github.com/charmbracelet/openai-go v0.0.0-20260617131321-5e4b9c18c4be/go.mod h1:1DahUaExbUZx/jD+FNT2PKP4L9rLE5+ZBRuI8mZjd/E=

83−github.com/charmbracelet/catwalk v0.6.5-0.20251015124117-3bfe9eb6d20f h1:9wLwRJy2LXcq44A7DJJuctYrTptH8nUDBSCj5y2e7c8=

111+github.com/charmbracelet/ultraviolet v0.0.0-20260703014108-f5a850f9c2b7 h1:3FmWoGNWK4STvqg0O0Aeav2T7rodWJAPeF0QpH+8gFw=

84−github.com/charmbracelet/catwalk v0.6.5-0.20251015124117-3bfe9eb6d20f/go.mod h1:ReU4SdrLfe63jkEjWMdX2wlZMV3k9r11oQAmzN0m+KY=

112+github.com/charmbracelet/ultraviolet v0.0.0-20260703014108-f5a850f9c2b7/go.mod h1:f/jRa757WUmaOZrbPspXymbg/GnbF+rwe4OLsG7aXYo=

85−github.com/charmbracelet/colorprofile v0.3.2 h1:9J27WdztfJQVAQKX2WOlSSRB+5gaKqqITmrvb1uTIiI=

113+github.com/charmbracelet/x/ansi v0.11.7 h1:kzv1kJvjg2S3r9KHo8hDdHFQLEqn4RBCb39dAYC84jI=

86−github.com/charmbracelet/colorprofile v0.3.2/go.mod h1:mTD5XzNeWHj8oqHb+S1bssQb7vIHbepiebQ2kPKVKbI=

114+github.com/charmbracelet/x/ansi v0.11.7/go.mod h1:9qGpnAVYz+8ACONkZBUWPtL7lulP9No6p1epAihUZwQ=

87−github.com/charmbracelet/fang v0.4.3 h1:qXeMxnL4H6mSKBUhDefHu8NfikFbP/MBNTfqTrXvzmY=

115+github.com/charmbracelet/x/editor v0.2.0 h1:7XLUKtaRaB8jN7bWU2p2UChiySyaAuIfYiIRg8gGWwk=

88−github.com/charmbracelet/fang v0.4.3/go.mod h1:wHJKQYO5ReYsxx+yZl+skDtrlKO/4LLEQ6EXsdHhRhg=

116+github.com/charmbracelet/x/editor v0.2.0/go.mod h1:p3oQ28TSL3YPd+GKJ1fHWcp+7bVGpedHpXmo0D6t1dY=

89−github.com/charmbracelet/glamour/v2 v2.0.0-20250811143442-a27abb32f018 h1:PU4Zvpagsk5sgaDxn5W4sxHuLp9QRMBZB3bFSk40A4w=

117+github.com/charmbracelet/x/etag v0.2.0 h1:Euj1VkheoHfTYA9y+TCwkeXF/hN8Fb9l4LqZl79pt04=

90−github.com/charmbracelet/glamour/v2 v2.0.0-20250811143442-a27abb32f018/go.mod h1:Z/GLmp9fzaqX4ze3nXG7StgWez5uBM5XtlLHK8V/qSk=

118+github.com/charmbracelet/x/etag v0.2.0/go.mod h1:C1B7/bsgvzzxpfu0Rabbd+rTHJa5TmC/qgTseCf6DF0=

91−github.com/charmbracelet/go-genai v0.0.0-20251021165952-9befde14ce97 h1:HK7B5Q+0FidxjQD5CovniMw7axkUeMHwgVkxkbmiW/s=

119+github.com/charmbracelet/x/exp/charmtone v0.0.0-20260527151214-009e6338d40d h1:sMilwx1YIYTrQva6jsB522AoRYAerNaDIKP4ZPtUq0A=

92−github.com/charmbracelet/go-genai v0.0.0-20251021165952-9befde14ce97/go.mod h1:ZagL2esO4qxlOJBj0d4PVvLM82akQFtne8s3ivxBnTQ=

93−github.com/charmbracelet/lipgloss/v2 v2.0.0-beta.3.0.20250917201909-41ff0bf215ea h1:g1HfUgSMvye8mgecMD1mPscpt+pzJoDEiSA+p2QXzdQ=

94−github.com/charmbracelet/lipgloss/v2 v2.0.0-beta.3.0.20250917201909-41ff0bf215ea/go.mod h1:ngHerf1JLJXBrDXdphn5gFrBPriCL437uwukd5c93pM=

95−github.com/charmbracelet/log/v2 v2.0.0-20250226163916-c379e29ff706 h1:WkwO6Ks3mSIGnGuSdKl9qDSyfbYK50z2wc2gGMggegE=

96−github.com/charmbracelet/log/v2 v2.0.0-20250226163916-c379e29ff706/go.mod h1:mjJGp00cxcfvD5xdCa+bso251Jt4owrQvuimJtVmEmM=

97−github.com/charmbracelet/ultraviolet v0.0.0-20250915111650-81d4262876ef h1:VrWaUi2LXYLjfjCHowdSOEc6dQ9Ro14KY7Bw4IWd19M=

98−github.com/charmbracelet/ultraviolet v0.0.0-20250915111650-81d4262876ef/go.mod h1:AThRsQH1t+dfyOKIwXRoJBniYFQUkUpQq4paheHMc2o=

99−github.com/charmbracelet/x/ansi v0.10.2 h1:ith2ArZS0CJG30cIUfID1LXN7ZFXRCww6RUvAPA+Pzw=

100−github.com/charmbracelet/x/ansi v0.10.2/go.mod h1:HbLdJjQH4UH4AqA2HpRWuWNluRE6zxJH/yteYEYCFa8=

101−github.com/charmbracelet/x/cellbuf v0.0.14-0.20250811133356-e0c5dbe5ea4a h1:zYSNtEJM9jwHbJts2k+Hroj+xQwsW1yxc4Wopdv7KaI=

102−github.com/charmbracelet/x/cellbuf v0.0.14-0.20250811133356-e0c5dbe5ea4a/go.mod h1:rc2bsPC6MWae3LdOxNO1mOb443NlMrrDL0xEya48NNc=

103−github.com/charmbracelet/x/exp/charmtone v0.0.0-20250708181618-a60a724ba6c3 h1:1xwHZg6eMZ9Wv5TE1UGub6ARubyOd1Lo5kPUI/6VL50=

104−github.com/charmbracelet/x/exp/charmtone v0.0.0-20250708181618-a60a724ba6c3/go.mod h1:T9jr8CzFpjhFVHjNjKwbAD7KwBNyFnj2pntAO7F2zw0=

120+github.com/charmbracelet/x/exp/charmtone v0.0.0-20260527151214-009e6338d40d/go.mod h1:nsExn0DGyX0lh9LwLHTn2Gg+hafdzfSXnC+QmEJTZFY=

105−github.com/charmbracelet/x/exp/golden v0.0.0-20250207160936-21c02780d27a h1:FsHEJ52OC4VuTzU8t+n5frMjLvpYWEznSr/u8tnkCYw=

121+github.com/charmbracelet/x/exp/golden v0.0.0-20250806222409-83e3a29d542f h1:pk6gmGpCE7F3FcjaOEKYriCvpmIN4+6OS/RD0vm4uIA=

106−github.com/charmbracelet/x/exp/golden v0.0.0-20250207160936-21c02780d27a/go.mod h1:wDlXFlCrmJ8J+swcL/MnGUuYnqgQdW9rhSD61oNMb6U=

122+github.com/charmbracelet/x/exp/golden v0.0.0-20250806222409-83e3a29d542f/go.mod h1:IfZAMTHB6XkZSeXUqriemErjAWCCzT0LwjKFYCZyw0I=

107github.com/charmbracelet/x/exp/ordered v0.1.0 h1:55/qLwjIh0gL0Vni+QAWk7T/qRVP6sBf+2agPBgnOFE=

123github.com/charmbracelet/x/exp/ordered v0.1.0 h1:55/qLwjIh0gL0Vni+QAWk7T/qRVP6sBf+2agPBgnOFE=

108github.com/charmbracelet/x/exp/ordered v0.1.0/go.mod h1:5UHwmG+is5THxMyCJHNPCn2/ecI07aKNrW+LcResjJ8=

124github.com/charmbracelet/x/exp/ordered v0.1.0/go.mod h1:5UHwmG+is5THxMyCJHNPCn2/ecI07aKNrW+LcResjJ8=

109−github.com/charmbracelet/x/exp/slice v0.0.0-20250904123553-b4e2667e5ad5 h1:DTSZxdV9qQagD4iGcAt9RgaRBZtJl01bfKgdLzUzUPI=

125+github.com/charmbracelet/x/exp/slice v0.0.0-20260622092256-25656177ba8e h1:TerxTCW/3BrnpqKxeouW0cWSjZb7PsVAmtNftRAAFRE=

110−github.com/charmbracelet/x/exp/slice v0.0.0-20250904123553-b4e2667e5ad5/go.mod h1:vI5nDVMWi6veaYH+0Fmvpbe/+cv/iJfMntdh+N0+Tms=

126+github.com/charmbracelet/x/exp/slice v0.0.0-20260622092256-25656177ba8e/go.mod h1:vqEfX6xzqW1pKKZUUiFOKg0OQ7bCh54Q2vR/tserrRA=

111−github.com/charmbracelet/x/json v0.2.0 h1:DqB+ZGx2h+Z+1s98HOuOyli+i97wsFQIxP2ZQANTPrQ=

127+github.com/charmbracelet/x/exp/strings v0.1.0 h1:i69S2XI7uG1u4NLGeJPSYU++Nmjvpo9nwd6aoEm7gkA=

112−github.com/charmbracelet/x/json v0.2.0/go.mod h1:opFIflx2YgXgi49xVUu8gEQ21teFAxyMwvOiZhIvWNM=

128+github.com/charmbracelet/x/exp/strings v0.1.0/go.mod h1:/ehtMPNh9K4odGFkqYJKpIYyePhdp1hLBRvyY4bWkH8=

113−github.com/charmbracelet/x/powernap v0.0.0-20251015113943-25f979b54ad4 h1:i/XilBPYK4L1Yo/mc9FPx0SyJzIsN0y4sj1MWq9Sscc=

129+github.com/charmbracelet/x/powernap v0.1.6 h1:tsnQWQVl9arYm5S/tQVXuMJcvnkUNNkXhBWlEBDRNqM=

114−github.com/charmbracelet/x/powernap v0.0.0-20251015113943-25f979b54ad4/go.mod h1:cmdl5zlP5mR8TF2Y68UKc7hdGUDiSJ2+4hk0h04Hsx4=

130+github.com/charmbracelet/x/powernap v0.1.6/go.mod h1:cmdl5zlP5mR8TF2Y68UKc7hdGUDiSJ2+4hk0h04Hsx4=

115−github.com/charmbracelet/x/term v0.2.1 h1:AQeHeLZ1OqSXhrAWpYUtZyX1T3zVxfpZuEQMIQaGIAQ=

131+github.com/charmbracelet/x/term v0.2.2 h1:xVRT/S2ZcKdhhOuSP4t5cLi5o+JxklsoEObBSgfgZRk=

116−github.com/charmbracelet/x/term v0.2.1/go.mod h1:oQ4enTYFV7QN4m0i9mzHrViD7TQKvNEEkHUMCmsxdUg=

132+github.com/charmbracelet/x/term v0.2.2/go.mod h1:kF8CY5RddLWrsgVwpw4kAa6TESp6EB5y3uxGLeCqzAI=

117github.com/charmbracelet/x/termios v0.1.1 h1:o3Q2bT8eqzGnGPOYheoYS8eEleT5ZVNYNy8JawjaNZY=

133github.com/charmbracelet/x/termios v0.1.1 h1:o3Q2bT8eqzGnGPOYheoYS8eEleT5ZVNYNy8JawjaNZY=

118github.com/charmbracelet/x/termios v0.1.1/go.mod h1:rB7fnv1TgOPOyyKRJ9o+AsTU/vK5WHJ2ivHeut/Pcwo=

134github.com/charmbracelet/x/termios v0.1.1/go.mod h1:rB7fnv1TgOPOyyKRJ9o+AsTU/vK5WHJ2ivHeut/Pcwo=

119github.com/charmbracelet/x/windows v0.2.2 h1:IofanmuvaxnKHuV04sC0eBy/smG6kIKrWG2/jYn2GuM=

135github.com/charmbracelet/x/windows v0.2.2 h1:IofanmuvaxnKHuV04sC0eBy/smG6kIKrWG2/jYn2GuM=

120github.com/charmbracelet/x/windows v0.2.2/go.mod h1:/8XtdKZzedat74NQFn0NGlGL4soHB0YQZrETF96h75k=

136github.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=

121github.com/cpuguy83/go-md2man/v2 v2.0.6/go.mod h1:oOW0eioCTA6cOiMLiUPZOpcVxMig6NIQQ7OS05n1F4g=

143github.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=

122github.com/creack/pty v1.1.24 h1:bJrF4RRfyJnbTJqzRLHzcGaZK1NeM5kTC9jGgovnR1s=

145github.com/creack/pty v1.1.24 h1:bJrF4RRfyJnbTJqzRLHzcGaZK1NeM5kTC9jGgovnR1s=

123github.com/creack/pty v1.1.24/go.mod h1:08sCNb52WyoAwi2QDyzUCTgcvVFhUzewun7wtTfvcwE=

146github.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=

124github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=

149github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=

125−github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=

126github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=

150github.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=

127github.com/denisbrodbeck/machineid v1.0.1 h1:geKr9qtkB876mXguW2X6TU4ZynleN6ezuMSRhl4D7AQ=

153github.com/denisbrodbeck/machineid v1.0.1 h1:geKr9qtkB876mXguW2X6TU4ZynleN6ezuMSRhl4D7AQ=

128github.com/denisbrodbeck/machineid v1.0.1/go.mod h1:dJUwb7PTidGDeYyUBmXZ2GphQBbjJCrnectwCyxcUSI=

154github.com/denisbrodbeck/machineid v1.0.1/go.mod h1:dJUwb7PTidGDeYyUBmXZ2GphQBbjJCrnectwCyxcUSI=

129−github.com/disintegration/gift v1.1.2 h1:9ZyHJr+kPamiH10FX3Pynt1AxFUob812bU9Wt4GMzhs=

155+github.com/disintegration/imaging v1.6.2 h1:w1LecBlG2Lnp8B3jk5zSuNqd7b4DXhcjwek1ei82L+c=

130−github.com/disintegration/gift v1.1.2/go.mod h1:Jh2i7f7Q2BM7Ezno3PhfezbR1xpUg9dUg3/RlKGr4HI=

156+github.com/disintegration/imaging v1.6.2/go.mod h1:44/5580QXChDfwIclfc/PCwrr44amcmDAg8hxG0Ewe4=

131−github.com/disintegration/imageorient v0.0.0-20180920195336-8147d86e83ec h1:YrB6aVr9touOt75I9O1SiancmR2GMg45U9UYf0gtgWg=

157+github.com/dlclark/regexp2/v2 v2.2.1 h1:mf4KkFUj0gJuarK8P+LgiS+Lit7m9N1yAwEfPbee7R0=

132−github.com/disintegration/imageorient v0.0.0-20180920195336-8147d86e83ec/go.mod h1:K0KBFIr1gWu/C1Gp10nFAcAE4hsB7JxE6OgLijrJ8Sk=

158+github.com/dlclark/regexp2/v2 v2.2.1/go.mod h1:avUrQvPaLz2DrFNHJF0taWAFFX2C1GMSSoeiqFjcBmU=

133−github.com/dlclark/regexp2 v1.11.5 h1:Q/sSnsKerHeCkc/jSTNq1oCm7KiVgUMZRDUoRu0JQZQ=

159+github.com/dnaeon/go-vcr v1.2.0 h1:zHCHvJYTMh1N7xnV7zf1m1GPBF9Ad0Jk/whtQ1663qI=

134−github.com/dlclark/regexp2 v1.11.5/go.mod h1:DHkYz0B9wPfa6wondMfaivmHpzrQ3v9q8cnmRbL6yW8=

160+github.com/dnaeon/go-vcr v1.2.0/go.mod h1:R4UdLID7HZT3taECzJs4YgbbH6PIGXB6W/sc5OLb6RQ=

135github.com/dustin/go-humanize v1.0.1 h1:GzkhY7T5VNhEkwH0PVJgjz+fX1rhBrR7pRT3mDkpeCY=

161github.com/dustin/go-humanize v1.0.1 h1:GzkhY7T5VNhEkwH0PVJgjz+fX1rhBrR7pRT3mDkpeCY=

136github.com/dustin/go-humanize v1.0.1/go.mod h1:Mu1zIs6XwVuF/gI1OepvI0qD18qycQx+mFykh5fBlto=

162github.com/dustin/go-humanize v1.0.1/go.mod h1:Mu1zIs6XwVuF/gI1OepvI0qD18qycQx+mFykh5fBlto=

137−github.com/felixge/httpsnoop v1.0.4 h1:NFTV2Zj1bL4mc9sqWACXbQFVBBg2W3GPvqp8/ESS2Wg=

163+github.com/ebitengine/purego v0.10.1 h1:dewVBCBT2GaMu1SrNTYxQhgQBethzfhiwvZiLGP/qyY=

138−github.com/felixge/httpsnoop v1.0.4/go.mod h1:m8KPJKqk1gH5J9DgRY2ASl2lWCfGKXixSwevea8zH2U=

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=

139github.com/fsnotify/fsnotify v1.6.0/go.mod h1:sl3t1tCWJFWoRz9R8WJCbQihKKwmorjAbSClcnxKAGw=

174github.com/fsnotify/fsnotify v1.6.0/go.mod h1:sl3t1tCWJFWoRz9R8WJCbQihKKwmorjAbSClcnxKAGw=

140github.com/fsnotify/fsnotify v1.9.0 h1:2Ml+OJNzbYCTzsxtv8vKSFD9PbJjmhYF14k/jKC7S9k=

175github.com/fsnotify/fsnotify v1.9.0 h1:2Ml+OJNzbYCTzsxtv8vKSFD9PbJjmhYF14k/jKC7S9k=

141github.com/fsnotify/fsnotify v1.9.0/go.mod h1:8jBTzvmWwFyi3Pb8djgCCO5IBqzKJ/Jwo8TRcHyHii0=

176github.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=

142github.com/go-logfmt/logfmt v0.6.0 h1:wGYYu3uicYdqXVgoYbvnkrPVXkuLM1p1ifugDMEdRi4=

187github.com/go-logfmt/logfmt v0.6.0 h1:wGYYu3uicYdqXVgoYbvnkrPVXkuLM1p1ifugDMEdRi4=

143github.com/go-logfmt/logfmt v0.6.0/go.mod h1:WYhtIu8zTZfxdn5+rREduYbwxfcBr/Vr6KEVveWlfTs=

188github.com/go-logfmt/logfmt v0.6.0/go.mod h1:WYhtIu8zTZfxdn5+rREduYbwxfcBr/Vr6KEVveWlfTs=

144github.com/go-logr/logr v1.2.2/go.mod h1:jdQByPbusPIv2/zmleS9BjJVeZ6kBagPoEUsqbVz/1A=

189github.com/go-logr/logr v1.2.2/go.mod h1:jdQByPbusPIv2/zmleS9BjJVeZ6kBagPoEUsqbVz/1A=

@@ -146,27 +191,50 @@ github.com/go-logr/logr v1.4.3 h1:CjnDlHq8ikf6E492q6eKboGOC0T8CDaOvkHCIg8idEI=

146github.com/go-logr/logr v1.4.3/go.mod h1:9T104GzyrTigFIr8wt5mBrctHMim0Nb2HLGrmQ40KvY=

191github.com/go-logr/logr v1.4.3/go.mod h1:9T104GzyrTigFIr8wt5mBrctHMim0Nb2HLGrmQ40KvY=

147github.com/go-logr/stdr v1.2.2 h1:hSWxHoqTgW2S2qGc0LTAI563KZ5YKYRhT3MFKZMbjag=

192github.com/go-logr/stdr v1.2.2 h1:hSWxHoqTgW2S2qGc0LTAI563KZ5YKYRhT3MFKZMbjag=

148github.com/go-logr/stdr v1.2.2/go.mod h1:mMo/vtBO5dYbehREoey6XUKy/eSumjCCveDpRre4VKE=

193github.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=

149github.com/go-quicktest/qt v1.101.0 h1:O1K29Txy5P2OK0dGo59b7b0LR6wKfIhttaAhHUyn7eI=

206github.com/go-quicktest/qt v1.101.0 h1:O1K29Txy5P2OK0dGo59b7b0LR6wKfIhttaAhHUyn7eI=

150github.com/go-quicktest/qt v1.101.0/go.mod h1:14Bz/f7NwaXPtdYEgzsx46kqSxVwTbzVZsDC26tQJow=

207github.com/go-quicktest/qt v1.101.0/go.mod h1:14Bz/f7NwaXPtdYEgzsx46kqSxVwTbzVZsDC26tQJow=

151−github.com/go-viper/mapstructure/v2 v2.4.0 h1:EBsztssimR/CONLSZZ04E8qAkxNYq4Qp9LvH92wZUgs=

208+github.com/go-viper/mapstructure/v2 v2.5.0 h1:vM5IJoUAy3d7zRSVtIwQgBj7BiWtMPfmPEgAXnvj1Ro=

152−github.com/go-viper/mapstructure/v2 v2.4.0/go.mod h1:oJDH3BJKyqBA2TXFhDsKDGDTlndYOZ6rGS0BRZIxGhM=

209+github.com/go-viper/mapstructure/v2 v2.5.0/go.mod h1:oJDH3BJKyqBA2TXFhDsKDGDTlndYOZ6rGS0BRZIxGhM=

153−github.com/golang-jwt/jwt/v5 v5.2.2 h1:Rl4B7itRWVtYIHFrSNd7vhTiz9UpLdi6gZhZ3wEeDy8=

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=

154−github.com/golang-jwt/jwt/v5 v5.2.2/go.mod h1:pqrtFR0X4osieyHYxtmOUWsAWrfe1Q5UVIyoH402zdk=

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=

155github.com/golang/protobuf v1.5.4 h1:i7eJL8qZTpSEXOPTxNKhASYpMn+8e5Q6AdndVa1dWek=

221github.com/golang/protobuf v1.5.4 h1:i7eJL8qZTpSEXOPTxNKhASYpMn+8e5Q6AdndVa1dWek=

156github.com/golang/protobuf v1.5.4/go.mod h1:lnTiLA8Wa4RWRcIUkrtSVa5nRhsEGBg48fD6rSs7xps=

222github.com/golang/protobuf v1.5.4/go.mod h1:lnTiLA8Wa4RWRcIUkrtSVa5nRhsEGBg48fD6rSs7xps=

157github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=

223github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=

158github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=

224github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=

159github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=

225github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=

160−github.com/google/jsonschema-go v0.3.0 h1:6AH2TxVNtk3IlvkkhjrtbUc4S8AvO0Xii0DxIygDg+Q=

226+github.com/google/jsonschema-go v0.4.3 h1:/DBOLZTfDow7pe2GmaJNhltueGTtDKICi8V8p+DQPd0=

161−github.com/google/jsonschema-go v0.3.0/go.mod h1:r5quNTdLOYEz95Ru18zA0ydNbBuYoo9tgaYcxEYhJVE=

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=

162github.com/google/s2a-go v0.1.9 h1:LGD7gtMgezd8a/Xak7mEWL0PjoTQFvpRudN895yqKW0=

230github.com/google/s2a-go v0.1.9 h1:LGD7gtMgezd8a/Xak7mEWL0PjoTQFvpRudN895yqKW0=

163github.com/google/s2a-go v0.1.9/go.mod h1:YA0Ei2ZQL3acow2O62kdp9UlnvMmU7kA6Eutn0dXayM=

231github.com/google/s2a-go v0.1.9/go.mod h1:YA0Ei2ZQL3acow2O62kdp9UlnvMmU7kA6Eutn0dXayM=

164github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=

232github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=

165github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=

233github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=

166−github.com/googleapis/enterprise-certificate-proxy v0.3.6 h1:GW/XbdyBFQ8Qe+YAmFU9uHLo7OnF5tL52HFAgMmyrf4=

234+github.com/googleapis/enterprise-certificate-proxy v0.3.17 h1:73NfMHdiqo9JFU9+7a5ExpVa10/R29pXfZIaW559nrg=

167−github.com/googleapis/enterprise-certificate-proxy v0.3.6/go.mod h1:MkHOF77EYAE7qfSuSS9PU6g4Nt4e11cnsDUowfwewLA=

235+github.com/googleapis/enterprise-certificate-proxy v0.3.17/go.mod h1:rSEsBUemEBZEexP2y6jPp16LUmUbjmSbcPMQizR0o4k=

168−github.com/googleapis/gax-go/v2 v2.15.0 h1:SyjDc1mGgZU5LncH8gimWo9lW1DtIfPibOG81vgd/bo=

236+github.com/googleapis/gax-go/v2 v2.22.0 h1:PjIWBpgGIVKGoCXuiCoP64altEJCj3/Ei+kSU5vlZD4=

169−github.com/googleapis/gax-go/v2 v2.15.0/go.mod h1:zVVkkxAQHa1RQpg9z2AUCMnKhi0Qld9rcmyfL1OZhoc=

237+github.com/googleapis/gax-go/v2 v2.22.0/go.mod h1:irWBbALSr0Sk3qlqb9SyJ1h68WjgeFuiOzI4Rqw5+aY=

170github.com/gorilla/css v1.0.1 h1:ntNaBIghp6JmvWnxbZKANoLyuXTPZ4cAMlo6RyhlbO8=

238github.com/gorilla/css v1.0.1 h1:ntNaBIghp6JmvWnxbZKANoLyuXTPZ4cAMlo6RyhlbO8=

171github.com/gorilla/css v1.0.1/go.mod h1:BvnYkspnSzMmwRK+b8/xgNPLiIuNZr6vbZBTPQ2A3b0=

239github.com/gorilla/css v1.0.1/go.mod h1:BvnYkspnSzMmwRK+b8/xgNPLiIuNZr6vbZBTPQ2A3b0=

172github.com/gorilla/websocket v1.4.1/go.mod h1:YR8l580nyteQvAITg2hZ9XVh4b55+EU/adAjf1fMHhE=

240github.com/gorilla/websocket v1.4.1/go.mod h1:YR8l580nyteQvAITg2hZ9XVh4b55+EU/adAjf1fMHhE=

@@ -178,15 +246,30 @@ github.com/hexops/gotextdiff v1.0.3 h1:gitA9+qJrrTCsiCl7+kh75nPqQt1cx4ZkudSTLoUq

178github.com/hexops/gotextdiff v1.0.3/go.mod h1:pSWU5MAI3yDq+fZBTazCSJysOMbxWL1BSow5/V2vxeg=

246github.com/hexops/gotextdiff v1.0.3/go.mod h1:pSWU5MAI3yDq+fZBTazCSJysOMbxWL1BSow5/V2vxeg=

179github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8=

247github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8=

180github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw=

248github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw=

181−github.com/invopop/jsonschema v0.13.0 h1:KvpoAJWEjR3uD9Kbm2HWJmqsEaHt8lBUpd0qHcIi21E=

249+github.com/invopop/jsonschema v0.14.0 h1:MHQqLhvpNUZfw+hM3AZDYK7jxO8FZoQeQM77g8iyZjg=

182−github.com/invopop/jsonschema v0.13.0/go.mod h1:ffZ5Km5SWWRAIN6wbDXItl95euhFz2uON45H2qjYt+0=

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=

183github.com/joho/godotenv v1.5.1 h1:7eLL/+HRGLY0ldzfGMeQkb7vMd0as4CfYvUVzLqw0N0=

259github.com/joho/godotenv v1.5.1 h1:7eLL/+HRGLY0ldzfGMeQkb7vMd0as4CfYvUVzLqw0N0=

184github.com/joho/godotenv v1.5.1/go.mod h1:f4LDr5Voq0i2e/R5DDNOoa2zzDfwtkZa6DnEwAbqwq4=

260github.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=

185github.com/josharian/intern v1.0.0/go.mod h1:5DoeVV0s6jJacbCEi61lwdGj/aVlrQvzHFFd8Hwg//Y=

264github.com/josharian/intern v1.0.0/go.mod h1:5DoeVV0s6jJacbCEi61lwdGj/aVlrQvzHFFd8Hwg//Y=

186−github.com/klauspost/compress v1.18.0 h1:c/Cqfb0r+Yi+JtIEq73FWXVkRonBlf0CRNYc8Zttxdo=

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=

187−github.com/klauspost/compress v1.18.0/go.mod h1:2Pp+KzxcywXVXMr50+X0Q/Lsb43OQHYWRCY2AiWywWQ=

270+github.com/klauspost/compress v1.18.6/go.mod h1:cwPg85FWrGar70rWktvGQj8/hthj3wpl0PGDogxkrSQ=

188−github.com/klauspost/cpuid/v2 v2.0.9 h1:lgaqFMSdTdQYdZ04uHyN2d/eKdOMyi2YLSvlQIBFYa4=

271+github.com/klauspost/cpuid/v2 v2.3.0 h1:S4CRMLnYUhGeDFDqkGriYKdfoFlDnMtqTiI/sFzhA9Y=

189−github.com/klauspost/cpuid/v2 v2.0.9/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg=

272+github.com/klauspost/cpuid/v2 v2.3.0/go.mod h1:hqwkgyIinND0mEev00jJYCxPNVRVXFQeu1XKlok6oO0=

190github.com/klauspost/pgzip v1.2.6 h1:8RXeL5crjEUFnR2/Sn6GJNWtSQ3Dk8pq4CL3jvdDyjU=

273github.com/klauspost/pgzip v1.2.6 h1:8RXeL5crjEUFnR2/Sn6GJNWtSQ3Dk8pq4CL3jvdDyjU=

191github.com/klauspost/pgzip v1.2.6/go.mod h1:Ch1tH69qFZu15pkjo5kYi6mth2Zzwzt50oCQKQE9RUs=

274github.com/klauspost/pgzip v1.2.6/go.mod h1:Ch1tH69qFZu15pkjo5kYi6mth2Zzwzt50oCQKQE9RUs=

192github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=

275github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=

@@ -198,22 +281,25 @@ github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=

198github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=

281github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=

199github.com/kylelemons/godebug v1.1.0 h1:RPNrshWIDI6G2gRW9EHilWtl7Z6Sb1BR0xunSBf0SNc=

282github.com/kylelemons/godebug v1.1.0 h1:RPNrshWIDI6G2gRW9EHilWtl7Z6Sb1BR0xunSBf0SNc=

200github.com/kylelemons/godebug v1.1.0/go.mod h1:9/0rRGxNHcop5bhtWyNeEfOS8JIWk580+fNqagV/RAw=

283github.com/kylelemons/godebug v1.1.0/go.mod h1:9/0rRGxNHcop5bhtWyNeEfOS8JIWk580+fNqagV/RAw=

201−github.com/lucasb-eyer/go-colorful v1.3.0 h1:2/yBRLdWBZKrf7gB40FoiKfAWYQ0lqNcbuQwVHXptag=

284+github.com/lucasb-eyer/go-colorful v1.4.0 h1:UtrWVfLdarDgc44HcS7pYloGHJUjHV/4FwW4TvVgFr4=

202−github.com/lucasb-eyer/go-colorful v1.3.0/go.mod h1:R4dSotOR9KMtayYi1e77YzuveK+i7ruzyGqttikkLy0=

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=

203github.com/mailru/easyjson v0.7.7 h1:UGYAvKxe3sBsEDzO8ZeWOSlIQfWFlxbzLZe7hwFURr0=

289github.com/mailru/easyjson v0.7.7 h1:UGYAvKxe3sBsEDzO8ZeWOSlIQfWFlxbzLZe7hwFURr0=

204github.com/mailru/easyjson v0.7.7/go.mod h1:xzfreul335JAWq5oZzymOObrkdz5UnU4kGfJJLY9Nlc=

290github.com/mailru/easyjson v0.7.7/go.mod h1:xzfreul335JAWq5oZzymOObrkdz5UnU4kGfJJLY9Nlc=

205−github.com/mattn/go-isatty v0.0.20 h1:xfD0iDuEKnDkl03q4limB+vH+GxLEtL/jb4xVJSWWEY=

291+github.com/mattn/go-isatty v0.0.22 h1:j8l17JJ9i6VGPUFUYoTUKPSgKe/83EYU2zBC7YNKMw4=

206−github.com/mattn/go-isatty v0.0.20/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=

292+github.com/mattn/go-isatty v0.0.22/go.mod h1:ZXfXG4SQHsB/w3ZeOYbR0PrPwLy+n6xiMrJlRFqopa4=

207−github.com/mattn/go-runewidth v0.0.17 h1:78v8ZlW0bP43XfmAfPsdXcoNCelfMHsDmd/pkENfrjQ=

293+github.com/mattn/go-runewidth v0.0.24 h1:cpokDiIn0MGnhdHwuWnJBITySJ20QyNGnY2kR/ay2DU=

208−github.com/mattn/go-runewidth v0.0.17/go.mod h1:Jdepj2loyihRzMpdS35Xk/zdY8IAYHsh153qUoGf23w=

294+github.com/mattn/go-runewidth v0.0.24/go.mod h1:XBkDxAl56ILZc9knddidhrOlY5R/pDhgLpndooCuJAs=

209github.com/mfridman/interpolate v0.0.2 h1:pnuTK7MQIxxFz1Gr+rjSIx9u7qVjf5VOoM/u6BbAxPY=

295github.com/mfridman/interpolate v0.0.2 h1:pnuTK7MQIxxFz1Gr+rjSIx9u7qVjf5VOoM/u6BbAxPY=

210github.com/mfridman/interpolate v0.0.2/go.mod h1:p+7uk6oE07mpE/Ik1b8EckO0O4ZXiGAfshKBWLUM9Xg=

296github.com/mfridman/interpolate v0.0.2/go.mod h1:p+7uk6oE07mpE/Ik1b8EckO0O4ZXiGAfshKBWLUM9Xg=

211github.com/microcosm-cc/bluemonday v1.0.27 h1:MpEUotklkwCSLeH+Qdx1VJgNqLlpY2KXwXFM08ygZfk=

297github.com/microcosm-cc/bluemonday v1.0.27 h1:MpEUotklkwCSLeH+Qdx1VJgNqLlpY2KXwXFM08ygZfk=

212github.com/microcosm-cc/bluemonday v1.0.27/go.mod h1:jFi9vgW+H7c3V0lb6nR74Ib/DIB5OBs92Dimizgw2cA=

298github.com/microcosm-cc/bluemonday v1.0.27/go.mod h1:jFi9vgW+H7c3V0lb6nR74Ib/DIB5OBs92Dimizgw2cA=

213github.com/mitchellh/mapstructure v1.5.0 h1:jeMsZIYE/09sWLaz43PL7Gy6RuMjD2eJVyuac5Z2hdY=

299github.com/mitchellh/mapstructure v1.5.0 h1:jeMsZIYE/09sWLaz43PL7Gy6RuMjD2eJVyuac5Z2hdY=

214github.com/mitchellh/mapstructure v1.5.0/go.mod h1:bFUtVrKA4DC2yAKiSyO/QUcy7e+RRV2QTWOzhPopBRo=

300github.com/mitchellh/mapstructure v1.5.0/go.mod h1:bFUtVrKA4DC2yAKiSyO/QUcy7e+RRV2QTWOzhPopBRo=

215−github.com/modelcontextprotocol/go-sdk v1.0.0 h1:Z4MSjLi38bTgLrd/LjSmofqRqyBiVKRyQSJgw8q8V74=

301+github.com/modelcontextprotocol/go-sdk v1.6.1 h1:0zOSupjKUxPKSocPT1Wtago+mUHU2/uZ4xSOY0FGReU=

216−github.com/modelcontextprotocol/go-sdk v1.0.0/go.mod h1:nYtYQroQ2KQiM0/SbyEPUWQ6xs4B95gJjEalc9AQyOs=

302+github.com/modelcontextprotocol/go-sdk v1.6.1/go.mod h1:kzm3kzFL1/+AziGOE0nUs3gvPoNxMCvkxokMkuFapXQ=

217github.com/muesli/cancelreader v0.2.2 h1:3I4Kt4BQjOR54NavqnDogx/MIoWBFa0StPA8ELUXHmA=

303github.com/muesli/cancelreader v0.2.2 h1:3I4Kt4BQjOR54NavqnDogx/MIoWBFa0StPA8ELUXHmA=

218github.com/muesli/cancelreader v0.2.2/go.mod h1:3XuTXfFS2VjM+HTLZY9Ak0l6eUKfijIfMUZ4EgX0QYo=

304github.com/muesli/cancelreader v0.2.2/go.mod h1:3XuTXfFS2VjM+HTLZY9Ak0l6eUKfijIfMUZ4EgX0QYo=

219github.com/muesli/mango v0.1.0 h1:DZQK45d2gGbql1arsYA4vfg4d7I9Hfx5rX/GCmzsAvI=

305github.com/muesli/mango v0.1.0 h1:DZQK45d2gGbql1arsYA4vfg4d7I9Hfx5rX/GCmzsAvI=

@@ -224,47 +310,62 @@ github.com/muesli/mango-pflag v0.1.0 h1:UADqbYgpUyRoBja3g6LUL+3LErjpsOwaC9ywvBWe

224github.com/muesli/mango-pflag v0.1.0/go.mod h1:YEQomTxaCUp8PrbhFh10UfbhbQrM/xJ4i2PB8VTLLW0=

310github.com/muesli/mango-pflag v0.1.0/go.mod h1:YEQomTxaCUp8PrbhFh10UfbhbQrM/xJ4i2PB8VTLLW0=

225github.com/muesli/roff v0.1.0 h1:YD0lalCotmYuF5HhZliKWlIx7IEhiXeSfq7hNjFqGF8=

311github.com/muesli/roff v0.1.0 h1:YD0lalCotmYuF5HhZliKWlIx7IEhiXeSfq7hNjFqGF8=

226github.com/muesli/roff v0.1.0/go.mod h1:pjAHQM9hdUUwm/krAfrLGgJkXJ+YuhtsfZ42kieB2Ig=

312github.com/muesli/roff v0.1.0/go.mod h1:pjAHQM9hdUUwm/krAfrLGgJkXJ+YuhtsfZ42kieB2Ig=

227−github.com/muesli/termenv v0.16.0 h1:S5AlUN9dENB57rsbnkPyfdGuWIlkmzJjbFf0Tf5FWUc=

313+github.com/ncruces/go-sqlite3 v0.35.1 h1:h/LaVyQwIvBBT0+2JmVe2tbYyWjUQ093/pYhpBqdxJo=

228−github.com/muesli/termenv v0.16.0/go.mod h1:ZRfOIKPFDYQoDFF4Olj7/QJbW60Ol/kL1pU3VfY/Cnk=

314+github.com/ncruces/go-sqlite3 v0.35.1/go.mod h1:fXOSIkWwN5NXgbJk+7Zls8QIW4xOflmgh11OFvcY+J0=

229−github.com/ncruces/go-sqlite3 v0.29.1 h1:NIi8AISWBToRHyoz01FXiTNvU147Tqdibgj2tFzJCqM=

315+github.com/ncruces/go-sqlite3-wasm/v3 v3.1.35302 h1:Cew7/eNAMd1zhpXYBjofBua/63pFvbvB2h4PM/p6gKU=

230−github.com/ncruces/go-sqlite3 v0.29.1/go.mod h1:PpccBNNhvjwUOwDQEn2gXQPFPTWdlromj0+fSkd5KSg=

316+github.com/ncruces/go-sqlite3-wasm/v3 v3.1.35302/go.mod h1:xe0CfafDUxfh+fSVKjHHMiAxoG9KALt5nFtbGNb/jRs=

231−github.com/ncruces/go-strftime v0.1.9 h1:bY0MQC28UADQmHmaF5dgpLmImcShSi2kHU9XLdhx/f4=

317+github.com/ncruces/go-strftime v1.0.0 h1:HMFp8mLCTPp341M/ZnA4qaf7ZlsbTc+miZjCLOFAw7w=

232−github.com/ncruces/go-strftime v0.1.9/go.mod h1:Fwc5htZGVVkseilnfgOVb9mKy6w1naJmn9CehxcKcls=

318+github.com/ncruces/go-strftime v1.0.0/go.mod h1:Fwc5htZGVVkseilnfgOVb9mKy6w1naJmn9CehxcKcls=

233github.com/ncruces/julianday v1.0.0 h1:fH0OKwa7NWvniGQtxdJRxAgkBMolni2BjDHaWTxqt7M=

319github.com/ncruces/julianday v1.0.0 h1:fH0OKwa7NWvniGQtxdJRxAgkBMolni2BjDHaWTxqt7M=

234github.com/ncruces/julianday v1.0.0/go.mod h1:Dusn2KvZrrovOMJuOt0TNXL6tB7U2E8kvza5fFc9G7g=

320github.com/ncruces/julianday v1.0.0/go.mod h1:Dusn2KvZrrovOMJuOt0TNXL6tB7U2E8kvza5fFc9G7g=

235github.com/nfnt/resize v0.0.0-20180221191011-83c6a9932646 h1:zYyBkD/k9seD2A7fsi6Oo2LfFZAehjjQMERAvZLEDnQ=

321github.com/nfnt/resize v0.0.0-20180221191011-83c6a9932646 h1:zYyBkD/k9seD2A7fsi6Oo2LfFZAehjjQMERAvZLEDnQ=

236github.com/nfnt/resize v0.0.0-20180221191011-83c6a9932646/go.mod h1:jpp1/29i3P1S/RLdc7JQKbRpFeM1dOBd8T9ki5s+AY8=

322github.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=

237github.com/nxadm/tail v1.4.11 h1:8feyoE3OzPrcshW5/MJ4sGESc5cqmGkGCWlco4l0bqY=

324github.com/nxadm/tail v1.4.11 h1:8feyoE3OzPrcshW5/MJ4sGESc5cqmGkGCWlco4l0bqY=

238github.com/nxadm/tail v1.4.11/go.mod h1:OTaG3NK980DZzxbRq6lEuzgU+mug70nY11sMd4JXXHc=

325github.com/nxadm/tail v1.4.11/go.mod h1:OTaG3NK980DZzxbRq6lEuzgU+mug70nY11sMd4JXXHc=

239−github.com/openai/openai-go/v2 v2.7.1 h1:/tfvTJhfv7hTSL8mWwc5VL4WLLSDL5yn9VqVykdu9r8=

326+github.com/onsi/gomega v1.34.1 h1:EUMJIKUjM8sKjYbtxQI9A4z2o+rruxnzNvpknOXie6k=

240−github.com/openai/openai-go/v2 v2.7.1/go.mod h1:jrJs23apqJKKbT+pqtFgNKpRju/KP9zpUTZhz3GElQE=

327+github.com/onsi/gomega v1.34.1/go.mod h1:kU1QgUvBDLXBJq618Xvm2LUX6rSAfRaFRTcdOeDLwwY=

241−github.com/pierrec/lz4/v4 v4.1.22 h1:cKFw6uJDK+/gfw5BcDL0JL5aBsAFdsIT18eRtLj7VIU=

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=

242−github.com/pierrec/lz4/v4 v4.1.22/go.mod h1:gZWDp/Ze/IJXGXf23ltt2EXimqmTUXEy0GFuRQyBid4=

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=

243github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c h1:+mdjkGKdHQG3305AYmdv1U2eRNDiU2ErMBj1gwrq8eQ=

334github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c h1:+mdjkGKdHQG3305AYmdv1U2eRNDiU2ErMBj1gwrq8eQ=

244github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c/go.mod h1:7rwL4CYBLnjLxUqIJNnCWiEdr3bn6IUYi15bNlnbCCU=

335github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c/go.mod h1:7rwL4CYBLnjLxUqIJNnCWiEdr3bn6IUYi15bNlnbCCU=

245github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=

336github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=

246−github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=

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=

247github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=

341github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=

248−github.com/posthog/posthog-go v1.6.11 h1:5G8Y3pxnOpc3S4+PK1z1dCmZRuldiWxBsqqvvSfC2+w=

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=

249−github.com/posthog/posthog-go v1.6.11/go.mod h1:LcC1Nu4AgvV22EndTtrMXTy+7RGVC0MhChSw7Qk5XkY=

345+github.com/posthog/posthog-go v1.17.5/go.mod h1://M430hNH3e8CDv4i8SJesb26816Mpa6GIZaiP4pNQU=

250−github.com/pressly/goose/v3 v3.25.0 h1:6WeYhMWGRCzpyd89SpODFnCBCKz41KrVbRT58nVjGng=

346+github.com/pressly/goose/v3 v3.27.2 h1:FjKNzcmMdGrQlSIu5alMSmakQtJFBgtw+A0bb1p/LC8=

251−github.com/pressly/goose/v3 v3.25.0/go.mod h1:4hC1KrritdCxtuFsqgs1R4AU5bWtTAf+cnWvfhf2DNY=

347+github.com/pressly/goose/v3 v3.27.2/go.mod h1:qWW+/8dkVtJYjJrbIpwD5xxnEJTUKvxkQ9JKQp9LaIM=

252−github.com/qjebbs/go-jsons v1.0.0-alpha.4 h1:Qsb4ohRUHQODIUAsJKdKJ/SIDbsO7oGOzsfy+h1yQZs=

348+github.com/qjebbs/go-jsons v1.0.0-alpha.6 h1:9pMjdrCT7rj9CDIM0FXf9Ilie8PEy9g1b4qMkCnedjQ=

253−github.com/qjebbs/go-jsons v1.0.0-alpha.4/go.mod h1:wNJrtinHyC3YSf6giEh4FJN8+yZV7nXBjvmfjhBIcw4=

349+github.com/qjebbs/go-jsons v1.0.0-alpha.6/go.mod h1:wNJrtinHyC3YSf6giEh4FJN8+yZV7nXBjvmfjhBIcw4=

254github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec h1:W09IVJc94icq4NjY3clb7Lk8O1qJ8BdBEF8z0ibU0rE=

350github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec h1:W09IVJc94icq4NjY3clb7Lk8O1qJ8BdBEF8z0ibU0rE=

255github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo=

351github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo=

256−github.com/rivo/uniseg v0.2.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJtxc=

257github.com/rivo/uniseg v0.4.7 h1:WUdvkW8uEhrYfLC4ZzdpI2ztxP1I582+49Oc5Mq64VQ=

352github.com/rivo/uniseg v0.4.7 h1:WUdvkW8uEhrYfLC4ZzdpI2ztxP1I582+49Oc5Mq64VQ=

258github.com/rivo/uniseg v0.4.7/go.mod h1:FN3SvrM+Zdj16jyLfmOkMNblXMcoc8DfTHruCPUcx88=

353github.com/rivo/uniseg v0.4.7/go.mod h1:FN3SvrM+Zdj16jyLfmOkMNblXMcoc8DfTHruCPUcx88=

259github.com/rogpeppe/go-internal v1.14.1 h1:UQB4HGPB6osV0SQTLymcB4TgvyWu6ZyliaW0tI/otEQ=

354github.com/rogpeppe/go-internal v1.14.1 h1:UQB4HGPB6osV0SQTLymcB4TgvyWu6ZyliaW0tI/otEQ=

260github.com/rogpeppe/go-internal v1.14.1/go.mod h1:MaRKkUm5W0goXpeCfT7UZI6fk/L7L7so1lCWt35ZSgc=

355github.com/rogpeppe/go-internal v1.14.1/go.mod h1:MaRKkUm5W0goXpeCfT7UZI6fk/L7L7so1lCWt35ZSgc=

261github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=

356github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=

262−github.com/sabhiram/go-gitignore v0.0.0-20210923224102-525f6e181f06 h1:OkMGxebDjyw0ULyrTYWeN0UNCCkmCWfjPnIA2W6oviI=

357+github.com/sahilm/fuzzy v0.1.3 h1:juByESSS32nVD81vr6tHmKmA/8zde7gE+x5CLxrzXPU=

263−github.com/sabhiram/go-gitignore v0.0.0-20210923224102-525f6e181f06/go.mod h1:+ePHsJ1keEjQtpvf9HHw0f4ZeJ0TLRsxhunSI2hYJSs=

264−github.com/sahilm/fuzzy v0.1.1 h1:ceu5RHF8DGgoi+/dR5PsECjCDH1BE3Fnmpo7aVXOdRA=

265−github.com/sahilm/fuzzy v0.1.1/go.mod h1:VFvziUEIMCrT6A6tw2RFIXPXXmzXbOsSHF0DOI8ZK9Y=

358+github.com/sahilm/fuzzy v0.1.3/go.mod h1:au6//VbVSqu6DFrkL2CfjlJ5iURpNCPeE+1GwY3XsT8=

266github.com/sebdah/goldie/v2 v2.5.3 h1:9ES/mNN+HNUbNWpVAlrzuZ7jE+Nrczbj8uFRjM7624Y=

359github.com/sebdah/goldie/v2 v2.5.3 h1:9ES/mNN+HNUbNWpVAlrzuZ7jE+Nrczbj8uFRjM7624Y=

267github.com/sebdah/goldie/v2 v2.5.3/go.mod h1:oZ9fp0+se1eapSRjfYbsV/0Hqhbuu3bJVvKI/NNtssI=

360github.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=

268github.com/sergi/go-diff v1.0.0/go.mod h1:0CfEIISq7TuYL3j771MWULgwwjU+GofnZX9QAmXWZgo=

369github.com/sergi/go-diff v1.0.0/go.mod h1:0CfEIISq7TuYL3j771MWULgwwjU+GofnZX9QAmXWZgo=

269github.com/sergi/go-diff v1.3.1/go.mod h1:aMJSSKb2lpPvRNec0+w3fl7LP9IOFzdc9Pa4NFbPK1I=

370github.com/sergi/go-diff v1.3.1/go.mod h1:aMJSSKb2lpPvRNec0+w3fl7LP9IOFzdc9Pa4NFbPK1I=

270github.com/sergi/go-diff v1.3.2-0.20230802210424-5b0b94c5c0d3 h1:n661drycOFuPLCN3Uc8sB6B/s6Z4t2xvBgU1htSHuq8=

371github.com/sergi/go-diff v1.3.2-0.20230802210424-5b0b94c5c0d3 h1:n661drycOFuPLCN3Uc8sB6B/s6Z4t2xvBgU1htSHuq8=

@@ -273,25 +374,32 @@ github.com/sethvargo/go-retry v0.3.0 h1:EEt31A35QhrcRZtrYFDTBg91cqZVnFL2navjDrah

273github.com/sethvargo/go-retry v0.3.0/go.mod h1:mNX17F0C/HguQMyMyJxcnU471gOZGxCLyYaFyAZraas=

374github.com/sethvargo/go-retry v0.3.0/go.mod h1:mNX17F0C/HguQMyMyJxcnU471gOZGxCLyYaFyAZraas=

274github.com/sourcegraph/jsonrpc2 v0.2.1 h1:2GtljixMQYUYCmIg7W9aF2dFmniq/mOr2T9tFRh6zSQ=

375github.com/sourcegraph/jsonrpc2 v0.2.1 h1:2GtljixMQYUYCmIg7W9aF2dFmniq/mOr2T9tFRh6zSQ=

275github.com/sourcegraph/jsonrpc2 v0.2.1/go.mod h1:ZafdZgk/axhT1cvZAPOhw+95nz2I/Ra5qMlU4gTRwIo=

376github.com/sourcegraph/jsonrpc2 v0.2.1/go.mod h1:ZafdZgk/axhT1cvZAPOhw+95nz2I/Ra5qMlU4gTRwIo=

276−github.com/spf13/cobra v1.10.1 h1:lJeBwCfmrnXthfAupyUTzJ/J4Nc1RsHC/mSRU2dll/s=

377+github.com/spf13/cobra v1.10.2 h1:DMTTonx5m65Ic0GOoRY2c16WCbHxOOw6xxezuLaBpcU=

277−github.com/spf13/cobra v1.10.1/go.mod h1:7SmJGaTHFVBY0jW4NXGluQoLvhqFQM+6XSKD+P4XaB0=

378+github.com/spf13/cobra v1.10.2/go.mod h1:7C1pvHqHw5A4vrJfjNwvOdzYu0Gml16OCs2GRiTUUS4=

278github.com/spf13/pflag v1.0.9 h1:9exaQaMOCwffKiiiYk6/BndUBv+iRViNW+4lEMi0PvY=

379github.com/spf13/pflag v1.0.9 h1:9exaQaMOCwffKiiiYk6/BndUBv+iRViNW+4lEMi0PvY=

279github.com/spf13/pflag v1.0.9/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=

380github.com/spf13/pflag v1.0.9/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=

280−github.com/srwiley/oksvg v0.0.0-20221011165216-be6e8873101c h1:km8GpoQut05eY3GiYWEedbTT0qnSxrCjsVbb7yKY1KE=

281−github.com/srwiley/oksvg v0.0.0-20221011165216-be6e8873101c/go.mod h1:cNQ3dwVJtS5Hmnjxy6AgTPd0Inb3pW05ftPSX7NZO7Q=

282−github.com/srwiley/rasterx v0.0.0-20220730225603-2ab79fcdd4ef h1:Ch6Q+AZUxDBCVqdkI8FSpFyZDtCVBc2VmejdNrm5rRQ=

283−github.com/srwiley/rasterx v0.0.0-20220730225603-2ab79fcdd4ef/go.mod h1:nXTWP6+gD5+LUJ8krVhhoeHjvHTutPxMYl5SvkcnJNE=

284github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=

381github.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=

285github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=

384github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=

286github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=

385github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=

287github.com/stretchr/testify v1.6.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=

386github.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=

288github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U=

390github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U=

289github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=

391github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=

290−github.com/tetratelabs/wazero v1.9.0 h1:IcZ56OuxrtaEz8UYNRHBrUa9bYeX9oVY93KspZZBf/I=

392+github.com/swaggo/files/v2 v2.0.0 h1:hmAt8Dkynw7Ssz46F6pn8ok6YmGZqHSVLZ+HQM7i0kw=

291−github.com/tetratelabs/wazero v1.9.0/go.mod h1:TSbcXCfFP0L2FGkRPxHphadXPjo1T6W+CseNNY7EkjM=

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=

292github.com/tidwall/gjson v1.14.2/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk=

400github.com/tidwall/gjson v1.14.2/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk=

293−github.com/tidwall/gjson v1.18.0 h1:FIDeeyB800efLX89e5a8Y0BNH+LOngJyGrIWxG2FKQY=

401+github.com/tidwall/gjson v1.19.0 h1:xwxm7n691Uf3u5OFjzngavjGTh55KX5q/9w9xHW88JU=

294−github.com/tidwall/gjson v1.18.0/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk=

402+github.com/tidwall/gjson v1.19.0/go.mod h1:V37/opeE/JbLUOfH0QTXiNez2l0RUjYUhpT4szFQAfc=

295github.com/tidwall/match v1.1.1 h1:+Ho715JplO36QYgwN9PGYNhgZvoUSc9X2c80KVTi+GA=

403github.com/tidwall/match v1.1.1 h1:+Ho715JplO36QYgwN9PGYNhgZvoUSc9X2c80KVTi+GA=

296github.com/tidwall/match v1.1.1/go.mod h1:eRSPERbgtNPcGhD8UCthc6PmLEQXEWd3PRB5JTxsfmM=

404github.com/tidwall/match v1.1.1/go.mod h1:eRSPERbgtNPcGhD8UCthc6PmLEQXEWd3PRB5JTxsfmM=

297github.com/tidwall/pretty v1.2.0/go.mod h1:ITEVvHYasfjBbM0u2Pg8T2nJnzm8xPwvNhhsoaGGjNU=

405github.com/tidwall/pretty v1.2.0/go.mod h1:ITEVvHYasfjBbM0u2Pg8T2nJnzm8xPwvNhhsoaGGjNU=

@@ -303,10 +411,10 @@ github.com/u-root/u-root v0.14.1-0.20250807200646-5e7721023dc7 h1:ax+jBy7xFhh+Ka

303github.com/u-root/u-root v0.14.1-0.20250807200646-5e7721023dc7/go.mod h1:/0Qr7qJeDwWxoKku2xKQ4Szc+SwBE3g9VE8jNiamsmc=

411github.com/u-root/u-root v0.14.1-0.20250807200646-5e7721023dc7/go.mod h1:/0Qr7qJeDwWxoKku2xKQ4Szc+SwBE3g9VE8jNiamsmc=

304github.com/u-root/uio v0.0.0-20240224005618-d2acac8f3701 h1:pyC9PaHYZFgEKFdlp3G8RaCKgVpHZnecvArXvPXcFkM=

412github.com/u-root/uio v0.0.0-20240224005618-d2acac8f3701 h1:pyC9PaHYZFgEKFdlp3G8RaCKgVpHZnecvArXvPXcFkM=

305github.com/u-root/uio v0.0.0-20240224005618-d2acac8f3701/go.mod h1:P3a5rG4X7tI17Nn3aOIAYr5HbIMukwXG0urG0WuL8OA=

413github.com/u-root/uio v0.0.0-20240224005618-d2acac8f3701/go.mod h1:P3a5rG4X7tI17Nn3aOIAYr5HbIMukwXG0urG0WuL8OA=

306−github.com/wk8/go-ordered-map/v2 v2.1.8 h1:5h/BUHu93oj4gIdvHHHGsScSTMijfx5PeYkE/fJgbpc=

307−github.com/wk8/go-ordered-map/v2 v2.1.8/go.mod h1:5nJHM5DyteebpVlHnWMV0rPz6Zp7+xBAnxjb1X5vnTw=

308github.com/xo/terminfo v0.0.0-20220910002029-abceb7e1c41e h1:JVG44RsyaB9T2KIHavMF/ppJZNG9ZpyihvCd0w101no=

414github.com/xo/terminfo v0.0.0-20220910002029-abceb7e1c41e h1:JVG44RsyaB9T2KIHavMF/ppJZNG9ZpyihvCd0w101no=

309github.com/xo/terminfo v0.0.0-20220910002029-abceb7e1c41e/go.mod h1:RbqR21r5mrJuqunuUZ/Dhy/avygyECGrLceyNeo4LiM=

415github.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=

310github.com/yosida95/uritemplate/v3 v3.0.2 h1:Ed3Oyj9yrmi9087+NczuL5BwkIc4wvTb5zIM+UJPGz4=

418github.com/yosida95/uritemplate/v3 v3.0.2 h1:Ed3Oyj9yrmi9087+NczuL5BwkIc4wvTb5zIM+UJPGz4=

311github.com/yosida95/uritemplate/v3 v3.0.2/go.mod h1:ILOh0sOhIJR3+L/8afwt/kE++YT040gmv5BQTMR2HP4=

419github.com/yosida95/uritemplate/v3 v3.0.2/go.mod h1:ILOh0sOhIJR3+L/8afwt/kE++YT040gmv5BQTMR2HP4=

312github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=

420github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=

@@ -317,28 +425,35 @@ github.com/yuin/goldmark-emoji v1.0.5 h1:EMVWyCGPlXJfUXBXpuMu+ii3TIaxbVBnEX9uaDC

317github.com/yuin/goldmark-emoji v1.0.5/go.mod h1:tTkZEbwu5wkPmgTcitqddVxY9osFZiavD+r4AzQrh1U=

425github.com/yuin/goldmark-emoji v1.0.5/go.mod h1:tTkZEbwu5wkPmgTcitqddVxY9osFZiavD+r4AzQrh1U=

318github.com/zeebo/assert v1.3.0 h1:g7C04CbJuIDKNPFHmsk4hwZDO5O+kntRxzaUoNXj+IQ=

426github.com/zeebo/assert v1.3.0 h1:g7C04CbJuIDKNPFHmsk4hwZDO5O+kntRxzaUoNXj+IQ=

319github.com/zeebo/assert v1.3.0/go.mod h1:Pq9JiuJQpG8JLJdtkwrJESF0Foym2/D9XMU5ciN/wJ0=

427github.com/zeebo/assert v1.3.0/go.mod h1:Pq9JiuJQpG8JLJdtkwrJESF0Foym2/D9XMU5ciN/wJ0=

320−github.com/zeebo/xxh3 v1.0.2 h1:xZmwmqxHZA8AI603jOQ0tMqmBr9lPeFwGg6d+xy9DC0=

428+github.com/zeebo/xxh3 v1.1.0 h1:s7DLGDK45Dyfg7++yxI0khrfwq9661w9EN78eP/UZVs=

321−github.com/zeebo/xxh3 v1.0.2/go.mod h1:5NWz9Sef7zIDm2JHfFlcQvNekmcEl9ekUZQQKCYaDcA=

429+github.com/zeebo/xxh3 v1.1.0/go.mod h1:IisAie1LELR4xhVinxWS5+zf1lA4p0MW4T+w+W07F5s=

322−go.opentelemetry.io/auto/sdk v1.1.0 h1:cH53jehLUN6UFLY71z+NDOiNJqDdPRaXzTel0sJySYA=

430+go.opentelemetry.io/auto/sdk v1.2.1 h1:jXsnJ4Lmnqd11kwkBV2LgLoFMZKizbCi5fNZ/ipaZ64=

323−go.opentelemetry.io/auto/sdk v1.1.0/go.mod h1:3wSPjt5PWp2RhlCcmmOial7AvC4DQqZb7a7wCow3W8A=

431+go.opentelemetry.io/auto/sdk v1.2.1/go.mod h1:KRTj+aOaElaLi+wW1kO/DZRXwkF4C5xPbEe3ZiIhN7Y=

324−go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.61.0 h1:q4XOmH/0opmeuJtPsbFNivyl7bCt7yRBbeEm2sC/XtQ=

432+go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.69.0 h1:2yEATaop1/a1I4psnSLgWVPLWwCzkqWakgJy7xTDVy0=

325−go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.61.0/go.mod h1:snMWehoOh2wsEwnvvwtDyFCxVeDAODenXHtn5vzrKjo=

433+go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.69.0/go.mod h1:D7J12YRapIekYyPWgGPlA/23pRmpSEZC5xJC/TTLI9U=

326−go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.61.0 h1:F7Jx+6hwnZ41NSFTO5q4LYDtJRXBf2PD0rNBkeB/lus=

434+go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.69.0 h1:8tvICD4vSTOOsNrsI4Ljf6C+6UKvpTEH5XY3JMoyPoo=

327−go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.61.0/go.mod h1:UHB22Z8QsdRDrnAtX4PntOl36ajSxcdUMt1sF7Y6E7Q=

435+go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.69.0/go.mod h1:z9+yiacE0IHRqM4qFfkbt/JYlmYXgss8GY/jXoNuPJI=

328−go.opentelemetry.io/otel v1.37.0 h1:9zhNfelUvx0KBfu/gb+ZgeAfAgtWrfHJZcAqFC228wQ=

436+go.opentelemetry.io/otel v1.44.0 h1:JjwHmHpA4iZ3wBxluu2fbbE7j4kqlE8jXyAyPXH7HqU=

329−go.opentelemetry.io/otel v1.37.0/go.mod h1:ehE/umFRLnuLa/vSccNq9oS1ErUlkkK71gMcN34UG8I=

437+go.opentelemetry.io/otel v1.44.0/go.mod h1:BMgjTHL9WPRlRjL2oZCBTL4whCGtXch2H4BhOPIAyYc=

330−go.opentelemetry.io/otel/metric v1.37.0 h1:mvwbQS5m0tbmqML4NqK+e3aDiO02vsf/WgbsdpcPoZE=

438+go.opentelemetry.io/otel/metric v1.44.0 h1:1w0gILTcHdr3YI+ixLyjemwrVnsMURbTZFrSYCdDdmc=

331−go.opentelemetry.io/otel/metric v1.37.0/go.mod h1:04wGrZurHYKOc+RKeye86GwKiTb9FKm1WHtO+4EVr2E=

439+go.opentelemetry.io/otel/metric v1.44.0/go.mod h1:8O7hanEPBNgEMmybD3s2VBKcgWOCsA6tzHBPODAiquo=

332−go.opentelemetry.io/otel/sdk v1.36.0 h1:b6SYIuLRs88ztox4EyrvRti80uXIFy+Sqzoh9kFULbs=

440+go.opentelemetry.io/otel/sdk v1.44.0 h1:nHYwb9lK+fJPU/dnT6s7W7Z8itMWyqrnVfbheVYrZ58=

333−go.opentelemetry.io/otel/sdk v1.36.0/go.mod h1:+lC+mTgD+MUWfjJubi2vvXWcVxyr9rmlshZni72pXeY=

441+go.opentelemetry.io/otel/sdk v1.44.0/go.mod h1:Osuydd3Se74nqjAKxid74N5eC+jfEqfTegHRnq58oK0=

334−go.opentelemetry.io/otel/sdk/metric v1.36.0 h1:r0ntwwGosWGaa0CrSt8cuNuTcccMXERFwHX4dThiPis=

442+go.opentelemetry.io/otel/sdk/metric v1.44.0 h1:3LlKgI+VjbVsjNRFZJZAJ30WjXC5VkNRks6si09iEfI=

335−go.opentelemetry.io/otel/sdk/metric v1.36.0/go.mod h1:qTNOhFDfKRwX0yXOqJYegL5WRaW376QbB7P4Pb0qva4=

443+go.opentelemetry.io/otel/sdk/metric v1.44.0/go.mod h1:5B5pMARnXxKhltooO4xUuCBorl65a4EpnTalObqOigA=

336−go.opentelemetry.io/otel/trace v1.37.0 h1:HLdcFNbRQBE2imdSEgm/kwqmQj1Or1l/7bW6mxVK7z4=

444+go.opentelemetry.io/otel/trace v1.44.0 h1:jxF5CsGYCe74MCRx2X4g7WsY/VBKRqqpNvXlX/6gtIk=

337−go.opentelemetry.io/otel/trace v1.37.0/go.mod h1:TlgrlQ+PtQO5XFerSPUYG0JSgGyryXewPGyayAWSBS0=

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=

338go.uber.org/multierr v1.11.0 h1:blXXJkSxSSfBVBlC76pxqeO+LN3aDfLQo+309xJstO0=

448go.uber.org/multierr v1.11.0 h1:blXXJkSxSSfBVBlC76pxqeO+LN3aDfLQo+309xJstO0=

339go.uber.org/multierr v1.11.0/go.mod h1:20+QtiLqy0Nd6FdQB9TLXag12DsQkrbs3htMFfDN80Y=

449go.uber.org/multierr v1.11.0/go.mod h1:20+QtiLqy0Nd6FdQB9TLXag12DsQkrbs3htMFfDN80Y=

340−go.yaml.in/yaml/v4 v4.0.0-rc.2 h1:/FrI8D64VSr4HtGIlUtlFMGsm7H7pWTbj6vOLVZcA6s=

450+go.yaml.in/yaml/v3 v3.0.4/go.mod h1:DhzuOOF2ATzADvBadXxruRBLzYTpT36CKvDb3+aBEFg=

451+go.yaml.in/yaml/v4 v4.0.0-rc.3 h1:3h1fjsh1CTAPjW7q/EMe+C8shx5d8ctzZTrLcs/j8Go=

341−go.yaml.in/yaml/v4 v4.0.0-rc.2/go.mod h1:aZqd9kCMsGL7AuUv/m/PvWLdg5sjJsZ4oHDEnfPPfY0=

452+go.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=

342golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=

457golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=

343golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=

458golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=

344golang.org/x/crypto v0.13.0/go.mod h1:y6Z2r+Rw4iayiXXAIxJIDAJ1zMW4yaTpebo8fPOliYc=

459golang.org/x/crypto v0.13.0/go.mod h1:y6Z2r+Rw4iayiXXAIxJIDAJ1zMW4yaTpebo8fPOliYc=

@@ -346,17 +461,24 @@ golang.org/x/crypto v0.19.0/go.mod h1:Iy9bg/ha4yyC70EfRS8jz+B6ybOBKMaSxLj6P6oBDf

346golang.org/x/crypto v0.22.0/go.mod h1:vr6Su+7cTlO45qkww3VDJlzDn0ctJvRgYbC2NvXHt+M=

461golang.org/x/crypto v0.22.0/go.mod h1:vr6Su+7cTlO45qkww3VDJlzDn0ctJvRgYbC2NvXHt+M=

347golang.org/x/crypto v0.23.0/go.mod h1:CKFgDieR+mRhux2Lsu27y0fO304Db0wZe70UKqHu0v8=

462golang.org/x/crypto v0.23.0/go.mod h1:CKFgDieR+mRhux2Lsu27y0fO304Db0wZe70UKqHu0v8=

348golang.org/x/crypto v0.31.0/go.mod h1:kDsLvtWBEx7MV9tJOj9bnXsPbxwJQ6csT/x4KIN4Ssk=

463golang.org/x/crypto v0.31.0/go.mod h1:kDsLvtWBEx7MV9tJOj9bnXsPbxwJQ6csT/x4KIN4Ssk=

349−golang.org/x/crypto v0.42.0 h1:chiH31gIWm57EkTXpwnqf8qeuMUi0yekh6mT2AvFlqI=

464+golang.org/x/crypto v0.53.0 h1:QZ4Muo8THX6CizN2vPPd5fBGHyogrdK9fG4wLPFUsto=

350−golang.org/x/crypto v0.42.0/go.mod h1:4+rDnOTJhQCx2q7/j6rAN5XDw8kPjeaXEUR2eL94ix8=

465+golang.org/x/crypto v0.53.0/go.mod h1:DNLU434OwVakk9PzuwV8w62mAJpRJL3vsgcfp4Qnsio=

351−golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b h1:M2rDM6z3Fhozi9O7NWsxAkg/yqS/lQJ6PmkyIV3YP+o=

466+golang.org/x/exp v0.0.0-20260410095643-746e56fc9e2f h1:W3F4c+6OLc6H2lb//N1q4WpJkhzJCK5J6kUi1NTVXfM=

352−golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b/go.mod h1:3//PLf8L/X+8b4vuAfHzxeRUl04Adcb341+IGKfnqS8=

467+golang.org/x/exp v0.0.0-20260410095643-746e56fc9e2f/go.mod h1:J1xhfL/vlindoeF/aINzNzt2Bket5bjo9sdOYzOsU80=

353−golang.org/x/image v0.27.0 h1:C8gA4oWU/tKkdCfYT6T2u4faJu3MeNS5O8UPWlPF61w=

468+golang.org/x/exp/shiny v0.0.0-20250606033433-dcc06ee1d476 h1:Wdx0vgH5Wgsw+lF//LJKmWOJBLWX6nprsMqnf99rYDE=

354−golang.org/x/image v0.27.0/go.mod h1:xbdrClrAUway1MUTEZDq9mz/UpRwYAkFFNUslZtcB+g=

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=

355golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=

475golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=

356golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=

476golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=

357golang.org/x/mod v0.12.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=

477golang.org/x/mod v0.12.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=

358golang.org/x/mod v0.15.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=

478golang.org/x/mod v0.15.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=

359golang.org/x/mod v0.17.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=

479golang.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=

360golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=

482golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=

361golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=

483golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=

362golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=

484golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=

@@ -368,10 +490,10 @@ golang.org/x/net v0.21.0/go.mod h1:bIjVDfnllIU7BJ2DNgfnXvpSvtn8VRwhlsaeUTyUS44=

368golang.org/x/net v0.24.0/go.mod h1:2Q7sJY5mzlzWjKtYUEXSlBWCdyaioyXzRB2RtU8KVE8=

490golang.org/x/net v0.24.0/go.mod h1:2Q7sJY5mzlzWjKtYUEXSlBWCdyaioyXzRB2RtU8KVE8=

369golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM=

491golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM=

370golang.org/x/net v0.33.0/go.mod h1:HXLR5J+9DxmrqMwG9qjGCxZ+zKXxBru04zlTvWlWuN4=

492golang.org/x/net v0.33.0/go.mod h1:HXLR5J+9DxmrqMwG9qjGCxZ+zKXxBru04zlTvWlWuN4=

371−golang.org/x/net v0.44.0 h1:evd8IRDyfNBMBTTY5XRF1vaZlD+EmWx6x8PkhR04H/I=

493+golang.org/x/net v0.56.0 h1:Rw8j/hFzGvJUZwNBXnAtf5sVDVt+65SK2C7IxCxZt5o=

372−golang.org/x/net v0.44.0/go.mod h1:ECOoLqd5U3Lhyeyo/QDCEVQ4sNgYsqvCZ722XogGieY=

494+golang.org/x/net v0.56.0/go.mod h1:D3Ku6r+V6JROoZK144D2XfMHFcMq/0zSfLelVTCFKec=

373−golang.org/x/oauth2 v0.32.0 h1:jsCblLleRMDrxMN29H3z/k1KliIvpLgCkE6R8FXXNgY=

495+golang.org/x/oauth2 v0.36.0 h1:peZ/1z27fi9hUOFCAZaHyrpWG5lwe0RJEEEeH0ThlIs=

374−golang.org/x/oauth2 v0.32.0/go.mod h1:lzm5WQJQwKZ3nwavOZ3IS5Aulzxi68dUSgRHujetwEA=

496+golang.org/x/oauth2 v0.36.0/go.mod h1:YDBUJMTkDnJS+A4BP4eZBjCqtokkg1hODuPjwiGPO7Q=

375golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=

497golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=

376golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=

498golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=

377golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=

499golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=

@@ -379,16 +501,16 @@ golang.org/x/sync v0.3.0/go.mod h1:FU7BRWz2tNW+3quACPkgCx/L+uEAv1htQ0V83Z9Rj+Y=

379golang.org/x/sync v0.6.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=

501golang.org/x/sync v0.6.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=

380golang.org/x/sync v0.7.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=

502golang.org/x/sync v0.7.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=

381golang.org/x/sync v0.10.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=

503golang.org/x/sync v0.10.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=

382−golang.org/x/sync v0.17.0 h1:l60nONMj9l5drqw6jlhIELNv9I0A4OFgRsG9k2oT9Ug=

504+golang.org/x/sync v0.21.0 h1:HLII4xRRTtCRkxYp4HNFF0Js/Og6q2i++KXbg0gHCwM=

383−golang.org/x/sync v0.17.0/go.mod h1:9KTHXmSnoGruLpwFjVSX0lNNA75CykiMECbovNTZqGI=

505+golang.org/x/sync v0.21.0/go.mod h1:9xrNwdLfx4jkKbNva9FpL6vEN7evnE43NNNJQ2LF3+0=

384golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=

506golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=

385golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=

507golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=

386golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=

508golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=

387golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=

509golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=

388golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=

510golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=

389golang.org/x/sys v0.0.0-20220908164124-27713097b956/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=

511golang.org/x/sys v0.0.0-20220908164124-27713097b956/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=

512+golang.org/x/sys v0.1.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=

390golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=

513golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=

391−golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=

392golang.org/x/sys v0.7.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=

514golang.org/x/sys v0.7.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=

393golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=

515golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=

394golang.org/x/sys v0.12.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=

516golang.org/x/sys v0.12.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=

@@ -396,8 +518,8 @@ golang.org/x/sys v0.17.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=

396golang.org/x/sys v0.19.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=

518golang.org/x/sys v0.19.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=

397golang.org/x/sys v0.20.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=

519golang.org/x/sys v0.20.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=

398golang.org/x/sys v0.28.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=

520golang.org/x/sys v0.28.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=

399−golang.org/x/sys v0.37.0 h1:fdNQudmxPjkdUTPnLn5mdQv7Zwvbvpaxqs831goi9kQ=

521+golang.org/x/sys v0.46.0 h1:noSf2Fq6F8DBgS+LysIkx7rIExoNHJsxOAtPp4rthXw=

400−golang.org/x/sys v0.37.0/go.mod h1:OgkHotnGiDImocRcuBABYBEXf8A9a87e/uXjp9XT3ks=

522+golang.org/x/sys v0.46.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=

401golang.org/x/telemetry v0.0.0-20240228155512-f48c80bd79b2/go.mod h1:TeRTkGYfJXctD9OcfyVLyj2J3IxLnKwHJR8f4D8a3YE=

523golang.org/x/telemetry v0.0.0-20240228155512-f48c80bd79b2/go.mod h1:TeRTkGYfJXctD9OcfyVLyj2J3IxLnKwHJR8f4D8a3YE=

402golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=

524golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=

403golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=

525golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=

@@ -409,8 +531,8 @@ golang.org/x/term v0.17.0/go.mod h1:lLRBjIVuehSbZlaOtGMbcMncT+aqLLLmKrsjNrUguwk=

409golang.org/x/term v0.19.0/go.mod h1:2CuTdWZ7KHSQwUzKva0cbMg6q2DMI3Mmxp+gKJbskEk=

531golang.org/x/term v0.19.0/go.mod h1:2CuTdWZ7KHSQwUzKva0cbMg6q2DMI3Mmxp+gKJbskEk=

410golang.org/x/term v0.20.0/go.mod h1:8UkIAJTvZgivsXaD6/pH6U9ecQzZ45awqEOzuCvwpFY=

532golang.org/x/term v0.20.0/go.mod h1:8UkIAJTvZgivsXaD6/pH6U9ecQzZ45awqEOzuCvwpFY=

411golang.org/x/term v0.27.0/go.mod h1:iMsnZpn0cago0GOrHO2+Y7u7JPn5AylBrcoWkElMTSM=

533golang.org/x/term v0.27.0/go.mod h1:iMsnZpn0cago0GOrHO2+Y7u7JPn5AylBrcoWkElMTSM=

412−golang.org/x/term v0.35.0 h1:bZBVKBudEyhRcajGcNc3jIfWPqV4y/Kt2XcoigOWtDQ=

534+golang.org/x/term v0.44.0 h1:0rLvDRCtNj0gZkyIXhCyOb2OAzEhLVqc4B+hrsBhrmc=

413−golang.org/x/term v0.35.0/go.mod h1:TPGtkTLesOwf2DE8CgVYiZinHAOuy5AYUYT1lENIZnA=

535+golang.org/x/term v0.44.0/go.mod h1:7ze4MdzUzLXpSAoFP1H0bOI9aXDqveSvatT5vKcFh2Y=

414golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=

536golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=

415golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=

537golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=

416golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=

538golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=

@@ -420,52 +542,85 @@ golang.org/x/text v0.13.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE=

420golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=

542golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=

421golang.org/x/text v0.15.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=

543golang.org/x/text v0.15.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=

422golang.org/x/text v0.21.0/go.mod h1:4IBbMaMmOPCJ8SecivzSH54+73PCFmPWxNTLm+vZkEQ=

544golang.org/x/text v0.21.0/go.mod h1:4IBbMaMmOPCJ8SecivzSH54+73PCFmPWxNTLm+vZkEQ=

423−golang.org/x/text v0.30.0 h1:yznKA/E9zq54KzlzBEAWn1NXSQ8DIp/NYMy88xJjl4k=

545+golang.org/x/text v0.38.0 h1:sXmwo9DwP3OK9EZ7PqAdaooSGozfl/3a6/xJcbzPRhE=

424−golang.org/x/text v0.30.0/go.mod h1:yDdHFIX9t+tORqspjENWgzaCVXgk0yYnYuSZ8UzzBVM=

546+golang.org/x/text v0.38.0/go.mod h1:YXZt3QhHUKYT53r2lLKFIVi6Ao1jdzrTR/KQ09qyxF4=

425−golang.org/x/time v0.12.0 h1:ScB/8o8olJvc+CQPWrK3fPZNfh7qgwCrY0zJmoEQLSE=

547+golang.org/x/time v0.15.0 h1:bbrp8t3bGUeFOx08pvsMYRTCVSMk89u4tKbNOZbp88U=

426−golang.org/x/time v0.12.0/go.mod h1:CDIdPxbZBQxdj6cxyCIdrNogrJKMJ7pr37NYpMcMDSg=

548+golang.org/x/time v0.15.0/go.mod h1:Y4YMaQmXwGQZoFaVFk4YpCt4FLQMYKZe9oeV/f4MSno=

427golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=

549golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=

428golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=

550golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=

429golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=

551golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=

430golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU=

552golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU=

431golang.org/x/tools v0.13.0/go.mod h1:HvlwmtVNQAhOuCjW7xxvovg8wbNq7LwfXh/k7wXUl58=

553golang.org/x/tools v0.13.0/go.mod h1:HvlwmtVNQAhOuCjW7xxvovg8wbNq7LwfXh/k7wXUl58=

432golang.org/x/tools v0.21.1-0.20240508182429-e35e4ccd0d2d/go.mod h1:aiJjzUbINMkxbQROHiO6hDPo2LHcIPhhQsa9DLh0yGk=

554golang.org/x/tools v0.21.1-0.20240508182429-e35e4ccd0d2d/go.mod h1:aiJjzUbINMkxbQROHiO6hDPo2LHcIPhhQsa9DLh0yGk=

433−golang.org/x/tools v0.37.0 h1:DVSRzp7FwePZW356yEAChSdNcQo6Nsp+fex1SUW09lE=

555+golang.org/x/tools v0.45.0 h1:18qN3FAooORvApf5XjCXgsuayZOEtXf6JK18I3+ONa8=

434−golang.org/x/tools v0.37.0/go.mod h1:MBN5QPQtLMHVdvsbtarmTNukZDdgwdwlO5qGacAzF0w=

556+golang.org/x/tools v0.45.0/go.mod h1:LuUGqqaXcXMEFEruIVJVm5mgDD8vww/z/SR1gQ4uE/0=

435golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=

557golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=

436−google.golang.org/api v0.239.0 h1:2hZKUnFZEy81eugPs4e2XzIJ5SOwQg0G82bpXD65Puo=

558+gonum.org/v1/gonum v0.17.0 h1:VbpOemQlsSMrYmn7T2OUvQ4dqxQXU+ouZFQsZOx50z4=

437−google.golang.org/api v0.239.0/go.mod h1:cOVEm2TpdAGHL2z+UwyS+kmlGr3bVWQQ6sYEqkKje50=

559+gonum.org/v1/gonum v0.17.0/go.mod h1:El3tOrEuMpv2UdMrbNlKEh9vd86bmQ6vqIcDwxEOc1E=

438−google.golang.org/genproto/googleapis/rpc v0.0.0-20250603155806-513f23925822 h1:fc6jSaCT0vBduLYZHYrBBNY4dsWuvgyff9noRNDdBeE=

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=

439−google.golang.org/genproto/googleapis/rpc v0.0.0-20250603155806-513f23925822/go.mod h1:qQ0YXyHHx3XkvlzUtpXDkS29lDSafHMZBAZDc03LQ3A=

569+google.golang.org/genproto/googleapis/rpc v0.0.0-20260622175928-b703f567277d/go.mod h1:4Hqkh8ycfw05ld/3BWL7rJOSfebL2Q+DVDeRgYgxUU8=

440−google.golang.org/grpc v1.74.2 h1:WoosgB65DlWVC9FqI82dGsZhWFNBSLjQ84bjROOpMu4=

570+google.golang.org/grpc v1.81.1 h1:VnnIIZ88UzOOKLukQi+ImGz8O1Wdp8nAGGnvOfEIWQQ=

441−google.golang.org/grpc v1.74.2/go.mod h1:CtQ+BGjaAIXHs/5YS3i473GqwBBa1zGQNevxdeBEXrM=

571+google.golang.org/grpc v1.81.1/go.mod h1:xGH9GfzOyMTGIOXBJmXt+BX/V0kcdQbdcuwQ/zNw42I=

442−google.golang.org/protobuf v1.36.10 h1:AYd7cD/uASjIL6Q9LiTjz8JLcrh/88q5UObnmY3aOOE=

572+google.golang.org/protobuf v1.36.11 h1:fV6ZwhNocDyBLK0dj+fg8ektcVegBBuEolpbTQyBNVE=

443−google.golang.org/protobuf v1.36.10/go.mod h1:HTf+CrKn2C3g5S8VImy6tdcUvCska2kB7j23XfzDpco=

573+google.golang.org/protobuf v1.36.11/go.mod h1:HTf+CrKn2C3g5S8VImy6tdcUvCska2kB7j23XfzDpco=

444gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=

574gopkg.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=

445gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=

576gopkg.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=

446gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=

578gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=

447gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=

579gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=

448−gopkg.in/dnaeon/go-vcr.v4 v4.0.6-0.20250923044825-7b4892dd3117 h1:fbE/sTnBb9UNfE8cJsOzrYYPqVWVHb7jWH4SI1W//cM=

580+gopkg.in/dnaeon/go-vcr.v4 v4.0.6-0.20251110073552-01de4eb40290 h1:g3ah7zaWmw41EtOgBNXpx8zk4HYuH3OMwB+qh1Dt834=

449−gopkg.in/dnaeon/go-vcr.v4 v4.0.6-0.20250923044825-7b4892dd3117/go.mod h1:YuVT9NPq7t3oT2WpUemB0DbNL7djIjgajZycxoDLnqs=

581+gopkg.in/dnaeon/go-vcr.v4 v4.0.6-0.20251110073552-01de4eb40290/go.mod h1:sbq5oMEcM4PXngbcNbHhzfCP9OdZodLhrbRYoyg09HY=

450gopkg.in/natefinch/lumberjack.v2 v2.2.1 h1:bBRl1b0OH9s/DuPhuXpNl+VtCaJXFZ5/uEFST95x9zc=

582gopkg.in/natefinch/lumberjack.v2 v2.2.1 h1:bBRl1b0OH9s/DuPhuXpNl+VtCaJXFZ5/uEFST95x9zc=

451gopkg.in/natefinch/lumberjack.v2 v2.2.1/go.mod h1:YD8tP3GAjkrDg1eZH7EGmyESg/lsYskCTPBJVb9jqSc=

583gopkg.in/natefinch/lumberjack.v2 v2.2.1/go.mod h1:YD8tP3GAjkrDg1eZH7EGmyESg/lsYskCTPBJVb9jqSc=

452gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7 h1:uRGJdciOHaEIrze2W8Q3AKkepLTh2hOroT7a+7czfdQ=

584gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7 h1:uRGJdciOHaEIrze2W8Q3AKkepLTh2hOroT7a+7czfdQ=

453gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7/go.mod h1:dt/ZhP58zS4L8KSrWDmTeBkI65Dw0HsyUHuEVlX15mw=

585gopkg.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=

454gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=

588gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=

455gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY=

589gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY=

456gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ=

590gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ=

457gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

591gopkg.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=

458gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=

593gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=

459gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

594gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

460−modernc.org/libc v1.66.3 h1:cfCbjTUcdsKyyZZfEUKfoHcP3S0Wkvz3jgSzByEWVCQ=

595+modernc.org/cc/v4 v4.28.4 h1:Hd/4Es+MBj+/7hSdZaisNyu6bv3V0Dp2MdllyfqaH+c=

461−modernc.org/libc v1.66.3/go.mod h1:XD9zO8kt59cANKvHPXpx7yS2ELPheAey0vjIuZOhOU8=

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=

462modernc.org/mathutil v1.7.1 h1:GCZVGXdaN8gTqB1Mf/usp1Y/hSqgI2vAGGP4jZMCxOU=

609modernc.org/mathutil v1.7.1 h1:GCZVGXdaN8gTqB1Mf/usp1Y/hSqgI2vAGGP4jZMCxOU=

463modernc.org/mathutil v1.7.1/go.mod h1:4p5IwJITfppl0G4sUEDtCr4DthTaT47/N3aT6MhfgJg=

610modernc.org/mathutil v1.7.1/go.mod h1:4p5IwJITfppl0G4sUEDtCr4DthTaT47/N3aT6MhfgJg=

464modernc.org/memory v1.11.0 h1:o4QC8aMQzmcwCK3t3Ux/ZHmwFPzE6hf2Y5LbkRs+hbI=

611modernc.org/memory v1.11.0 h1:o4QC8aMQzmcwCK3t3Ux/ZHmwFPzE6hf2Y5LbkRs+hbI=

465modernc.org/memory v1.11.0/go.mod h1:/JP4VbVC+K5sU2wZi9bHoq2MAkCnrt2r98UGeSK7Mjw=

612modernc.org/memory v1.11.0/go.mod h1:/JP4VbVC+K5sU2wZi9bHoq2MAkCnrt2r98UGeSK7Mjw=

466−modernc.org/sqlite v1.38.2 h1:Aclu7+tgjgcQVShZqim41Bbw9Cho0y/7WzYptXqkEek=

613+modernc.org/opt v0.2.0 h1:tGyef5ApycA7FSEOMraay9SaTk5zmbx7Tu+cJs4QKZg=

467−modernc.org/sqlite v1.38.2/go.mod h1:cPTJYSlgg3Sfg046yBShXENNtPrWrDX8bsbAQBzgQ5E=

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=

468mvdan.cc/sh/moreinterp v0.0.0-20250902163504-3cf4fd5717a5 h1:mO2lyKtGwu4mGQ+Qqjx0+fd5UU5BXhX/rslFmxd5aco=

623mvdan.cc/sh/moreinterp v0.0.0-20250902163504-3cf4fd5717a5 h1:mO2lyKtGwu4mGQ+Qqjx0+fd5UU5BXhX/rslFmxd5aco=

469mvdan.cc/sh/moreinterp v0.0.0-20250902163504-3cf4fd5717a5/go.mod h1:Of9PCedbLDYT8b3EyiYG64rNnx5nOp27OLCVdDrjJyo=

624mvdan.cc/sh/moreinterp v0.0.0-20250902163504-3cf4fd5717a5/go.mod h1:Of9PCedbLDYT8b3EyiYG64rNnx5nOp27OLCVdDrjJyo=

470−mvdan.cc/sh/v3 v3.12.1-0.20250902163504-3cf4fd5717a5 h1:e7Z/Lgw/zMijvQBVrfh/vUDZ+9FpuSLrJDVGBuoJtuo=

625+mvdan.cc/sh/v3 v3.13.1 h1:DP3TfgZhDkT7lerUdnp6PTGKyxxzz6T+cOlY/xEvfWk=

471−mvdan.cc/sh/v3 v3.12.1-0.20250902163504-3cf4fd5717a5/go.mod h1:P21wo2gLLe3426sP+CmANLBaixSEbRtPl35w3YlM6dg=

626+mvdan.cc/sh/v3 v3.13.1/go.mod h1:lXJ8SexMvEVcHCoDvAGLZgFJ9Wsm2sulmoNEXGhYZD0=

internal/agent/.env.sample+1

@@ -1,4 +1,5 @@

1CRUSH_ANTHROPIC_API_KEY=

2+CRUSH_HYPER_API_KEY=

2CRUSH_OPENAI_API_KEY=

3CRUSH_OPENAI_API_KEY=

3CRUSH_OPENROUTER_API_KEY=

4CRUSH_OPENROUTER_API_KEY=

4CRUSH_ZAI_API_KEY=

5CRUSH_ZAI_API_KEY=

internal/agent/accepted_run_test.gonew file+231

@@ -0,0 +1,231 @@

1+package agent

3+import (

4+ "context"

5+ "testing"

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+1672−196

@@ -1,39 +1,89 @@

1+// Package agent is the core orchestration layer for Crush AI agents.

2+//

3+// It provides session-based AI agent functionality for managing

4+// conversations, tool execution, and message handling. It coordinates

5+// interactions between language models, messages, sessions, and tools while

6+// handling features like automatic summarization, queuing, and token

7+// management.

1package agent

8package agent

3import (

10import (

11+ "cmp"

4 "context"

12 "context"

5 _ "embed"

13 _ "embed"

14+ "encoding/base64"

15+ "encoding/json"

6 "errors"

16 "errors"

7 "fmt"

17 "fmt"

8 "log/slog"

18 "log/slog"

19+ "math"

20+ "net/http"

9 "os"

21 "os"

22+ "regexp"

10 "strconv"

23 "strconv"

11 "strings"

24 "strings"

12 "sync"

25 "sync"

26+ "sync/atomic"

13 "time"

27 "time"

29+ "charm.land/catwalk/pkg/catwalk"

15 "charm.land/fantasy"

30 "charm.land/fantasy"

16 "charm.land/fantasy/providers/anthropic"

31 "charm.land/fantasy/providers/anthropic"

17 "charm.land/fantasy/providers/bedrock"

32 "charm.land/fantasy/providers/bedrock"

18 "charm.land/fantasy/providers/google"

33 "charm.land/fantasy/providers/google"

19 "charm.land/fantasy/providers/openai"

34 "charm.land/fantasy/providers/openai"

35+ "charm.land/fantasy/providers/openrouter"

36+ "charm.land/fantasy/providers/vercel"

37+ "charm.land/lipgloss/v2"

20− "github.com/charmbracelet/catwalk/pkg/catwalk"

38+ "github.com/charmbracelet/crush/internal/agent/hyper"

39+ "github.com/charmbracelet/crush/internal/agent/notify"

21 "github.com/charmbracelet/crush/internal/agent/tools"

40 "github.com/charmbracelet/crush/internal/agent/tools"

41+ "github.com/charmbracelet/crush/internal/agent/tools/mcp"

22 "github.com/charmbracelet/crush/internal/config"

42 "github.com/charmbracelet/crush/internal/config"

23 "github.com/charmbracelet/crush/internal/csync"

43 "github.com/charmbracelet/crush/internal/csync"

24 "github.com/charmbracelet/crush/internal/message"

44 "github.com/charmbracelet/crush/internal/message"

25− "github.com/charmbracelet/crush/internal/permission"

45+ "github.com/charmbracelet/crush/internal/pubsub"

26 "github.com/charmbracelet/crush/internal/session"

46 "github.com/charmbracelet/crush/internal/session"

47+ "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"

27)

51)

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+

29//go:embed templates/title.md

64//go:embed templates/title.md

30var titlePrompt []byte

65var titlePrompt []byte

32//go:embed templates/summary.md

67//go:embed templates/summary.md

33var summaryPrompt []byte

68var summaryPrompt []byte

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+

35type SessionAgentCall struct {

76type SessionAgentCall struct {

36− SessionID string

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

37 Prompt string

87 Prompt string

38 ProviderOptions fantasy.ProviderOptions

88 ProviderOptions fantasy.ProviderOptions

39 Attachments []message.Attachment

89 Attachments []message.Attachment

@@ -43,95 +93,592 @@ type SessionAgentCall struct {

43 TopK *int64

93 TopK *int64

44 FrequencyPenalty *float64

94 FrequencyPenalty *float64

45 PresencePenalty *float64

95 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

46}

127}

128

48type SessionAgent interface {

129type SessionAgent interface {

49 Run(context.Context, SessionAgentCall) (*fantasy.AgentResult, error)

130 Run(context.Context, SessionAgentCall) (*fantasy.AgentResult, error)

131+ BeginAccepted(sessionID string) *AcceptedRun

50 SetModels(large Model, small Model)

132 SetModels(large Model, small Model)

51 SetTools(tools []fantasy.AgentTool)

133 SetTools(tools []fantasy.AgentTool)

134+ SetSystemPrompt(systemPrompt string)

52 Cancel(sessionID string)

135 Cancel(sessionID string)

53 CancelAll()

136 CancelAll()

54 IsSessionBusy(sessionID string) bool

137 IsSessionBusy(sessionID string) bool

55 IsBusy() bool

138 IsBusy() bool

56 QueuedPrompts(sessionID string) int

139 QueuedPrompts(sessionID string) int

140+ QueuedPromptsList(sessionID string) []string

57 ClearQueue(sessionID string)

141 ClearQueue(sessionID string)

58 Summarize(context.Context, string, fantasy.ProviderOptions) error

142 Summarize(context.Context, string, fantasy.ProviderOptions) error

59 Model() Model

143 Model() Model

144+ GenerateTitle(ctx context.Context, sessionID, userPrompt string)

60}

145}

146

62type Model struct {

147type Model struct {

63 Model fantasy.LanguageModel

148 Model fantasy.LanguageModel

64 CatwalkCfg catwalk.Model

149 CatwalkCfg catwalk.Model

65 ModelCfg config.SelectedModel

150 ModelCfg config.SelectedModel

151+ FlatRate bool

66}

152}

153

68type sessionAgent struct {

154type sessionAgent struct {

69− largeModel Model

155+ largeModel *csync.Value[Model]

70− smallModel Model

156+ smallModel *csync.Value[Model]

157+ systemPromptPrefix *csync.Value[string]

71− systemPrompt string

158+ systemPrompt *csync.Value[string]

72− tools []fantasy.AgentTool

159+ tools *csync.Slice[fantasy.AgentTool]

160+ toolsGen atomic.Uint64 // bumped by SetTools; lets PrepareStep skip re-copying unchanged tools

161+

162+ isSubAgent bool

73 sessions session.Service

163 sessions session.Service

74 messages message.Service

164 messages message.Service

75 disableAutoSummarize bool

165 disableAutoSummarize bool

166+ isYolo bool

167+ notify pubsub.Publisher[notify.Notification]

168+ runComplete pubsub.Publisher[notify.RunComplete]

169

77 messageQueue *csync.Map[string, []SessionAgentCall]

170 messageQueue *csync.Map[string, []SessionAgentCall]

78 activeRequests *csync.Map[string, context.CancelFunc]

171 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

79}

209}

210

81type SessionAgentOptions struct {

211type SessionAgentOptions struct {

82 LargeModel Model

212 LargeModel Model

83 SmallModel Model

213 SmallModel Model

214+ SystemPromptPrefix string

84 SystemPrompt string

215 SystemPrompt string

216+ IsSubAgent bool

85 DisableAutoSummarize bool

217 DisableAutoSummarize bool

218+ IsYolo bool

86 Sessions session.Service

219 Sessions session.Service

87 Messages message.Service

220 Messages message.Service

88 Tools []fantasy.AgentTool

221 Tools []fantasy.AgentTool

222+ Notify pubsub.Publisher[notify.Notification]

223+ RunComplete pubsub.Publisher[notify.RunComplete]

89}

224}

225

91func NewSessionAgent(

226func NewSessionAgent(

92 opts SessionAgentOptions,

227 opts SessionAgentOptions,

93) SessionAgent {

228) SessionAgent {

94 return &sessionAgent{

229 return &sessionAgent{

95− largeModel: opts.LargeModel,

230+ largeModel: csync.NewValue(opts.LargeModel),

96− smallModel: opts.SmallModel,

231+ smallModel: csync.NewValue(opts.SmallModel),

232+ systemPromptPrefix: csync.NewValue(opts.SystemPromptPrefix),

97− systemPrompt: opts.SystemPrompt,

233+ systemPrompt: csync.NewValue(opts.SystemPrompt),

234+ isSubAgent: opts.IsSubAgent,

98 sessions: opts.Sessions,

235 sessions: opts.Sessions,

99 messages: opts.Messages,

236 messages: opts.Messages,

100 disableAutoSummarize: opts.DisableAutoSummarize,

237 disableAutoSummarize: opts.DisableAutoSummarize,

101− tools: opts.Tools,

238+ tools: csync.NewSliceFrom(opts.Tools),

239+ isYolo: opts.IsYolo,

240+ notify: opts.Notify,

241+ runComplete: opts.RunComplete,

102 messageQueue: csync.NewMap[string, []SessionAgentCall](),

242 messageQueue: csync.NewMap[string, []SessionAgentCall](),

103 activeRequests: csync.NewMap[string, context.CancelFunc](),

243 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](),

104 }

247 }

105}

248}

106

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.

107−func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (*fantasy.AgentResult, error) {

494+func (a *sessionAgent) persistCanceledTurn(ctx context.Context, call SessionAgentCall, userMsgCreated bool) error {

108− if call.Prompt == "" {

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

511+ }

512+ assistant.AddFinish(message.FinishReasonCanceled, "User canceled request", "")

513+ return a.messages.Update(writeCtx, assistant)

514+}

515+

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) {

109− return nil, ErrEmptyPrompt

544+ return ErrEmptyPrompt

110 }

545 }

111 if call.SessionID == "" {

546 if call.SessionID == "" {

112− return nil, ErrSessionMissing

547+ return ErrSessionMissing

113 }

548 }

549+ return nil

550+}

114

551

115− // Queue the message if busy

552+func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (result *fantasy.AgentResult, retErr error) {

116− if a.IsSessionBusy(call.SessionID) {

553+ if err := ValidateCall(call); err != nil {

554+ return nil, err

555+ }

556+

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.

117− existing, ok := a.messageQueue.Get(call.SessionID)

576+ mu := a.sessionMu(call.SessionID)

118− if !ok {

577+ mu.Lock()

119− existing = []SessionAgentCall{}

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

120 }

618 }

121− existing = append(existing, call)

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)

122− a.messageQueue.Set(call.SessionID, existing)

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)

123 return nil, nil

641 return nil, nil

124 }

642 }

125

643

126− if len(a.tools) > 0 {

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 {

127− // add anthropic caching to the last tool

673+ // Add Anthropic caching to the last tool.

128− a.tools[len(a.tools)-1].SetProviderOptions(a.getCacheControlOptions())

674+ agentTools[len(agentTools)-1].SetProviderOptions(a.getCacheControlOptions())

129 }

675 }

130

676

131 agent := fantasy.NewAgent(

677 agent := fantasy.NewAgent(

132− a.largeModel.Model,

678+ largeModel.Model,

133− fantasy.WithSystemPrompt(a.systemPrompt),

679+ fantasy.WithSystemPrompt(systemPrompt),

134− fantasy.WithTools(a.tools...),

680+ fantasy.WithTools(agentTools...),

681+ fantasy.WithUserAgent(userAgent),

135 )

682 )

136

683

137 sessionLock := sync.Mutex{}

684 sessionLock := sync.Mutex{}

@@ -146,56 +693,150 @@ func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (*fantasy

146 }

693 }

147

694

148 var wg sync.WaitGroup

695 var wg sync.WaitGroup

149− // Generate title if first message

696+ // Generate title from the first real (non-shell) user prompt.

150− if len(msgs) == 0 {

697+ if !hasUserTextMessage(msgs) {

698+ titleCtx := ctx // Copy to avoid race with ctx reassignment below.

151 wg.Go(func() {

699 wg.Go(func() {

152− sessionLock.Lock()

700+ a.GenerateTitle(titleCtx, call.SessionID, call.Prompt)

153− a.generateTitle(ctx, &currentSession, call.Prompt)

154− sessionLock.Unlock()

155 })

701 })

156 }

702 }

703+ defer wg.Wait()

157

704

158− // Add the user message to the session

705+ // Add the user message to the session.

159 _, err = a.createUserMessage(ctx, call)

706 _, err = a.createUserMessage(ctx, call)

160 if err != nil {

707 if err != nil {

161 return nil, err

708 return nil, err

162 }

709 }

710+ userMsgCreated = true

163

711

164− // add the session to the context

712+ // Add the session to the context.

165 ctx = context.WithValue(ctx, tools.SessionIDContextKey, call.SessionID)

713 ctx = context.WithValue(ctx, tools.SessionIDContextKey, call.SessionID)

166

714

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 {

167− genCtx, cancel := context.WithCancel(ctx)

720+ genCtx, cancel = context.WithCancel(ctx)

168− a.activeRequests.Set(call.SessionID, cancel)

721+ a.activeRequests.Set(call.SessionID, cancel)

169−

170− defer cancel()

171− defer a.activeRequests.Del(call.SessionID)

172−

173− history, files := a.preparePrompt(msgs, call.Attachments...)

174

722

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.

175 var currentAssistant *message.Message

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...)

787+

788+ startTime := time.Now()

789+ a.eventPromptSent(call.SessionID)

790+

791+ var stepMessages []fantasy.Message

176 var shouldSummarize bool

792 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+ }

177− result, err := agent.Stream(genCtx, fantasy.AgentStreamCall{

799+ result, err = agent.Stream(genCtx, fantasy.AgentStreamCall{

178− Prompt: call.Prompt,

800+ Prompt: message.PromptWithTextAttachments(call.Prompt, call.Attachments),

179 Files: files,

801 Files: files,

180 Messages: history,

802 Messages: history,

181 ProviderOptions: call.ProviderOptions,

803 ProviderOptions: call.ProviderOptions,

182− MaxOutputTokens: &call.MaxOutputTokens,

804+ MaxOutputTokens: maxOutputTokens,

183 TopP: call.TopP,

805 TopP: call.TopP,

184 Temperature: call.Temperature,

806 Temperature: call.Temperature,

185 PresencePenalty: call.PresencePenalty,

807 PresencePenalty: call.PresencePenalty,

186 TopK: call.TopK,

808 TopK: call.TopK,

187 FrequencyPenalty: call.FrequencyPenalty,

809 FrequencyPenalty: call.FrequencyPenalty,

188− // Before each step create the new assistant message

189 PrepareStep: func(callContext context.Context, options fantasy.PrepareStepFunctionOptions) (_ context.Context, prepared fantasy.PrepareStepResult, err error) {

810 PrepareStep: func(callContext context.Context, options fantasy.PrepareStepFunctionOptions) (_ context.Context, prepared fantasy.PrepareStepResult, err error) {

190 prepared.Messages = options.Messages

811 prepared.Messages = options.Messages

191− // reset all cached items

192 for i := range prepared.Messages {

812 for i := range prepared.Messages {

193 prepared.Messages[i].ProviderOptions = nil

813 prepared.Messages[i].ProviderOptions = nil

194 }

814 }

195

815

196− queuedCalls, _ := a.messageQueue.Get(call.SessionID)

816+ // Use latest tools (updated by SetTools when MCP tools change).

197− a.messageQueue.Del(call.SessionID)

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)

198− for _, queued := range queuedCalls {

839+ for _, queued := range fold {

199 userMessage, createErr := a.createUserMessage(callContext, queued)

840 userMessage, createErr := a.createUserMessage(callContext, queued)

200 if createErr != nil {

841 if createErr != nil {

201 return callContext, prepared, createErr

842 return callContext, prepared, createErr

@@ -203,36 +844,55 @@ func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (*fantasy

203 prepared.Messages = append(prepared.Messages, userMessage.ToAIMessage()...)

844 prepared.Messages = append(prepared.Messages, userMessage.ToAIMessage()...)

204 }

845 }

205

846

847+ prepared.Messages = a.workaroundProviderMediaLimitations(prepared.Messages, largeModel)

848+

206 lastSystemRoleInx := 0

849 lastSystemRoleInx := 0

207 systemMessageUpdated := false

850 systemMessageUpdated := false

208 for i, msg := range prepared.Messages {

851 for i, msg := range prepared.Messages {

209− // only add cache control to the last message

852+ // Only add cache control to the last message.

210 if msg.Role == fantasy.MessageRoleSystem {

853 if msg.Role == fantasy.MessageRoleSystem {

211 lastSystemRoleInx = i

854 lastSystemRoleInx = i

212 } else if !systemMessageUpdated {

855 } else if !systemMessageUpdated {

213 prepared.Messages[lastSystemRoleInx].ProviderOptions = a.getCacheControlOptions()

856 prepared.Messages[lastSystemRoleInx].ProviderOptions = a.getCacheControlOptions()

214 systemMessageUpdated = true

857 systemMessageUpdated = true

215 }

858 }

216− // than add cache control to the last 2 messages

859+ // Than add cache control to the last 2 messages.

217 if i > len(prepared.Messages)-3 {

860 if i > len(prepared.Messages)-3 {

218 prepared.Messages[i].ProviderOptions = a.getCacheControlOptions()

861 prepared.Messages[i].ProviderOptions = a.getCacheControlOptions()

219 }

862 }

220 }

863 }

221

864

865+ if promptPrefix != "" {

866+ prepared.Messages = append([]fantasy.Message{fantasy.NewSystemMessage(promptPrefix)}, prepared.Messages...)

867+ }

868+

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+

222 var assistantMsg message.Message

876 var assistantMsg message.Message

223 assistantMsg, err = a.messages.Create(callContext, call.SessionID, message.CreateMessageParams{

877 assistantMsg, err = a.messages.Create(callContext, call.SessionID, message.CreateMessageParams{

224 Role: message.Assistant,

878 Role: message.Assistant,

225 Parts: []message.ContentPart{},

879 Parts: []message.ContentPart{},

226− Model: a.largeModel.ModelCfg.Model,

880+ Model: largeModel.ModelCfg.Model,

227− Provider: a.largeModel.ModelCfg.Provider,

881+ Provider: largeModel.ModelCfg.Provider,

228 })

882 })

229 if err != nil {

883 if err != nil {

230 return callContext, prepared, err

884 return callContext, prepared, err

231 }

885 }

232 callContext = context.WithValue(callContext, tools.MessageIDContextKey, assistantMsg.ID)

886 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)

233 currentAssistant = &assistantMsg

889 currentAssistant = &assistantMsg

234 return callContext, prepared, err

890 return callContext, prepared, err

235 },

891 },

892+ OnReasoningStart: func(id string, reasoning fantasy.ReasoningContent) error {

893+ currentAssistant.AppendReasoningContent(reasoning.Text)

894+ return a.messages.Update(genCtx, *currentAssistant)

895+ },

236 OnReasoningDelta: func(id string, text string) error {

896 OnReasoningDelta: func(id string, text string) error {

237 currentAssistant.AppendReasoningContent(text)

897 currentAssistant.AppendReasoningContent(text)

238 return a.messages.Update(genCtx, *currentAssistant)

898 return a.messages.Update(genCtx, *currentAssistant)

@@ -246,7 +906,7 @@ func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (*fantasy

246 }

906 }

247 if googleData, ok := reasoning.ProviderMetadata[google.Name]; ok {

907 if googleData, ok := reasoning.ProviderMetadata[google.Name]; ok {

248 if reasoning, ok := googleData.(*google.ReasoningMetadata); ok {

908 if reasoning, ok := googleData.(*google.ReasoningMetadata); ok {

249− currentAssistant.AppendReasoningSignature(reasoning.Signature)

909+ currentAssistant.AppendThoughtSignature(reasoning.Signature, reasoning.ToolID)

250 }

910 }

251 }

911 }

252 if openaiData, ok := reasoning.ProviderMetadata[openai.Name]; ok {

912 if openaiData, ok := reasoning.ProviderMetadata[openai.Name]; ok {

@@ -258,6 +918,13 @@ func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (*fantasy

258 return a.messages.Update(genCtx, *currentAssistant)

918 return a.messages.Update(genCtx, *currentAssistant)

259 },

919 },

260 OnTextDelta: func(id string, text string) error {

920 OnTextDelta: func(id string, text string) error {

921+ // Strip leading newline from initial text content. This is is

922+ // particularly important in non-interactive mode where leading

923+ // newlines are very visible.

924+ if len(currentAssistant.Parts) == 0 {

925+ text = strings.TrimPrefix(text, "\n")

926+ }

927+

261 currentAssistant.AppendContent(text)

928 currentAssistant.AppendContent(text)

262 return a.messages.Update(genCtx, *currentAssistant)

929 return a.messages.Update(genCtx, *currentAssistant)

263 },

930 },

@@ -269,59 +936,50 @@ func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (*fantasy

269 Finished: false,

936 Finished: false,

270 }

937 }

271 currentAssistant.AddToolCall(toolCall)

938 currentAssistant.AddToolCall(toolCall)

939+ // Use parent ctx instead of genCtx to ensure the update succeeds

940+ // even if the request is canceled mid-stream

272− return a.messages.Update(genCtx, *currentAssistant)

941+ return a.messages.Update(ctx, *currentAssistant)

273 },

942 },

274− OnRetry: func(err *fantasy.APICallError, delay time.Duration) {

943+ OnRetry: func(err *fantasy.ProviderError, delay time.Duration) {

275− // TODO: implement

944+ slog.Warn("Provider request failed, retrying", providerRetryLogFields(err, delay)...)

276 },

945 },

277 OnToolCall: func(tc fantasy.ToolCallContent) error {

946 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+ }

278 toolCall := message.ToolCall{

951 toolCall := message.ToolCall{

279 ID: tc.ToolCallID,

952 ID: tc.ToolCallID,

280 Name: tc.ToolName,

953 Name: tc.ToolName,

281− Input: tc.Input,

954+ Input: input,

282 ProviderExecuted: false,

955 ProviderExecuted: false,

283 Finished: true,

956 Finished: true,

284 }

957 }

285 currentAssistant.AddToolCall(toolCall)

958 currentAssistant.AddToolCall(toolCall)

959+ // Use parent ctx instead of genCtx to ensure the update succeeds

960+ // even if the request is canceled mid-stream

286− return a.messages.Update(genCtx, *currentAssistant)

961+ return a.messages.Update(ctx, *currentAssistant)

287 },

962 },

288 OnToolResult: func(result fantasy.ToolResultContent) error {

963 OnToolResult: func(result fantasy.ToolResultContent) error {

289− var resultContent string

964+ toolResult := a.convertToToolResult(result)

290− isError := false

965+ if sanitizedToolCalls[result.ToolCallID] {

291− switch result.Result.GetType() {

966+ toolResult.Content = "Tool call failed: arguments were not valid JSON. Please check your tool call format and try again."

292− case fantasy.ToolResultContentTypeText:

293− r, ok := fantasy.AsToolResultOutputType[fantasy.ToolResultOutputContentText](result.Result)

294− if ok {

295− resultContent = r.Text

296− }

297− case fantasy.ToolResultContentTypeError:

298− r, ok := fantasy.AsToolResultOutputType[fantasy.ToolResultOutputContentError](result.Result)

299− if ok {

300− isError = true

301− resultContent = r.Error.Error()

302− }

303− case fantasy.ToolResultContentTypeMedia:

304− // TODO: handle this message type

305− }

306− toolResult := message.ToolResult{

307− ToolCallID: result.ToolCallID,

308− Name: result.ToolName,

309− Content: resultContent,

310− IsError: isError,

967+ toolResult.IsError = true

311− Metadata: result.ClientMetadata,

312 }

968 }

969+ // Use parent ctx instead of genCtx to ensure the message is created

970+ // even if the request is canceled mid-stream

313− _, createMsgErr := a.messages.Create(genCtx, currentAssistant.SessionID, message.CreateMessageParams{

971+ _, createMsgErr := a.messages.Create(ctx, currentAssistant.SessionID, message.CreateMessageParams{

314 Role: message.Tool,

972 Role: message.Tool,

315 Parts: []message.ContentPart{

973 Parts: []message.ContentPart{

316 toolResult,

974 toolResult,

317 },

975 },

318 })

976 })

319− if createMsgErr != nil {

320− return createMsgErr

977+ return createMsgErr

321− }

322− return nil

323 },

978 },

324 OnStepFinish: func(stepResult fantasy.StepResult) error {

979 OnStepFinish: func(stepResult fantasy.StepResult) error {

980+ for _, w := range stepResult.Warnings {

981+ slog.Warn("Provider warning", "type", w.Type, "message", w.Message)

982+ }

325 finishReason := message.FinishReasonUnknown

983 finishReason := message.FinishReasonUnknown

326 switch stepResult.FinishReason {

984 switch stepResult.FinishReason {

327 case fantasy.FinishReasonLength:

985 case fantasy.FinishReasonLength:

@@ -331,40 +989,100 @@ func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (*fantasy

331 case fantasy.FinishReasonToolCalls:

989 case fantasy.FinishReasonToolCalls:

332 finishReason = message.FinishReasonToolUse

990 finishReason = message.FinishReasonToolUse

333 }

991 }

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+ }

334 currentAssistant.AddFinish(finishReason, "", "")

1004 currentAssistant.AddFinish(finishReason, "", "")

335− a.updateSessionUsage(a.largeModel, &currentSession, stepResult.Usage)

336 sessionLock.Lock()

1005 sessionLock.Lock()

1006+ defer sessionLock.Unlock()

1007+

1008+ updatedSession, getSessionErr := a.sessions.Get(ctx, call.SessionID)

1009+ if getSessionErr != nil {

1010+ return getSessionErr

1011+ }

1012+ usage, estimated := fallbackStepUsage(stepMessages, stepResult)

1013+ a.updateSessionUsage(largeModel, &updatedSession, usage, a.openrouterCost(stepResult.ProviderMetadata), estimated)

1014+ extractHyperCredits(stepResult.ProviderMetadata)

337− _, sessionErr := a.sessions.Save(genCtx, currentSession)

1015+ _, sessionErr := a.sessions.Save(ctx, updatedSession)

338− sessionLock.Unlock()

339 if sessionErr != nil {

1016 if sessionErr != nil {

340 return sessionErr

1017 return sessionErr

341 }

1018 }

1019+ currentSession = updatedSession

342 return a.messages.Update(genCtx, *currentAssistant)

1020 return a.messages.Update(genCtx, *currentAssistant)

343 },

1021 },

344 StopWhen: []fantasy.StopCondition{

1022 StopWhen: []fantasy.StopCondition{

345 func(_ []fantasy.StepResult) bool {

1023 func(_ []fantasy.StepResult) bool {

346− contextWindow := a.largeModel.CatwalkCfg.ContextWindow

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+ }

347 tokens := currentSession.CompletionTokens + currentSession.PromptTokens

1030 tokens := currentSession.CompletionTokens + currentSession.PromptTokens

348− percentage := (float64(tokens) / float64(contextWindow)) * 100

1031+ remaining := cw - tokens

1032+ var threshold int64

1033+ if cw > largeContextWindowThreshold {

1034+ threshold = largeContextWindowBuffer

1035+ } else {

1036+ threshold = int64(float64(cw) * smallContextWindowRatio)

1037+ }

349− if (percentage > 80) && !a.disableAutoSummarize {

1038+ if (remaining <= threshold) && !a.disableAutoSummarize {

350 shouldSummarize = true

1039 shouldSummarize = true

351 return true

1040 return true

352 }

1041 }

353 return false

1042 return false

354 },

1043 },

1044+ func(steps []fantasy.StepResult) bool {

1045+ return hasRepeatedToolCalls(steps, loopDetectionWindowSize, loopDetectionMaxRepeats)

1046+ },

355 },

1047 },

356 })

1048 })

1049+

1050+ a.eventPromptResponded(call.SessionID, time.Since(startTime).Truncate(time.Second))

1051+

357 if err != nil {

1052 if err != nil {

1053+ isHyper := largeModel.ModelCfg.Provider == hyper.Name

358 isCancelErr := errors.Is(err, context.Canceled)

1054 isCancelErr := errors.Is(err, context.Canceled)

359− isPermissionErr := errors.Is(err, permission.ErrorPermissionDenied)

360 if currentAssistant == nil {

1055 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+ }

361 return result, err

1068 return result, err

362 }

1069 }

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()

363− // Ensure we finish thinking on error to close the reasoning state

1079+ // Ensure we finish thinking on error to close the reasoning state.

364 currentAssistant.FinishThinking()

1080 currentAssistant.FinishThinking()

365 toolCalls := currentAssistant.ToolCalls()

1081 toolCalls := currentAssistant.ToolCalls()

366− // INFO: we use the parent context here because the genCtx has been cancelled

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.

367− msgs, createErr := a.messages.List(ctx, currentAssistant.SessionID)

1085+ msgs, createErr := a.messages.ListAfter(cleanupCtx, currentAssistant.SessionID, currentAssistant.ID)

368 if createErr != nil {

1086 if createErr != nil {

369 return nil, createErr

1087 return nil, createErr

370 }

1088 }

@@ -373,7 +1091,7 @@ func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (*fantasy

373 tc.Finished = true

1091 tc.Finished = true

374 tc.Input = "{}"

1092 tc.Input = "{}"

375 currentAssistant.AddToolCall(tc)

1093 currentAssistant.AddToolCall(tc)

376− updateErr := a.messages.Update(ctx, *currentAssistant)

1094+ updateErr := a.messages.Update(cleanupCtx, *currentAssistant)

377 if updateErr != nil {

1095 if updateErr != nil {

378 return nil, updateErr

1096 return nil, updateErr

379 }

1097 }

@@ -398,9 +1116,7 @@ func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (*fantasy

398 }

1116 }

399 content := "There was an error while executing the tool"

1117 content := "There was an error while executing the tool"

400 if isCancelErr {

1118 if isCancelErr {

401− content = "Tool execution canceled by user"

1119+ content = "Error: user cancelled assistant tool calling"

402− } else if isPermissionErr {

403− content = "Permission denied"

404 }

1120 }

405 toolResult := message.ToolResult{

1121 toolResult := message.ToolResult{

406 ToolCallID: tc.ID,

1122 ToolCallID: tc.ID,

@@ -408,7 +1124,7 @@ func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (*fantasy

408 Content: content,

1124 Content: content,

409 IsError: true,

1125 IsError: true,

410 }

1126 }

411− _, createErr = a.messages.Create(context.Background(), currentAssistant.SessionID, message.CreateMessageParams{

1127+ _, createErr = a.messages.Create(cleanupCtx, currentAssistant.SessionID, message.CreateMessageParams{

412 Role: message.Tool,

1128 Role: message.Tool,

413 Parts: []message.ContentPart{

1129 Parts: []message.ContentPart{

414 toolResult,

1130 toolResult,

@@ -418,28 +1134,50 @@ func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (*fantasy

418 return nil, createErr

1134 return nil, createErr

419 }

1135 }

420 }

1136 }

1137+ var fantasyErr *fantasy.Error

1138+ var providerErr *fantasy.ProviderError

1139+ const defaultTitle = "Provider Error"

1140+ linkStyle := lipgloss.NewStyle().Foreground(charmtone.Guac).Underline(true)

421 if isCancelErr {

1141 if isCancelErr {

422− currentAssistant.AddFinish(message.FinishReasonCanceled, "Request cancelled", "")

1142+ currentAssistant.AddFinish(message.FinishReasonCanceled, "User canceled request", "")

423− } else if isPermissionErr {

1143+ } else if isHyper && errors.As(err, &providerErr) && providerErr.StatusCode == http.StatusUnauthorized {

424− currentAssistant.AddFinish(message.FinishReasonPermissionDenied, "Permission denied", "")

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 {

1146+ url := hyper.BaseURL()

1147+ link := linkStyle.Hyperlink(url, "id=hyper").Render(url)

1148+ currentAssistant.AddFinish(message.FinishReasonError, "No credits", "You're out of credits. Add more at "+link)

1149+ } else if errors.As(err, &providerErr) {

1150+ if providerErr.Message == "The requested model is not supported." {

1151+ url := "https://github.com/settings/copilot/features"

1152+ link := linkStyle.Hyperlink(url, "id=copilot").Render(url)

1153+ currentAssistant.AddFinish(

1154+ message.FinishReasonError,

1155+ "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),

1157+ )

1158+ } else {

1159+ currentAssistant.AddFinish(message.FinishReasonError, cmp.Or(stringext.Capitalize(providerErr.Title), defaultTitle), providerErr.Message)

1160+ }

1161+ } else if errors.As(err, &fantasyErr) {

1162+ currentAssistant.AddFinish(message.FinishReasonError, cmp.Or(stringext.Capitalize(fantasyErr.Title), defaultTitle), fantasyErr.Message)

425 } else {

1163 } else {

426− currentAssistant.AddFinish(message.FinishReasonError, "API Error", err.Error())

1164+ currentAssistant.AddFinish(message.FinishReasonError, defaultTitle, err.Error())

427 }

1165 }

428− // INFO: we use the parent context here because the genCtx has been cancelled

1166+ // Note: we use the cleanup context here because the genCtx has been

1167+ // cancelled.

429− updateErr := a.messages.Update(ctx, *currentAssistant)

1168+ updateErr := a.messages.Update(cleanupCtx, *currentAssistant)

430 if updateErr != nil {

1169 if updateErr != nil {

431 return nil, updateErr

1170 return nil, updateErr

432 }

1171 }

433 return nil, err

1172 return nil, err

434 }

1173 }

435− wg.Wait()

436

1174

437 if shouldSummarize {

1175 if shouldSummarize {

438 a.activeRequests.Del(call.SessionID)

1176 a.activeRequests.Del(call.SessionID)

439 if summarizeErr := a.Summarize(genCtx, call.SessionID, call.ProviderOptions); summarizeErr != nil {

1177 if summarizeErr := a.Summarize(genCtx, call.SessionID, call.ProviderOptions); summarizeErr != nil {

440 return nil, summarizeErr

1178 return nil, summarizeErr

441 }

1179 }

442− // if the agent was not done...

1180+ // If the agent wasn't done...

443 if len(currentAssistant.ToolCalls()) > 0 {

1181 if len(currentAssistant.ToolCalls()) > 0 {

444 existing, ok := a.messageQueue.Get(call.SessionID)

1182 existing, ok := a.messageQueue.Get(call.SessionID)

445 if !ok {

1183 if !ok {

@@ -451,17 +1189,123 @@ func (a *sessionAgent) Run(ctx context.Context, call SessionAgentCall) (*fantasy

451 }

1189 }

452 }

1190 }

453

1191

454− // release active request before processing queued messages

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.

455 a.activeRequests.Del(call.SessionID)

1196 a.activeRequests.Del(call.SessionID)

456 cancel()

1197 cancel()

457

1198

458− queuedMessages, ok := a.messageQueue.Get(call.SessionID)

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+ }

459− if !ok || len(queuedMessages) == 0 {

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()

460 return result, err

1263 return result, err

461 }

1264 }

462− // there are queued messages restart the loop

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+ }

463 firstQueuedMessage := queuedMessages[0]

1288 firstQueuedMessage := queuedMessages[0]

464 a.messageQueue.Set(call.SessionID, queuedMessages[1:])

1289 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+ }

465 return a.Run(ctx, firstQueuedMessage)

1309 return a.Run(ctx, firstQueuedMessage)

466}

1310}

467

1311

@@ -470,6 +1314,10 @@ func (a *sessionAgent) Summarize(ctx context.Context, sessionID string, opts fan

470 return ErrSessionBusy

1314 return ErrSessionBusy

471 }

1315 }

472

1316

1317+ // Copy mutable fields under lock to avoid races with SetModels.

1318+ largeModel := a.largeModel.Get()

1319+ systemPromptPrefix := a.systemPromptPrefix.Get()

1320+

473 currentSession, err := a.sessions.Get(ctx, sessionID)

1321 currentSession, err := a.sessions.Get(ctx, sessionID)

474 if err != nil {

1322 if err != nil {

475 return fmt.Errorf("failed to get session: %w", err)

1323 return fmt.Errorf("failed to get session: %w", err)

@@ -479,40 +1327,56 @@ func (a *sessionAgent) Summarize(ctx context.Context, sessionID string, opts fan

479 return err

1327 return err

480 }

1328 }

481 if len(msgs) == 0 {

1329 if len(msgs) == 0 {

482− // nothing to summarize

1330+ // Nothing to summarize.

483 return nil

1331 return nil

484 }

1332 }

485

1333

486− aiMsgs, _ := a.preparePrompt(msgs)

1334+ aiMsgs, _ := a.preparePrompt(msgs, largeModel.CatwalkCfg.SupportsImages)

487

1335

488 genCtx, cancel := context.WithCancel(ctx)

1336 genCtx, cancel := context.WithCancel(ctx)

489 a.activeRequests.Set(sessionID, cancel)

1337 a.activeRequests.Set(sessionID, cancel)

490 defer a.activeRequests.Del(sessionID)

1338 defer a.activeRequests.Del(sessionID)

491 defer cancel()

1339 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+ }()

492

1345

493− agent := fantasy.NewAgent(a.largeModel.Model,

1346+ agent := fantasy.NewAgent(

1347+ largeModel.Model,

494 fantasy.WithSystemPrompt(string(summaryPrompt)),

1348 fantasy.WithSystemPrompt(string(summaryPrompt)),

1349+ fantasy.WithUserAgent(userAgent),

495 )

1350 )

496 summaryMessage, err := a.messages.Create(ctx, sessionID, message.CreateMessageParams{

1351 summaryMessage, err := a.messages.Create(ctx, sessionID, message.CreateMessageParams{

497 Role: message.Assistant,

1352 Role: message.Assistant,

498− Model: a.largeModel.Model.Model(),

1353+ Model: largeModel.ModelCfg.Model,

499− Provider: a.largeModel.Model.Provider(),

1354+ Provider: largeModel.ModelCfg.Provider,

500 IsSummaryMessage: true,

1355 IsSummaryMessage: true,

501 })

1356 })

502 if err != nil {

1357 if err != nil {

503 return err

1358 return err

504 }

1359 }

505

1360

1361+ summaryPromptText := buildSummaryPrompt(currentSession.Todos)

1362+

506 resp, err := agent.Stream(genCtx, fantasy.AgentStreamCall{

1363 resp, err := agent.Stream(genCtx, fantasy.AgentStreamCall{

507− Prompt: "Provide a detailed summary of our conversation above.",

1364+ Prompt: summaryPromptText,

508 Messages: aiMsgs,

1365 Messages: aiMsgs,

509 ProviderOptions: opts,

1366 ProviderOptions: opts,

1367+ PrepareStep: func(callContext context.Context, options fantasy.PrepareStepFunctionOptions) (_ context.Context, prepared fantasy.PrepareStepResult, err error) {

1368+ prepared.Messages = options.Messages

1369+ if systemPromptPrefix != "" {

1370+ prepared.Messages = append([]fantasy.Message{fantasy.NewSystemMessage(systemPromptPrefix)}, prepared.Messages...)

1371+ }

1372+ return callContext, prepared, nil

1373+ },

510 OnReasoningDelta: func(id string, text string) error {

1374 OnReasoningDelta: func(id string, text string) error {

511 summaryMessage.AppendReasoningContent(text)

1375 summaryMessage.AppendReasoningContent(text)

512 return a.messages.Update(genCtx, summaryMessage)

1376 return a.messages.Update(genCtx, summaryMessage)

513 },

1377 },

514 OnReasoningEnd: func(id string, reasoning fantasy.ReasoningContent) error {

1378 OnReasoningEnd: func(id string, reasoning fantasy.ReasoningContent) error {

515− // handle anthropic signature

1379+ // Handle anthropic signature.

516 if anthropicData, ok := reasoning.ProviderMetadata["anthropic"]; ok {

1380 if anthropicData, ok := reasoning.ProviderMetadata["anthropic"]; ok {

517 if signature, ok := anthropicData.(*anthropic.ReasoningOptionMetadata); ok && signature.Signature != "" {

1381 if signature, ok := anthropicData.(*anthropic.ReasoningOptionMetadata); ok && signature.Signature != "" {

518 summaryMessage.AppendReasoningSignature(signature.Signature)

1382 summaryMessage.AppendReasoningSignature(signature.Signature)

@@ -529,10 +1393,16 @@ func (a *sessionAgent) Summarize(ctx context.Context, sessionID string, opts fan

529 if err != nil {

1393 if err != nil {

530 isCancelErr := errors.Is(err, context.Canceled)

1394 isCancelErr := errors.Is(err, context.Canceled)

531 if isCancelErr {

1395 if isCancelErr {

532− // User cancelled summarize we need to remove the summary message

1396+ // User cancelled summarize we need to remove the summary message.

533 deleteErr := a.messages.Delete(ctx, summaryMessage.ID)

1397 deleteErr := a.messages.Delete(ctx, summaryMessage.ID)

534 return deleteErr

1398 return deleteErr

535 }

1399 }

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+ }

536 return err

1406 return err

537 }

1407 }

538

1408

@@ -542,18 +1412,52 @@ func (a *sessionAgent) Summarize(ctx context.Context, sessionID string, opts fan

542 return err

1412 return err

543 }

1413 }

544

1414

1415+ var openrouterCost *float64

1416+ for _, step := range resp.Steps {

1417+ stepCost := a.openrouterCost(step.ProviderMetadata)

1418+ if stepCost != nil {

1419+ newCost := *stepCost

1420+ if openrouterCost != nil {

1421+ newCost += *openrouterCost

1422+ }

1423+ openrouterCost = &newCost

1424+ }

1425+ extractHyperCredits(step.ProviderMetadata)

1426+ }

1427+

545− a.updateSessionUsage(a.largeModel, &currentSession, resp.TotalUsage)

1428+ a.updateSessionUsage(largeModel, &currentSession, resp.TotalUsage, openrouterCost, false)

546

1429

547− // just in case get just the last usage

1430+ // Just in case, get just the last usage info.

548 usage := resp.Response.Usage

1431 usage := resp.Response.Usage

549 currentSession.SummaryMessageID = summaryMessage.ID

1432 currentSession.SummaryMessageID = summaryMessage.ID

550− currentSession.CompletionTokens = usage.OutputTokens

1433+ currentSession.CompletionTokens = summaryCompletionTokens(usage, summaryMessage)

551 currentSession.PromptTokens = 0

1434 currentSession.PromptTokens = 0

1435+ currentSession.EstimatedUsage = usageIsZero(usage)

552 _, err = a.sessions.Save(genCtx, currentSession)

1436 _, err = a.sessions.Save(genCtx, currentSession)

1437+ if err != nil {

553− return err

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

554}

1455}

555

1456

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.

556−func (a *sessionAgent) getCacheControlOptions() fantasy.ProviderOptions {

1460+var cacheControlOptions = sync.OnceValue(func() fantasy.ProviderOptions {

557 if t, _ := strconv.ParseBool(os.Getenv("CRUSH_DISABLE_ANTHROPIC_CACHE")); t {

1461 if t, _ := strconv.ParseBool(os.Getenv("CRUSH_DISABLE_ANTHROPIC_CACHE")); t {

558 return fantasy.ProviderOptions{}

1462 return fantasy.ProviderOptions{}

559 }

1463 }

@@ -564,15 +1468,22 @@ func (a *sessionAgent) getCacheControlOptions() fantasy.ProviderOptions {

564 bedrock.Name: &anthropic.ProviderCacheControlOptions{

1468 bedrock.Name: &anthropic.ProviderCacheControlOptions{

565 CacheControl: anthropic.CacheControl{Type: "ephemeral"},

1469 CacheControl: anthropic.CacheControl{Type: "ephemeral"},

566 },

1470 },

1471+ vercel.Name: &anthropic.ProviderCacheControlOptions{

1472+ CacheControl: anthropic.CacheControl{Type: "ephemeral"},

1473+ },

567 }

1474 }

1475+})

1476+

1477+func (a *sessionAgent) getCacheControlOptions() fantasy.ProviderOptions {

1478+ return cacheControlOptions()

568}

1479}

569

1480

570func (a *sessionAgent) createUserMessage(ctx context.Context, call SessionAgentCall) (message.Message, error) {

1481func (a *sessionAgent) createUserMessage(ctx context.Context, call SessionAgentCall) (message.Message, error) {

1482+ parts := []message.ContentPart{message.TextContent{Text: call.Prompt}}

571 var attachmentParts []message.ContentPart

1483 var attachmentParts []message.ContentPart

572 for _, attachment := range call.Attachments {

1484 for _, attachment := range call.Attachments {

573 attachmentParts = append(attachmentParts, message.BinaryContent{Path: attachment.FilePath, MIMEType: attachment.MimeType, Data: attachment.Content})

1485 attachmentParts = append(attachmentParts, message.BinaryContent{Path: attachment.FilePath, MIMEType: attachment.MimeType, Data: attachment.Content})

574 }

1486 }

575− parts := []message.ContentPart{message.TextContent{Text: call.Prompt}}

576 parts = append(parts, attachmentParts...)

1487 parts = append(parts, attachmentParts...)

577 msg, err := a.messages.Create(ctx, call.SessionID, message.CreateMessageParams{

1488 msg, err := a.messages.Create(ctx, call.SessionID, message.CreateMessageParams{

578 Role: message.User,

1489 Role: message.User,

@@ -584,21 +1495,73 @@ func (a *sessionAgent) createUserMessage(ctx context.Context, call SessionAgentC

584 return msg, nil

1495 return msg, nil

585}

1496}

586

1497

587−func (a *sessionAgent) preparePrompt(msgs []message.Message, attachments ...message.Attachment) ([]fantasy.Message, []fantasy.FilePart) {

1498+func (a *sessionAgent) preparePrompt(msgs []message.Message, supportsImages bool, attachments ...message.Attachment) ([]fantasy.Message, []fantasy.FilePart) {

588− var history []fantasy.Message

1499+ history := make([]fantasy.Message, 0, len(msgs)+1)

1500+ if !a.isSubAgent {

1501+ history = append(history, fantasy.NewUserMessage(

1502+ fmt.Sprintf(

1503+ "<system_reminder>%s</system_reminder>",

1504+ `This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.

1505+If you are working on tasks that would benefit from a todo list please use the "todos" tool to create one.

1506+If not, please feel free to ignore. Again do not mention this message to the user.`,

1507+ ),

1508+ ))

1509+ }

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+

589 for _, m := range msgs {

1529 for _, m := range msgs {

590 if len(m.Parts) == 0 {

1530 if len(m.Parts) == 0 {

591 continue

1531 continue

592 }

1532 }

593− // Assistant message without content or tool calls (cancelled before it returned anything)

1533+ // Assistant message without content or tool calls (cancelled before it returned anything).

594 if m.Role == message.Assistant && len(m.ToolCalls()) == 0 && m.Content().Text == "" && m.ReasoningContent().String() == "" {

1534 if m.Role == message.Assistant && len(m.ToolCalls()) == 0 && m.Content().Text == "" && m.ReasoningContent().String() == "" {

595 continue

1535 continue

596 }

1536 }

1537+ if m.Role == message.Tool {

1538+ if msg, ok := filterOrphanedToolResults(m, knownToolCallIDs); ok {

597− history = append(history, m.ToAIMessage()...)

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+ }

598 }

1558 }

599

1559

600 var files []fantasy.FilePart

1560 var files []fantasy.FilePart

601 for _, attachment := range attachments {

1561 for _, attachment := range attachments {

1562+ if attachment.IsText() {

1563+ continue

1564+ }

602 files = append(files, fantasy.FilePart{

1565 files = append(files, fantasy.FilePart{

603 Filename: attachment.FileName,

1566 Filename: attachment.FileName,

604 Data: attachment.Content,

1567 Data: attachment.Content,

@@ -609,109 +1572,410 @@ func (a *sessionAgent) preparePrompt(msgs []message.Message, attachments ...mess

609 return history, files

1572 return history, files

610}

1573}

611

1574

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+

612func (a *sessionAgent) getSessionMessages(ctx context.Context, session session.Session) ([]message.Message, error) {

1657func (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+

613 msgs, err := a.messages.List(ctx, session.ID)

1669 msgs, err := a.messages.List(ctx, session.ID)

614 if err != nil {

1670 if err != nil {

615 return nil, fmt.Errorf("failed to list messages: %w", err)

1671 return nil, fmt.Errorf("failed to list messages: %w", err)

616 }

1672 }

1673+ return msgs, nil

1674+}

617

1675

618− if session.SummaryMessageID != "" {

1676+// hasUserTextMessage reports whether any user message in msgs contains

619− summaryMsgInex := -1

1677+// text content (as opposed to only shell commands or other non-text parts).

1678+func hasUserTextMessage(msgs []message.Message) bool {

620− for i, msg := range msgs {

1679+ for _, msg := range msgs {

621− if msg.ID == session.SummaryMessageID {

1680+ if msg.Role != message.User {

622− summaryMsgInex = i

1681+ continue

623− break

624− }

625 }

1682 }

626− if summaryMsgInex != -1 {

1683+ for _, part := range msg.Parts {

627− msgs = msgs[summaryMsgInex:]

1684+ if tc, ok := part.(message.TextContent); ok && tc.Text != "" {

628− msgs[0].Role = message.User

1685+ return true

1686+ }

629 }

1687 }

630 }

1688 }

631− return msgs, nil

1689+ return false

632}

1690}

633

1691

1692+// GenerateTitle generates a session title based on the initial prompt.

634−func (a *sessionAgent) generateTitle(ctx context.Context, session *session.Session, prompt string) {

1693+func (a *sessionAgent) GenerateTitle(ctx context.Context, sessionID string, userPrompt string) {

635− if prompt == "" {

1694+ if userPrompt == "" {

636 return

1695 return

637 }

1696 }

638

1697

639− var maxOutput int64 = 40

1698+ // Ensure the session always gets a title even if every path below

640− if a.smallModel.CatwalkCfg.CanReason {

1699+ // fails or the context is cancelled before we finish.

641− maxOutput = a.smallModel.CatwalkCfg.DefaultMaxTokens

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+ )

642 }

1722 }

643

1723

644− agent := fantasy.NewAgent(a.smallModel.Model,

1724+ streamCall := fantasy.AgentStreamCall{

645− fantasy.WithSystemPrompt(string(titlePrompt)+"\n /no_think"),

1725+ Prompt: fmt.Sprintf("Generate a concise title for the following content:\n\n%s\n <think>\n\n</think>", userPrompt),

646− fantasy.WithMaxOutputTokens(maxOutput),

1726+ PrepareStep: func(callCtx context.Context, opts fantasy.PrepareStepFunctionOptions) (_ context.Context, prepared fantasy.PrepareStepResult, err error) {

647− )

1727+ prepared.Messages = opts.Messages

1728+ if systemPromptPrefix != "" {

1729+ prepared.Messages = append([]fantasy.Message{

1730+ fantasy.NewSystemMessage(systemPromptPrefix),

1731+ }, prepared.Messages...)

1732+ }

1733+ return callCtx, prepared, nil

1734+ },

1735+ }

648

1736

649− resp, err := agent.Stream(ctx, fantasy.AgentStreamCall{

1737+ type modelAttempt struct {

650− Prompt: fmt.Sprintf("Generate a concise title for the following content:\n\n%s\n <think>\n\n</think>", prompt),

1738+ name string

651− })

1739+ model Model

652− if err != nil {

1740+ }

653− slog.Error("error generating title", "err", err)

1741+ attempts := []modelAttempt{

654− return

1742+ {"small", smallModel},

1743+ {"large", largeModel},

655 }

1744 }

656

1745

657− title := resp.Response.Content.Text()

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.

1771+ return

1772+ }

658

1773

1774+ // Clean up title.

1775+ var title string

659− title = strings.ReplaceAll(title, "\n", " ")

1776+ title = strings.ReplaceAll(resp.Response.Content.Text(), "\n", " ")

660

1777

661− // remove thinking tags if present

1778+ // Remove thinking tags if present.

662− if idx := strings.Index(title, "</think>"); idx > 0 {

1779+ title = thinkTagRegex.ReplaceAllString(title, "")

663− title = title[idx+len("</think>"):]

1780+ title = orphanThinkTagRegex.ReplaceAllString(title, "")

664− }

665

1781

666 title = strings.TrimSpace(title)

1782 title = strings.TrimSpace(title)

667 if title == "" {

1783 if title == "" {

668− slog.Warn("failed to generate title", "warn", "empty title")

1784+ // LLM returned empty content. Use the prompt itself as a

669− return

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)

1793+ }

1794+

1795+ // Calculate usage and cost.

1796+ var openrouterCost *float64

1797+ for _, step := range resp.Steps {

1798+ stepCost := a.openrouterCost(step.ProviderMetadata)

1799+ if stepCost != nil {

1800+ newCost := *stepCost

1801+ if openrouterCost != nil {

1802+ newCost += *openrouterCost

1803+ }

1804+ openrouterCost = &newCost

1805+ }

1806+ extractHyperCredits(step.ProviderMetadata)

1807+ }

1808+

1809+ modelConfig := model.CatwalkCfg

1810+ cost := modelConfig.CostPer1MInCached/1e6*float64(resp.TotalUsage.CacheCreationTokens) +

1811+ modelConfig.CostPer1MOutCached/1e6*float64(resp.TotalUsage.CacheReadTokens) +

1812+ modelConfig.CostPer1MIn/1e6*float64(resp.TotalUsage.InputTokens) +

1813+ modelConfig.CostPer1MOut/1e6*float64(resp.TotalUsage.OutputTokens)

1814+

1815+ // Use override cost if available (e.g., from OpenRouter).

1816+ if openrouterCost != nil {

1817+ cost = *openrouterCost

1818+ }

1819+

1820+ // Skip cost accumulation

1821+ if model.FlatRate {

1822+ cost = 0

670 }

1823 }

671

1824

672− session.Title = title

1825+ promptTokens := resp.TotalUsage.InputTokens + resp.TotalUsage.CacheCreationTokens

673− a.updateSessionUsage(a.smallModel, session, resp.TotalUsage)

1826+ completionTokens := resp.TotalUsage.OutputTokens

674− _, saveErr := a.sessions.Save(ctx, *session)

1827+

1828+ // Atomically update only title and usage fields to avoid overriding other

1829+ // concurrent session updates.

1830+ saveErr := a.sessions.UpdateTitleAndUsage(ctx, sessionID, title, promptTokens, completionTokens, cost)

675 if saveErr != nil {

1831 if saveErr != nil {

676− slog.Error("failed to save session title & usage", "error", saveErr)

1832+ slog.Error("Failed to save session title and usage", "error", saveErr)

1833+ return

1834+ }

1835+ titleSaved = true

1836+}

1837+

1838+func (a *sessionAgent) openrouterCost(metadata fantasy.ProviderMetadata) *float64 {

1839+ openrouterMetadata, ok := metadata[openrouter.Name]

1840+ if !ok {

1841+ return nil

1842+ }

1843+

1844+ opts, ok := openrouterMetadata.(*openrouter.ProviderMetadata)

1845+ if !ok {

1846+ return nil

1847+ }

1848+ return &opts.Usage.Cost

1849+}

1850+

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 {

677 return

1860 return

678 }

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+ }

679}

1868}

680

1869

681−func (a *sessionAgent) updateSessionUsage(model Model, session *session.Session, usage fantasy.Usage) {

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+

682 modelConfig := model.CatwalkCfg

1875 modelConfig := model.CatwalkCfg

683 cost := modelConfig.CostPer1MInCached/1e6*float64(usage.CacheCreationTokens) +

1876 cost := modelConfig.CostPer1MInCached/1e6*float64(usage.CacheCreationTokens) +

684 modelConfig.CostPer1MOutCached/1e6*float64(usage.CacheReadTokens) +

1877 modelConfig.CostPer1MOutCached/1e6*float64(usage.CacheReadTokens) +

685 modelConfig.CostPer1MIn/1e6*float64(usage.InputTokens) +

1878 modelConfig.CostPer1MIn/1e6*float64(usage.InputTokens) +

686 modelConfig.CostPer1MOut/1e6*float64(usage.OutputTokens)

1879 modelConfig.CostPer1MOut/1e6*float64(usage.OutputTokens)

1880+

1881+ if !estimated {

1882+ a.eventTokensUsed(session.ID, model, usage, cost)

1883+ }

1884+

1885+ if estimated {

1886+ 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+ }

1897+ }

1898+

687 session.Cost += cost

1899 session.Cost += cost

1900+ updateSessionTokenCounters(session, usage)

1901+}

1902+

1903+func updateSessionTokenCounters(session *session.Session, usage fantasy.Usage) {

1904+ if usage.OutputTokens != 0 {

688− session.CompletionTokens = usage.OutputTokens + usage.CacheReadTokens

1905+ session.CompletionTokens = usage.OutputTokens

1906+ }

1907+ if promptTokens := usage.InputTokens + usage.CacheReadTokens; promptTokens != 0 {

689− session.PromptTokens = usage.InputTokens + usage.CacheCreationTokens

1908+ session.PromptTokens = promptTokens

1909+ }

1910+}

1911+

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())

690}

1917}

691

1918

692func (a *sessionAgent) Cancel(sessionID string) {

1919func (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+

693− // Cancel regular requests

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.

694− if cancel, ok := a.activeRequests.Take(sessionID); ok && cancel != nil {

1934+ if cancel, ok := a.activeRequests.Get(sessionID); ok && cancel != nil {

695− slog.Info("Request cancellation initiated", "session_id", sessionID)

1935+ slog.Debug("Request cancellation initiated", "session_id", sessionID)

696 cancel()

1936 cancel()

697 }

1937 }

698

1938

699− // Also check for summarize requests

1939+ // Also check for summarize requests.

700− if cancel, ok := a.activeRequests.Take(sessionID + "-summarize"); ok && cancel != nil {

1940+ if cancel, ok := a.activeRequests.Get(sessionID + "-summarize"); ok && cancel != nil {

701− slog.Info("Summarize cancellation initiated", "session_id", sessionID)

1941+ slog.Debug("Summarize cancellation initiated", "session_id", sessionID)

702 cancel()

1942 cancel()

703 }

1943 }

704

1944

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+

705 if a.QueuedPrompts(sessionID) > 0 {

1969 if a.QueuedPrompts(sessionID) > 0 {

706− slog.Info("Clearing queued prompts", "session_id", sessionID)

1970+ slog.Debug("Clearing queued prompts", "session_id", sessionID)

707− a.messageQueue.Del(sessionID)

1971+ a.clearQueueAndNotify(sessionID)

708 }

1972 }

709}

1973}

710

1974

711func (a *sessionAgent) ClearQueue(sessionID string) {

1975func (a *sessionAgent) ClearQueue(sessionID string) {

712 if a.QueuedPrompts(sessionID) > 0 {

1976 if a.QueuedPrompts(sessionID) > 0 {

713− slog.Info("Clearing queued prompts", "session_id", sessionID)

1977+ slog.Debug("Clearing queued prompts", "session_id", sessionID)

714− a.messageQueue.Del(sessionID)

1978+ a.clearQueueAndNotify(sessionID)

715 }

1979 }

716}

1980}

717

1981

@@ -735,14 +1999,10 @@ func (a *sessionAgent) CancelAll() {

735}

1999}

736

2000

737func (a *sessionAgent) IsBusy() bool {

2001func (a *sessionAgent) IsBusy() bool {

738− var busy bool

2002+ // activeRequests only ever holds non-nil cancel funcs (Set with a

739− for cancelFunc := range a.activeRequests.Seq() {

2003+ // real func, removed via Del), so a length check is exact — and it

740− if cancelFunc != nil {

2004+ // avoids cloning the whole map, which Seq() does on every call.

741− busy = true

2005+ return a.activeRequests.Len() > 0

742− break

743− }

744− }

745− return busy

746}

2006}

747

2007

748func (a *sessionAgent) IsSessionBusy(sessionID string) bool {

2008func (a *sessionAgent) IsSessionBusy(sessionID string) bool {

@@ -758,15 +2018,231 @@ func (a *sessionAgent) QueuedPrompts(sessionID string) int {

758 return len(l)

2018 return len(l)

759}

2019}

760

2020

2021+func (a *sessionAgent) QueuedPromptsList(sessionID string) []string {

2022+ l, ok := a.messageQueue.Get(sessionID)

2023+ if !ok {

2024+ return nil

2025+ }

2026+ prompts := make([]string, len(l))

2027+ for i, call := range l {

2028+ prompts[i] = call.Prompt

2029+ }

2030+ return prompts

2031+}

2032+

761func (a *sessionAgent) SetModels(large Model, small Model) {

2033func (a *sessionAgent) SetModels(large Model, small Model) {

762− a.largeModel = large

2034+ a.largeModel.Set(large)

763− a.smallModel = small

2035+ a.smallModel.Set(small)

764}

2036}

765

2037

766func (a *sessionAgent) SetTools(tools []fantasy.AgentTool) {

2038func (a *sessionAgent) SetTools(tools []fantasy.AgentTool) {

767− a.tools = tools

2039+ a.tools.SetSlice(tools)

2040+ a.toolsGen.Add(1)

2041+}

2042+

2043+func (a *sessionAgent) SetSystemPrompt(systemPrompt string) {

2044+ a.systemPrompt.Set(systemPrompt)

768}

2045}

769

2046

770func (a *sessionAgent) Model() Model {

2047func (a *sessionAgent) Model() Model {

771− return a.largeModel

2048+ return a.largeModel.Get()

2049+}

2050+

2051+// convertToToolResult converts a fantasy tool result to a message tool result.

2052+func (a *sessionAgent) convertToToolResult(result fantasy.ToolResultContent) message.ToolResult {

2053+ baseResult := message.ToolResult{

2054+ ToolCallID: result.ToolCallID,

2055+ Name: result.ToolName,

2056+ Metadata: result.ClientMetadata,

2057+ }

2058+

2059+ switch result.Result.GetType() {

2060+ case fantasy.ToolResultContentTypeText:

2061+ if r, ok := fantasy.AsToolResultOutputType[fantasy.ToolResultOutputContentText](result.Result); ok {

2062+ baseResult.Content = r.Text

2063+ }

2064+ case fantasy.ToolResultContentTypeError:

2065+ if r, ok := fantasy.AsToolResultOutputType[fantasy.ToolResultOutputContentError](result.Result); ok {

2066+ baseResult.Content = r.Error.Error()

2067+ baseResult.IsError = true

2068+ }

2069+ case fantasy.ToolResultContentTypeMedia:

2070+ 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

2087+ }

2088+ }

2089+ }

2090+

2091+ return baseResult

2092+}

2093+

2094+// workaroundProviderMediaLimitations converts media content in tool results to

2095+// user messages for providers that don't natively support images in tool results.

2096+//

2097+// Problem: OpenAI, Google, OpenRouter, and other OpenAI-compatible providers

2098+// don't support sending images/media in tool result messages - they only accept

2099+// text in tool results. However, they DO support images in user messages.

2100+//

2101+// If we send media in tool results to these providers, the API returns an error.

2102+//

2103+// Solution: For these providers, we:

2104+// 1. Replace the media in the tool result with a text placeholder

2105+// 2. Inject a user message immediately after with the image as a file attachment

2106+// 3. This maintains the tool execution flow while working around API limitations

2107+//

2108+// Anthropic and Bedrock support images natively in tool results, so we skip

2109+// this workaround for them.

2110+//

2111+// Example transformation:

2112+//

2113+// BEFORE: [tool result: image data]

2114+// 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)

2119+

2120+ if providerSupportsMedia {

2121+ return messages

2122+ }

2123+

2124+ supportsImages := largeModel.CatwalkCfg.SupportsImages

2125+

2126+ convertedMessages := make([]fantasy.Message, 0, len(messages))

2127+

2128+ for _, msg := range messages {

2129+ if msg.Role != fantasy.MessageRoleTool {

2130+ convertedMessages = append(convertedMessages, msg)

2131+ continue

2132+ }

2133+

2134+ textParts := make([]fantasy.MessagePart, 0, len(msg.Content))

2135+ var mediaFiles []fantasy.FilePart

2136+

2137+ for _, part := range msg.Content {

2138+ toolResult, ok := fantasy.AsMessagePart[fantasy.ToolResultPart](part)

2139+ if !ok {

2140+ textParts = append(textParts, part)

2141+ continue

2142+ }

2143+

2144+ 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+

2160+ decoded, err := base64.StdEncoding.DecodeString(media.Data)

2161+ if err != nil {

2162+ slog.Warn("Failed to decode media data", "error", err)

2163+ textParts = append(textParts, part)

2164+ continue

2165+ }

2166+

2167+ mediaFiles = append(mediaFiles, fantasy.FilePart{

2168+ Data: decoded,

2169+ MediaType: media.MediaType,

2170+ Filename: fmt.Sprintf("tool-result-%s", toolResult.ToolCallID),

2171+ })

2172+

2173+ textParts = append(textParts, fantasy.ToolResultPart{

2174+ ToolCallID: toolResult.ToolCallID,

2175+ Output: fantasy.ToolResultOutputContentText{

2176+ Text: "[Image/media content loaded - see attached file]",

2177+ },

2178+ ProviderOptions: toolResult.ProviderOptions,

2179+ })

2180+ } else {

2181+ textParts = append(textParts, part)

2182+ }

2183+ }

2184+

2185+ convertedMessages = append(convertedMessages, fantasy.Message{

2186+ Role: fantasy.MessageRoleTool,

2187+ Content: textParts,

2188+ })

2189+

2190+ if len(mediaFiles) > 0 {

2191+ convertedMessages = append(convertedMessages, fantasy.NewUserMessage(

2192+ "Here is the media content from the tool result:",

2193+ mediaFiles...,

2194+ ))

2195+ }

2196+ }

2197+

2198+ return convertedMessages

2199+}

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

772}

2248}

internal/agent/agent_test.go+417−16

@@ -1,30 +1,39 @@

1package agent

3import (

4+ "encoding/base64"

5+ "fmt"

6+ "log/slog"

4 "os"

7 "os"

5 "path/filepath"

8 "path/filepath"

9+ "runtime"

6 "strings"

10 "strings"

7 "testing"

11 "testing"

12+ "time"

14+ "charm.land/catwalk/pkg/catwalk"

9 "charm.land/fantasy"

15 "charm.land/fantasy"

16+ "charm.land/x/vcr"

10 "github.com/charmbracelet/crush/internal/agent/tools"

17 "github.com/charmbracelet/crush/internal/agent/tools"

18+ "github.com/charmbracelet/crush/internal/config"

11 "github.com/charmbracelet/crush/internal/message"

19 "github.com/charmbracelet/crush/internal/message"

12− "github.com/charmbracelet/crush/internal/shell"

20+ "github.com/charmbracelet/crush/internal/session"

13 "github.com/stretchr/testify/assert"

21 "github.com/stretchr/testify/assert"

14 "github.com/stretchr/testify/require"

22 "github.com/stretchr/testify/require"

15− "gopkg.in/dnaeon/go-vcr.v4/pkg/recorder"

17 _ "github.com/joho/godotenv/autoload"

24 _ "github.com/joho/godotenv/autoload"

18)

25)

27+func TestMain(m *testing.M) {

28+ slog.SetLogLoggerLevel(slog.LevelError)

29+ m.Run()

30+}

31+

20var modelPairs = []modelPair{

32var modelPairs = []modelPair{

21− {"anthropic-sonnet", anthropicBuilder("claude-sonnet-4-5-20250929"), anthropicBuilder("claude-3-5-haiku-20241022")},

33+ {"glm-5.1", hyperBuilder("glm-5.1"), hyperBuilder("gpt-oss-120b")},

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")},

25}

34}

27−func getModels(t *testing.T, r *recorder.Recorder, pair modelPair) (fantasy.LanguageModel, fantasy.LanguageModel) {

36+func getModels(t *testing.T, r *vcr.Recorder, pair modelPair) (fantasy.LanguageModel, fantasy.LanguageModel) {

28 large, err := pair.largeModel(t, r)

37 large, err := pair.largeModel(t, r)

29 require.NoError(t, err)

38 require.NoError(t, err)

30 small, err := pair.smallModel(t, r)

39 small, err := pair.smallModel(t, r)

@@ -32,19 +41,22 @@ func getModels(t *testing.T, r *recorder.Recorder, pair modelPair) (fantasy.Lang

32 return large, small

41 return large, small

33}

42}

35−func setupAgent(t *testing.T, pair modelPair) (SessionAgent, env) {

44+func setupAgent(t *testing.T, pair modelPair) (SessionAgent, fakeEnv) {

36− r := newRecorder(t)

45+ r := vcr.NewRecorder(t)

37 large, small := getModels(t, r, pair)

46 large, small := getModels(t, r, pair)

38 env := testEnv(t)

47 env := testEnv(t)

40 createSimpleGoProject(t, env.workingDir)

49 createSimpleGoProject(t, env.workingDir)

41 agent, err := coderAgent(r, env, large, small)

50 agent, err := coderAgent(r, env, large, small)

42− shell.Reset(env.workingDir)

43 require.NoError(t, err)

51 require.NoError(t, err)

44 return agent, env

52 return agent, env

45}

53}

47func TestCoderAgent(t *testing.T) {

55func TestCoderAgent(t *testing.T) {

56+ if runtime.GOOS == "windows" {

57+ t.Skip("skipping on windows for now")

58+ }

59+

48 for _, pair := range modelPairs {

60 for _, pair := range modelPairs {

49 t.Run(pair.name, func(t *testing.T) {

61 t.Run(pair.name, func(t *testing.T) {

50 t.Run("simple test", func(t *testing.T) {

62 t.Run("simple test", func(t *testing.T) {

@@ -165,7 +177,7 @@ func TestCoderAgent(t *testing.T) {

165 require.NoError(t, err)

177 require.NoError(t, err)

166

178

167 res, err := agent.Run(t.Context(), SessionAgentCall{

179 res, err := agent.Run(t.Context(), SessionAgentCall{

168− Prompt: "use bash to create a file named test.txt with content 'hello bash'",

180+ Prompt: "use bash to create a file named test.txt with content 'hello bash'. do not print its timestamp",

169 SessionID: session.ID,

181 SessionID: session.ID,

170 MaxOutputTokens: 10000,

182 MaxOutputTokens: 10000,

171 })

183 })

@@ -209,7 +221,7 @@ func TestCoderAgent(t *testing.T) {

209 require.NoError(t, err)

221 require.NoError(t, err)

210

222

211 res, err := agent.Run(t.Context(), SessionAgentCall{

223 res, err := agent.Run(t.Context(), SessionAgentCall{

212− Prompt: "download the file from https://httpbin.org/robots.txt and save it as robots.txt",

224+ Prompt: "download the file from https://example-files.online-convert.com/document/txt/example.txt and save it as example.txt",

213 SessionID: session.ID,

225 SessionID: session.ID,

214 MaxOutputTokens: 10000,

226 MaxOutputTokens: 10000,

215 })

227 })

@@ -241,9 +253,9 @@ func TestCoderAgent(t *testing.T) {

241

253

242 require.True(t, foundDownload, "Expected to find a download operation")

254 require.True(t, foundDownload, "Expected to find a download operation")

243

255

244− robotsPath := filepath.Join(env.workingDir, "robots.txt")

256+ examplePath := filepath.Join(env.workingDir, "example.txt")

245− _, err = os.Stat(robotsPath)

257+ _, err = os.Stat(examplePath)

246− require.NoError(t, err, "Expected robots.txt file to exist")

258+ require.NoError(t, err, "Expected example.txt file to exist")

247 })

259 })

248 t.Run("fetch tool", func(t *testing.T) {

260 t.Run("fetch tool", func(t *testing.T) {

249 agent, env := setupAgent(t, pair)

261 agent, env := setupAgent(t, pair)

@@ -252,7 +264,7 @@ func TestCoderAgent(t *testing.T) {

252 require.NoError(t, err)

264 require.NoError(t, err)

253

265

254 res, err := agent.Run(t.Context(), SessionAgentCall{

266 res, err := agent.Run(t.Context(), SessionAgentCall{

255− Prompt: "fetch the content from https://httpbin.org/html and tell me if it contains the word 'Herman'",

267+ Prompt: "fetch the content from https://example-files.online-convert.com/website/html/example.html and tell me if it contains the word 'John Doe'",

256 SessionID: session.ID,

268 SessionID: session.ID,

257 MaxOutputTokens: 10000,

269 MaxOutputTokens: 10000,

258 })

270 })

@@ -612,3 +624,392 @@ func TestCoderAgent(t *testing.T) {

612 })

624 })

613 }

625 }

614}

626}

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+14−55

@@ -3,9 +3,7 @@ package agent

3import (

4 "context"

5 _ "embed"

6− "encoding/json"

7 "errors"

6 "errors"

8− "fmt"

10 "charm.land/fantasy"

8 "charm.land/fantasy"

@@ -15,7 +13,7 @@ import (

15)

13)

17//go:embed templates/agent_tool.md

15//go:embed templates/agent_tool.md

18−var agentToolDescription []byte

16+var agentToolDescription string

20type AgentParams struct {

18type AgentParams struct {

21 Prompt string `json:"prompt" description:"The task for the agent to perform"`

19 Prompt string `json:"prompt" description:"The task for the agent to perform"`

@@ -26,7 +24,7 @@ const (

26)

24)

28func (c *coordinator) agentTool(ctx context.Context) (fantasy.AgentTool, error) {

26func (c *coordinator) agentTool(ctx context.Context) (fantasy.AgentTool, error) {

29− agentCfg, ok := c.cfg.Agents[config.AgentTask]

27+ agentCfg, ok := c.cfg.Config().Agents[config.AgentTask]

30 if !ok {

28 if !ok {

31 return nil, errors.New("task agent not configured")

29 return nil, errors.New("task agent not configured")

32 }

30 }

@@ -35,17 +33,14 @@ func (c *coordinator) agentTool(ctx context.Context) (fantasy.AgentTool, error)

35 return nil, err

33 return nil, err

36 }

34 }

38− agent, err := c.buildAgent(ctx, prompt, agentCfg)

36+ agent, err := c.buildAgent(ctx, prompt, agentCfg, true)

39 if err != nil {

37 if err != nil {

40 return nil, err

38 return nil, err

41 }

39 }

42− return fantasy.NewAgentTool(

40+ return fantasy.NewParallelAgentTool(

43 AgentToolName,

41 AgentToolName,

44− string(agentToolDescription),

42+ agentToolDescription,

45 func(ctx context.Context, params AgentParams, call fantasy.ToolCall) (fantasy.ToolResponse, error) {

43 func(ctx context.Context, params AgentParams, call fantasy.ToolCall) (fantasy.ToolResponse, error) {

46− if err := json.Unmarshal([]byte(call.Input), &params); err != nil {

47− return fantasy.NewTextErrorResponse(fmt.Sprintf("error parsing parameters: %s", err)), nil

48− }

49 if params.Prompt == "" {

44 if params.Prompt == "" {

50 return fantasy.NewTextErrorResponse("prompt is required"), nil

45 return fantasy.NewTextErrorResponse("prompt is required"), nil

51 }

46 }

@@ -60,50 +55,14 @@ func (c *coordinator) agentTool(ctx context.Context) (fantasy.AgentTool, error)

60 return fantasy.ToolResponse{}, errors.New("agent message id missing from context")

55 return fantasy.ToolResponse{}, errors.New("agent message id missing from context")

61 }

56 }

63− agentToolSessionID := c.sessions.CreateAgentToolSessionID(agentMessageID, call.ID)

58+ return c.runSubAgent(ctx, subAgentParams{

64− session, err := c.sessions.CreateTaskSession(ctx, agentToolSessionID, sessionID, "New Agent Session")

59+ Agent: agent,

65− if err != nil {

60+ SessionID: sessionID,

66− return fantasy.ToolResponse{}, fmt.Errorf("error creating session: %s", err)

61+ AgentMessageID: agentMessageID,

67− }

62+ ToolCallID: call.ID,

68− model := agent.Model()

69− maxTokens := model.CatwalkCfg.DefaultMaxTokens

70− if model.ModelCfg.MaxTokens != 0 {

71− maxTokens = model.ModelCfg.MaxTokens

72− }

73−

74− providerCfg, ok := c.cfg.Providers.Get(model.ModelCfg.Provider)

75− if !ok {

76− return fantasy.ToolResponse{}, errors.New("model provider not configured")

77− }

78− result, err := agent.Run(ctx, SessionAgentCall{

79− SessionID: session.ID,

80− Prompt: params.Prompt,

63+ Prompt: params.Prompt,

81− MaxOutputTokens: maxTokens,

64+ SessionTitle: "New Agent Session",

82− ProviderOptions: getProviderOptions(model, providerCfg.Type),

83− Temperature: model.ModelCfg.Temperature,

84− TopP: model.ModelCfg.TopP,

85− TopK: model.ModelCfg.TopK,

86− FrequencyPenalty: model.ModelCfg.FrequencyPenalty,

87− PresencePenalty: model.ModelCfg.PresencePenalty,

88 })

65 })

89− if err != nil {

66+ },

90− return fantasy.NewTextErrorResponse("error generating response"), nil

91− }

92− updatedSession, err := c.sessions.Get(ctx, session.ID)

93− if err != nil {

94− return fantasy.ToolResponse{}, fmt.Errorf("error getting session: %s", err)

95− }

96− parentSession, err := c.sessions.Get(ctx, sessionID)

97− if err != nil {

98− return fantasy.ToolResponse{}, fmt.Errorf("error getting parent session: %s", err)

99− }

100−

101− parentSession.Cost += updatedSession.Cost

102−

103− _, err = c.sessions.Save(ctx, parentSession)

104− if err != nil {

105− return fantasy.ToolResponse{}, fmt.Errorf("error saving parent session: %s", err)

106− }

107− return fantasy.NewTextResponse(result.Response.Content.Text()), nil

108− }), nil

67+ ), nil

109}

68}

internal/agent/agentic_fetch_tool.gonew file+206

@@ -0,0 +1,206 @@

1+package agent

3+import (

4+ "context"

5+ _ "embed"

6+ "errors"

7+ "fmt"

8+ "net/http"

9+ "os"

10+ "time"

11+

12+ "charm.land/fantasy"

13+

14+ "github.com/charmbracelet/crush/internal/agent/prompt"

15+ "github.com/charmbracelet/crush/internal/agent/tools"

16+ "github.com/charmbracelet/crush/internal/permission"

17+)

18+

19+//go:embed templates/agentic_fetch.md

20+var agenticFetchToolDescription string

21+

22+// agenticFetchValidationResult holds the validated parameters from the tool call context.

23+type agenticFetchValidationResult struct {

24+ SessionID string

25+ AgentMessageID string

26+}

27+

28+// validateAgenticFetchParams validates the tool call parameters and extracts required context values.

29+func validateAgenticFetchParams(ctx context.Context, params tools.AgenticFetchParams) (agenticFetchValidationResult, error) {

30+ if params.Prompt == "" {

31+ return agenticFetchValidationResult{}, errors.New("prompt is required")

32+ }

33+

34+ sessionID := tools.GetSessionFromContext(ctx)

35+ if sessionID == "" {

36+ return agenticFetchValidationResult{}, errors.New("session id missing from context")

37+ }

38+

39+ agentMessageID := tools.GetMessageFromContext(ctx)

40+ if agentMessageID == "" {

41+ return agenticFetchValidationResult{}, errors.New("agent message id missing from context")

42+ }

43+

44+ return agenticFetchValidationResult{

45+ SessionID: sessionID,

46+ AgentMessageID: agentMessageID,

47+ }, nil

48+}

49+

50+//go:embed templates/agentic_fetch_prompt.md.tpl

51+var agenticFetchPromptTmpl []byte

52+

53+func (c *coordinator) agenticFetchTool(_ context.Context, client *http.Client) (fantasy.AgentTool, error) {

54+ 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+

60+ client = &http.Client{

61+ Timeout: 30 * time.Second,

62+ Transport: transport,

63+ }

64+ }

65+

66+ return fantasy.NewParallelAgentTool(

67+ tools.AgenticFetchToolName,

68+ agenticFetchToolDescription,

69+ func(ctx context.Context, params tools.AgenticFetchParams, call fantasy.ToolCall) (fantasy.ToolResponse, error) {

70+ validationResult, err := validateAgenticFetchParams(ctx, params)

71+ if err != nil {

72+ return fantasy.NewTextErrorResponse(err.Error()), nil

73+ }

74+

75+ // Determine description based on mode.

76+ var description string

77+ if params.URL != "" {

78+ description = fmt.Sprintf("Fetch and analyze content from URL: %s", params.URL)

79+ } else {

80+ description = "Search the web and analyze results"

81+ }

82+

83+ p, err := c.permissions.Request(

84+ ctx,

85+ permission.CreatePermissionRequest{

86+ SessionID: validationResult.SessionID,

87+ Path: c.cfg.WorkingDir(),

88+ ToolCallID: call.ID,

89+ ToolName: tools.AgenticFetchToolName,

90+ Action: "fetch",

91+ Description: description,

92+ Params: tools.AgenticFetchPermissionsParams(params),

93+ },

94+ )

95+ if err != nil {

96+ return fantasy.ToolResponse{}, err

97+ }

98+ if !p {

99+ return tools.NewPermissionDeniedResponse(), nil

100+ }

101+

102+ tmpDir, err := os.MkdirTemp(c.cfg.Config().Options.DataDirectory, "crush-fetch-*")

103+ if err != nil {

104+ return fantasy.NewTextErrorResponse(fmt.Sprintf("Failed to create temporary directory: %s", err)), nil

105+ }

106+ defer os.RemoveAll(tmpDir)

107+

108+ var fullPrompt string

109+

110+ if params.URL != "" {

111+ // URL mode: fetch the URL content first.

112+ content, err := tools.FetchURLAndConvert(ctx, client, params.URL)

113+ if err != nil {

114+ return fantasy.NewTextErrorResponse(fmt.Sprintf("Failed to fetch URL: %s", err)), nil

115+ }

116+

117+ hasLargeContent := len(content) > tools.LargeContentThreshold

118+

119+ if hasLargeContent {

120+ tempFile, err := os.CreateTemp(tmpDir, "page-*.md")

121+ if err != nil {

122+ return fantasy.NewTextErrorResponse(fmt.Sprintf("Failed to create temporary file: %s", err)), nil

123+ }

124+ tempFilePath := tempFile.Name()

125+

126+ if _, err := tempFile.WriteString(content); err != nil {

127+ tempFile.Close()

128+ return fantasy.NewTextErrorResponse(fmt.Sprintf("Failed to write content to file: %s", err)), nil

129+ }

130+ tempFile.Close()

131+

132+ fullPrompt = fmt.Sprintf("%s\n\nThe web page from %s has been saved to: %s\n\nUse the view and grep tools to analyze this file and extract the requested information.", params.Prompt, params.URL, tempFilePath)

133+ } else {

134+ fullPrompt = fmt.Sprintf("%s\n\nWeb page URL: %s\n\n<webpage_content>\n%s\n</webpage_content>", params.Prompt, params.URL, content)

135+ }

136+ } else {

137+ // Search mode: let the sub-agent search and fetch as needed.

138+ fullPrompt = fmt.Sprintf("%s\n\nUse the web_search tool to find relevant information. Break down the question into smaller, focused searches if needed. After searching, use web_fetch to get detailed content from the most relevant results.", params.Prompt)

139+ }

140+

141+ promptOpts := []prompt.Option{

142+ prompt.WithWorkingDir(tmpDir),

143+ }

144+

145+ promptTemplate, err := prompt.NewPrompt("agentic_fetch", string(agenticFetchPromptTmpl), promptOpts...)

146+ if err != nil {

147+ return fantasy.ToolResponse{}, fmt.Errorf("error creating prompt: %s", err)

148+ }

149+

150+ _, small, err := c.buildAgentModels(ctx, true)

151+ if err != nil {

152+ return fantasy.ToolResponse{}, fmt.Errorf("error building models: %s", err)

153+ }

154+

155+ systemPrompt, err := promptTemplate.Build(ctx, small.Model.Provider(), small.Model.Model(), c.cfg)

156+ if err != nil {

157+ return fantasy.ToolResponse{}, fmt.Errorf("error building system prompt: %s", err)

158+ }

159+

160+ smallProviderCfg, ok := c.cfg.Config().Providers.Get(small.ModelCfg.Provider)

161+ if !ok {

162+ return fantasy.ToolResponse{}, errors.New("small model provider not configured")

163+ }

164+

165+ webFetchTool := tools.NewWebFetchTool(tmpDir, client)

166+ webSearchTool := tools.NewWebSearchTool(client)

167+ fetchTools := []fantasy.AgentTool{

168+ webFetchTool,

169+ webSearchTool,

170+ tools.NewGlobTool(tmpDir, c.cfg.Config().Tools.Glob),

171+ tools.NewGrepTool(tmpDir, c.cfg.Config().Tools.Grep),

172+ tools.NewSourcegraphTool(client),

173+ tools.NewViewTool(c.lspManager, c.permissions, c.filetracker, nil, tmpDir),

174+ }

175+

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+

181+ agent := NewSessionAgent(SessionAgentOptions{

182+ LargeModel: small, // Use small model for both (fetch doesn't need large)

183+ SmallModel: small,

184+ SystemPromptPrefix: smallProviderCfg.SystemPromptPrefix,

185+ SystemPrompt: systemPrompt,

186+ DisableAutoSummarize: c.cfg.Config().Options.DisableAutoSummarize,

187+ IsYolo: c.permissions.SkipRequests(),

188+ Sessions: c.sessions,

189+ Messages: c.messages,

190+ Tools: fetchTools,

191+ })

192+

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+ },

203+ })

204+ },

205+ ), nil

206+}

internal/agent/agenttest/coordinator.gonew file+80

@@ -0,0 +1,80 @@

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

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+72−73

@@ -1,44 +1,45 @@

1package agent

3import (

4+ "context"

4 "net/http"

5 "net/http"

5 "os"

6 "os"

6 "path/filepath"

7 "path/filepath"

7 "testing"

8 "testing"

8 "time"

9 "time"

11+ "charm.land/catwalk/pkg/catwalk"

10 "charm.land/fantasy"

12 "charm.land/fantasy"

11− "charm.land/fantasy/providers/anthropic"

12− "charm.land/fantasy/providers/openai"

13 "charm.land/fantasy/providers/openaicompat"

14− "charm.land/fantasy/providers/openrouter"

14+ "charm.land/x/vcr"

15− "github.com/charmbracelet/catwalk/pkg/catwalk"

16 "github.com/charmbracelet/crush/internal/agent/prompt"

15 "github.com/charmbracelet/crush/internal/agent/prompt"

17 "github.com/charmbracelet/crush/internal/agent/tools"

16 "github.com/charmbracelet/crush/internal/agent/tools"

18 "github.com/charmbracelet/crush/internal/config"

17 "github.com/charmbracelet/crush/internal/config"

19 "github.com/charmbracelet/crush/internal/csync"

18 "github.com/charmbracelet/crush/internal/csync"

20 "github.com/charmbracelet/crush/internal/db"

19 "github.com/charmbracelet/crush/internal/db"

20+ "github.com/charmbracelet/crush/internal/filetracker"

21 "github.com/charmbracelet/crush/internal/history"

22 "github.com/charmbracelet/crush/internal/lsp"

23 "github.com/charmbracelet/crush/internal/message"

24 "github.com/charmbracelet/crush/internal/permission"

25 "github.com/charmbracelet/crush/internal/session"

26 "github.com/stretchr/testify/require"

27− "gopkg.in/dnaeon/go-vcr.v4/pkg/recorder"

29 _ "github.com/joho/godotenv/autoload"

28 _ "github.com/joho/godotenv/autoload"

30)

29)

31+// fakeEnv is an environment for testing.

32−type env struct {

32+type fakeEnv struct {

33 workingDir string

34 sessions session.Service

35 messages message.Service

36 permissions permission.Service

37 history history.Service

38+ filetracker *filetracker.Service

38 lspClients *csync.Map[string, *lsp.Client]

39 lspClients *csync.Map[string, *lsp.Client]

39}

40}

41−type builderFunc func(t *testing.T, r *recorder.Recorder) (fantasy.LanguageModel, error)

42+type builderFunc func(t *testing.T, r *vcr.Recorder) (fantasy.LanguageModel, error)

43type modelPair struct {

44type modelPair struct {

44 name string

45 name string

@@ -46,50 +47,11 @@ type modelPair struct {

46 smallModel builderFunc

47 smallModel builderFunc

47}

48}

49−func anthropicBuilder(model string) builderFunc {

50+func hyperBuilder(model string) builderFunc {

50− return func(t *testing.T, r *recorder.Recorder) (fantasy.LanguageModel, error) {

51− provider, err := anthropic.New(

52− anthropic.WithAPIKey(os.Getenv("CRUSH_ANTHROPIC_API_KEY")),

53− anthropic.WithHTTPClient(&http.Client{Transport: r}),

54− )

55− if err != nil {

56− return nil, err

57− }

58− return provider.LanguageModel(t.Context(), model)

59− }

60−}

61−

62−func openaiBuilder(model string) builderFunc {

63− return func(t *testing.T, r *recorder.Recorder) (fantasy.LanguageModel, error) {

64− provider, err := openai.New(

65− openai.WithAPIKey(os.Getenv("CRUSH_OPENAI_API_KEY")),

66− openai.WithHTTPClient(&http.Client{Transport: r}),

67− )

68− if err != nil {

69− return nil, err

70− }

71− return provider.LanguageModel(t.Context(), model)

72− }

73−}

74−

75−func openRouterBuilder(model string) builderFunc {

76− return func(t *testing.T, r *recorder.Recorder) (fantasy.LanguageModel, error) {

77− provider, err := openrouter.New(

78− openrouter.WithAPIKey(os.Getenv("CRUSH_OPENROUTER_API_KEY")),

79− openrouter.WithHTTPClient(&http.Client{Transport: r}),

80− )

81− if err != nil {

82− return nil, err

83− }

84− return provider.LanguageModel(t.Context(), model)

85− }

86−}

87−

88−func zAIBuilder(model string) builderFunc {

89− return func(t *testing.T, r *recorder.Recorder) (fantasy.LanguageModel, error) {

51+ return func(t *testing.T, r *vcr.Recorder) (fantasy.LanguageModel, error) {

90 provider, err := openaicompat.New(

52 provider, err := openaicompat.New(

91− openaicompat.WithBaseURL("https://api.z.ai/api/coding/paas/v4"),

53+ openaicompat.WithBaseURL("https://hyper.charm.land/v1"),

92− openaicompat.WithAPIKey(os.Getenv("CRUSH_ZAI_API_KEY")),

54+ openaicompat.WithAPIKey(os.Getenv("CRUSH_HYPER_API_KEY")),

93 openaicompat.WithHTTPClient(&http.Client{Transport: r}),

55 openaicompat.WithHTTPClient(&http.Client{Transport: r}),

94 )

56 )

95 if err != nil {

57 if err != nil {

@@ -99,34 +61,42 @@ func zAIBuilder(model string) builderFunc {

99 }

61 }

100}

62}

101

102−func testEnv(t *testing.T) env {

64+func testEnv(t *testing.T) fakeEnv {

103− testDir := filepath.Join("/tmp/crush-test/", t.Name())

65+ workingDir := filepath.Join("/tmp/crush-test/", t.Name())

104− os.RemoveAll(testDir)

66+ os.RemoveAll(workingDir)

67+

105− err := os.MkdirAll(testDir, 0o755)

68+ err := os.MkdirAll(workingDir, 0o755)

106− t.Cleanup(func() {

107− os.RemoveAll(testDir)

108− })

109 require.NoError(t, err)

69 require.NoError(t, err)

110− workingDir := testDir

70+

111 conn, err := db.Connect(t.Context(), t.TempDir())

71 conn, err := db.Connect(t.Context(), t.TempDir())

112 require.NoError(t, err)

72 require.NoError(t, err)

73+

113 q := db.New(conn)

74 q := db.New(conn)

114− sessions := session.NewService(q)

75+ sessions := session.NewService(q, conn)

115 messages := message.NewService(q)

76 messages := message.NewService(q)

77+

116 permissions := permission.NewPermissionService(workingDir, true, []string{})

78 permissions := permission.NewPermissionService(workingDir, true, []string{})

117 history := history.NewService(q, conn)

79 history := history.NewService(q, conn)

80+ filetrackerService := filetracker.NewService(q)

118 lspClients := csync.NewMap[string, *lsp.Client]()

81 lspClients := csync.NewMap[string, *lsp.Client]()

82+

83+ t.Cleanup(func() {

84+ conn.Close()

85+ os.RemoveAll(workingDir)

86+ })

87+

119− return env{

88+ return fakeEnv{

120 workingDir,

89 workingDir,

121 sessions,

90 sessions,

122 messages,

91 messages,

123 permissions,

92 permissions,

124 history,

93 history,

94+ &filetrackerService,

125 lspClients,

95 lspClients,

126 }

96 }

127}

97}

128

129−func testSessionAgent(env env, large, small fantasy.LanguageModel, systemPrompt string, tools ...fantasy.AgentTool) SessionAgent {

99+func testSessionAgent(env fakeEnv, large, small fantasy.LanguageModel, systemPrompt string, tools ...fantasy.AgentTool) SessionAgent {

130 largeModel := Model{

100 largeModel := Model{

131 Model: large,

101 Model: large,

132 CatwalkCfg: catwalk.Model{

102 CatwalkCfg: catwalk.Model{

@@ -141,11 +111,19 @@ func testSessionAgent(env env, large, small fantasy.LanguageModel, systemPrompt

141 DefaultMaxTokens: 10000,

111 DefaultMaxTokens: 10000,

142 },

112 },

143 }

113 }

144− agent := NewSessionAgent(SessionAgentOptions{largeModel, smallModel, systemPrompt, false, env.sessions, env.messages, tools})

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+ })

145 return agent

123 return agent

146}

124}

147

125

148−func coderAgent(r *recorder.Recorder, env env, large, small fantasy.LanguageModel) (SessionAgent, error) {

126+func coderAgent(r *vcr.Recorder, env fakeEnv, large, small fantasy.LanguageModel) (SessionAgent, error) {

149 fixedTime := func() time.Time {

127 fixedTime := func() time.Time {

150 t, _ := time.Parse("1/2/2006", "1/1/2025")

128 t, _ := time.Parse("1/2/2006", "1/1/2025")

151 return t

129 return t

@@ -153,7 +131,7 @@ func coderAgent(r *recorder.Recorder, env env, large, small fantasy.LanguageMode

153 prompt, err := coderPrompt(

131 prompt, err := coderPrompt(

154 prompt.WithTimeFunc(fixedTime),

132 prompt.WithTimeFunc(fixedTime),

155 prompt.WithPlatform("linux"),

133 prompt.WithPlatform("linux"),

156− prompt.WithWorkingDir(env.workingDir),

134+ prompt.WithWorkingDir(filepath.ToSlash(env.workingDir)),

157 )

135 )

158 if err != nil {

136 if err != nil {

159 return nil, err

137 return nil, err

@@ -163,22 +141,43 @@ func coderAgent(r *recorder.Recorder, env env, large, small fantasy.LanguageMode

163 return nil, err

141 return nil, err

164 }

142 }

165

143

144+ // NOTE(@andreynering): Set a fixed config to ensure cassettes match

145+ // independently of user config on `$HOME/.config/crush/crush.json`.

146+ cfg.Config().Options.Attribution = &config.Attribution{

147+ TrailerStyle: "co-authored-by",

148+ GeneratedWith: true,

149+ }

150+

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+

166− systemPrompt, err := prompt.Build(large.Provider(), large.Model(), *cfg)

158+ systemPrompt, err := prompt.Build(context.TODO(), large.Provider(), large.Model(), cfg)

167 if err != nil {

159 if err != nil {

168 return nil, err

160 return nil, err

169 }

161 }

162+

163+ // Get the model name for the bash tool

164+ modelName := large.Model() // fallback to ID if Name not available

165+ if model := cfg.Config().GetModel(large.Provider(), large.Model()); model != nil {

166+ modelName = model.Name

167+ }

168+

170 allTools := []fantasy.AgentTool{

169 allTools := []fantasy.AgentTool{

171− tools.NewBashTool(env.permissions, env.workingDir, cfg.Options.Attribution),

170+ tools.NewBashTool(env.permissions, env.workingDir, cfg.Config().Options.Attribution, modelName),

172 tools.NewDownloadTool(env.permissions, env.workingDir, r.GetDefaultClient()),

171 tools.NewDownloadTool(env.permissions, env.workingDir, r.GetDefaultClient()),

173− tools.NewEditTool(env.lspClients, env.permissions, env.history, env.workingDir),

172+ tools.NewEditTool(nil, env.permissions, env.history, *env.filetracker, env.workingDir),

174− tools.NewMultiEditTool(env.lspClients, env.permissions, env.history, env.workingDir),

173+ tools.NewMultiEditTool(nil, env.permissions, env.history, *env.filetracker, env.workingDir),

175 tools.NewFetchTool(env.permissions, env.workingDir, r.GetDefaultClient()),

174 tools.NewFetchTool(env.permissions, env.workingDir, r.GetDefaultClient()),

176− tools.NewGlobTool(env.workingDir),

175+ tools.NewGlobTool(env.workingDir, cfg.Config().Tools.Glob),

177− tools.NewGrepTool(env.workingDir),

176+ tools.NewGrepTool(env.workingDir, cfg.Config().Tools.Grep),

178− tools.NewLsTool(env.permissions, env.workingDir, cfg.Tools.Ls),

177+ tools.NewLsTool(env.permissions, env.workingDir, cfg.Config().Tools.Ls),

179 tools.NewSourcegraphTool(r.GetDefaultClient()),

178 tools.NewSourcegraphTool(r.GetDefaultClient()),

180− tools.NewViewTool(env.lspClients, env.permissions, env.workingDir),

179+ tools.NewViewTool(nil, env.permissions, *env.filetracker, nil, env.workingDir),

181− tools.NewWriteTool(env.lspClients, env.permissions, env.history, env.workingDir),

180+ tools.NewWriteTool(nil, env.permissions, env.history, *env.filetracker, env.workingDir),

182 }

181 }

183

182

184 return testSessionAgent(env, large, small, systemPrompt, allTools...), nil

183 return testSessionAgent(env, large, small, systemPrompt, allTools...), nil

internal/agent/convert_test.gonew file+94

@@ -0,0 +1,94 @@

1+package agent

3+import (

4+ "encoding/base64"

5+ "testing"

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+1164−170

@@ -6,82 +6,203 @@ import (

6 "context"

7 "encoding/json"

8 "errors"

9+ "fmt"

9 "io"

10 "io"

10 "log/slog"

11 "log/slog"

12+ "maps"

13+ "net/http"

14+ "os"

15+ "path/filepath"

11 "slices"

16 "slices"

12 "strings"

17 "strings"

18+ "sync"

19+ "sync/atomic"

21+ "charm.land/catwalk/pkg/catwalk"

14 "charm.land/fantasy"

22 "charm.land/fantasy"

15− "github.com/charmbracelet/catwalk/pkg/catwalk"

23+ "github.com/charmbracelet/crush/internal/agent/hyper"

24+ "github.com/charmbracelet/crush/internal/agent/notify"

16 "github.com/charmbracelet/crush/internal/agent/prompt"

25 "github.com/charmbracelet/crush/internal/agent/prompt"

17 "github.com/charmbracelet/crush/internal/agent/tools"

26 "github.com/charmbracelet/crush/internal/agent/tools"

27+ "github.com/charmbracelet/crush/internal/agent/tools/mcp"

18 "github.com/charmbracelet/crush/internal/config"

28 "github.com/charmbracelet/crush/internal/config"

19 "github.com/charmbracelet/crush/internal/csync"

29 "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"

20 "github.com/charmbracelet/crush/internal/history"

33 "github.com/charmbracelet/crush/internal/history"

34+ "github.com/charmbracelet/crush/internal/hooks"

21 "github.com/charmbracelet/crush/internal/log"

35 "github.com/charmbracelet/crush/internal/log"

22 "github.com/charmbracelet/crush/internal/lsp"

36 "github.com/charmbracelet/crush/internal/lsp"

23 "github.com/charmbracelet/crush/internal/message"

37 "github.com/charmbracelet/crush/internal/message"

38+ "github.com/charmbracelet/crush/internal/oauth/copilot"

24 "github.com/charmbracelet/crush/internal/permission"

39 "github.com/charmbracelet/crush/internal/permission"

40+ "github.com/charmbracelet/crush/internal/pubsub"

25 "github.com/charmbracelet/crush/internal/session"

41 "github.com/charmbracelet/crush/internal/session"

42+ "github.com/charmbracelet/crush/internal/skills"

43+ "golang.org/x/sync/errgroup"

27 "charm.land/fantasy/providers/anthropic"

45 "charm.land/fantasy/providers/anthropic"

28 "charm.land/fantasy/providers/azure"

46 "charm.land/fantasy/providers/azure"

47+ "charm.land/fantasy/providers/bedrock"

29 "charm.land/fantasy/providers/google"

48 "charm.land/fantasy/providers/google"

30 "charm.land/fantasy/providers/openai"

49 "charm.land/fantasy/providers/openai"

31 "charm.land/fantasy/providers/openaicompat"

50 "charm.land/fantasy/providers/openaicompat"

32 "charm.land/fantasy/providers/openrouter"

51 "charm.land/fantasy/providers/openrouter"

52+ "charm.land/fantasy/providers/vercel"

53+ openaisdk "github.com/charmbracelet/openai-go/option"

33 "github.com/qjebbs/go-jsons"

54 "github.com/qjebbs/go-jsons"

34)

55)

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+

36type Coordinator interface {

85type Coordinator interface {

37 // INFO: (kujtim) this is not used yet we will use this when we have multiple agents

86 // INFO: (kujtim) this is not used yet we will use this when we have multiple agents

38 // SetMainAgent(string)

87 // SetMainAgent(string)

39 Run(ctx context.Context, sessionID, prompt string, attachments ...message.Attachment) (*fantasy.AgentResult, error)

88 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

40 Cancel(sessionID string)

98 Cancel(sessionID string)

41 CancelAll()

99 CancelAll()

42 IsSessionBusy(sessionID string) bool

100 IsSessionBusy(sessionID string) bool

43 IsBusy() bool

101 IsBusy() bool

44 QueuedPrompts(sessionID string) int

102 QueuedPrompts(sessionID string) int

103+ QueuedPromptsList(sessionID string) []string

45 ClearQueue(sessionID string)

104 ClearQueue(sessionID string)

46 Summarize(context.Context, string) error

105 Summarize(context.Context, string) error

47 Model() Model

106 Model() Model

48 UpdateModels(ctx context.Context) error

107 UpdateModels(ctx context.Context) error

108+ GenerateTitle(ctx context.Context, sessionID, prompt string)

49}

109}

110

51type coordinator struct {

111type coordinator struct {

52− cfg *config.Config

112+ cfg *config.ConfigStore

53 sessions session.Service

113 sessions session.Service

54 messages message.Service

114 messages message.Service

55 permissions permission.Service

115 permissions permission.Service

56 history history.Service

116 history history.Service

57− lspClients *csync.Map[string, *lsp.Client]

117+ filetracker filetracker.Service

118+ lspManager *lsp.Manager

119+ notify pubsub.Publisher[notify.Notification]

120+ runComplete pubsub.Publisher[notify.RunComplete]

121

59 currentAgent SessionAgent

122 currentAgent SessionAgent

60 agents map[string]SessionAgent

123 agents map[string]SessionAgent

124+

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+

156+ readyWg errgroup.Group

61}

157}

158

63func NewCoordinator(

159func NewCoordinator(

64 ctx context.Context,

160 ctx context.Context,

65− cfg *config.Config,

161+ cfg *config.ConfigStore,

66 sessions session.Service,

162 sessions session.Service,

67 messages message.Service,

163 messages message.Service,

68 permissions permission.Service,

164 permissions permission.Service,

69 history history.Service,

165 history history.Service,

70− lspClients *csync.Map[string, *lsp.Client],

166+ filetracker filetracker.Service,

167+ lspManager *lsp.Manager,

168+ notify pubsub.Publisher[notify.Notification],

169+ runComplete pubsub.Publisher[notify.RunComplete],

170+ skillsMgr *skills.Manager,

71) (Coordinator, error) {

171) (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

72− c := &coordinator{

175+ // discovery so the coordinator still works.

73− cfg: cfg,

176+ var allSkills, activeSkills []*skills.Skill

74− sessions: sessions,

177+ if skillsMgr != nil {

75− messages: messages,

178+ allSkills = skillsMgr.AllSkills()

76− permissions: permissions,

179+ activeSkills = skillsMgr.ActiveSkills()

77− history: history,

180+ } else {

78− lspClients: lspClients,

181+ allSkills, activeSkills = discoverSkills(cfg)

79− agents: make(map[string]SessionAgent),

80− }

182+ }

183+ skillTracker := skills.NewTracker(activeSkills)

184

185+ 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+

82− agentCfg, ok := cfg.Agents[config.AgentCoder]

203+ agentCfg, ok := cfg.Config().Agents[config.AgentCoder]

83 if !ok {

204 if !ok {

84− return nil, errors.New("coder agent not configured")

205+ return nil, errCoderAgentNotConfigured

85 }

206 }

207

87 // TODO: make this dynamic when we support multiple agents

208 // TODO: make this dynamic when we support multiple agents

@@ -90,17 +211,51 @@ func NewCoordinator(

90 return nil, err

211 return nil, err

91 }

212 }

213

93− agent, err := c.buildAgent(ctx, prompt, agentCfg)

214+ agent, err := c.buildAgent(ctx, prompt, agentCfg, false)

94 if err != nil {

215 if err != nil {

95 return nil, err

216 return nil, err

96 }

217 }

97 c.currentAgent = agent

218 c.currentAgent = agent

98 c.agents[config.AgentCoder] = agent

219 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+

99 return c, nil

231 return c, nil

100}

232}

101

233

102// Run implements Coordinator.

234// Run implements Coordinator.

103func (c *coordinator) Run(ctx context.Context, sessionID string, prompt string, attachments ...message.Attachment) (*fantasy.AgentResult, error) {

235func (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) {

250+ if err := c.readyWg.Wait(); err != nil {

251+ return nil, err

252+ }

253+

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+

104 model := c.currentAgent.Model()

259 model := c.currentAgent.Model()

105 maxTokens := model.CatwalkCfg.DefaultMaxTokens

260 maxTokens := model.CatwalkCfg.DefaultMaxTokens

106 if model.ModelCfg.MaxTokens != 0 {

261 if model.ModelCfg.MaxTokens != 0 {

@@ -108,34 +263,124 @@ func (c *coordinator) Run(ctx context.Context, sessionID string, prompt string,

108 }

263 }

109

264

110 if !model.CatwalkCfg.SupportsImages && attachments != nil {

265 if !model.CatwalkCfg.SupportsImages && attachments != nil {

266+ // filter out image attachments

267+ filteredAttachments := make([]message.Attachment, 0, len(attachments))

111− attachments = nil

268+ for _, att := range attachments {

269+ if att.IsText() {

270+ filteredAttachments = append(filteredAttachments, att)

271+ }

272+ }

273+ attachments = filteredAttachments

112 }

274 }

113

275

114− providerCfg, ok := c.cfg.Providers.Get(model.ModelCfg.Provider)

276+ providerCfg, ok := c.cfg.Config().Providers.Get(model.ModelCfg.Provider)

115 if !ok {

277 if !ok {

116− return nil, errors.New("model provider not configured")

278+ return nil, errModelProviderNotConfigured

117− }

279+ }

118−

280+

119− mergedOptions, temp, topP, topK, freqPenalty, presPenalty := mergeCallOptions(model, providerCfg.Type)

281+ mergedOptions, temp, topP, topK, freqPenalty, presPenalty := c.cachedMergeCallOptions(model, providerCfg)

120−

282+

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)

287+ }

288+

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)

313+ run := func() (*fantasy.AgentResult, error) {

121− return c.currentAgent.Run(ctx, SessionAgentCall{

314+ return c.currentAgent.Run(ctx, SessionAgentCall{

122− SessionID: sessionID,

315+ SessionID: sessionID,

316+ RunID: runID,

123− Prompt: prompt,

317+ Prompt: prompt,

124− Attachments: attachments,

318+ Attachments: attachments,

125− MaxOutputTokens: maxTokens,

319+ MaxOutputTokens: maxTokens,

126− ProviderOptions: mergedOptions,

320+ ProviderOptions: mergedOptions,

127− Temperature: temp,

321+ Temperature: temp,

128− TopP: topP,

322+ TopP: topP,

129− TopK: topK,

323+ TopK: topK,

130− FrequencyPenalty: freqPenalty,

324+ FrequencyPenalty: freqPenalty,

131− PresencePenalty: presPenalty,

325+ 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

132 })

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,

345+ })

346+ }

347+

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 ""

365+ }

366+

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 ""

133}

377}

134

378

135−func getProviderOptions(model Model, tp catwalk.Type) fantasy.ProviderOptions {

379+func getProviderOptions(model Model, providerCfg config.ProviderConfig) fantasy.ProviderOptions {

136 options := fantasy.ProviderOptions{}

380 options := fantasy.ProviderOptions{}

137

381

138 cfgOpts := []byte("{}")

382 cfgOpts := []byte("{}")

383+ providerCfgOpts := []byte("{}")

139 catwalkOpts := []byte("{}")

384 catwalkOpts := []byte("{}")

140

385

141 if model.ModelCfg.ProviderOptions != nil {

386 if model.ModelCfg.ProviderOptions != nil {

@@ -145,6 +390,13 @@ func getProviderOptions(model Model, tp catwalk.Type) fantasy.ProviderOptions {

145 }

390 }

146 }

391 }

147

392

393+ if providerCfg.ProviderOptions != nil {

394+ data, err := json.Marshal(providerCfg.ProviderOptions)

395+ if err == nil {

396+ providerCfgOpts = data

397+ }

398+ }

399+

148 if model.CatwalkCfg.Options.ProviderOptions != nil {

400 if model.CatwalkCfg.Options.ProviderOptions != nil {

149 data, err := json.Marshal(model.CatwalkCfg.Options.ProviderOptions)

401 data, err := json.Marshal(model.CatwalkCfg.Options.ProviderOptions)

150 if err == nil {

402 if err == nil {

@@ -154,6 +406,7 @@ func getProviderOptions(model Model, tp catwalk.Type) fantasy.ProviderOptions {

154

406

155 readers := []io.Reader{

407 readers := []io.Reader{

156 bytes.NewReader(catwalkOpts),

408 bytes.NewReader(catwalkOpts),

409+ bytes.NewReader(providerCfgOpts),

157 bytes.NewReader(cfgOpts),

410 bytes.NewReader(cfgOpts),

158 }

411 }

159

412

@@ -171,11 +424,16 @@ func getProviderOptions(model Model, tp catwalk.Type) fantasy.ProviderOptions {

171 return options

424 return options

172 }

425 }

173

426

427+ reasoningEffort := effectiveReasoningEffort(model)

428+ shouldSetEffort := model.CatwalkCfg.CanReason &&

429+ reasoningEffort != "" &&

430+ slices.Contains(model.CatwalkCfg.ReasoningLevels, reasoningEffort)

431+

174− switch tp {

432+ switch providerCfg.Type {

175− case openai.Name:

433+ case openai.Name, azure.Name:

176 _, hasReasoningEffort := mergedOptions["reasoning_effort"]

434 _, hasReasoningEffort := mergedOptions["reasoning_effort"]

177− if !hasReasoningEffort && model.ModelCfg.ReasoningEffort != "" {

435+ if !hasReasoningEffort && shouldSetEffort {

178− mergedOptions["reasoning_effort"] = model.ModelCfg.ReasoningEffort

436+ mergedOptions["reasoning_effort"] = reasoningEffort

179 }

437 }

180 if openai.IsResponsesModel(model.CatwalkCfg.ID) {

438 if openai.IsResponsesModel(model.CatwalkCfg.ID) {

181 if openai.IsResponsesReasoningModel(model.CatwalkCfg.ID) {

439 if openai.IsResponsesReasoningModel(model.CatwalkCfg.ID) {

@@ -192,14 +450,37 @@ func getProviderOptions(model Model, tp catwalk.Type) fantasy.ProviderOptions {

192 options[openai.Name] = parsed

450 options[openai.Name] = parsed

193 }

451 }

194 }

452 }

453+

195− case anthropic.Name:

454+ case anthropic.Name, bedrock.Name:

455+ var (

196− _, hasThink := mergedOptions["thinking"]

456+ _, hasEffort = mergedOptions["effort"]

197− if !hasThink && model.ModelCfg.Think {

198− mergedOptions["thinking"] = map[string]any{

457+ _, hasThink = mergedOptions["thinking"]

199− // TODO: kujtim see if we need to make this dynamic

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:

200− "budget_tokens": 2000,

480+ mergedOptions["thinking"] = map[string]any{"budget_tokens": 2000}

201 }

481 }

202 }

482 }

483+

203 parsed, err := anthropic.ParseOptions(mergedOptions)

484 parsed, err := anthropic.ParseOptions(mergedOptions)

204 if err == nil {

485 if err == nil {

205 options[anthropic.Name] = parsed

486 options[anthropic.Name] = parsed

@@ -207,54 +488,130 @@ func getProviderOptions(model Model, tp catwalk.Type) fantasy.ProviderOptions {

207

488

208 case openrouter.Name:

489 case openrouter.Name:

209 _, hasReasoning := mergedOptions["reasoning"]

490 _, hasReasoning := mergedOptions["reasoning"]

210− if !hasReasoning && model.ModelCfg.ReasoningEffort != "" {

491+ if !hasReasoning && shouldSetEffort {

211 mergedOptions["reasoning"] = map[string]any{

492 mergedOptions["reasoning"] = map[string]any{

212 "enabled": true,

493 "enabled": true,

213− "effort": model.ModelCfg.ReasoningEffort,

494+ "effort": reasoningEffort,

214 }

495 }

215 }

496 }

216 parsed, err := openrouter.ParseOptions(mergedOptions)

497 parsed, err := openrouter.ParseOptions(mergedOptions)

217 if err == nil {

498 if err == nil {

218 options[openrouter.Name] = parsed

499 options[openrouter.Name] = parsed

219 }

500 }

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+

220 case google.Name:

515 case google.Name:

221 _, hasReasoning := mergedOptions["thinking_config"]

516 _, hasReasoning := mergedOptions["thinking_config"]

222 if !hasReasoning {

517 if !hasReasoning {

518+ if strings.HasPrefix(model.CatwalkCfg.ID, "gemini-2") {

223− mergedOptions["thinking_config"] = map[string]any{

519+ mergedOptions["thinking_config"] = map[string]any{

224− "thinking_budget": 2000,

520+ "thinking_budget": 2000,

521+ "include_thoughts": true,

522+ }

523+ } else {

524+ mergedOptions["thinking_config"] = map[string]any{

525+ "thinking_level": reasoningEffort,

225− "include_thoughts": true,

526+ "include_thoughts": true,

527+ }

226 }

528 }

227 }

529 }

228 parsed, err := google.ParseOptions(mergedOptions)

530 parsed, err := google.ParseOptions(mergedOptions)

229 if err == nil {

531 if err == nil {

230 options[google.Name] = parsed

532 options[google.Name] = parsed

231 }

533 }

232− case azure.Name:

534+

535+ case openaicompat.Name, hyper.Name:

536+ extraBody := make(map[string]any)

537+

233 _, hasReasoningEffort := mergedOptions["reasoning_effort"]

538 _, hasReasoningEffort := mergedOptions["reasoning_effort"]

234− if !hasReasoningEffort && model.ModelCfg.ReasoningEffort != "" {

539+ if !hasReasoningEffort && shouldSetEffort {

235− mergedOptions["reasoning_effort"] = model.ModelCfg.ReasoningEffort

540+ switch providerCfg.ID {

236− }

541+ case string(catwalk.InferenceProviderIoNet):

237− // azure uses the same options as openaicompat

542+ extraBody["reasoning"] = map[string]string{"effort": reasoningEffort}

238− parsed, err := openaicompat.ParseOptions(mergedOptions)

543+ default:

239− if err == nil {

544+ mergedOptions["reasoning_effort"] = reasoningEffort

240− options[azure.Name] = parsed

545+ }

241 }

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 {

242− case openaicompat.Name:

553+ case hyper.Name:

243− _, hasReasoningEffort := mergedOptions["reasoning_effort"]

554+ extraBody["thinking"] = model.ModelCfg.Think

244− if !hasReasoningEffort && model.ModelCfg.ReasoningEffort != "" {

555+ case string(catwalk.InferenceProviderIoNet):

245− mergedOptions["reasoning_effort"] = model.ModelCfg.ReasoningEffort

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+ }

246 }

590 }

591+

592+ mergedOptions["extra_body"] = extraBody

593+

247 parsed, err := openaicompat.ParseOptions(mergedOptions)

594 parsed, err := openaicompat.ParseOptions(mergedOptions)

248 if err == nil {

595 if err == nil {

249 options[openaicompat.Name] = parsed

596 options[openaicompat.Name] = parsed

250 }

597 }

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+ }

251 }

608 }

252

609

253 return options

610 return options

254}

611}

255

612

256−func mergeCallOptions(model Model, tp catwalk.Type) (fantasy.ProviderOptions, *float64, *float64, *int64, *float64, *float64) {

613+func mergeCallOptions(model Model, cfg config.ProviderConfig) (fantasy.ProviderOptions, *float64, *float64, *int64, *float64, *float64) {

257− modelOptions := getProviderOptions(model, tp)

614+ modelOptions := getProviderOptions(model, cfg)

258 temp := cmp.Or(model.ModelCfg.Temperature, model.CatwalkCfg.Options.Temperature)

615 temp := cmp.Or(model.ModelCfg.Temperature, model.CatwalkCfg.Options.Temperature)

259 topP := cmp.Or(model.ModelCfg.TopP, model.CatwalkCfg.Options.TopP)

616 topP := cmp.Or(model.ModelCfg.TopP, model.CatwalkCfg.Options.TopP)

260 topK := cmp.Or(model.ModelCfg.TopK, model.CatwalkCfg.Options.TopK)

617 topK := cmp.Or(model.ModelCfg.TopK, model.CatwalkCfg.Options.TopK)

@@ -263,25 +620,83 @@ func mergeCallOptions(model Model, tp catwalk.Type) (fantasy.ProviderOptions, *f

263 return modelOptions, temp, topP, topK, freqPenalty, presPenalty

620 return modelOptions, temp, topP, topK, freqPenalty, presPenalty

264}

621}

265

622

266−func (c *coordinator) buildAgent(ctx context.Context, prompt *prompt.Prompt, agent config.Agent) (SessionAgent, error) {

623+// cachedMergeCallOptions wraps mergeCallOptions with a memoization cache.

267− large, small, err := c.buildAgentModels(ctx)

624+// The provider options JSON merge is expensive (3× marshal + merge +

268− if err != nil {

625+// unmarshal) and the inputs rarely change between turns. The cache key

269− return nil, err

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

270− }

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+}

271

655

272− systemPrompt, err := prompt.Build(large.Model.Provider(), large.Model.Model(), *c.cfg)

656+func (c *coordinator) buildAgent(ctx context.Context, prompt *prompt.Prompt, agent config.Agent, isSubAgent bool) (SessionAgent, error) {

657+ large, small, err := c.buildAgentModels(ctx, isSubAgent)

273 if err != nil {

658 if err != nil {

274 return nil, err

659 return nil, err

275 }

660 }

276

661

277− tools, err := c.buildTools(ctx, agent)

662+ largeProviderCfg, _ := c.cfg.Config().Providers.Get(large.ModelCfg.Provider)

278− if err != nil {

279− return nil, err

280− }

281− return NewSessionAgent(SessionAgentOptions{large, small, systemPrompt, c.cfg.Options.DisableAutoSummarize, c.sessions, c.messages, tools}), nil

663+ 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,

676+ })

677+

678+ 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)

689+ if err != nil {

690+ return err

691+ }

692+ result.SetTools(tools)

693+ return nil

694+ })

695+

696+ return result, nil

282}

697}

283

698

284−func (c *coordinator) buildTools(ctx context.Context, agent config.Agent) ([]fantasy.AgentTool, error) {

699+func (c *coordinator) buildTools(ctx context.Context, agent config.Agent, isSubAgent bool) ([]fantasy.AgentTool, error) {

285 var allTools []fantasy.AgentTool

700 var allTools []fantasy.AgentTool

286 if slices.Contains(agent.AllowedTools, AgentToolName) {

701 if slices.Contains(agent.AllowedTools, AgentToolName) {

287 agentTool, err := c.agentTool(ctx)

702 agentTool, err := c.agentTool(ctx)

@@ -291,22 +706,61 @@ func (c *coordinator) buildTools(ctx context.Context, agent config.Agent) ([]fan

291 allTools = append(allTools, agentTool)

706 allTools = append(allTools, agentTool)

292 }

707 }

293

708

709+ if slices.Contains(agent.AllowedTools, tools.AgenticFetchToolName) {

710+ agenticFetchTool, err := c.agenticFetchTool(ctx, nil)

711+ if err != nil {

712+ return nil, err

713+ }

714+ allTools = append(allTools, agenticFetchTool)

715+ }

716+

717+ // 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

722+ }

723+ }

724+

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+

294− allTools = append(allTools,

733+ allTools = append(

734+ allTools,

295− tools.NewBashTool(c.permissions, c.cfg.WorkingDir(), c.cfg.Options.Attribution),

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),

738+ tools.NewJobOutputTool(),

739+ tools.NewJobKillTool(),

296 tools.NewDownloadTool(c.permissions, c.cfg.WorkingDir(), nil),

740 tools.NewDownloadTool(c.permissions, c.cfg.WorkingDir(), nil),

297− tools.NewEditTool(c.lspClients, c.permissions, c.history, c.cfg.WorkingDir()),

741+ tools.NewEditTool(c.lspManager, c.permissions, c.history, c.filetracker, c.cfg.WorkingDir()),

298− tools.NewMultiEditTool(c.lspClients, c.permissions, c.history, c.cfg.WorkingDir()),

742+ tools.NewMultiEditTool(c.lspManager, c.permissions, c.history, c.filetracker, c.cfg.WorkingDir()),

299 tools.NewFetchTool(c.permissions, c.cfg.WorkingDir(), nil),

743 tools.NewFetchTool(c.permissions, c.cfg.WorkingDir(), nil),

300− tools.NewGlobTool(c.cfg.WorkingDir()),

744+ tools.NewGlobTool(c.cfg.WorkingDir(), c.cfg.Config().Tools.Glob),

301− tools.NewGrepTool(c.cfg.WorkingDir()),

745+ tools.NewGrepTool(c.cfg.WorkingDir(), c.cfg.Config().Tools.Grep),

302− tools.NewLsTool(c.permissions, c.cfg.WorkingDir(), c.cfg.Tools.Ls),

746+ tools.NewLsTool(c.permissions, c.cfg.WorkingDir(), c.cfg.Config().Tools.Ls),

303 tools.NewSourcegraphTool(nil),

747 tools.NewSourcegraphTool(nil),

748+ tools.NewTodosTool(c.sessions),

304− tools.NewViewTool(c.lspClients, c.permissions, c.cfg.WorkingDir()),

749+ tools.NewViewTool(c.lspManager, c.permissions, c.filetracker, c.skillTracker, c.cfg.WorkingDir(), c.cfg.Config().Options.SkillsPaths...),

305− tools.NewWriteTool(c.lspClients, c.permissions, c.history, c.cfg.WorkingDir()),

750+ tools.NewWriteTool(c.lspManager, c.permissions, c.history, c.filetracker, c.cfg.WorkingDir()),

306 )

751 )

307

752

308− if len(c.cfg.LSP) > 0 {

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 {

309− allTools = append(allTools, tools.NewDiagnosticsTool(c.lspClients), tools.NewReferencesTool(c.lspClients))

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+ )

310 }

764 }

311

765

312 var filteredTools []fantasy.AgentTool

766 var filteredTools []fantasy.AgentTool

@@ -316,64 +770,70 @@ func (c *coordinator) buildTools(ctx context.Context, agent config.Agent) ([]fan

316 }

770 }

317 }

771 }

318

772

319− mcpTools := tools.GetMCPTools(context.Background(), c.permissions, c.cfg)

773+ for _, tool := range tools.GetMCPTools(c.permissions, c.cfg, c.cfg.WorkingDir()) {

320−

321− for _, mcpTool := range mcpTools {

322 if agent.AllowedMCP == nil {

774 if agent.AllowedMCP == nil {

323 // No MCP restrictions

775 // No MCP restrictions

324− filteredTools = append(filteredTools, mcpTool)

776+ filteredTools = append(filteredTools, tool)

777+ continue

778+ }

325− } else if len(agent.AllowedMCP) == 0 {

779+ if len(agent.AllowedMCP) == 0 {

326− // no mcps allowed

780+ // No MCPs allowed

781+ slog.Debug("No MCPs allowed", "tool", tool.Name(), "agent", agent.Name)

327 break

782 break

328 }

783 }

329

784

330 for mcp, tools := range agent.AllowedMCP {

785 for mcp, tools := range agent.AllowedMCP {

331− if mcp == mcpTool.MCP() {

786+ if mcp != tool.MCP() {

332− if len(tools) == 0 {

787+ continue

333− filteredTools = append(filteredTools, mcpTool)

788+ }

334− }

789+ if len(tools) == 0 || slices.Contains(tools, tool.MCPToolName()) {

335− for _, t := range tools {

336− if t == mcpTool.MCPToolName() {

337− filteredTools = append(filteredTools, mcpTool)

790+ filteredTools = append(filteredTools, tool)

338− }

339− }

340 break

791 break

341 }

792 }

793+ slog.Debug("MCP not allowed", "tool", tool.Name(), "agent", agent.Name)

342 }

794 }

343 }

795 }

344 slices.SortFunc(filteredTools, func(a, b fantasy.AgentTool) int {

796 slices.SortFunc(filteredTools, func(a, b fantasy.AgentTool) int {

345 return strings.Compare(a.Info().Name, b.Info().Name)

797 return strings.Compare(a.Info().Name, b.Info().Name)

346 })

798 })

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+

347 return filteredTools, nil

807 return filteredTools, nil

348}

808}

349

809

350// TODO: when we support multiple agents we need to change this so that we pass in the agent specific model config

810// TODO: when we support multiple agents we need to change this so that we pass in the agent specific model config

351−func (c *coordinator) buildAgentModels(ctx context.Context) (Model, Model, error) {

811+func (c *coordinator) buildAgentModels(ctx context.Context, isSubAgent bool) (Model, Model, error) {

352− largeModelCfg, ok := c.cfg.Models[config.SelectedModelTypeLarge]

812+ largeModelCfg, ok := c.cfg.Config().Models[config.SelectedModelTypeLarge]

353 if !ok {

813 if !ok {

354− return Model{}, Model{}, errors.New("large model not selected")

814+ return Model{}, Model{}, errLargeModelNotSelected

355 }

815 }

356− smallModelCfg, ok := c.cfg.Models[config.SelectedModelTypeSmall]

816+ smallModelCfg, ok := c.cfg.Config().Models[config.SelectedModelTypeSmall]

357 if !ok {

817 if !ok {

358− return Model{}, Model{}, errors.New("small model not selected")

818+ return Model{}, Model{}, errSmallModelNotSelected

359 }

819 }

360

820

361− largeProviderCfg, ok := c.cfg.Providers.Get(largeModelCfg.Provider)

821+ largeProviderCfg, ok := c.cfg.Config().Providers.Get(largeModelCfg.Provider)

362 if !ok {

822 if !ok {

363− return Model{}, Model{}, errors.New("large model provider not configured")

823+ return Model{}, Model{}, errLargeModelProviderNotConfigured

364 }

824 }

365

825

366− largeProvider, err := c.buildProvider(largeProviderCfg, largeModelCfg)

826+ largeProvider, err := c.buildProvider(largeProviderCfg, largeModelCfg, isSubAgent)

367 if err != nil {

827 if err != nil {

368 return Model{}, Model{}, err

828 return Model{}, Model{}, err

369 }

829 }

370

830

371− smallProviderCfg, ok := c.cfg.Providers.Get(smallModelCfg.Provider)

831+ smallProviderCfg, ok := c.cfg.Config().Providers.Get(smallModelCfg.Provider)

372 if !ok {

832 if !ok {

373− return Model{}, Model{}, errors.New("large model provider not configured")

833+ return Model{}, Model{}, errSmallModelProviderNotConfigured

374 }

834 }

375

835

376− smallProvider, err := c.buildProvider(smallProviderCfg, largeModelCfg)

836+ smallProvider, err := c.buildProvider(smallProviderCfg, smallModelCfg, true)

377 if err != nil {

837 if err != nil {

378 return Model{}, Model{}, err

838 return Model{}, Model{}, err

379 }

839 }

@@ -393,18 +853,29 @@ func (c *coordinator) buildAgentModels(ctx context.Context) (Model, Model, error

393 }

853 }

394

854

395 if largeCatwalkModel == nil {

855 if largeCatwalkModel == nil {

396− return Model{}, Model{}, errors.New("large model not found in provider config")

856+ return Model{}, Model{}, errLargeModelNotFound

397 }

857 }

398

858

399 if smallCatwalkModel == nil {

859 if smallCatwalkModel == nil {

400− return Model{}, Model{}, errors.New("snall model not found in provider config")

860+ return Model{}, Model{}, errSmallModelNotFound

401 }

861 }

402

862

863+ largeModelID := largeModelCfg.Model

864+ smallModelID := smallModelCfg.Model

865+

866+ if largeModelCfg.Provider == openrouter.Name && isExactoSupported(largeModelID) {

867+ largeModelID += ":exacto"

868+ }

869+

870+ if smallModelCfg.Provider == openrouter.Name && isExactoSupported(smallModelID) {

871+ smallModelID += ":exacto"

872+ }

873+

403− largeModel, err := largeProvider.LanguageModel(ctx, largeModelCfg.Model)

874+ largeModel, err := largeProvider.LanguageModel(ctx, largeModelID)

404 if err != nil {

875 if err != nil {

405 return Model{}, Model{}, err

876 return Model{}, Model{}, err

406 }

877 }

407− smallModel, err := smallProvider.LanguageModel(ctx, smallModelCfg.Model)

878+ smallModel, err := smallProvider.LanguageModel(ctx, smallModelID)

408 if err != nil {

879 if err != nil {

409 return Model{}, Model{}, err

880 return Model{}, Model{}, err

410 }

881 }

@@ -413,29 +884,29 @@ func (c *coordinator) buildAgentModels(ctx context.Context) (Model, Model, error

413 Model: largeModel,

884 Model: largeModel,

414 CatwalkCfg: *largeCatwalkModel,

885 CatwalkCfg: *largeCatwalkModel,

415 ModelCfg: largeModelCfg,

886 ModelCfg: largeModelCfg,

887+ FlatRate: largeProviderCfg.FlatRate,

416 }, Model{

888 }, Model{

417 Model: smallModel,

889 Model: smallModel,

418 CatwalkCfg: *smallCatwalkModel,

890 CatwalkCfg: *smallCatwalkModel,

419 ModelCfg: smallModelCfg,

891 ModelCfg: smallModelCfg,

892+ FlatRate: smallProviderCfg.FlatRate,

420 }, nil

893 }, nil

421}

894}

422

895

423−func (c *coordinator) buildAnthropicProvider(baseURL, apiKey string, headers map[string]string) (fantasy.Provider, error) {

896+func (c *coordinator) buildAnthropicProvider(baseURL, apiKey string, headers map[string]string, providerID string) (fantasy.Provider, error) {

424− hasBearerAuth := false

425− for key := range headers {

426− if strings.ToLower(key) == "authorization" {

427− hasBearerAuth = true

428− break

429− }

430− }

431− if hasBearerAuth {

432− apiKey = "" // clear apiKey to avoid using X-Api-Key header

433− }

434−

435 var opts []anthropic.Option

897 var opts []anthropic.Option

436

898

437− if apiKey != "" {

899+ switch {

900+ case strings.HasPrefix(apiKey, "Bearer "):

901+ // NOTE: Prevent the SDK from picking up the API key from env.

902+ 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 != "":

438− // Use standard X-Api-Key header

909+ // X-Api-Key header

439 opts = append(opts, anthropic.WithAPIKey(apiKey))

910 opts = append(opts, anthropic.WithAPIKey(apiKey))

440 }

911 }

441

912

@@ -447,11 +918,10 @@ func (c *coordinator) buildAnthropicProvider(baseURL, apiKey string, headers map

447 opts = append(opts, anthropic.WithBaseURL(baseURL))

918 opts = append(opts, anthropic.WithBaseURL(baseURL))

448 }

919 }

449

920

450− if c.cfg.Options.Debug {

921+ if c.cfg.Config().Options.Debug {

451 httpClient := log.NewHTTPClient()

922 httpClient := log.NewHTTPClient()

452 opts = append(opts, anthropic.WithHTTPClient(httpClient))

923 opts = append(opts, anthropic.WithHTTPClient(httpClient))

453 }

924 }

454−

455 return anthropic.New(opts...)

925 return anthropic.New(opts...)

456}

926}

457

927

@@ -460,7 +930,7 @@ func (c *coordinator) buildOpenaiProvider(baseURL, apiKey string, headers map[st

460 openai.WithAPIKey(apiKey),

930 openai.WithAPIKey(apiKey),

461 openai.WithUseResponsesAPI(),

931 openai.WithUseResponsesAPI(),

462 }

932 }

463− if c.cfg.Options.Debug {

933+ if c.cfg.Config().Options.Debug {

464 httpClient := log.NewHTTPClient()

934 httpClient := log.NewHTTPClient()

465 opts = append(opts, openai.WithHTTPClient(httpClient))

935 opts = append(opts, openai.WithHTTPClient(httpClient))

466 }

936 }

@@ -477,7 +947,7 @@ func (c *coordinator) buildOpenrouterProvider(_, apiKey string, headers map[stri

477 opts := []openrouter.Option{

947 opts := []openrouter.Option{

478 openrouter.WithAPIKey(apiKey),

948 openrouter.WithAPIKey(apiKey),

479 }

949 }

480− if c.cfg.Options.Debug {

950+ if c.cfg.Config().Options.Debug {

481 httpClient := log.NewHTTPClient()

951 httpClient := log.NewHTTPClient()

482 opts = append(opts, openrouter.WithHTTPClient(httpClient))

952 opts = append(opts, openrouter.WithHTTPClient(httpClient))

483 }

953 }

@@ -487,19 +957,54 @@ func (c *coordinator) buildOpenrouterProvider(_, apiKey string, headers map[stri

487 return openrouter.New(opts...)

957 return openrouter.New(opts...)

488}

958}

489

959

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+

490−func (c *coordinator) buildOpenaiCompatProvider(baseURL, apiKey string, headers map[string]string) (fantasy.Provider, error) {

974+func (c *coordinator) buildOpenaiCompatProvider(baseURL, apiKey string, headers map[string]string, extraBody map[string]any, providerID string, isSubAgent bool) (fantasy.Provider, error) {

491 opts := []openaicompat.Option{

975 opts := []openaicompat.Option{

492 openaicompat.WithBaseURL(baseURL),

976 openaicompat.WithBaseURL(baseURL),

493 openaicompat.WithAPIKey(apiKey),

977 openaicompat.WithAPIKey(apiKey),

494 }

978 }

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+ }

495− if c.cfg.Options.Debug {

993+ if httpClient == nil && c.cfg.Config().Options.Debug {

496− httpClient := log.NewHTTPClient()

994+ httpClient = log.NewHTTPClient()

995+ }

996+ if httpClient != nil {

497 opts = append(opts, openaicompat.WithHTTPClient(httpClient))

997 opts = append(opts, openaicompat.WithHTTPClient(httpClient))

498 }

998 }

999+

499 if len(headers) > 0 {

1000 if len(headers) > 0 {

500 opts = append(opts, openaicompat.WithHeaders(headers))

1001 opts = append(opts, openaicompat.WithHeaders(headers))

501 }

1002 }

502

1003

1004+ for extraKey, extraValue := range extraBody {

1005+ opts = append(opts, openaicompat.WithSDKOptions(openaisdk.WithJSONSet(extraKey, extraValue)))

1006+ }

1007+

503 return openaicompat.New(opts...)

1008 return openaicompat.New(opts...)

504}

1009}

505

1010

@@ -507,8 +1012,9 @@ func (c *coordinator) buildAzureProvider(baseURL, apiKey string, headers map[str

507 opts := []azure.Option{

1012 opts := []azure.Option{

508 azure.WithBaseURL(baseURL),

1013 azure.WithBaseURL(baseURL),

509 azure.WithAPIKey(apiKey),

1014 azure.WithAPIKey(apiKey),

1015+ azure.WithUseResponsesAPI(),

510 }

1016 }

511− if c.cfg.Options.Debug {

1017+ if c.cfg.Config().Options.Debug {

512 httpClient := log.NewHTTPClient()

1018 httpClient := log.NewHTTPClient()

513 opts = append(opts, azure.WithHTTPClient(httpClient))

1019 opts = append(opts, azure.WithHTTPClient(httpClient))

514 }

1020 }

@@ -525,12 +1031,41 @@ func (c *coordinator) buildAzureProvider(baseURL, apiKey string, headers map[str

525 return azure.New(opts...)

1031 return azure.New(opts...)

526}

1032}

527

1033

1034+func (c *coordinator) buildBedrockProvider(apiKey string, headers map[string]string, providerID string) (fantasy.Provider, error) {

1035+ var opts []bedrock.Option

1036+ if c.cfg.Config().Options.Debug {

1037+ httpClient := log.NewHTTPClient()

1038+ opts = append(opts, bedrock.WithHTTPClient(httpClient))

1039+ }

1040+ if len(headers) > 0 {

1041+ opts = append(opts, bedrock.WithHeaders(headers))

1042+ }

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"))

1058+ }

1059+

1060+ return bedrock.New(opts...)

1061+}

1062+

528func (c *coordinator) buildGoogleProvider(baseURL, apiKey string, headers map[string]string) (fantasy.Provider, error) {

1063func (c *coordinator) buildGoogleProvider(baseURL, apiKey string, headers map[string]string) (fantasy.Provider, error) {

529 opts := []google.Option{

1064 opts := []google.Option{

530 google.WithBaseURL(baseURL),

1065 google.WithBaseURL(baseURL),

531 google.WithGeminiAPIKey(apiKey),

1066 google.WithGeminiAPIKey(apiKey),

532 }

1067 }

533− if c.cfg.Options.Debug {

1068+ if c.cfg.Config().Options.Debug {

534 httpClient := log.NewHTTPClient()

1069 httpClient := log.NewHTTPClient()

535 opts = append(opts, google.WithHTTPClient(httpClient))

1070 opts = append(opts, google.WithHTTPClient(httpClient))

536 }

1071 }

@@ -542,7 +1077,7 @@ func (c *coordinator) buildGoogleProvider(baseURL, apiKey string, headers map[st

542

1077

543func (c *coordinator) buildGoogleVertexProvider(headers map[string]string, options map[string]string) (fantasy.Provider, error) {

1078func (c *coordinator) buildGoogleVertexProvider(headers map[string]string, options map[string]string) (fantasy.Provider, error) {

544 opts := []google.Option{}

1079 opts := []google.Option{}

545− if c.cfg.Options.Debug {

1080+ if c.cfg.Config().Options.Debug {

546 httpClient := log.NewHTTPClient()

1081 httpClient := log.NewHTTPClient()

547 opts = append(opts, google.WithHTTPClient(httpClient))

1082 opts = append(opts, google.WithHTTPClient(httpClient))

548 }

1083 }

@@ -562,51 +1097,161 @@ func (c *coordinator) isAnthropicThinking(model config.SelectedModel) bool {

562 if model.Think {

1097 if model.Think {

563 return true

1098 return true

564 }

1099 }

565−

566− if model.ProviderOptions == nil {

567− return false

568− }

569−

570 opts, err := anthropic.ParseOptions(model.ProviderOptions)

1100 opts, err := anthropic.ParseOptions(model.ProviderOptions)

571− if err != nil {

572− return false

573− }

574− if opts.Thinking != nil {

1101+ return err == nil && opts.Thinking != nil

575− return true

576− }

577− return false

578}

1102}

579

1103

580−func (c *coordinator) buildProvider(providerCfg config.ProviderConfig, model config.SelectedModel) (fantasy.Provider, error) {

1104+func (c *coordinator) buildProvider(providerCfg config.ProviderConfig, model config.SelectedModel, isSubAgent bool) (fantasy.Provider, error) {

581− headers := providerCfg.ExtraHeaders

1105+ headers := maps.Clone(providerCfg.ExtraHeaders)

1106+ if headers == nil {

1107+ headers = make(map[string]string)

1108+ }

582

1109

583 // handle special headers for anthropic

1110 // handle special headers for anthropic

584 if providerCfg.Type == anthropic.Name && c.isAnthropicThinking(model) {

1111 if providerCfg.Type == anthropic.Name && c.isAnthropicThinking(model) {

1112+ if v, ok := headers["anthropic-beta"]; ok {

585− headers["anthropic-beta"] = "interleaved-thinking-2025-05-14"

1113+ headers["anthropic-beta"] = v + ",interleaved-thinking-2025-05-14"

1114+ } else {

1115+ headers["anthropic-beta"] = "interleaved-thinking-2025-05-14"

1116+ }

586 }

1117 }

587

1118

588− // TODO: make sure we have

589 apiKey, _ := c.cfg.Resolve(providerCfg.APIKey)

1119 apiKey, _ := c.cfg.Resolve(providerCfg.APIKey)

590 baseURL, _ := c.cfg.Resolve(providerCfg.BaseURL)

1120 baseURL, _ := c.cfg.Resolve(providerCfg.BaseURL)

591

1121

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+

592 switch providerCfg.Type {

1198 switch providerCfg.Type {

593 case openai.Name:

1199 case openai.Name:

594 return c.buildOpenaiProvider(baseURL, apiKey, headers)

1200 return c.buildOpenaiProvider(baseURL, apiKey, headers)

595 case anthropic.Name:

1201 case anthropic.Name:

596− return c.buildAnthropicProvider(baseURL, apiKey, headers)

1202+ return c.buildAnthropicProvider(baseURL, apiKey, headers, providerCfg.ID)

597 case openrouter.Name:

1203 case openrouter.Name:

598 return c.buildOpenrouterProvider(baseURL, apiKey, headers)

1204 return c.buildOpenrouterProvider(baseURL, apiKey, headers)

1205+ case vercel.Name:

1206+ return c.buildVercelProvider(baseURL, apiKey, headers)

599 case azure.Name:

1207 case azure.Name:

600 return c.buildAzureProvider(baseURL, apiKey, headers, providerCfg.ExtraParams)

1208 return c.buildAzureProvider(baseURL, apiKey, headers, providerCfg.ExtraParams)

1209+ case bedrock.Name:

1210+ return c.buildBedrockProvider(apiKey, headers, providerCfg.ID)

601 case google.Name:

1211 case google.Name:

602 return c.buildGoogleProvider(baseURL, apiKey, headers)

1212 return c.buildGoogleProvider(baseURL, apiKey, headers)

603− case "vertexai":

1213+ case "google-vertex":

604 return c.buildGoogleVertexProvider(headers, providerCfg.ExtraParams)

1214 return c.buildGoogleVertexProvider(headers, providerCfg.ExtraParams)

605− case openaicompat.Name:

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):

1221+ if providerCfg.ExtraBody == nil {

1222+ providerCfg.ExtraBody = map[string]any{}

1223+ }

1224+ providerCfg.ExtraBody["tool_stream"] = true

1225+ }

606− return c.buildOpenaiCompatProvider(baseURL, apiKey, headers)

1226+ return c.buildOpenaiCompatProvider(baseURL, apiKey, headers, providerCfg.ExtraBody, providerCfg.ID, isSubAgent)

607 default:

1227 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+ }

608− return nil, errors.New("provider type not supported")

1233+ return nil, fmt.Errorf("provider type not supported: %q", providerCfg.Type)

1234+ }

1235+}

1236+

1237+func isExactoSupported(modelID string) bool {

1238+ supportedModels := []string{

1239+ "moonshotai/kimi-k2-0905",

1240+ "deepseek/deepseek-v3.1-terminus",

1241+ "z-ai/glm-4.6",

1242+ "openai/gpt-oss-120b",

1243+ "qwen/qwen3-coder",

609 }

1244 }

1245+ return slices.Contains(supportedModels, modelID)

1246+}

1247+

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)

610}

1255}

611

1256

612func (c *coordinator) Cancel(sessionID string) {

1257func (c *coordinator) Cancel(sessionID string) {

@@ -635,21 +1280,40 @@ func (c *coordinator) Model() Model {

635

1280

636func (c *coordinator) UpdateModels(ctx context.Context) error {

1281func (c *coordinator) UpdateModels(ctx context.Context) error {

637 // build the models again so we make sure we get the latest config

1282 // build the models again so we make sure we get the latest config

638− large, small, err := c.buildAgentModels(ctx)

1283+ large, small, err := c.buildAgentModels(ctx, false)

639 if err != nil {

1284 if err != nil {

640 return err

1285 return err

641 }

1286 }

642 c.currentAgent.SetModels(large, small)

1287 c.currentAgent.SetModels(large, small)

643

1288

1289+ cfg := c.cfg.Config()

644− agentCfg, ok := c.cfg.Agents[config.AgentCoder]

1290+ agentCfg, ok := cfg.Agents[config.AgentCoder]

645 if !ok {

1291 if !ok {

646− return errors.New("coder agent not configured")

1292+ return errCoderAgentNotConfigured

647 }

1293 }

648

1294

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+

649− tools, err := c.buildTools(ctx, agentCfg)

1306+ tools, err := c.buildTools(ctx, agentCfg, false)

650 if err != nil {

1307 if err != nil {

651 return err

1308 return err

652 }

1309 }

1310+

1311+ c.toolsCacheMu.Lock()

1312+ c.toolsCache = tools

1313+ c.toolsCacheCfg = cfg

1314+ c.toolsCacheMCP = mcpGen

1315+ c.toolsCacheMu.Unlock()

1316+

653 c.currentAgent.SetTools(tools)

1317 c.currentAgent.SetTools(tools)

654 return nil

1318 return nil

655}

1319}

@@ -658,10 +1322,340 @@ func (c *coordinator) QueuedPrompts(sessionID string) int {

658 return c.currentAgent.QueuedPrompts(sessionID)

1322 return c.currentAgent.QueuedPrompts(sessionID)

659}

1323}

660

1324

1325+func (c *coordinator) QueuedPromptsList(sessionID string) []string {

1326+ return c.currentAgent.QueuedPromptsList(sessionID)

1327+}

1328+

661func (c *coordinator) Summarize(ctx context.Context, sessionID string) error {

1329func (c *coordinator) Summarize(ctx context.Context, sessionID string) error {

662− providerCfg, ok := c.cfg.Providers.Get(c.currentAgent.Model().ModelCfg.Provider)

1330+ providerCfg, ok := c.cfg.Config().Providers.Get(c.currentAgent.Model().ModelCfg.Provider)

663 if !ok {

1331 if !ok {

664− return errors.New("model provider not configured")

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)

665 }

1337 }

1338+

1339+ summarize := func() error {

666− return c.currentAgent.Summarize(ctx, sessionID, getProviderOptions(c.currentAgent.Model(), providerCfg.Type))

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

1390+ }

1391+}

1392+

1393+func (c *coordinator) isUnauthorized(err error) bool {

1394+ var providerErr *fantasy.ProviderError

1395+ return errors.As(err, &providerErr) && providerErr.StatusCode == http.StatusUnauthorized

1396+}

1397+

1398+func (c *coordinator) refreshOAuth2Token(ctx context.Context, providerCfg config.ProviderConfig) error {

1399+ if err := c.cfg.RefreshOAuthToken(ctx, config.ScopeGlobal, providerCfg.ID); err != nil {

1400+ slog.Error("Failed to refresh OAuth token after 401 error", "provider", providerCfg.ID, "error", err)

1401+ return err

1402+ }

1403+ if err := c.UpdateModels(ctx); err != nil {

1404+ return err

1405+ }

1406+ return nil

1407+}

1408+

1409+func (c *coordinator) refreshApiKeyTemplate(ctx context.Context, providerCfg config.ProviderConfig) error {

1410+ newAPIKey, err := c.cfg.Resolve(providerCfg.APIKeyTemplate)

1411+ if err != nil {

1412+ slog.Error("Failed to re-resolve API key after 401 error", "provider", providerCfg.ID, "error", err)

1413+ return err

1414+ }

1415+

1416+ providerCfg.APIKey = newAPIKey

1417+ c.cfg.Config().Providers.Set(providerCfg.ID, providerCfg)

1418+

1419+ if err := c.UpdateModels(ctx); err != nil {

1420+ return err

1421+ }

1422+ return nil

1423+}

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+ )

667}

1661}

internal/agent/coordinator_test.gonew file+554

@@ -0,0 +1,554 @@

1+package agent

3+import (

4+ "context"

5+ "errors"

6+ "testing"

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.gonew file+447

@@ -0,0 +1,447 @@

1+package agent

3+import (

4+ "context"

5+ "errors"

6+ "sync/atomic"

7+ "testing"

8+ "time"

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/errors.go+1−8

@@ -1,9 +1,6 @@

1package agent

3−import (

3+import "errors"

4− "context"

5− "errors"

6−)

8var (

5var (

9 ErrRequestCancelled = errors.New("request canceled by user")

6 ErrRequestCancelled = errors.New("request canceled by user")

@@ -11,7 +8,3 @@ var (

11 ErrEmptyPrompt = errors.New("prompt is empty")

8 ErrEmptyPrompt = errors.New("prompt is empty")

12 ErrSessionMissing = errors.New("session id is missing")

9 ErrSessionMissing = errors.New("session id is missing")

13)

10)

14−

15−func isCancelledErr(err error) bool {

16− return errors.Is(err, context.Canceled) || errors.Is(err, ErrRequestCancelled)

17−}

internal/agent/event.gonew file+51

@@ -0,0 +1,51 @@

1+package agent

3+import (

4+ "time"

6+ "charm.land/fantasy"

7+ "github.com/charmbracelet/crush/internal/event"

8+)

10+func (a *sessionAgent) eventPromptSent(sessionID string) {

11+ event.PromptSent(

12+ a.eventCommon(sessionID, a.largeModel.Get())...,

13+ )

14+}

15+

16+func (a *sessionAgent) eventPromptResponded(sessionID string, duration time.Duration) {

17+ event.PromptResponded(

18+ append(

19+ a.eventCommon(sessionID, a.largeModel.Get()),

20+ "prompt duration pretty", duration.String(),

21+ "prompt duration in seconds", int64(duration.Seconds()),

22+ )...,

23+ )

24+}

25+

26+func (a *sessionAgent) eventTokensUsed(sessionID string, model Model, usage fantasy.Usage, cost float64) {

27+ event.TokensUsed(

28+ append(

29+ a.eventCommon(sessionID, model),

30+ "input tokens", usage.InputTokens,

31+ "output tokens", usage.OutputTokens,

32+ "cache read tokens", usage.CacheReadTokens,

33+ "cache creation tokens", usage.CacheCreationTokens,

34+ "total tokens", usage.InputTokens+usage.OutputTokens+usage.CacheReadTokens+usage.CacheCreationTokens,

35+ "cost", cost,

36+ )...,

37+ )

38+}

39+

40+func (a *sessionAgent) eventCommon(sessionID string, model Model) []any {

41+ m := model.ModelCfg

42+

43+ return []any{

44+ "session id", sessionID,

45+ "provider", m.Provider,

46+ "model", m.Model,

47+ "reasoning effort", m.ReasoningEffort,

48+ "thinking mode", m.Think,

49+ "yolo mode", a.isYolo,

50+ }

51+}

internal/agent/hooked_tool.gonew file+142

@@ -0,0 +1,142 @@

1+package agent

3+import (

4+ "context"

5+ "encoding/json"

6+ "fmt"

7+ "log/slog"

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.gonew file+147

@@ -0,0 +1,147 @@

1+package agent

3+import (

4+ "context"

5+ "testing"

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.gonew file+105

@@ -0,0 +1,105 @@

1+// Package hyper provides a fantasy.Provider that proxies requests to Hyper.

2+package hyper

4+import (

5+ "cmp"

6+ "context"

7+ _ "embed"

8+ "encoding/json"

9+ "fmt"

10+ "log/slog"

11+ "net/http"

12+ "os"

13+ "sync"

14+ "sync/atomic"

15+ "time"

16+

17+ "charm.land/catwalk/pkg/catwalk"

18+)

19+

20+//go:generate wget -O provider.json https://hyper.charm.land/v1/provider

21+

22+//go:embed provider.json

23+var embedded []byte

24+

25+// Embedded returns the embedded Hyper provider.

26+var Embedded = sync.OnceValue(func() catwalk.Provider {

27+ var provider catwalk.Provider

28+ 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"

33+ }

34+ return provider

35+})

36+

37+const (

38+ // Name is the default name of this meta provider.

39+ Name = "hyper"

40+ // DisplayName is the display name of Hyper.

41+ DisplayName = "Charm Hyper"

42+ // defaultBaseURL is the default proxy URL.

43+ defaultBaseURL = "https://hyper.charm.land"

44+)

45+

46+// BaseURL returns the base URL, which is either $HYPER_URL or the default.

47+var BaseURL = sync.OnceValue(func() string {

48+ return cmp.Or(os.Getenv("HYPER_URL"), defaultBaseURL)

49+})

50+

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

55+

56+// hasBalance tracks whether lastKnownBalance has been set.

57+var hasBalance atomic.Bool

58+

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)

63+}

64+

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+ )

81+ if err != nil {

82+ return 0, fmt.Errorf("could not create request: %w", err)

83+ }

84+ req.Header.Set("Authorization", "Bearer "+apiKey)

85+

86+ client := &http.Client{Timeout: 10 * time.Second}

87+ resp, err := client.Do(req)

88+ if err != nil {

89+ return 0, fmt.Errorf("failed to make request: %w", err)

90+ }

91+ defer resp.Body.Close()

92+

93+ if resp.StatusCode != http.StatusOK {

94+ return 0, fmt.Errorf("unexpected status code: %d", resp.StatusCode)

95+ }

96+

97+ var result struct {

98+ Balance int `json:"balance"`

99+ }

100+ if err := json.NewDecoder(resp.Body).Decode(&result); err != nil {

101+ return 0, fmt.Errorf("failed to decode response: %w", err)

102+ }

103+

104+ return result.Balance, nil

105+}

internal/agent/hyper/provider.jsonnew file+295

@@ -0,0 +1,295 @@

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+}

internal/agent/loop_detection.gonew file+92

@@ -0,0 +1,92 @@

1+package agent

3+import (

4+ "hash/fnv"

5+ "io"

7+ "charm.land/fantasy"

8+)

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.gonew file+205

@@ -0,0 +1,205 @@

1+package agent

3+import (

4+ "fmt"

5+ "testing"

7+ "charm.land/fantasy"

8+)

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.gonew file+63

@@ -0,0 +1,63 @@

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

6+// Type identifies the kind of agent notification.

7+type Type string

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+151−43

@@ -1,7 +1,10 @@

1package prompt

3import (

4+ "cmp"

5+ "context"

4 "fmt"

6 "fmt"

7+ "log/slog"

5 "os"

8 "os"

6 "path/filepath"

9 "path/filepath"

7 "runtime"

10 "runtime"

@@ -10,7 +13,10 @@ import (

10 "time"

13 "time"

12 "github.com/charmbracelet/crush/internal/config"

15 "github.com/charmbracelet/crush/internal/config"

16+ "github.com/charmbracelet/crush/internal/filepathext"

13 "github.com/charmbracelet/crush/internal/home"

17 "github.com/charmbracelet/crush/internal/home"

18+ "github.com/charmbracelet/crush/internal/shell"

19+ "github.com/charmbracelet/crush/internal/skills"

14)

20)

16// Prompt represents a template-based prompt generator.

22// Prompt represents a template-based prompt generator.

@@ -23,14 +29,17 @@ type Prompt struct {

23}

29}

25type PromptDat struct {

31type PromptDat struct {

26− Provider string

32+ Provider string

27− Model string

33+ Model string

28− Config config.Config

34+ Config config.Config

29− WorkingDir string

35+ WorkingDir string

30− IsGitRepo bool

36+ IsGitRepo bool

31− Platform string

37+ Platform string

38+ Date string

32− Date string

39+ GitStatus string

33− ContextFiles []ContextFile

40+ ContextFiles []ContextFile

41+ GlobalContextFiles []ContextFile

42+ AvailSkillXML string

34}

43}

36type ContextFile struct {

45type ContextFile struct {

@@ -70,13 +79,17 @@ func NewPrompt(name, promptTemplate string, opts ...Option) (*Prompt, error) {

70 return p, nil

79 return p, nil

71}

80}

73−func (p *Prompt) Build(provider, model string, cfg config.Config) (string, error) {

82+func (p *Prompt) Build(ctx context.Context, provider, model string, store *config.ConfigStore) (string, error) {

74 t, err := template.New(p.name).Parse(p.template)

83 t, err := template.New(p.name).Parse(p.template)

75 if err != nil {

84 if err != nil {

76 return "", fmt.Errorf("parsing template: %w", err)

85 return "", fmt.Errorf("parsing template: %w", err)

77 }

86 }

78 var sb strings.Builder

87 var sb strings.Builder

88+ d, err := p.promptData(ctx, provider, model, store)

89+ if err != nil {

90+ return "", err

91+ }

79− if err := t.Execute(&sb, p.promptData(provider, model, cfg)); err != nil {

92+ if err := t.Execute(&sb, d); err != nil {

80 return "", fmt.Errorf("executing template: %w", err)

93 return "", fmt.Errorf("executing template: %w", err)

81 }

94 }

@@ -94,18 +107,15 @@ func processFile(filePath string) *ContextFile {

94 }

107 }

95}

108}

109

97−func processContextPath(p string, cfg config.Config) []ContextFile {

110+func processContextPath(p string, store *config.ConfigStore) []ContextFile {

98 var contexts []ContextFile

111 var contexts []ContextFile

99− fullPath := p

112+ fullPath := filepathext.SmartJoin(store.WorkingDir(), p)

100− if !filepath.IsAbs(p) {

101− fullPath = filepath.Join(cfg.WorkingDir(), p)

102− }

103 info, err := os.Stat(fullPath)

113 info, err := os.Stat(fullPath)

104 if err != nil {

114 if err != nil {

105 return contexts

115 return contexts

106 }

116 }

107 if info.IsDir() {

117 if info.IsDir() {

108− filepath.WalkDir(fullPath, func(path string, d os.DirEntry, err error) error {

118+ _ = filepath.WalkDir(fullPath, func(path string, d os.DirEntry, err error) error {

109 if err != nil {

119 if err != nil {

110 return err

120 return err

111 }

121 }

@@ -126,11 +136,11 @@ func processContextPath(p string, cfg config.Config) []ContextFile {

126}

136}

127

137

128// expandPath expands ~ and environment variables in file paths

138// expandPath expands ~ and environment variables in file paths

129−func expandPath(path string, cfg config.Config) string {

139+func expandPath(path string, store *config.ConfigStore) string {

130 path = home.Long(path)

140 path = home.Long(path)

131 // Handle environment variable expansion using the same pattern as config

141 // Handle environment variable expansion using the same pattern as config

132 if strings.HasPrefix(path, "$") {

142 if strings.HasPrefix(path, "$") {

133− if expanded, err := cfg.Resolver().ResolveValue(path); err == nil {

143+ if expanded, err := store.Resolver().ResolveValue(path); err == nil {

134 path = expanded

144 path = expanded

135 }

145 }

136 }

146 }

@@ -138,42 +148,88 @@ func expandPath(path string, cfg config.Config) string {

138 return path

148 return path

139}

149}

140

150

141−func (p *Prompt) promptData(provider, model string, cfg config.Config) PromptDat {

151+// loadContextFiles loads and deduplicates context files from a list of paths.

142− workingDir := cfg.WorkingDir()

152+func loadContextFiles(paths []string, store *config.ConfigStore) map[string][]ContextFile {

143− if p.workingDir != "" {

144− workingDir = p.workingDir

145− }

146− platform := runtime.GOOS

147− if p.platform != "" {

148− platform = p.platform

149− }

150−

151 files := map[string][]ContextFile{}

153 files := map[string][]ContextFile{}

152−

153− for _, pth := range cfg.Options.ContextPaths {

154+ for _, pth := range paths {

154− expanded := expandPath(pth, cfg)

155+ expanded := expandPath(pth, store)

155 pathKey := strings.ToLower(expanded)

156 pathKey := strings.ToLower(expanded)

156 if _, ok := files[pathKey]; ok {

157 if _, ok := files[pathKey]; ok {

157 continue

158 continue

158 }

159 }

159− content := processContextPath(expanded, cfg)

160+ files[pathKey] = processContextPath(expanded, store)

160− files[pathKey] = content

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)

162

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

181+ }

182+

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())

163 data := PromptDat{

208 data := PromptDat{

164− Provider: provider,

209+ Provider: provider,

165− Model: model,

210+ Model: model,

166− Config: cfg,

211+ Config: *cfg,

167− WorkingDir: workingDir,

212+ WorkingDir: filepath.ToSlash(workingDir),

168− IsGitRepo: isGitRepo(cfg.WorkingDir()),

213+ IsGitRepo: isGit,

169− Platform: platform,

214+ Platform: platform,

170− Date: p.now().Format("1/2/2006"),

215+ Date: p.now().Format("1/2/2006"),

216+ AvailSkillXML: availSkillXML,

217+ }

218+ if isGit {

219+ var err error

220+ data.GitStatus, err = getGitStatus(ctx, store.WorkingDir())

221+ if err != nil {

222+ return PromptDat{}, err

223+ }

171 }

224 }

172

225

173− for _, contextFiles := range files {

226+ for _, files := range contextFiles {

174− data.ContextFiles = append(data.ContextFiles, contextFiles...)

227+ data.ContextFiles = append(data.ContextFiles, files...)

228+ }

229+ for _, files := range globalContextFiles {

230+ data.GlobalContextFiles = append(data.GlobalContextFiles, files...)

175 }

231 }

176− return data

232+ return data, nil

177}

233}

178

234

179func isGitRepo(dir string) bool {

235func isGitRepo(dir string) bool {

@@ -181,6 +237,58 @@ func isGitRepo(dir string) bool {

181 return err == nil

237 return err == nil

182}

238}

183

239

240+func getGitStatus(ctx context.Context, dir string) (string, error) {

241+ sh := shell.NewShell(&shell.Options{

242+ WorkingDir: dir,

243+ })

244+ branch, err := getGitBranch(ctx, sh)

245+ if err != nil {

246+ return "", err

247+ }

248+ status, err := getGitStatusSummary(ctx, sh)

249+ if err != nil {

250+ return "", err

251+ }

252+ commits, err := getGitRecentCommits(ctx, sh)

253+ if err != nil {

254+ return "", err

255+ }

256+ return branch + status + commits, nil

257+}

258+

259+func getGitBranch(ctx context.Context, sh *shell.Shell) (string, error) {

260+ out, _, err := sh.Exec(ctx, "git branch --show-current 2>/dev/null")

261+ if err != nil {

262+ return "", nil

263+ }

264+ out = strings.TrimSpace(out)

265+ if out == "" {

266+ return "", nil

267+ }

268+ return fmt.Sprintf("Current branch: %s\n", out), nil

269+}

270+

271+func getGitStatusSummary(ctx context.Context, sh *shell.Shell) (string, error) {

272+ out, _, err := sh.Exec(ctx, "git status --short 2>/dev/null | head -20")

273+ if err != nil {

274+ return "", nil

275+ }

276+ out = strings.TrimSpace(out)

277+ if out == "" {

278+ return "Status: clean\n", nil

279+ }

280+ return fmt.Sprintf("Status:\n%s\n", out), nil

281+}

282+

283+func getGitRecentCommits(ctx context.Context, sh *shell.Shell) (string, error) {

284+ out, _, err := sh.Exec(ctx, "git log --oneline -n 3 2>/dev/null")

285+ if err != nil || out == "" {

286+ return "", nil

287+ }

288+ out = strings.TrimSpace(out)

289+ return fmt.Sprintf("Recent commits:\n%s\n", out), nil

290+}

291+

184func (p *Prompt) Name() string {

292func (p *Prompt) Name() string {

185 return p.name

293 return p.name

186}

294}

internal/agent/prompts.go+10−4

@@ -1,9 +1,11 @@

1package agent

3import (

4+ "context"

4 _ "embed"

5 _ "embed"

6 "github.com/charmbracelet/crush/internal/agent/prompt"

7 "github.com/charmbracelet/crush/internal/agent/prompt"

8+ "github.com/charmbracelet/crush/internal/config"

9//go:embed templates/coder.md.tpl

11//go:embed templates/coder.md.tpl

@@ -12,8 +14,8 @@ var coderPromptTmpl []byte

12//go:embed templates/task.md.tpl

14//go:embed templates/task.md.tpl

13var taskPromptTmpl []byte

15var taskPromptTmpl []byte

15−//go:embed templates/initialize.md

17+//go:embed templates/initialize.md.tpl

16−var initializePrompt []byte

18+var initializePromptTmpl []byte

18func coderPrompt(opts ...prompt.Option) (*prompt.Prompt, error) {

20func coderPrompt(opts ...prompt.Option) (*prompt.Prompt, error) {

19 systemPrompt, err := prompt.NewPrompt("coder", string(coderPromptTmpl), opts...)

21 systemPrompt, err := prompt.NewPrompt("coder", string(coderPromptTmpl), opts...)

@@ -31,6 +33,10 @@ func taskPrompt(opts ...prompt.Option) (*prompt.Prompt, error) {

31 return systemPrompt, nil

33 return systemPrompt, nil

32}

34}

34−func InitializePrompt() string {

36+func InitializePrompt(cfg *config.ConfigStore) (string, error) {

35− return string(initializePrompt)

37+ systemPrompt, err := prompt.NewPrompt("initialize", string(initializePromptTmpl))

38+ if err != nil {

39+ return "", err

40+ }

41+ return systemPrompt.Build(context.Background(), "", "", cfg)

36}

42}

internal/agent/queued_runid_test.gonew file+181

@@ -0,0 +1,181 @@

1+package agent

3+import (

4+ "context"

5+ "errors"

6+ "sync/atomic"

7+ "testing"

8+ "time"

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/recorder_test.godeleted−104

@@ -1,104 +0,0 @@

1−package agent

2−

3−import (

4− "bytes"

5− "encoding/json"

6− "io"

7− "net/http"

8− "path/filepath"

9− "reflect"

10− "strings"

11− "testing"

12−

13− "go.yaml.in/yaml/v4"

14− "gopkg.in/dnaeon/go-vcr.v4/pkg/cassette"

15− "gopkg.in/dnaeon/go-vcr.v4/pkg/recorder"

16−)

17−

18−func newRecorder(t *testing.T) *recorder.Recorder {

19− cassetteName := filepath.Join("testdata", t.Name())

20−

21− r, err := recorder.New(

22− cassetteName,

23− recorder.WithMode(recorder.ModeRecordOnce),

24− recorder.WithMatcher(customMatcher(t)),

25− recorder.WithMarshalFunc(marshalFunc),

26− recorder.WithSkipRequestLatency(true), // disable sleep to simulate response time, makes tests faster

27− recorder.WithHook(hookRemoveHeaders, recorder.AfterCaptureHook),

28− )

29− if err != nil {

30− t.Fatalf("recorder: failed to create recorder: %v", err)

31− }

32−

33− t.Cleanup(func() {

34− if err := r.Stop(); err != nil {

35− t.Errorf("recorder: failed to stop recorder: %v", err)

36− }

37− })

38−

39− return r

40−}

41−

42−func customMatcher(t *testing.T) recorder.MatcherFunc {

43− return func(r *http.Request, i cassette.Request) bool {

44− if r.Body == nil || r.Body == http.NoBody {

45− return cassette.DefaultMatcher(r, i)

46− }

47− if r.Method != i.Method || r.URL.String() != i.URL {

48− return false

49− }

50−

51− reqBody, err := io.ReadAll(r.Body)

52− if err != nil {

53− t.Fatalf("recorder: failed to read request body")

54− }

55− r.Body.Close()

56− r.Body = io.NopCloser(bytes.NewBuffer(reqBody))

57−

58− // Some providers can sometimes generate JSON requests with keys in

59− // a different order, which means a direct string comparison will fail.

60− // Falling back to deserializing the content if we don't have a match.

61− if string(reqBody) == i.Body { // hot path

62− return true

63− }

64− var content1, content2 any

65− if err := json.Unmarshal(reqBody, &content1); err != nil {

66− return false

67− }

68− if err := json.Unmarshal([]byte(i.Body), &content2); err != nil {

69− return false

70− }

71− return reflect.DeepEqual(content1, content2)

72− }

73−}

74−

75−func marshalFunc(in any) ([]byte, error) {

76− var buff bytes.Buffer

77− enc := yaml.NewEncoder(&buff)

78− enc.SetIndent(2)

79− enc.CompactSeqIndent()

80− if err := enc.Encode(in); err != nil {

81− return nil, err

82− }

83− return buff.Bytes(), nil

84−}

85−

86−var headersToKeep = map[string]struct{}{

87− "accept": {},

88− "content-type": {},

89− "user-agent": {},

90−}

91−

92−func hookRemoveHeaders(i *cassette.Interaction) error {

93− for k := range i.Request.Headers {

94− if _, ok := headersToKeep[strings.ToLower(k)]; !ok {

95− delete(i.Request.Headers, k)

96− }

97− }

98− for k := range i.Response.Headers {

99− if _, ok := headersToKeep[strings.ToLower(k)]; !ok {

100− delete(i.Response.Headers, k)

101− }

102− }

103− return nil

104−}

internal/agent/run_complete_test.gonew file+322

@@ -0,0 +1,322 @@

1+package agent

3+import (

4+ "context"

5+ "testing"

6+ "time"

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.gonew file+52

@@ -0,0 +1,52 @@

1+package agent

3+import (

4+ "context"

5+ "sync/atomic"

6+)

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.gonew file+33

@@ -0,0 +1,33 @@

1+package agent

3+import "context"

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+1−15

@@ -1,15 +1 @@

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.

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.

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.mdnew file+1

@@ -0,0 +1 @@

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.

internal/agent/templates/agentic_fetch_prompt.md.tplnew file+76

@@ -0,0 +1,76 @@

1+You are a web content analysis agent for Crush. Your task is to analyze web content, search results, or web pages to extract the information requested by the user.

3+<rules>

4+1. Be concise and direct in your responses

5+2. Focus only on the information requested in the user's prompt

6+3. If the content is provided in a file path, use the grep and view tools to efficiently search through it

7+4. When relevant, quote specific sections from the content to support your answer

8+5. If the requested information is not found, clearly state that

9+6. Any file paths you use MUST be absolute

10+7. **IMPORTANT**: If you need information from a linked page or search result, use the web_fetch tool to get that content

11+8. **IMPORTANT**: If you need to search for more information, use the web_search tool

12+9. After fetching a link, analyze the content yourself to extract what's needed

13+10. Don't hesitate to follow multiple links or perform multiple searches if necessary to get complete information

14+11. **CRITICAL**: At the end of your response, include a "Sources" section listing ALL URLs that were useful in answering the question

15+</rules>

16+

17+<search_strategy>

18+When searching for information:

19+

20+1. **Break down complex questions** - If the user's question has multiple parts, search for each part separately

21+2. **Use specific, targeted queries** - Prefer multiple small searches over one broad search

22+ - Bad: "Python 3.12 new features performance improvements async changes"

23+ - Good: First "Python 3.12 new features", then "Python 3.12 performance improvements", then "Python 3.12 async changes"

24+3. **Iterate and refine** - If initial results aren't helpful, try different search terms or more specific queries

25+4. **Search for different aspects** - For comprehensive answers, search for different angles of the topic

26+5. **Follow up on promising results** - When you find a good source, fetch it and look for links to related information

27+

28+Example workflow for "What are the pros and cons of using Rust vs Go for web services?":

29+- Search 1: "Rust web services advantages"

30+- Search 2: "Go web services advantages"

31+- Search 3: "Rust vs Go performance comparison"

32+- Search 4: "Rust vs Go developer experience"

33+- Then fetch the most relevant results from each search

34+</search_strategy>

35+

36+<response_format>

37+Your response should be structured as follows:

38+

39+[Your answer to the user's question]

40+

41+## Sources

42+- [URL 1 that was useful]

43+- [URL 2 that was useful]

44+- [URL 3 that was useful]

45+...

46+

47+Only include URLs that actually contributed information to your answer. Include the main URL or search results that were helpful. Add any additional URLs you fetched that provided relevant information.

48+</response_format>

49+

50+<env>

51+Working directory: {{.WorkingDir}}

52+Platform: {{.Platform}}

53+Today's date: {{.Date}}

54+</env>

55+

56+<web_search_tool>

57+You have access to a web_search tool that allows you to search the web:

58+- Provide a search query and optionally max_results (default: 10)

59+- The tool returns search results with titles, URLs, and snippets

60+- After getting search results, use web_fetch to get full content from relevant URLs

61+- **Prefer multiple focused searches over single broad searches**

62+- Keep queries short and specific (3-6 words is often ideal)

63+- If results aren't relevant, try rephrasing with different keywords

64+- Don't be afraid to do 3-5+ searches to thoroughly answer a complex question

65+</web_search_tool>

66+

67+<web_fetch_tool>

68+You have access to a web_fetch tool that allows you to fetch web pages:

69+- Use it when you need to follow links from search results or the current page

70+- Provide just the URL (no prompt parameter)

71+- The tool will fetch and return the content (or save to a file if large)

72+- YOU must then analyze that content to answer the user's question

73+- **Use this liberally** - if a link seems relevant to answering the question, fetch it!

74+- You can fetch multiple pages in sequence to gather all needed information

75+- Remember to include any fetched URLs in your Sources section if they were helpful

76+</web_fetch_tool>

internal/agent/templates/coder.md.tpl+250−22

@@ -3,24 +3,35 @@ You are Crush, a powerful AI Assistant that runs in the CLI.

3<critical_rules>

4These rules override everything else. Follow them strictly:

6−1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)

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.

7−2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act

7+2. **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.

8−3. **TEST AFTER CHANGES**: Run tests immediately after each modification

8+3. **TEST AFTER CHANGES**: Run tests immediately after each modification.

9−4. **BE CONCISE**: Under 4 lines unless user asks for detail

9+4. **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.

10−5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace

10+5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.

11−6. **NEVER COMMIT**: Unless user explicitly says "commit"

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.

127. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.

13−8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so

13+8. **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.

14+9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.

15+10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.

16+11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.

17+12. **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.

14</critical_rules>

21</critical_rules>

16<communication_style>

23<communication_style>

17Keep responses minimal:

24Keep responses minimal:

25+- ALWAYS think and respond in the same spoken language the prompt was written in.

18- Under 4 lines of text (tool use doesn't count)

26- Under 4 lines of text (tool use doesn't count)

27+- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.

19- No preamble ("Here's...", "I'll...")

28- No preamble ("Here's...", "I'll...")

20- No postamble ("Let me know...", "Hope this helps...")

29- No postamble ("Let me know...", "Hope this helps...")

21- One-word answers when possible

30- One-word answers when possible

22- No emojis ever

31- No emojis ever

23- No explanations unless user asks

32- No explanations unless user asks

33+- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.

34+- 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.

25Examples:

36Examples:

26user: what is 2+2?

37user: what is 2+2?

@@ -36,8 +47,17 @@ assistant: src/foo.c

36user: add error handling to the login function

47user: add error handling to the login function

37assistant: [searches for login, reads file, edits with exact match, runs tests]

48assistant: [searches for login, reads file, edits with exact match, runs tests]

38Done

49Done

50+

51+user: Where are errors from the client handled?

52+assistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.

39</communication_style>

53</communication_style>

55+<code_references>

56+When referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:

57+- Example: "The error is handled in src/main.go:45"

58+- Example: "See the implementation in pkg/utils/helper.go:123-145"

59+</code_references>

60+

41<workflow>

61<workflow>

42For every task, follow this sequence internally (don't narrate it):

62For every task, follow this sequence internally (don't narrate it):

@@ -46,15 +66,23 @@ For every task, follow this sequence internally (don't narrate it):

46- Read files to understand current state

66- Read files to understand current state

47- Check memory for stored commands

67- Check memory for stored commands

48- Identify what needs to change

68- Identify what needs to change

69+- Use `git log` and `git blame` for additional context when needed

50**While acting**:

71**While acting**:

51- Read entire file before editing it

72- Read entire file before editing it

73+- Before editing: verify exact whitespace and indentation from View output

52- Use exact text for find/replace (include whitespace)

74- Use exact text for find/replace (include whitespace)

53- Make one logical change at a time

75- Make one logical change at a time

54- After each change: run tests

76- After each change: run tests

55- If tests fail: fix immediately

77- If tests fail: fix immediately

78+- If edit fails: read more context, don't guess - the text must match exactly

79+- Keep going until query is completely resolved before yielding to user

80+- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points

57**Before finishing**:

82**Before finishing**:

83+- Verify ENTIRE query is resolved (not just first step)

84+- All described next steps must be completed

85+- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.

58- Run lint/typecheck if in memory

86- Run lint/typecheck if in memory

59- Verify all changes work

87- Verify all changes work

60- Keep response under 4 lines

88- Keep response under 4 lines

@@ -64,6 +92,8 @@ For every task, follow this sequence internally (don't narrate it):

64- Follow existing patterns (check similar files)

92- Follow existing patterns (check similar files)

65- If stuck, try different approach (don't repeat failures)

93- If stuck, try different approach (don't repeat failures)

66- Make decisions yourself (search first, don't ask)

94- Make decisions yourself (search first, don't ask)

95+- Fix problems at root cause, not surface-level patches

96+- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)

67</workflow>

97</workflow>

69<decision_making>

99<decision_making>

@@ -73,12 +103,27 @@ For every task, follow this sequence internally (don't narrate it):

73- Check similar code

103- Check similar code

74- Infer from context

104- Infer from context

75- Try most likely approach

105- Try most likely approach

106+- 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.

107

77−**Only ask user if**:

108+**Only stop/ask user if**:

78- Truly ambiguous business requirement

109- Truly ambiguous business requirement

79- Multiple valid approaches with big tradeoffs

110- Multiple valid approaches with big tradeoffs

80- Could cause data loss

111- Could cause data loss

81−- Exhausted all attempts

112+- Exhausted all attempts and hit actual blocking errors

113+

114+**When requesting information/access**:

115+- Exhaust all available tools, searches, and reasonable assumptions first.

116+- Never say "Need more info" without detail.

117+- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.

118+- State exactly what you will do once the information arrives so the user knows the next step.

119+

120+When 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.

121+

122+**Never stop for**:

123+- Task seems too large (break it down)

124+- Multiple files to change (change them)

125+- Concerns about "session limits" (no such limits exist)

126+- Work will take many steps (do all the steps)

127

83Examples of autonomous decisions:

128Examples of autonomous decisions:

84- File location → search for similar files

129- File location → search for similar files

@@ -89,43 +134,125 @@ Examples of autonomous decisions:

89</decision_making>

134</decision_making>

135

91<editing_files>

136<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+

92−Critical: ALWAYS read files before editing them in this conversation.

144+Critical: ALWAYS read the relevant context of files before editing them in this conversation.

145

94When using edit tools:

146When using edit tools:

95−1. Read the file first

147+1. Read the relevant context first - note the EXACT indentation (spaces vs tabs, count)

96−2. Find exact text to replace (include indentation/spaces)

148+2. Copy the exact text including ALL whitespace, newlines, and indentation

97−3. Make replacement unambiguous (enough context)

149+3. Include 3-5 lines of context before and after the target

150+4. Verify your old_string would appear exactly once in the file

151+5. If uncertain about whitespace, include more surrounding context

98−4. Verify edit succeeded

152+6. Verify edit succeeded

99−5. Run tests

153+7. Run tests

154+

155+**Whitespace matters**:

156+- Count spaces/tabs carefully (use View tool line numbers as reference)

157+- Include blank lines if they exist

158+- Match line endings exactly

159+- When in doubt, include MORE context rather than less

160+

161+Efficiency tips:

162+- Don't re-read files after successful edits (tool will fail if it didn't work)

163+- Same applies for making folders, deleting files, etc.

100

164

101Common mistakes to avoid:

165Common mistakes to avoid:

102- Editing without reading first

166- Editing without reading first

103- Approximate text matches

167- Approximate text matches

104−- Wrong indentation

168+- Wrong indentation (spaces vs tabs, wrong count)

169+- Missing or extra blank lines

105- Not enough context (text appears multiple times)

170- Not enough context (text appears multiple times)

171+- Trimming whitespace that exists in the original

106- Not testing after changes

172- Not testing after changes

107</editing_files>

173</editing_files>

108

174

175+<whitespace_and_exact_matching>

176+The Edit tool is extremely literal. "Close enough" will fail.

177+

178+**Before every edit**:

179+1. View the file and locate the exact lines to change

180+2. Copy the text EXACTLY including:

181+ - Every space and tab

182+ - Every blank line

183+ - Opening/closing braces position

184+ - Comment formatting

185+3. Include enough surrounding lines (3-5) to make it unique

186+4. Double-check indentation level matches

187+

188+**Common failures**:

189+- `func foo() {` vs `func foo(){` (space before brace)

190+- Tab vs 4 spaces vs 2 spaces

191+- Missing blank line before/after

192+- `// comment` vs `//comment` (space after //)

193+- Different number of spaces in indentation

194+

195+**If edit fails**:

196+- View the file again at the specific location

197+- Copy even more context

198+- Check for tabs vs spaces

199+- Verify line endings

200+- Try including the entire function/block if needed

201+- Never retry with guessed changes - get the exact text first

202+</whitespace_and_exact_matching>

203+

204+<task_completion>

205+Ensure every task is implemented completely, not partially or sketched.

206+

207+1. **Think before acting** (for non-trivial tasks)

208+ - Identify all components that need changes (models, logic, routes, config, tests, docs)

209+ - Consider edge cases and error paths upfront

210+ - Form a mental checklist of requirements before making the first edit

211+ - This planning happens internally - don't narrate it to the user

212+

213+2. **Implement end-to-end**

214+ - Treat every request as complete work: if adding a feature, wire it fully

215+ - Update all affected files (callers, configs, tests, docs)

216+ - Don't leave TODOs or "you'll also need to..." - do it yourself

217+ - No task is too large - break it down and complete all parts

218+ - 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.

219+

220+3. **Verify before finishing**

221+ - Re-read the original request and verify each requirement is met

222+ - Check for missing error handling, edge cases, or unwired code

223+ - Run tests to confirm the implementation works

224+ - Only say "Done" when truly done - never stop mid-task

225+</task_completion>

226+

109<error_handling>

227<error_handling>

110When errors occur:

228When errors occur:

1111. Read complete error message

2291. Read complete error message

112−2. Understand root cause

230+2. Understand root cause (isolate with debug logs or minimal reproduction if needed)

1133. Try different approach (don't repeat same action)

2313. Try different approach (don't repeat same action)

1144. Search for similar code that works

2324. Search for similar code that works

1155. Make targeted fix

2335. Make targeted fix

1166. Test to verify

2346. Test to verify

235+7. 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.

117

236

118Common errors:

237Common errors:

119- Import/Module → check paths, spelling, what exists

238- Import/Module → check paths, spelling, what exists

120- Syntax → check brackets, indentation, typos

239- Syntax → check brackets, indentation, typos

121- Tests fail → read test, see what it expects

240- Tests fail → read test, see what it expects

122- File not found → use ls, check exact path

241- File not found → use ls, check exact path

242+

243+**Edit tool "old_string not found"**:

244+- View the file again at the target location

245+- Copy the EXACT text including all whitespace

246+- Include more surrounding context (full function if needed)

247+- Check for tabs vs spaces, extra/missing blank lines

248+- Count indentation spaces carefully

249+- Don't retry with approximate matches - get the exact text

123</error_handling>

250</error_handling>

124

251

125<memory_instructions>

252<memory_instructions>

126Memory files store commands, preferences, and codebase info. Update them when you discover:

253Memory files store commands, preferences, and codebase info. Update them when you discover:

127- Build/test/lint commands

254- Build/test/lint commands

128−- Code style preferences

255+- Code style preferences

129- Important codebase patterns

256- Important codebase patterns

130- Useful project information

257- Useful project information

131</memory_instructions>

258</memory_instructions>

@@ -137,40 +264,106 @@ Before writing code:

1373. Match existing style

2643. Match existing style

1384. Use same libraries/frameworks

2654. Use same libraries/frameworks

1395. Follow security best practices (never log secrets)

2665. Follow security best practices (never log secrets)

267+6. Don't use one-letter variable names unless requested

140

268

141Never assume libraries are available - verify first.

269Never assume libraries are available - verify first.

270+

271+**Ambition vs. precision**:

272+- New projects → be creative and ambitious with implementation

273+- Existing codebases → be surgical and precise, respect surrounding code

274+- Don't change filenames or variables unnecessarily

275+- Don't add formatters/linters/tests to codebases that don't have them

142</code_conventions>

276</code_conventions>

143

277

144<testing>

278<testing>

145After significant changes:

279After significant changes:

280+- Start testing as specific as possible to code changed, then broaden to build confidence

281+- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions

146- Run relevant test suite

282- Run relevant test suite

147- If tests fail, fix before continuing

283- If tests fail, fix before continuing

148- Check memory for test commands

284- Check memory for test commands

149−- Run lint/typecheck if available

285+- Run lint/typecheck if available (on precise targets when possible)

286+- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue

150- Suggest adding commands to memory if not found

287- Suggest adding commands to memory if not found

288+- Don't fix unrelated bugs or test failures (not your responsibility)

151</testing>

289</testing>

152

290

153<tool_usage>

291<tool_usage>

292+- 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.

154- Search before assuming

293- Search before assuming

155- Read files before editing

294- Read files before editing

295+- Always use absolute paths for file operations (editing, reading, writing)

156- Use Agent tool for complex searches

296- Use Agent tool for complex searches

157- Run tools in parallel when safe (no dependencies)

297- Run tools in parallel when safe (no dependencies)

298+- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution

158- Summarize tool output for user (they don't see it)

299- Summarize tool output for user (they don't see it)

300+- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.

301+- Only use the tools you know exist.

302+

303+<bash_commands>

304+**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.

305+

306+When running non-trivial bash commands (especially those that modify the system):

307+- Briefly explain what the command does and why you're running it

308+- This ensures the user understands potentially dangerous operations

309+- Simple read-only commands (ls, cat, etc.) don't need explanation

310+- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)

311+- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)

312+- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)

313+</bash_commands>

159</tool_usage>

314</tool_usage>

160

315

161<proactiveness>

316<proactiveness>

162Balance autonomy with user intent:

317Balance autonomy with user intent:

163−- When asked to do something → do it fully (including follow-ups)

318+- When asked to do something → do it fully (including ALL follow-ups and "next steps")

319+- Never describe what you'll do next - just do it

320+- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.

321+- 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.

164- When asked how to approach → explain first, don't auto-implement

322- When asked how to approach → explain first, don't auto-implement

165- After completing work → stop, don't explain (unless asked)

323- After completing work → stop, don't explain (unless asked)

166- Don't surprise user with unexpected actions

324- Don't surprise user with unexpected actions

167</proactiveness>

325</proactiveness>

168

326

327+<final_answers>

328+Adapt verbosity to match the work completed:

329+

330+**Default (under 4 lines)**:

331+- Simple questions or single-file changes

332+- Casual conversation, greetings, acknowledgements

333+- One-word answers when possible

334+

335+**More detail allowed (up to 10-15 lines)**:

336+- Large multi-file changes that need walkthrough

337+- Complex refactoring where rationale adds value

338+- Tasks where understanding the approach is important

339+- When mentioning unrelated bugs/issues found

340+- Suggesting logical next steps user might want

341+- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.

342+

343+**What to include in verbose answers**:

344+- Brief summary of what was done and why

345+- Key files/functions changed (with `file:line` references)

346+- Any important decisions or tradeoffs made

347+- Next steps or things user should verify

348+- Issues found but not fixed

349+

350+**What to avoid**:

351+- Don't show full file contents unless explicitly asked

352+- Don't explain how to save files or copy code (user has access to your work)

353+- Don't use "Here's what I did" or "Let me know if..." style preambles/postambles

354+- Keep tone direct and factual, like handing off work to a teammate

355+</final_answers>

356+

169<env>

357<env>

170Working directory: {{.WorkingDir}}

358Working directory: {{.WorkingDir}}

171Is directory a git repo: {{if .IsGitRepo}}yes{{else}}no{{end}}

359Is directory a git repo: {{if .IsGitRepo}}yes{{else}}no{{end}}

172Platform: {{.Platform}}

360Platform: {{.Platform}}

173Today's date: {{.Date}}

361Today's date: {{.Date}}

362+{{if .GitStatus}}

363+

364+Git status (snapshot at conversation start - may be outdated):

365+{{.GitStatus}}

366+{{end}}

174</env>

367</env>

175

368

176{{if gt (len .Config.LSP) 0}}

369{{if gt (len .Config.LSP) 0}}

@@ -180,13 +373,48 @@ Diagnostics (lint/typecheck) included in tool output.

180- Ignore issues in files you didn't touch (unless user asks)

373- Ignore issues in files you didn't touch (unless user asks)

181</lsp>

374</lsp>

182{{end}}

375{{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}}

183

397

184{{if .ContextFiles}}

398{{if .ContextFiles}}

185−<memory>

399+# Project-Specific Context

400+Make sure to follow the instructions in the context below.

401+<project_context>

186{{range .ContextFiles}}

402{{range .ContextFiles}}

187<file path="{{.Path}}">

403<file path="{{.Path}}">

188{{.Content}}

404{{.Content}}

189</file>

405</file>

190{{end}}

406{{end}}

191−</memory>

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>

192{{end}}

420{{end}}

internal/agent/templates/initialize.mddeleted−9

@@ -1,9 +0,0 @@

1−Please analyze this codebase and create a **CRUSH.md** file containing:

2−

3−- Build/lint/test commands - especially for running a single test

4−- Code style guidelines including imports, formatting, types, naming conventions, error handling, etc.

5−

6−The file you create will be given to agentic coding agents (such as yourself) that operate in this repository. Make it about 20-30 lines long.

7−If there's already a **CRUSH.md**, improve it.

8−

9−If there are Cursor rules (in `.cursor/rules/` or `.cursorrules`) or Copilot rules (in `.github/copilot-instructions.md`), make sure to include them.

internal/agent/templates/initialize.md.tplnew file+29

@@ -0,0 +1,29 @@

1+Analyze this codebase and create/update **{{.Config.Options.InitializeAs}}** to help future agents work effectively in this repository.

3+**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}}."

5+**Goal**: Document what an agent needs to know to work in this codebase - commands, patterns, conventions, gotchas, overall architecture, how components fit together

7+**Discovery process**:

9+1. Check directory contents with `ls`

10+2. Look for existing rule files (`.cursor/rules/*.md`, `.cursorrules`, `.github/copilot-instructions.md`, `claude.md`, `agents.md`) - only read if they exist

11+3. Identify project type from config files and directory structure

12+4. 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

14+6. If {{.Config.Options.InitializeAs}} exists, read and improve it

15+

16+**Content to include**:

17+

18+- Essential commands (build, test, run, deploy, etc.) - whatever is relevant for this project

19+- Code organization and structure, application architecture and control/data flow

20+- Naming conventions and style patterns

21+- Testing approach and patterns

22+- Important gotchas or non-obvious patterns

23+- Any project-specific context from existing rule files

24+

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+

27+**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.

28+

29+**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/summary.md+43−12

@@ -1,17 +1,48 @@

1−You are a helpful AI assistant tasked with summarizing conversations.

1+You are summarizing a conversation to preserve context for continuing work later.

3−When asked to summarize, provide a detailed but concise summary of the conversation.

3+**Critical**: This summary will be the ONLY context available when the conversation resumes. Assume all previous messages will be lost. Be thorough.

4−Focus on information that would be helpful for continuing the conversation, including:

6−- What was done

5+**Required sections**:

7−- What is currently being worked on

8−- Which files are being modified

9−- Helpful commands that helped you implement this task so far

10−- Any context that would be needed to continue working on the task

11−- What needs to be done next

13−Your summary should be comprehensive enough to provide context to be quickly understood.

7+## Current State

15−It is very important to keep context of files that are important and strategy you are following.

9+- What task is being worked on (exact user request)

10+- Current progress and what's been completed

11+- What's being worked on right now (incomplete work)

12+- What remains to be done (specific next steps, not vague)

17−It is very important to have the next steps clearly defined.

14+## Files & Changes

15+

16+- Files that were modified (with brief description of changes)

17+- Files that were read/analyzed (why they're relevant)

18+- Key files not yet touched but will need changes

19+- File paths and line numbers for important code locations

20+

21+## Technical Context

22+

23+- Architecture decisions made and why

24+- Patterns being followed (with examples)

25+- Libraries/frameworks being used

26+- Commands that worked (exact commands with context)

27+- Commands that failed (what was tried and why it didn't work)

28+- Environment details (language versions, dependencies, etc.)

29+

30+## Strategy & Approach

31+

32+- Overall approach being taken

33+- Why this approach was chosen over alternatives

34+- Key insights or gotchas discovered

35+- Assumptions made

36+- Any blockers or risks identified

37+

38+## Exact Next Steps

39+

40+Be specific. Don't write "implement authentication" - write:

41+

42+1. Add JWT middleware to src/middleware/auth.js:15

43+2. Update login handler in src/routes/user.js:45 to return token

44+3. Test with: npm test -- auth.test.js

45+

46+**Tone**: Write as if briefing a teammate taking over mid-task. Include everything they'd need to continue without asking questions. No emojis ever.

47+

48+**Length**: No limit. Err on the side of too much detail rather than too little. Critical context is worth the tokens.

internal/agent/templates/title.md+8−7

@@ -1,10 +1,11 @@

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.

3<rules>

4+- Keep the title in the same language that the user wrote their message in.

4−- ensure it is not more than 50 characters long

5+- Ensure it is not more than 50 characters long.

5−- the title should be a summary of the user's message

6+- The title should be a summary of the user's message.

6−- it should be one line long

7+- It should be one line long.

7−- do not use quotes or colons

8+- Do not use quotes or colons.

8−- the entire text you return will be used as the title

9+- The entire text you return will be used as the title.

9−- never return anything that is more than one sentence (one line) long

10+- Never return anything that is more than one sentence (one line) long.

10</rules>

11</rules>

internal/agent/testdata/TestCoderAgent/anthropic-sonnet/bash_tool.yamldeleted−204

@@ -1,204 +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: 774

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''\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 1.12.0

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_0134NcQsuCWiH9G2f1pFdbjd","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":147,"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 Message"} }

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":147,"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: 580.862ms

63−- id: 1

64− request:

65− proto: HTTP/1.1

66− proto_major: 1

67− proto_minor: 1

68− content_length: 32080

69− host: ""

70− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use bash to create a file named test.txt with content 'hello bash'\",\"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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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 1.12.0

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_014HBZ4z2bf13yA4JhmVnxwF","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":1807,"cache_read_input_tokens":6853,"cache_creation":{"ephemeral_5m_input_tokens":1807,"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_01YBoqWcXiuoc1fZf4muKFXn","name":"bash","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":"{\"com"} }

97−

98− event: content_block_delta

99− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"mand"} }

100−

101− event: content_block_delta

102− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\": \"echo 'h"} }

103−

104− event: content_block_delta

105− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ello bas"} }

106−

107− event: content_block_delta

108− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"h'"} }

109−

110− event: content_block_delta

111− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" > te"} }

112−

113− event: content_block_delta

114− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"st.txt\""} }

115−

116− event: content_block_delta

117− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"descript"} }

118−

119− event: content_block_delta

120− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ion\": \"C"} }

121−

122− event: content_block_delta

123− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"reat"} }

124−

125− event: content_block_delta

126− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"e tes"} }

127−

128− event: content_block_delta

129− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"t.txt with"} }

130−

131− event: content_block_delta

132− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" content 'h"} }

133−

134− event: content_block_delta

135− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"el"} }

136−

137− event: content_block_delta

138− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"lo bash'\"}"} }

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":3,"cache_creation_input_tokens":1807,"cache_read_input_tokens":6853,"output_tokens":87} }

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: 2.250892459s

155−- id: 2

156− request:

157− proto: HTTP/1.1

158− proto_major: 1

159− proto_minor: 1

160− content_length: 32481

161− host: ""

162− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use bash to create a file named test.txt with content 'hello bash'\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01YBoqWcXiuoc1fZf4muKFXn\",\"input\":{\"command\":\"echo 'hello bash' \\u003e test.txt\",\"description\":\"Create test.txt with content 'hello bash'\"},\"name\":\"bash\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01YBoqWcXiuoc1fZf4muKFXn\",\"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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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 1.12.0

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_01VhFdZK9M9rh9iPzGkdoG1R","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":6,"cache_creation_input_tokens":99,"cache_read_input_tokens":8660,"cache_creation":{"ephemeral_5m_input_tokens":99,"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":"File"} }

186−

187− event: content_block_delta

188− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" created successfully."} }

189−

190− event: content_block_stop

191− data: {"type":"content_block_stop","index":0 }

192−

193− event: message_delta

194− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":6,"cache_creation_input_tokens":99,"cache_read_input_tokens":8660,"output_tokens":7} }

195−

196− event: message_stop

197− data: {"type":"message_stop" }

198−

199− headers:

200− Content-Type:

201− - text/event-stream; charset=utf-8

202− status: 200 OK

203− code: 200

204− duration: 2.466855833s

internal/agent/testdata/TestCoderAgent/anthropic-sonnet/download_tool.yamldeleted−227

@@ -1,227 +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: 787

10− host: ""

11− body: '{"max_tokens":40,"messages":[{"content":[{"text":"Generate a concise title for the following content:\n\ndownload the file from https://httpbin.org/robots.txt and save it as robots.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 1.12.0

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_01HgEdLNNxYjaZP4qdjC1kgA","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":151,"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 robots"} }

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":".txt from http"} }

44−

45− event: content_block_delta

46− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"bin.org"} }

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":151,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":12} }

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: 538.064375ms

63−- id: 1

64− request:

65− proto: HTTP/1.1

66− proto_major: 1

67− proto_minor: 1

68− content_length: 32097

69− host: ""

70− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"download the file from https://httpbin.org/robots.txt and save it as robots.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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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 1.12.0

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_019KcWmqSk79v6LJf1bza4q3","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":1811,"cache_read_input_tokens":6853,"cache_creation":{"ephemeral_5m_input_tokens":1811,"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_01TQRnNYg7te6aMms1MBRHL8","name":"download","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":"{\"u"} }

97−

98− event: content_block_delta

99− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"rl\": \"https:"} }

100−

101− event: content_block_delta

102− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"//httpbin."}}

103−

104− event: content_block_delta

105− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"org/robots."} }

106−

107− event: content_block_delta

108− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"txt\""} }

109−

110− event: content_block_delta

111− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"file_pat"} }

112−

113− event: content_block_delta

114− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"h\": \"rob"} }

115−

116− event: content_block_delta

117− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ots.tx"} }

118−

119− event: content_block_delta

120− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"t\"}"} }

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":3,"cache_creation_input_tokens":1811,"cache_read_input_tokens":6853,"output_tokens":81} }

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: 2.481377833s

137−- id: 2

138− request:

139− proto: HTTP/1.1

140− proto_major: 1

141− proto_minor: 1

142− content_length: 0

143− host: httpbin.org

144− headers:

145− User-Agent:

146− - crush/1.0

147− url: https://httpbin.org/robots.txt

148− method: GET

149− response:

150− proto: HTTP/2.0

151− proto_major: 2

152− proto_minor: 0

153− content_length: 30

154− body: |

155− User-agent: *

156− Disallow: /deny

157− headers:

158− Content-Type:

159− - text/plain

160− status: 200 OK

161− code: 200

162− duration: 1.07370375s

163−- id: 3

164− request:

165− proto: HTTP/1.1

166− proto_major: 1

167− proto_minor: 1

168− content_length: 32588

169− host: ""

170− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"download the file from https://httpbin.org/robots.txt and save it as robots.txt\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01TQRnNYg7te6aMms1MBRHL8\",\"input\":{\"file_path\":\"robots.txt\",\"url\":\"https://httpbin.org/robots.txt\"},\"name\":\"download\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01TQRnNYg7te6aMms1MBRHL8\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"Successfully downloaded 30 bytes to /tmp/crush-test/TestCoderAgent/anthropic-sonnet/download_tool/robots.txt (Content-Type: text/plain)\",\"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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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}"

171− headers:

172− Accept:

173− - application/json

174− Content-Type:

175− - application/json

176− User-Agent:

177− - Anthropic/Go 1.12.0

178− url: https://api.anthropic.com/v1/messages

179− method: POST

180− response:

181− proto: HTTP/2.0

182− proto_major: 2

183− proto_minor: 0

184− content_length: -1

185− body: |+

186− event: message_start

187− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01HaRYTipxH4buqTj1ojHLri","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":132,"cache_read_input_tokens":8664,"cache_creation":{"ephemeral_5m_input_tokens":132,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

188−

189− event: content_block_start

190− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

191−

192− event: content_block_delta

193− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Done"} }

194−

195− event: content_block_delta

196− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":". Downloaded 30 bytes to `"} }

197−

198− event: ping

199− data: {"type": "ping"}

200−

201− event: content_block_delta

202− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"robots.txt`."} }

203−

204− event: ping

205− data: {"type": "ping"}

206−

207− event: content_block_stop

208− data: {"type":"content_block_stop","index":0 }

209−

210− event: ping

211− data: {"type": "ping"}

212−

213− event: ping

214− data: {"type": "ping"}

215−

216− event: message_delta

217− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":132,"cache_read_input_tokens":8664,"output_tokens":16} }

218−

219− event: message_stop

220− data: {"type":"message_stop" }

221−

222− headers:

223− Content-Type:

224− - text/event-stream; charset=utf-8

225− status: 200 OK

226− code: 200

227− duration: 2.018951292s

internal/agent/testdata/TestCoderAgent/anthropic-sonnet/fetch_tool.yamldeleted−245

@@ -1,245 +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: 800

10− host: ""

11− body: '{"max_tokens":40,"messages":[{"content":[{"text":"Generate a concise title for the following content:\n\nfetch the content from https://httpbin.org/html and tell me if it contains the word ''Herman''\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 1.12.0

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_01FxSVzNELCauTsk6fSTg87j","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":154,"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":" Scraping Content"} }

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":" Specific"} }

47−

48− event: content_block_delta

49− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Wor"} }

50−

51− event: content_block_delta

52− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d"}}

53−

54− event: content_block_stop

55− data: {"type":"content_block_stop","index":0 }

56−

57− event: message_delta

58− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":154,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":12} }

59−

60− event: message_stop

61− data: {"type":"message_stop" }

62−

63− headers:

64− Content-Type:

65− - text/event-stream; charset=utf-8

66− status: 200 OK

67− code: 200

68− duration: 555.344458ms

69−- id: 1

70− request:

71− proto: HTTP/1.1

72− proto_major: 1

73− proto_minor: 1

74− content_length: 32107

75− host: ""

76− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"fetch the content from https://httpbin.org/html and tell me if it contains the word 'Herman'\",\"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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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}"

77− headers:

78− Accept:

79− - application/json

80− Content-Type:

81− - application/json

82− User-Agent:

83− - Anthropic/Go 1.12.0

84− url: https://api.anthropic.com/v1/messages

85− method: POST

86− response:

87− proto: HTTP/2.0

88− proto_major: 2

89− proto_minor: 0

90− content_length: -1

91− body: |+

92− event: message_start

93− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01SiShydSKVnKzai3nv14vyP","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":1814,"cache_read_input_tokens":6853,"cache_creation":{"ephemeral_5m_input_tokens":1814,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}}}

94−

95− event: content_block_start

96− data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01GWL89Gxjkj9y4Eg5VDVbty","name":"fetch","input":{}} }

97−

98− event: content_block_delta

99− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }

100−

101− event: content_block_delta

102− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"url"} }

103−

104− event: content_block_delta

105− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\":"} }

106−

107− event: content_block_delta

108− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" \"https"} }

109−

110− event: content_block_delta

111− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"://ht"} }

112−

113− event: content_block_delta

114− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tpbi"} }

115−

116− event: content_block_delta

117− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"n.or"} }

118−

119− event: content_block_delta

120− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"g/h"} }

121−

122− event: content_block_delta

123− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tml\""} }

124−

125− event: content_block_delta

126− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", "} }

127−

128− event: content_block_delta

129− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"format\":"} }

130−

131− event: content_block_delta

132− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" \"tex"} }

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_stop

138− data: {"type":"content_block_stop","index":0 }

139−

140− event: message_delta

141− data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":3,"cache_creation_input_tokens":1814,"cache_read_input_tokens":6853,"output_tokens":75} }

142−

143− event: message_stop

144− data: {"type":"message_stop" }

145−

146− headers:

147− Content-Type:

148− - text/event-stream; charset=utf-8

149− status: 200 OK

150− code: 200

151− duration: 2.398155292s

152−- id: 2

153− request:

154− proto: HTTP/1.1

155− proto_major: 1

156− proto_minor: 1

157− content_length: 0

158− host: httpbin.org

159− headers:

160− User-Agent:

161− - crush/1.0

162− url: https://httpbin.org/html

163− method: GET

164− response:

165− proto: HTTP/2.0

166− proto_major: 2

167− proto_minor: 0

168− content_length: 3741

169− body: |-

170− <!DOCTYPE html>

171− <html>

172− <head>

173− </head>

174− <body>

175− <h1>Herman Melville - Moby-Dick</h1>

176−

177− <div>

178−

179− Availing himself of the mild, summer-cool weather that now reigned in these latitudes, and in preparation for the peculiarly active pursuits shortly to be anticipated, Perth, the begrimed, blistered old blacksmith, had not removed his portable forge to the hold again, after concluding his contributory work for Ahab's leg, but still retained it on deck, fast lashed to ringbolts by the foremast; being now almost incessantly invoked by the headsmen, and harpooneers, and bowsmen to do some little job for them; altering, or repairing, or new shaping their various weapons and boat furniture. Often he would be surrounded by an eager circle, all waiting to be served; holding boat-spades, pike-heads, harpoons, and lances, and jealously watching his every sooty movement, as he toiled. Nevertheless, this old man's was a patient hammer wielded by a patient arm. No murmur, no impatience, no petulance did come from him. Silent, slow, and solemn; bowing over still further his chronically broken back, he toiled away, as if toil were life itself, and the heavy beating of his hammer the heavy beating of his heart. And so it was.—Most miserable! A peculiar walk in this old man, a certain slight but painful appearing yawing in his gait, had at an early period of the voyage excited the curiosity of the mariners. And to the importunity of their persisted questionings he had finally given in; and so it came to pass that every one now knew the shameful story of his wretched fate. Belated, and not innocently, one bitter winter's midnight, on the road running between two country towns, the blacksmith half-stupidly felt the deadly numbness stealing over him, and sought refuge in a leaning, dilapidated barn. The issue was, the loss of the extremities of both feet. Out of this revelation, part by part, at last came out the four acts of the gladness, and the one long, and as yet uncatastrophied fifth act of the grief of his life's drama. He was an old man, who, at the age of nearly sixty, had postponedly encountered that thing in sorrow's technicals called ruin. He had been an artisan of famed excellence, and with plenty to do; owned a house and garden; embraced a youthful, daughter-like, loving wife, and three blithe, ruddy children; every Sunday went to a cheerful-looking church, planted in a grove. But one night, under cover of darkness, and further concealed in a most cunning disguisement, a desperate burglar slid into his happy home, and robbed them all of everything. And darker yet to tell, the blacksmith himself did ignorantly conduct this burglar into his family's heart. It was the Bottle Conjuror! Upon the opening of that fatal cork, forth flew the fiend, and shrivelled up his home. Now, for prudent, most wise, and economic reasons, the blacksmith's shop was in the basement of his dwelling, but with a separate entrance to it; so that always had the young and loving healthy wife listened with no unhappy nervousness, but with vigorous pleasure, to the stout ringing of her young-armed old husband's hammer; whose reverberations, muffled by passing through the floors and walls, came up to her, not unsweetly, in her nursery; and so, to stout Labor's iron lullaby, the blacksmith's infants were rocked to slumber. Oh, woe on woe! Oh, Death, why canst thou not sometimes be timely? Hadst thou taken this old blacksmith to thyself ere his full ruin came upon him, then had the young widow had a delicious grief, and her orphans a truly venerable, legendary sire to dream of in their after years; and all of them a care-killing competency.

180−

181− </div>

182− </body>

183− </html>

184− headers:

185− Content-Type:

186− - text/html; charset=utf-8

187− status: 200 OK

188− code: 200

189− duration: 461.971291ms

190−- id: 3

191− request:

192− proto: HTTP/1.1

193− proto_major: 1

194− proto_minor: 1

195− content_length: 36041

196− host: ""

197− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"fetch the content from https://httpbin.org/html and tell me if it contains the word 'Herman'\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01GWL89Gxjkj9y4Eg5VDVbty\",\"input\":{\"format\":\"text\",\"url\":\"https://httpbin.org/html\"},\"name\":\"fetch\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01GWL89Gxjkj9y4Eg5VDVbty\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"Herman Melville - Moby-Dick Availing himself of the mild, summer-cool weather that now reigned in these latitudes, and in preparation for the peculiarly active pursuits shortly to be anticipated, Perth, the begrimed, blistered old blacksmith, had not removed his portable forge to the hold again, after concluding his contributory work for Ahab's leg, but still retained it on deck, fast lashed to ringbolts by the foremast; being now almost incessantly invoked by the headsmen, and harpooneers, and bowsmen to do some little job for them; altering, or repairing, or new shaping their various weapons and boat furniture. Often he would be surrounded by an eager circle, all waiting to be served; holding boat-spades, pike-heads, harpoons, and lances, and jealously watching his every sooty movement, as he toiled. Nevertheless, this old man's was a patient hammer wielded by a patient arm. No murmur, no impatience, no petulance did come from him. Silent, slow, and solemn; bowing over still further his chronically broken back, he toiled away, as if toil were life itself, and the heavy beating of his hammer the heavy beating of his heart. And so it was.—Most miserable! A peculiar walk in this old man, a certain slight but painful appearing yawing in his gait, had at an early period of the voyage excited the curiosity of the mariners. And to the importunity of their persisted questionings he had finally given in; and so it came to pass that every one now knew the shameful story of his wretched fate. Belated, and not innocently, one bitter winter's midnight, on the road running between two country towns, the blacksmith half-stupidly felt the deadly numbness stealing over him, and sought refuge in a leaning, dilapidated barn. The issue was, the loss of the extremities of both feet. Out of this revelation, part by part, at last came out the four acts of the gladness, and the one long, and as yet uncatastrophied fifth act of the grief of his life's drama. He was an old man, who, at the age of nearly sixty, had postponedly encountered that thing in sorrow's technicals called ruin. He had been an artisan of famed excellence, and with plenty to do; owned a house and garden; embraced a youthful, daughter-like, loving wife, and three blithe, ruddy children; every Sunday went to a cheerful-looking church, planted in a grove. But one night, under cover of darkness, and further concealed in a most cunning disguisement, a desperate burglar slid into his happy home, and robbed them all of everything. And darker yet to tell, the blacksmith himself did ignorantly conduct this burglar into his family's heart. It was the Bottle Conjuror! Upon the opening of that fatal cork, forth flew the fiend, and shrivelled up his home. Now, for prudent, most wise, and economic reasons, the blacksmith's shop was in the basement of his dwelling, but with a separate entrance to it; so that always had the young and loving healthy wife listened with no unhappy nervousness, but with vigorous pleasure, to the stout ringing of her young-armed old husband's hammer; whose reverberations, muffled by passing through the floors and walls, came up to her, not unsweetly, in her nursery; and so, to stout Labor's iron lullaby, the blacksmith's infants were rocked to slumber. Oh, woe on woe! Oh, Death, why canst thou not sometimes be timely? Hadst thou taken this old blacksmith to thyself ere his full ruin came upon him, then had the young widow had a delicious grief, and her orphans a truly venerable, legendary sire to dream of in their after years; and all of them a care-killing competency.\",\"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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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}"

198− headers:

199− Accept:

200− - application/json

201− Content-Type:

202− - application/json

203− User-Agent:

204− - Anthropic/Go 1.12.0

205− url: https://api.anthropic.com/v1/messages

206− method: POST

207− response:

208− proto: HTTP/2.0

209− proto_major: 2

210− proto_minor: 0

211− content_length: -1

212− body: |+

213− event: message_start

214− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_013boRMcJ6WXTJLGeihTDTQn","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":980,"cache_read_input_tokens":8667,"cache_creation":{"ephemeral_5m_input_tokens":980,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

215−

216− event: content_block_start

217− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

218−

219− event: content_block_delta

220− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Yes"} }

221−

222− event: content_block_delta

223− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":", it contains \"Herman\" (Herman"} }

224−

225− event: ping

226− data: {"type": "ping"}

227−

228− event: content_block_delta

229− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Melville) in the first line."} }

230−

231− event: content_block_stop

232− data: {"type":"content_block_stop","index":0 }

233−

234− event: message_delta

235− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":980,"cache_read_input_tokens":8667,"output_tokens":21} }

236−

237− event: message_stop

238− data: {"type":"message_stop" }

239−

240− headers:

241− Content-Type:

242− - text/event-stream; charset=utf-8

243− status: 200 OK

244− code: 200

245− duration: 2.482454875s

internal/agent/testdata/TestCoderAgent/anthropic-sonnet/glob_tool.yamldeleted−168

@@ -1,168 +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: 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 1.12.0

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_01FXonqh4CRaskWcSFpTBVeC","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":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":"Finding"} }

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":" Files with"}}

44−

45− event: content_block_delta

46− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Glob"} }

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":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: 550.481417ms

63−- id: 1

64− request:

65− proto: HTTP/1.1

66− proto_major: 1

67− proto_minor: 1

68− content_length: 32069

69− host: ""

70− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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 1.12.0

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_015aAoWx6ygTpFGHtvfoYkez","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":1802,"cache_read_input_tokens":6853,"cache_creation":{"ephemeral_5m_input_tokens":1802,"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_01CiThu8c8L9DgtKyE1RwQbU","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":3,"cache_creation_input_tokens":1802,"cache_read_input_tokens":6853,"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: 2.538935s

119−- id: 2

120− request:

121− proto: HTTP/1.1

122− proto_major: 1

123− proto_minor: 1

124− content_length: 32439

125− host: ""

126− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use glob to find all .go files in the current directory\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01CiThu8c8L9DgtKyE1RwQbU\",\"input\":{\"pattern\":\"*.go\"},\"name\":\"glob\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01CiThu8c8L9DgtKyE1RwQbU\",\"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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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 1.12.0

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_01VogCUV3zi9sLYPDKeEq64p","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":6,"cache_creation_input_tokens":86,"cache_read_input_tokens":8655,"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":"`"} }

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":6,"cache_creation_input_tokens":86,"cache_read_input_tokens":8655,"output_tokens":8} }

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: 2.1703915s

internal/agent/testdata/TestCoderAgent/anthropic-sonnet/grep_tool.yamldeleted−183

@@ -1,183 +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: 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 1.12.0

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_012JHSdafaYGKa7doAmoqq17","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: 592.433333ms

66−- id: 1

67− request:

68− proto: HTTP/1.1

69− proto_major: 1

70− proto_minor: 1

71− content_length: 32067

72− host: ""

73− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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 1.12.0

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_01T85q5no8RwmV56PJA7PFXc","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":1804,"cache_read_input_tokens":6853,"cache_creation":{"ephemeral_5m_input_tokens":1804,"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_01BpVu9fuTSX8GtfcFtF4B5i","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":"{\"patter"} }

100−

101− event: content_block_delta

102− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"n\": \"packag"} }

103−

104− event: content_block_delta

105− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"e\""} }

106−

107− event: content_block_delta

108− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"include\":"} }

109−

110− event: content_block_delta

111− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" \"*.go\"}"} }

112−

113− event: content_block_stop

114− data: {"type":"content_block_stop","index":0 }

115−

116− event: message_delta

117− data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":3,"cache_creation_input_tokens":1804,"cache_read_input_tokens":6853,"output_tokens":69} }

118−

119− event: message_stop

120− data: {"type":"message_stop" }

121−

122− headers:

123− Content-Type:

124− - text/event-stream; charset=utf-8

125− status: 200 OK

126− code: 200

127− duration: 2.190177334s

128−- id: 2

129− request:

130− proto: HTTP/1.1

131− proto_major: 1

132− proto_minor: 1

133− content_length: 32501

134− host: ""

135− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use grep to search for the word 'package' in go files\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01BpVu9fuTSX8GtfcFtF4B5i\",\"input\":{\"include\":\"*.go\",\"pattern\":\"package\"},\"name\":\"grep\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01BpVu9fuTSX8GtfcFtF4B5i\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"Found 1 matches\\n/tmp/crush-test/TestCoderAgent/anthropic-sonnet/grep_tool/main.go:\\n Line 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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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}"

136− headers:

137− Accept:

138− - application/json

139− Content-Type:

140− - application/json

141− User-Agent:

142− - Anthropic/Go 1.12.0

143− url: https://api.anthropic.com/v1/messages

144− method: POST

145− response:

146− proto: HTTP/2.0

147− proto_major: 2

148− proto_minor: 0

149− content_length: -1

150− body: |+

151− event: message_start

152− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01FAo1UdYq7G9CPG6q95Yrya","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":6,"cache_creation_input_tokens":120,"cache_read_input_tokens":8657,"cache_creation":{"ephemeral_5m_input_tokens":120,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

153−

154− event: content_block_start

155− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

156−

157− event: content_block_delta

158− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Foun"} }

159−

160− event: content_block_delta

161− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d 1 match in `main"} }

162−

163− event: ping

164− data: {"type": "ping"}

165−

166− event: content_block_delta

167− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":".go` at line 1."} }

168−

169− event: content_block_stop

170− data: {"type":"content_block_stop","index":0 }

171−

172− event: message_delta

173− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":6,"cache_creation_input_tokens":120,"cache_read_input_tokens":8657,"output_tokens":19} }

174−

175− event: message_stop

176− data: {"type":"message_stop" }

177−

178− headers:

179− Content-Type:

180− - text/event-stream; charset=utf-8

181− status: 200 OK

182− code: 200

183− duration: 1.973956917s

internal/agent/testdata/TestCoderAgent/anthropic-sonnet/ls_tool.yamldeleted−174

@@ -1,174 +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: 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 1.12.0

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_01WsuD73Q7FNCwhY6r9yesAF","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":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":"List"} }

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":140,"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: 508.105833ms

63−- id: 1

64− request:

65− proto: HTTP/1.1

66− proto_major: 1

67− proto_minor: 1

68− content_length: 32061

69− host: ""

70− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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 1.12.0

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_01EQmDNVC4ukLghSgfd5NSuj","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":1800,"cache_read_input_tokens":6853,"cache_creation":{"ephemeral_5m_input_tokens":1800,"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_014cpfm3Fz4JYkeqR2cjbpNm","name":"ls","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":"{\"path\":"}}

97−

98− event: content_block_delta

99− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" \".\"}"} }

100−

101− event: content_block_stop

102− data: {"type":"content_block_stop","index":0 }

103−

104− event: message_delta

105− data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":3,"cache_creation_input_tokens":1800,"cache_read_input_tokens":6853,"output_tokens":50} }

106−

107− event: message_stop

108− data: {"type":"message_stop" }

109−

110− headers:

111− Content-Type:

112− - text/event-stream; charset=utf-8

113− status: 200 OK

114− code: 200

115− duration: 2.599475s

116−- id: 2

117− request:

118− proto: HTTP/1.1

119− proto_major: 1

120− proto_minor: 1

121− content_length: 32445

122− host: ""

123− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use ls to list the files in the current directory\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_014cpfm3Fz4JYkeqR2cjbpNm\",\"input\":{\"path\":\".\"},\"name\":\"ls\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_014cpfm3Fz4JYkeqR2cjbpNm\",\"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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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}"

124− headers:

125− Accept:

126− - application/json

127− Content-Type:

128− - application/json

129− User-Agent:

130− - Anthropic/Go 1.12.0

131− url: https://api.anthropic.com/v1/messages

132− method: POST

133− response:

134− proto: HTTP/2.0

135− proto_major: 2

136− proto_minor: 0

137− content_length: -1

138− body: |+

139− event: message_start

140− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01HYUPtHYzevgHi9AXRzhzaM","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":6,"cache_creation_input_tokens":97,"cache_read_input_tokens":8653,"cache_creation":{"ephemeral_5m_input_tokens":97,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

141−

142− event: content_block_start

143− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

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":"\ngo.mod\nmain.go\n```"} }

150−

151− event: ping

152− data: {"type": "ping"}

153−

154− event: content_block_stop

155− data: {"type":"content_block_stop","index":0 }

156−

157− event: ping

158− data: {"type": "ping"}

159−

160− event: ping

161− data: {"type": "ping"}

162−

163− event: message_delta

164− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":6,"cache_creation_input_tokens":97,"cache_read_input_tokens":8653,"output_tokens":14} }

165−

166− event: message_stop

167− data: {"type":"message_stop" }

168−

169− headers:

170− Content-Type:

171− - text/event-stream; charset=utf-8

172− status: 200 OK

173− code: 200

174− duration: 2.239520333s

internal/agent/testdata/TestCoderAgent/anthropic-sonnet/multiedit_tool.yamldeleted−314

@@ -1,314 +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: 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 1.12.0

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_012wZCQZFhzqRTZZ7xbNXT9P","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":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":"Modify"} }

35−

36− event: content_block_delta

37− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Greeting in"} }

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":" main.go File"} }

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":170,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":12} }

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: 593.423917ms

60−- id: 1

61− request:

62− proto: HTTP/1.1

63− proto_major: 1

64− proto_minor: 1

65− content_length: 32147

66− host: ""

67− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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 1.12.0

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_01TY1ypWiFAWPQkRLEmEo4Tt","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":1832,"cache_read_input_tokens":6853,"cache_creation":{"ephemeral_5m_input_tokens":1832,"ephemeral_1h_input_tokens":0},"output_tokens":3,"service_tier":"standard"}} }

85−

86− event: content_block_start

87− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

88−

89− event: content_block_delta

90− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"I'll first"} }

91−

92− event: content_block_delta

93− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" check the content of main.go, then use mult"} }

94−

95− event: ping

96− data: {"type": "ping"}

97−

98− event: content_block_delta

99− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"iedit to make both changes."} }

100−

101− event: content_block_stop

102− data: {"type":"content_block_stop","index":0 }

103−

104− event: content_block_start

105− data: {"type":"content_block_start","index":1,"content_block":{"type":"tool_use","id":"toolu_01EkVHzmaPGJju2LRYbGM3gJ","name":"view","input":{}} }

106−

107− event: content_block_delta

108− data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":""} }

109−

110− event: content_block_delta

111− data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"{\"f"} }

112−

113− event: content_block_delta

114− data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"ile_path\""} }

115−

116− event: content_block_delta

117− data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":": \"main.g"} }

118−

119− event: content_block_delta

120− data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"o\"}"} }

121−

122− event: content_block_stop

123− data: {"type":"content_block_stop","index":1 }

124−

125− event: message_delta

126− data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":3,"cache_creation_input_tokens":1832,"cache_read_input_tokens":6853,"output_tokens":77} }

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: 2.025194292s

137−- id: 2

138− request:

139− proto: HTTP/1.1

140− proto_major: 1

141− proto_minor: 1

142− content_length: 32736

143− host: ""

144− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"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 first check the content of main.go, then use multiedit to make both changes.\",\"type\":\"text\"},{\"id\":\"toolu_01EkVHzmaPGJju2LRYbGM3gJ\",\"input\":{\"file_path\":\"main.go\"},\"name\":\"view\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01EkVHzmaPGJju2LRYbGM3gJ\",\"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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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 1.12.0

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_01FWCXTK929EjksLY27954m7","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":6,"cache_creation_input_tokens":141,"cache_read_input_tokens":8685,"cache_creation":{"ephemeral_5m_input_tokens":141,"ephemeral_1h_input_tokens":0},"output_tokens":25,"service_tier":"standard"}} }

162−

163− event: content_block_start

164− data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01SwJeR8LmvPpgUvmyVq4DRp","name":"multiedit","input":{}} }

165−

166− event: content_block_delta

167− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }

168−

169− event: content_block_delta

170− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\""} }

171−

172− event: content_block_delta

173− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"file_pat"} }

174−

175− event: content_block_delta

176− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"h\": \"m"} }

177−

178− event: content_block_delta

179− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ain.go\""} }

180−

181− event: content_block_delta

182− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"edi"} }

183−

184− event: content_block_delta

185− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ts\": [{"}}

186−

187− event: content_block_delta

188− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"old_str"} }

189−

190− event: content_block_delta

191− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ing"}}

192−

193− event: content_block_delta

194− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\":\"\\tfmt"} }

195−

196− event: content_block_delta

197− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".Println(\\\""} }

198−

199− event: content_block_delta

200− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"Hel"} }

201−

202− event: content_block_delta

203− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"lo, Worl"} }

204−

205− event: content_block_delta

206− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"d!\\\")\""} }

207−

208− event: content_block_delta

209− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":",\"new_s"} }

210−

211− event: content_block_delta

212− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tring"} }

213−

214− event: content_block_delta

215− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\":\"\\t// Gr"} }

216−

217− event: content_block_delta

218− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"eet"} }

219−

220− event: content_block_delta

221− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ing"} }

222−

223− event: content_block_delta

224− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\\n\\tf"} }

225−

226− event: content_block_delta

227− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"mt.Printl"} }

228−

229− event: content_block_delta

230− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"n(\\\"Hell"} }

231−

232− event: content_block_delta

233− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"o, Cru"} }

234−

235− event: content_block_delta

236− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"sh!\\\")\"}"} }

237−

238− event: content_block_delta

239− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"]}"} }

240−

241− event: content_block_stop

242− data: {"type":"content_block_stop","index":0 }

243−

244− event: message_delta

245− data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":6,"cache_creation_input_tokens":141,"cache_read_input_tokens":8685,"output_tokens":133} }

246−

247− event: message_stop

248− data: {"type":"message_stop" }

249−

250− headers:

251− Content-Type:

252− - text/event-stream; charset=utf-8

253− status: 200 OK

254− code: 200

255− duration: 2.222343667s

256−- id: 3

257− request:

258− proto: HTTP/1.1

259− proto_major: 1

260− proto_minor: 1

261− content_length: 33275

262− host: ""

263− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"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 first check the content of main.go, then use multiedit to make both changes.\",\"type\":\"text\"},{\"id\":\"toolu_01EkVHzmaPGJju2LRYbGM3gJ\",\"input\":{\"file_path\":\"main.go\"},\"name\":\"view\",\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01EkVHzmaPGJju2LRYbGM3gJ\",\"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_01SwJeR8LmvPpgUvmyVq4DRp\",\"input\":{\"edits\":[{\"new_string\":\"\\t// Greeting\\n\\tfmt.Println(\\\"Hello, Crush!\\\")\",\"old_string\":\"\\tfmt.Println(\\\"Hello, World!\\\")\"}],\"file_path\":\"main.go\"},\"name\":\"multiedit\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01SwJeR8LmvPpgUvmyVq4DRp\",\"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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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}"

264− headers:

265− Accept:

266− - application/json

267− Content-Type:

268− - application/json

269− User-Agent:

270− - Anthropic/Go 1.12.0

271− url: https://api.anthropic.com/v1/messages

272− method: POST

273− response:

274− proto: HTTP/2.0

275− proto_major: 2

276− proto_minor: 0

277− content_length: -1

278− body: |+

279− event: message_start

280− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_018XV2bezokrWMT4B8rr8dnp","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":6,"cache_creation_input_tokens":178,"cache_read_input_tokens":8826,"cache_creation":{"ephemeral_5m_input_tokens":178,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

281−

282− event: content_block_start

283− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

284−

285− event: content_block_delta

286− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Done"} }

287−

288− event: content_block_delta

289− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":". Changed \"Hello, World!\" to \"Hello"} }

290−

291− event: ping

292− data: {"type": "ping"}

293−

294− event: content_block_delta

295− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":", Crush!\" and added the comment above the println"} }

296−

297− event: content_block_delta

298− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"."} }

299−

300− event: content_block_stop

301− data: {"type":"content_block_stop","index":0 }

302−

303− event: message_delta

304− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":6,"cache_creation_input_tokens":178,"cache_read_input_tokens":8826,"output_tokens":26}}

305−

306− event: message_stop

307− data: {"type":"message_stop" }

308−

309− headers:

310− Content-Type:

311− - text/event-stream; charset=utf-8

312− status: 200 OK

313− code: 200

314− duration: 2.106580459s

internal/agent/testdata/TestCoderAgent/anthropic-sonnet/parallel_tool_calls.yamldeleted−201

@@ -1,201 +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: 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 1.12.0

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_01QG9K82nFdNjFtQk7NoK5QB","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":" Search and Directory"} }

44−

45− event: content_block_delta

46− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" 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":12} }

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: 514.665167ms

63−- id: 1

64− request:

65− proto: HTTP/1.1

66− proto_major: 1

67− proto_minor: 1

68− content_length: 32158

69− host: ""

70− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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 1.12.0

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_0145i9s7oaHwEazjgovKd81D","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":1821,"cache_read_input_tokens":6853,"cache_creation":{"ephemeral_5m_input_tokens":1821,"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_01TeEXyjpFCqWrAh2Wd8qBh7","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":"{\"pat"} }

97−

98− event: content_block_delta

99− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tern"} }

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":" \"**/*"} }

106−

107− event: content_block_delta

108− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".g"} }

109−

110− event: content_block_delta

111− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"o\"}"} }

112−

113− event: content_block_stop

114− data: {"type":"content_block_stop","index":0 }

115−

116− event: content_block_start

117− data: {"type":"content_block_start","index":1,"content_block":{"type":"tool_use","id":"toolu_01N8sSFCLzvYCd2uXbz4jUGT","name":"ls","input":{}} }

118−

119− event: content_block_delta

120− data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":""} }

121−

122− event: content_block_delta

123− data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"{\"path\": \""} }

124−

125− event: content_block_delta

126− data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":".\"}"} }

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":3,"cache_creation_input_tokens":1821,"cache_read_input_tokens":6853,"output_tokens":86} }

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: 2.443706708s

143−- id: 2

144− request:

145− proto: HTTP/1.1

146− proto_major: 1

147− proto_minor: 1

148− content_length: 32839

149− host: ""

150− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"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_01TeEXyjpFCqWrAh2Wd8qBh7\",\"input\":{\"pattern\":\"**/*.go\"},\"name\":\"glob\",\"type\":\"tool_use\"},{\"id\":\"toolu_01N8sSFCLzvYCd2uXbz4jUGT\",\"input\":{\"path\":\".\"},\"name\":\"ls\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01TeEXyjpFCqWrAh2Wd8qBh7\",\"content\":[{\"text\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/parallel_tool_calls/main.go\",\"type\":\"text\"}],\"type\":\"tool_result\"},{\"tool_use_id\":\"toolu_01N8sSFCLzvYCd2uXbz4jUGT\",\"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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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 1.12.0

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_01CfHH9AC59iAZSPJ4Ec3Khu","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":7,"cache_creation_input_tokens":207,"cache_read_input_tokens":8674,"cache_creation":{"ephemeral_5m_input_tokens":207,"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":"Foun"} }

174−

175− event: content_block_delta

176− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d 1 Go file:"} }

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":" `main.go`\n\nCurrent directory contains"} }

183−

184− event: content_block_delta

185− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":": `go.mod` and `main.go`"} }

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":7,"cache_creation_input_tokens":207,"cache_read_input_tokens":8674,"output_tokens":31} }

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: 2.043650083s

internal/agent/testdata/TestCoderAgent/anthropic-sonnet/read_a_file.yamldeleted−183

@@ -1,183 +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: 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 1.12.0

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_01AosjrFVVXCqAidJohxn6E7","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":" Details"}}

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: 550.275666ms

63−- id: 1

64− request:

65− proto: HTTP/1.1

66− proto_major: 1

67− proto_minor: 1

68− content_length: 32031

69− host: ""

70− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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 1.12.0

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_01EfY8UeWMNayyJJUGdNLeWM","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":1796,"cache_read_input_tokens":6853,"cache_creation":{"ephemeral_5m_input_tokens":1796,"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_016p6McX7tVqThB1FwChHmMm","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_path\""} }

97−

98− event: content_block_delta

99− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":": \"go.mod"} }

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_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":3,"cache_creation_input_tokens":1796,"cache_read_input_tokens":6853,"output_tokens":55} }

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: 2.078621417s

119−- id: 2

120− request:

121− proto: HTTP/1.1

122− proto_major: 1

123− proto_minor: 1

124− content_length: 32441

125− host: ""

126− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"Read the go mod\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_016p6McX7tVqThB1FwChHmMm\",\"input\":{\"file_path\":\"go.mod\"},\"name\":\"view\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_016p6McX7tVqThB1FwChHmMm\",\"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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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 1.12.0

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_019XZCDz8LmAGBwQsusVMYtg","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":6,"cache_creation_input_tokens":96,"cache_read_input_tokens":8649,"cache_creation":{"ephemeral_5m_input_tokens":96,"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":"```"} }

150−

151− event: content_block_delta

152− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"\nmodule example.com/testproject\n\ngo 1.23"} }

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":"\n```"} }

159−

160− event: ping

161− data: {"type": "ping"}

162−

163− event: content_block_stop

164− data: {"type":"content_block_stop","index":0 }

165−

166− event: ping

167− data: {"type": "ping"}

168−

169− event: ping

170− data: {"type": "ping"}

171−

172− event: message_delta

173− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":6,"cache_creation_input_tokens":96,"cache_read_input_tokens":8649,"output_tokens":20} }

174−

175− event: message_stop

176− data: {"type":"message_stop" }

177−

178− headers:

179− Content-Type:

180− - text/event-stream; charset=utf-8

181− status: 200 OK

182− code: 200

183− duration: 2.382524875s

internal/agent/testdata/TestCoderAgent/anthropic-sonnet/simple_test.yamldeleted−109

@@ -1,109 +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: 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 1.12.0

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_01FAWvBoccVMmLTBJwcdyBep","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":" Chat"} }

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":" Start"} }

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":131,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":6} }

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: 733.150917ms

60−- id: 1

61− request:

62− proto: HTTP/1.1

63− proto_major: 1

64− proto_minor: 1

65− content_length: 32021

66− host: ""

67− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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 1.12.0

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_016wHt1RPkbhRGGRDo89QjdQ","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":8644,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":8644,"ephemeral_1h_input_tokens":0},"output_tokens":3,"service_tier":"standard"}} }

85−

86− event: content_block_start

87− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

88−

89− event: content_block_delta

90− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Hello! How"} }

91−

92− event: content_block_delta

93− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" can I help you today?"} }

94−

95− event: content_block_stop

96− data: {"type":"content_block_stop","index":0 }

97−

98− event: message_delta

99− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":3,"cache_creation_input_tokens":8644,"cache_read_input_tokens":0,"output_tokens":12}}

100−

101− event: message_stop

102− data: {"type":"message_stop" }

103−

104− headers:

105− Content-Type:

106− - text/event-stream; charset=utf-8

107− status: 200 OK

108− code: 200

109− duration: 2.528825917s

internal/agent/testdata/TestCoderAgent/anthropic-sonnet/sourcegraph_tool.yamldeleted−223

@@ -1,223 +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: 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 1.12.0

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_0137phYsnpb3ZLZ6xWV4o1qc","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":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":" 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":" Repos"} }

44−

45− event: content_block_delta

46− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" for Main"} }

47−

48− event: content_block_delta

49− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Functions"} }

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":145,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":11} }

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: 561.671875ms

66−- id: 1

67− request:

68− proto: HTTP/1.1

69− proto_major: 1

70− proto_minor: 1

71− content_length: 32081

72− host: ""

73− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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 1.12.0

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_01L5zZBpdDM2uiQ2eLwF7YxE","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":1807,"cache_read_input_tokens":6853,"cache_creation":{"ephemeral_5m_input_tokens":1807,"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_01SSVxWDkehx1WmUUkrDb3xg","name":"sourcegraph","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":"{\""} }

100−

101− event: content_block_delta

102− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"query"} }

103−

104− event: content_block_delta

105− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\": \"lang:go "} }

106−

107− event: content_block_delta

108− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"func "} }

109−

110− event: content_block_delta

111− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"main\""} }

112−

113− event: content_block_delta

114− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \""} }

115−

116− event: content_block_delta

117− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"count\": 10}"} }

118−

119− event: content_block_stop

120− data: {"type":"content_block_stop","index":0 }

121−

122− event: message_delta

123− data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":3,"cache_creation_input_tokens":1807,"cache_read_input_tokens":6853,"output_tokens":74} }

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: 2.650093625s

134−- id: 2

135− request:

136− proto: HTTP/1.1

137− proto_major: 1

138− proto_minor: 1

139− content_length: 424

140− host: sourcegraph.com

141− 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"}}'

142− headers:

143− Content-Type:

144− - application/json

145− User-Agent:

146− - crush/1.0

147− url: https://sourcegraph.com/.api/graphql

148− method: POST

149− response:

150− proto: HTTP/2.0

151− proto_major: 2

152− proto_minor: 0

153− content_length: -1

154− uncompressed: true

155− body: '{"data":{"search":{"results":{"matchCount":30,"limitHit":true,"resultCount":30,"approximateResultCount":"30+","missing":[],"timedout":[],"indexUnavailable":false,"results":[{"__typename":"FileMatch","repository":{"name":"github.com/pingguoxueyuan/gostudy"},"file":{"path":"listen15/defer/main.go","url":"/github.com/pingguoxueyuan/gostudy/-/blob/listen15/defer/main.go","content":"package main\n\nimport (\n\t\"fmt\"\n)\n\nfunc funcA() int {\n\tx := 5\n\tdefer func() {\n\t\tx += 1\n\t}()\n\treturn x\n}\n\nfunc funcB() (x int) {\n\tdefer func() {\n\t\tx += 1\n\t}()\n\treturn 5\n}\n\nfunc funcC() (y int) {\n\tx := 5\n\tdefer func() {\n\t\tx += 1\n\t}()\n\treturn x\n}\n\nfunc funcD() (x int) {\n\tdefer func(x int) {\n\t\tx += 1\n\t}(x)\n\treturn 5\n}\n\nfunc main() {\n\t//fmt.Println(funcA())\n\t//fmt.Println(funcB())\n\t//fmt.Println(funcC())\n\tfmt.Println(funcD())\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":36,"offsetAndLengths":[[0,9]]},{"preview":"\t//fmt.Println(funcA())","lineNumber":37,"offsetAndLengths":[[15,4]]},{"preview":"\t//fmt.Println(funcB())","lineNumber":38,"offsetAndLengths":[[15,4]]},{"preview":"\t//fmt.Println(funcC())","lineNumber":39,"offsetAndLengths":[[15,4]]},{"preview":"\tfmt.Println(funcD())","lineNumber":40,"offsetAndLengths":[[13,4]]},{"preview":"func funcA() int {","lineNumber":6,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tdefer func() {","lineNumber":8,"offsetAndLengths":[[7,4]]},{"preview":"package main","lineNumber":0,"offsetAndLengths":[[8,4]]},{"preview":"func funcB() (x int) {","lineNumber":14,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tdefer func() {","lineNumber":15,"offsetAndLengths":[[7,4]]},{"preview":"func funcC() (y int) {","lineNumber":21,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tdefer func() {","lineNumber":23,"offsetAndLengths":[[7,4]]},{"preview":"func funcD() (x int) {","lineNumber":29,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tdefer func(x int) {","lineNumber":30,"offsetAndLengths":[[7,4]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/Zhouchaowen/golang-tutorial"},"file":{"path":"12-library/8-error/ch_1/main.go","url":"/github.com/Zhouchaowen/golang-tutorial/-/blob/12-library/8-error/ch_1/main.go","content":"package main\n\nimport (\n\t\"errors\"\n\t\"fmt\"\n)\n\nfunc func1() error {\n\treturn errors.New(\"func1 error\")\n}\n\nfunc func2() error {\n\treturn fmt.Errorf(\"func2 error: %w\", func1())\n}\n\nfunc main() {\n\terr := func2()\n\tif err != nil {\n\t\tfmt.Println(err)\n\t}\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":15,"offsetAndLengths":[[0,9]]},{"preview":"\terr := func2()","lineNumber":16,"offsetAndLengths":[[8,4]]},{"preview":"func func1() error {","lineNumber":7,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\treturn errors.New(\"func1 error\")","lineNumber":8,"offsetAndLengths":[[20,4]]},{"preview":"func func2() error {","lineNumber":11,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\treturn fmt.Errorf(\"func2 error: %w\", func1())","lineNumber":12,"offsetAndLengths":[[20,4],[38,4]]},{"preview":"package main","lineNumber":0,"offsetAndLengths":[[8,4]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/GoesToEleven/lynda"},"file":{"path":"cc/00_language-fundamentals/14_functions/10_func-expression/01_before-func-expression/main.go","url":"/github.com/GoesToEleven/lynda/-/blob/cc/00_language-fundamentals/14_functions/10_func-expression/01_before-func-expression/main.go","content":"package main\n\nimport \"fmt\"\n\nfunc greeting() {\n\tfmt.Println(\"Hello world!\")\n}\n\nfunc main() {\n\tgreeting()\n}\n\n/*\nAll material is licensed under the Apache License Version 2.0, January 2004\nhttp://www.apache.org/licenses/LICENSE-2.0\n*/\n"},"lineMatches":[{"preview":"func main() {","lineNumber":8,"offsetAndLengths":[[0,9]]},{"preview":"package main","lineNumber":0,"offsetAndLengths":[[8,4]]}]}]}}}}'

156− headers:

157− Content-Type:

158− - application/json

159− status: 200 OK

160− code: 200

161− duration: 1.454512083s

162−- id: 3

163− request:

164− proto: HTTP/1.1

165− proto_major: 1

166− proto_minor: 1

167− content_length: 40202

168− host: ""

169− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use sourcegraph to search for 'func main' in Go repositories\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01SSVxWDkehx1WmUUkrDb3xg\",\"input\":{\"count\":10,\"query\":\"lang:go func main\"},\"name\":\"sourcegraph\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01SSVxWDkehx1WmUUkrDb3xg\",\"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/pingguoxueyuan/gostudy/listen15/defer/main.go\\n\\nURL: /github.com/pingguoxueyuan/gostudy/-/blob/listen15/defer/main.go\\n\\n```\\n26| \\t}()\\n27| \\treturn x\\n28| }\\n29| \\n30| func funcD() (x int) {\\n31| \\tdefer func(x int) {\\n32| \\t\\tx += 1\\n33| \\t}(x)\\n34| \\treturn 5\\n35| }\\n36| func main() {\\n37| func main() {\\n38| \\t//fmt.Println(funcA())\\n39| \\t//fmt.Println(funcB())\\n40| \\t//fmt.Println(funcC())\\n41| \\tfmt.Println(funcD())\\n42| }\\n43| \\n```\\n\\n```\\n27| \\treturn x\\n28| }\\n29| \\n30| func funcD() (x int) {\\n31| \\tdefer func(x int) {\\n32| \\t\\tx += 1\\n33| \\t}(x)\\n34| \\treturn 5\\n35| }\\n36| \\n37| \\t//fmt.Println(funcA())\\n38| \\t//fmt.Println(funcA())\\n39| \\t//fmt.Println(funcB())\\n40| \\t//fmt.Println(funcC())\\n41| \\tfmt.Println(funcD())\\n42| }\\n43| \\n```\\n\\n```\\n28| }\\n29| \\n30| func funcD() (x int) {\\n31| \\tdefer func(x int) {\\n32| \\t\\tx += 1\\n33| \\t}(x)\\n34| \\treturn 5\\n35| }\\n36| \\n37| func main() {\\n38| \\t//fmt.Println(funcB())\\n39| \\t//fmt.Println(funcB())\\n40| \\t//fmt.Println(funcC())\\n41| \\tfmt.Println(funcD())\\n42| }\\n43| \\n```\\n\\n```\\n29| \\n30| func funcD() (x int) {\\n31| \\tdefer func(x int) {\\n32| \\t\\tx += 1\\n33| \\t}(x)\\n34| \\treturn 5\\n35| }\\n36| \\n37| func main() {\\n38| \\t//fmt.Println(funcA())\\n39| \\t//fmt.Println(funcC())\\n40| \\t//fmt.Println(funcC())\\n41| \\tfmt.Println(funcD())\\n42| }\\n43| \\n```\\n\\n```\\n30| func funcD() (x int) {\\n31| \\tdefer func(x int) {\\n32| \\t\\tx += 1\\n33| \\t}(x)\\n34| \\treturn 5\\n35| }\\n36| \\n37| func main() {\\n38| \\t//fmt.Println(funcA())\\n39| \\t//fmt.Println(funcB())\\n40| \\tfmt.Println(funcD())\\n41| \\tfmt.Println(funcD())\\n42| }\\n43| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import (\\n4| \\t\\\"fmt\\\"\\n5| )\\n6| func funcA() int {\\n7| func funcA() int {\\n8| \\tx := 5\\n9| \\tdefer func() {\\n10| \\t\\tx += 1\\n11| \\t}()\\n12| \\treturn x\\n13| }\\n14| \\n15| func funcB() (x int) {\\n16| \\tdefer func() {\\n```\\n\\n```\\n1| package main\\n2| \\n3| import (\\n4| \\t\\\"fmt\\\"\\n5| )\\n6| \\n7| func funcA() int {\\n8| \\tdefer func() {\\n9| \\tdefer func() {\\n10| \\t\\tx += 1\\n11| \\t}()\\n12| \\treturn x\\n13| }\\n14| \\n15| func funcB() (x int) {\\n16| \\tdefer func() {\\n17| \\t\\tx += 1\\n18| \\t}()\\n```\\n\\n```\\n0| package main\\n1| package main\\n2| \\n3| import (\\n4| \\t\\\"fmt\\\"\\n5| )\\n6| \\n7| func funcA() int {\\n8| \\tx := 5\\n9| \\tdefer func() {\\n10| \\t\\tx += 1\\n```\\n\\n```\\n4| \\t\\\"fmt\\\"\\n5| )\\n6| \\n7| func funcA() int {\\n8| \\tx := 5\\n9| \\tdefer func() {\\n10| \\t\\tx += 1\\n11| \\t}()\\n12| \\treturn x\\n13| }\\n14| func funcB() (x int) {\\n15| func funcB() (x int) {\\n16| \\tdefer func() {\\n17| \\t\\tx += 1\\n18| \\t}()\\n19| \\treturn 5\\n20| }\\n21| \\n22| func funcC() (y int) {\\n23| \\tx := 5\\n24| \\tdefer func() {\\n```\\n\\n```\\n5| )\\n6| \\n7| func funcA() int {\\n8| \\tx := 5\\n9| \\tdefer func() {\\n10| \\t\\tx += 1\\n11| \\t}()\\n12| \\treturn x\\n13| }\\n14| \\n15| \\tdefer func() {\\n16| \\tdefer func() {\\n17| \\t\\tx += 1\\n18| \\t}()\\n19| \\treturn 5\\n20| }\\n21| \\n22| func funcC() (y int) {\\n23| \\tx := 5\\n24| \\tdefer func() {\\n25| \\t\\tx += 1\\n```\\n\\n```\\n11| \\t}()\\n12| \\treturn x\\n13| }\\n14| \\n15| func funcB() (x int) {\\n16| \\tdefer func() {\\n17| \\t\\tx += 1\\n18| \\t}()\\n19| \\treturn 5\\n20| }\\n21| func funcC() (y int) {\\n22| func funcC() (y int) {\\n23| \\tx := 5\\n24| \\tdefer func() {\\n25| \\t\\tx += 1\\n26| \\t}()\\n27| \\treturn x\\n28| }\\n29| \\n30| func funcD() (x int) {\\n31| \\tdefer func(x int) {\\n```\\n\\n```\\n13| }\\n14| \\n15| func funcB() (x int) {\\n16| \\tdefer func() {\\n17| \\t\\tx += 1\\n18| \\t}()\\n19| \\treturn 5\\n20| }\\n21| \\n22| func funcC() (y int) {\\n23| \\tdefer func() {\\n24| \\tdefer func() {\\n25| \\t\\tx += 1\\n26| \\t}()\\n27| \\treturn x\\n28| }\\n29| \\n30| func funcD() (x int) {\\n31| \\tdefer func(x int) {\\n32| \\t\\tx += 1\\n33| \\t}(x)\\n```\\n\\n```\\n19| \\treturn 5\\n20| }\\n21| \\n22| func funcC() (y int) {\\n23| \\tx := 5\\n24| \\tdefer func() {\\n25| \\t\\tx += 1\\n26| \\t}()\\n27| \\treturn x\\n28| }\\n29| func funcD() (x int) {\\n30| func funcD() (x int) {\\n31| \\tdefer func(x int) {\\n32| \\t\\tx += 1\\n33| \\t}(x)\\n34| \\treturn 5\\n35| }\\n36| \\n37| func main() {\\n38| \\t//fmt.Println(funcA())\\n39| \\t//fmt.Println(funcB())\\n```\\n\\n```\\n20| }\\n21| \\n22| func funcC() (y int) {\\n23| \\tx := 5\\n24| \\tdefer func() {\\n25| \\t\\tx += 1\\n26| \\t}()\\n27| \\treturn x\\n28| }\\n29| \\n30| \\tdefer func(x int) {\\n31| \\tdefer func(x int) {\\n32| \\t\\tx += 1\\n33| \\t}(x)\\n34| \\treturn 5\\n35| }\\n36| \\n37| func main() {\\n38| \\t//fmt.Println(funcA())\\n39| \\t//fmt.Println(funcB())\\n40| \\t//fmt.Println(funcC())\\n```\\n\\n## Result 2: github.com/Zhouchaowen/golang-tutorial/12-library/8-error/ch_1/main.go\\n\\nURL: /github.com/Zhouchaowen/golang-tutorial/-/blob/12-library/8-error/ch_1/main.go\\n\\n```\\n5| \\t\\\"fmt\\\"\\n6| )\\n7| \\n8| func func1() error {\\n9| \\treturn errors.New(\\\"func1 error\\\")\\n10| }\\n11| \\n12| func func2() error {\\n13| \\treturn fmt.Errorf(\\\"func2 error: %w\\\", func1())\\n14| }\\n15| func main() {\\n16| func main() {\\n17| \\terr := func2()\\n18| \\tif err != nil {\\n19| \\t\\tfmt.Println(err)\\n20| \\t}\\n21| }\\n22| \\n```\\n\\n```\\n6| )\\n7| \\n8| func func1() error {\\n9| \\treturn errors.New(\\\"func1 error\\\")\\n10| }\\n11| \\n12| func func2() error {\\n13| \\treturn fmt.Errorf(\\\"func2 error: %w\\\", func1())\\n14| }\\n15| \\n16| \\terr := func2()\\n17| \\terr := func2()\\n18| \\tif err != nil {\\n19| \\t\\tfmt.Println(err)\\n20| \\t}\\n21| }\\n22| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import (\\n4| \\t\\\"errors\\\"\\n5| \\t\\\"fmt\\\"\\n6| )\\n7| func func1() error {\\n8| func func1() error {\\n9| \\treturn errors.New(\\\"func1 error\\\")\\n10| }\\n11| \\n12| func func2() error {\\n13| \\treturn fmt.Errorf(\\\"func2 error: %w\\\", func1())\\n14| }\\n15| \\n16| func main() {\\n17| \\terr := func2()\\n```\\n\\n```\\n1| package main\\n2| \\n3| import (\\n4| \\t\\\"errors\\\"\\n5| \\t\\\"fmt\\\"\\n6| )\\n7| \\n8| \\treturn errors.New(\\\"func1 error\\\")\\n9| \\treturn errors.New(\\\"func1 error\\\")\\n10| }\\n11| \\n12| func func2() error {\\n13| \\treturn fmt.Errorf(\\\"func2 error: %w\\\", func1())\\n14| }\\n15| \\n16| func main() {\\n17| \\terr := func2()\\n18| \\tif err != nil {\\n```\\n\\n```\\n1| package main\\n2| \\n3| import (\\n4| \\t\\\"errors\\\"\\n5| \\t\\\"fmt\\\"\\n6| )\\n7| \\n8| func func1() error {\\n9| \\treturn errors.New(\\\"func1 error\\\")\\n10| }\\n11| func func2() error {\\n12| func func2() error {\\n13| \\treturn fmt.Errorf(\\\"func2 error: %w\\\", func1())\\n14| }\\n15| \\n16| func main() {\\n17| \\terr := func2()\\n18| \\tif err != nil {\\n19| \\t\\tfmt.Println(err)\\n20| \\t}\\n21| }\\n```\\n\\n```\\n2| \\n3| import (\\n4| \\t\\\"errors\\\"\\n5| \\t\\\"fmt\\\"\\n6| )\\n7| \\n8| func func1() error {\\n9| \\treturn errors.New(\\\"func1 error\\\")\\n10| }\\n11| \\n12| \\treturn fmt.Errorf(\\\"func2 error: %w\\\", func1())\\n13| \\treturn fmt.Errorf(\\\"func2 error: %w\\\", func1())\\n14| }\\n15| \\n16| func main() {\\n17| \\terr := func2()\\n18| \\tif err != nil {\\n19| \\t\\tfmt.Println(err)\\n20| \\t}\\n21| }\\n22| \\n```\\n\\n```\\n0| package main\\n1| package main\\n2| \\n3| import (\\n4| \\t\\\"errors\\\"\\n5| \\t\\\"fmt\\\"\\n6| )\\n7| \\n8| func func1() error {\\n9| \\treturn errors.New(\\\"func1 error\\\")\\n10| }\\n```\\n\\n## Result 3: github.com/GoesToEleven/lynda/cc/00_language-fundamentals/14_functions/10_func-expression/01_before-func-expression/main.go\\n\\nURL: /github.com/GoesToEleven/lynda/-/blob/cc/00_language-fundamentals/14_functions/10_func-expression/01_before-func-expression/main.go\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func greeting() {\\n6| \\tfmt.Println(\\\"Hello world!\\\")\\n7| }\\n8| func main() {\\n9| func main() {\\n10| \\tgreeting()\\n11| }\\n12| \\n13| /*\\n14| All material is licensed under the Apache License Version 2.0, January 2004\\n15| http://www.apache.org/licenses/LICENSE-2.0\\n16| */\\n17| \\n```\\n\\n```\\n0| package main\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func greeting() {\\n6| \\tfmt.Println(\\\"Hello world!\\\")\\n7| }\\n8| \\n9| func main() {\\n10| \\tgreeting()\\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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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}"

170− headers:

171− Accept:

172− - application/json

173− Content-Type:

174− - application/json

175− User-Agent:

176− - Anthropic/Go 1.12.0

177− url: https://api.anthropic.com/v1/messages

178− method: POST

179− response:

180− proto: HTTP/2.0

181− proto_major: 2

182− proto_minor: 0

183− content_length: -1

184− body: |+

185− event: message_start

186− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01LRLuMdSjNZajNN2EUxAd4C","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":6,"cache_creation_input_tokens":3612,"cache_read_input_tokens":8660,"cache_creation":{"ephemeral_5m_input_tokens":3612,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

187−

188− event: content_block_start

189− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

190−

191− event: content_block_delta

192− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Foun"} }

193−

194− event: content_block_delta

195− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d 30 matches across 30 files. The"} }

196−

197− event: ping

198− data: {"type": "ping"}

199−

200− event: content_block_delta

201− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" search returned Go repositories containing `func main` declarations"} }

202−

203− event: content_block_delta

204− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":", including examples from tutorial repositories showing"} }

205−

206− event: content_block_delta

207− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" various Go language features like defer statements, error handling, and function expressions."} }

208−

209− event: content_block_stop

210− data: {"type":"content_block_stop","index":0 }

211−

212− event: message_delta

213− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":6,"cache_creation_input_tokens":3612,"cache_read_input_tokens":8660,"output_tokens":47} }

214−

215− event: message_stop

216− data: {"type":"message_stop" }

217−

218− headers:

219− Content-Type:

220− - text/event-stream; charset=utf-8

221− status: 200 OK

222− code: 200

223− duration: 2.523495s

internal/agent/testdata/TestCoderAgent/anthropic-sonnet/update_a_file.yamldeleted−293

@@ -1,293 +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: 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 1.12.0

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_0124XpcSuB61ZBx1SPUnu1Qb","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: 648.821083ms

63−- id: 1

64− request:

65− proto: HTTP/1.1

66− proto_major: 1

67− proto_minor: 1

68− content_length: 32087

69− host: ""

70− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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 1.12.0

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_01WDos6sXG37avomBTwjHnLi","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":1807,"cache_read_input_tokens":6853,"cache_creation":{"ephemeral_5m_input_tokens":1807,"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_012eFK8SiD9DLuu1r9G1riKx","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":"{\""} }

97−

98− event: content_block_delta

99− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"fi"} }

100−

101− event: content_block_delta

102− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"le_p"} }

103−

104− event: content_block_delta

105− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ath"} }

106−

107− event: content_block_delta

108− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\": \"main"} }

109−

110− event: content_block_delta

111− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".go\"}"} }

112−

113− event: content_block_stop

114− data: {"type":"content_block_stop","index":0 }

115−

116− event: message_delta

117− data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":3,"cache_creation_input_tokens":1807,"cache_read_input_tokens":6853,"output_tokens":55} }

118−

119− event: message_stop

120− data: {"type":"message_stop" }

121−

122− headers:

123− Content-Type:

124− - text/event-stream; charset=utf-8

125− status: 200 OK

126− code: 200

127− duration: 2.504401167s

128−- id: 2

129− request:

130− proto: HTTP/1.1

131− proto_major: 1

132− proto_minor: 1

133− content_length: 32569

134− host: ""

135− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"update the main.go file by changing the print to say hello from crush\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_012eFK8SiD9DLuu1r9G1riKx\",\"input\":{\"file_path\":\"main.go\"},\"name\":\"view\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_012eFK8SiD9DLuu1r9G1riKx\",\"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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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}"

136− headers:

137− Accept:

138− - application/json

139− Content-Type:

140− - application/json

141− User-Agent:

142− - Anthropic/Go 1.12.0

143− url: https://api.anthropic.com/v1/messages

144− method: POST

145− response:

146− proto: HTTP/2.0

147− proto_major: 2

148− proto_minor: 0

149− content_length: -1

150− body: |+

151− event: message_start

152− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_011Y6PAeHJdg3Ph6ZFLMNuwG","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":6,"cache_creation_input_tokens":120,"cache_read_input_tokens":8660,"cache_creation":{"ephemeral_5m_input_tokens":120,"ephemeral_1h_input_tokens":0},"output_tokens":25,"service_tier":"standard"}} }

153−

154− event: content_block_start

155− data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_019M2MmqUbzyvMfw9WaD3VFa","name":"edit","input":{}} }

156−

157− event: content_block_delta

158− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }

159−

160− event: content_block_delta

161− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"file_p"} }

162−

163− event: content_block_delta

164− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ath\": \"mai"} }

165−

166− event: content_block_delta

167− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"n."} }

168−

169− event: content_block_delta

170− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"go\""} }

171−

172− event: content_block_delta

173− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"old_"} }

174−

175− event: content_block_delta

176− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"stri"} }

177−

178− event: content_block_delta

179− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ng\": \"fu"} }

180−

181− event: content_block_delta

182− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"nc main() {\\"} }

183−

184− event: content_block_delta

185− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"n\\tfmt."} }

186−

187− event: content_block_delta

188− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"Println(\\\""} }

189−

190− event: content_block_delta

191− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"Hello, "} }

192−

193− event: content_block_delta

194− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"Wo"} }

195−

196− event: content_block_delta

197− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"rld!\\\")"} }

198−

199− event: content_block_delta

200− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\\n}\""} }

201−

202− event: content_block_delta

203− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"new_stri"} }

204−

205− event: content_block_delta

206− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ng\": \"func "}}

207−

208− event: content_block_delta

209− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"main() {\\n\\"} }

210−

211− event: content_block_delta

212− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tfmt.Pri"} }

213−

214− event: content_block_delta

215− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ntln(\\\"hello"} }

216−

217− event: content_block_delta

218− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" from cr"} }

219−

220− event: content_block_delta

221− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ush\\\""} }

222−

223− event: content_block_delta

224− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":")\\"}}

225−

226− event: content_block_delta

227− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"n}\"}"} }

228−

229− event: content_block_stop

230− data: {"type":"content_block_stop","index":0 }

231−

232− event: message_delta

233− data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":6,"cache_creation_input_tokens":120,"cache_read_input_tokens":8660,"output_tokens":123}}

234−

235− event: message_stop

236− data: {"type":"message_stop" }

237−

238− headers:

239− Content-Type:

240− - text/event-stream; charset=utf-8

241− status: 200 OK

242− code: 200

243− duration: 2.590338541s

244−- id: 3

245− request:

246− proto: HTTP/1.1

247− proto_major: 1

248− proto_minor: 1

249− content_length: 33115

250− host: ""

251− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"update the main.go file by changing the print to say hello from crush\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_012eFK8SiD9DLuu1r9G1riKx\",\"input\":{\"file_path\":\"main.go\"},\"name\":\"view\",\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_012eFK8SiD9DLuu1r9G1riKx\",\"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_019M2MmqUbzyvMfw9WaD3VFa\",\"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_019M2MmqUbzyvMfw9WaD3VFa\",\"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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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}"

252− headers:

253− Accept:

254− - application/json

255− Content-Type:

256− - application/json

257− User-Agent:

258− - Anthropic/Go 1.12.0

259− url: https://api.anthropic.com/v1/messages

260− method: POST

261− response:

262− proto: HTTP/2.0

263− proto_major: 2

264− proto_minor: 0

265− content_length: -1

266− body: |+

267− event: message_start

268− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_016L6sSaeRFwHpTNycXatjPG","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":6,"cache_creation_input_tokens":175,"cache_read_input_tokens":8780,"cache_creation":{"ephemeral_5m_input_tokens":175,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

269−

270− event: content_block_start

271− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

272−

273− event: content_block_delta

274− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Done"} }

275−

276− event: content_block_delta

277− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"."} }

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":6,"cache_creation_input_tokens":175,"cache_read_input_tokens":8780,"output_tokens":5} }

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: 3.520432916s

internal/agent/testdata/TestCoderAgent/anthropic-sonnet/write_tool.yamldeleted−243

@@ -1,243 +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: 817

10− host: ""

11− 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}'

12− headers:

13− Accept:

14− - application/json

15− Content-Type:

16− - application/json

17− User-Agent:

18− - Anthropic/Go 1.12.0

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_01JMWchmGYjGvwhk1QHW8zM2","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"}} }

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":"Create"} }

35−

36− event: content_block_delta

37− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" JSON"} }

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":" Configuration"} }

44−

45− event: content_block_delta

46− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" File"} }

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":161,"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: 525.572291ms

63−- id: 1

64− request:

65− proto: HTTP/1.1

66− proto_major: 1

67− proto_minor: 1

68− content_length: 32124

69− host: ""

70− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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 1.12.0

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_01GtViPWmhueXgG64JgCJ7m2","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":1821,"cache_read_input_tokens":6853,"cache_creation":{"ephemeral_5m_input_tokens":1821,"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_014LZ2qfDhfKZ43DAp3QDDGd","name":"write","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_path"}}

97−

98− event: content_block_delta

99− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\": \"/tmp/cr"} }

100−

101− event: content_block_delta

102− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ush-t"} }

103−

104− event: content_block_delta

105− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"est/Te"} }

106−

107− event: content_block_delta

108− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"stCoderAgen"} }

109−

110− event: content_block_delta

111− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"t/anthrop"} }

112−

113− event: content_block_delta

114− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ic-"} }

115−

116− event: content_block_delta

117− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"son"} }

118−

119− event: content_block_delta

120− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"net/write"} }

121−

122− event: content_block_delta

123− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"_to"} }

124−

125− event: content_block_delta

126− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ol/co"} }

127−

128− event: content_block_delta

129− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"nfig.j"} }

130−

131− event: content_block_delta

132− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"so"} }

133−

134− event: content_block_delta

135− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"n\""} }

136−

137− event: content_block_delta

138− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"co"} }

139−

140− event: content_block_delta

141− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ntent\": \""} }

142−

143− event: content_block_delta

144− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\\\"name\\\":"} }

145−

146− event: content_block_delta

147− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" \\\"test\\\", \\"} }

148−

149− event: content_block_delta

150− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"vers"} }

151−

152− event: content_block_delta

153− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ion\\\""} }

154−

155− event: content_block_delta

156− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":": \\"} }

157−

158− event: content_block_delta

159− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"1.0.0\\\""} }

160−

161− event: content_block_delta

162− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"}\"}"} }

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":3,"cache_creation_input_tokens":1821,"cache_read_input_tokens":6853,"output_tokens":109}}

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: 3.78905875s

179−- id: 2

180− request:

181− proto: HTTP/1.1

182− proto_major: 1

183− proto_minor: 1

184− content_length: 32693

185− host: ""

186− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"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_014LZ2qfDhfKZ43DAp3QDDGd\",\"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_014LZ2qfDhfKZ43DAp3QDDGd\",\"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.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\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\\u003c/env\\u003e\\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\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\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. Output Processing: Truncate if exceeds 30000 characters\\n5. 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, timeout optional (max 600000ms/10min, default 30min if unspecified)\\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- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\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 Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(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\\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- 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\\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\\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\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\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\":{\"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\"}},\"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\\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- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\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 content from URL and returns it in specified format.\\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- 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\\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\\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\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"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\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\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\\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}"

187− headers:

188− Accept:

189− - application/json

190− Content-Type:

191− - application/json

192− User-Agent:

193− - Anthropic/Go 1.12.0

194− url: https://api.anthropic.com/v1/messages

195− method: POST

196− response:

197− proto: HTTP/2.0

198− proto_major: 2

199− proto_minor: 0

200− content_length: -1

201− body: |+

202− event: message_start

203− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_012m9RadV58H14GKHAK3vy9V","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":155,"cache_read_input_tokens":8674,"cache_creation":{"ephemeral_5m_input_tokens":155,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

204−

205− event: content_block_start

206− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

207−

208− event: content_block_delta

209− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Create"} }

210−

211− event: content_block_delta

212− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d `config.json` with the specifie"}}

213−

214− event: ping

215− data: {"type": "ping"}

216−

217− event: content_block_delta

218− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d content."}}

219−

220− event: ping

221− data: {"type": "ping"}

222−

223− event: content_block_stop

224− data: {"type":"content_block_stop","index":0}

225−

226− event: ping

227− data: {"type": "ping"}

228−

229− event: ping

230− data: {"type": "ping"}

231−

232− event: message_delta

233− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":155,"cache_read_input_tokens":8674,"output_tokens":14} }

234−

235− event: message_stop

236− data: {"type":"message_stop" }

237−

238− headers:

239− Content-Type:

240− - text/event-stream; charset=utf-8

241− status: 200 OK

242− code: 200

243− duration: 2.228601375s

internal/agent/testdata/TestCoderAgent/glm-5.1/bash_tool.yamlnew file+425

@@ -0,0 +1,425 @@

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.yamlnew file+483

@@ -0,0 +1,483 @@

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.yamlnew file+650

@@ -0,0 +1,650 @@

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+ Purpose: Provide example of this file type

541+ Document file type: HTML

542+ Version: 1.0

543+ Remark:

544+

545+ <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+ QDbSXevHjFAnvgfxiHZHB1GELoyHjxhjqYPArmgg3ADQLpbP243KXEAcDy/k8GKkhpHX/NuKGdBTom0Hj4XjUy9QVUbDrT/eMWZBUCWsPGj1lulNiNPk/wB3gOgTeF/mbmAHRAs292TfjeC2PkxPt4zTNUhdfQ3A3wJofYjtwK8FGop66PHvxhAZ1RzG+u8IKy+D43jx5YLwgvKUfiugcsGSANrsBNjsmub1kEP7ASnP6HnBTsEHCSbeNZSfUSH+WEtaxIGkFX66we4s8W9Dn1mnmEXrfbMA4oNU7T5576yLjRJK15PPePosNit7deXKIg/5EPOHzSKIeB73m21KUDheTvv85pCoVIQ4Xh/27w0q15IN5a63Pd96YDwpaKDvg/8AM22Am4FDLOeTjpMVSvWJ0bOi9zbecFqo0O3vs5xAI7VGcc01Zs5CRk0QdYOOg3s4zQcek2fUw3P66/bFHIb1Tr1hVexyxR8YEXvxEH/uVAtm8xygBJUFNdMdZdwcudVehCSewGqesmAid1IiQ4BU1YzFQok+bzNO+N7wKrfqAsG71qJ0cdlJcZvTsDfJA+KopKyGgEtLzd89waMS2yLuu2lTe98kcP28h5hWlvHV63gtRq6FdF3834c4gxTsklI6jN0riX6jeNJ9tVhWPVap968J+ZzmtUI2Vt+eA58/OWNKCgbcIadv1jaRhB1vW2z+/ksEkgMKABvbjSNnwwPtxsO0HNF0ho/jPaWbpvGgYYCF1HoHq/M897xB1IEUHtPWKccSTsMPagbth983HNSmuX2XGCOnYP2w+E1XKADpG/vrCGMUwvHy4iEUREF6Q6w4CI0dlan72DN3I+gRaC962+/WBiIbi8331Tv/AN0iFE2++MmwBJLnxB4CfGXPSNufwYCgE6Y3yzrAWrRD03/WK0KdG2SWWOASfrN6LDvZ5dTESjeg37n96wlIBtpfZ/esMJGdhxz795sQ8LBHpNjp7xtWhhN5oDRdKQQGFVBsyI+g65rwyGIiYSnuZ2FhQKaHKhsygpbjVDJsABJb4cQAo7SNdXrHqKVF+Nn+c3/X67js8YFEbaM3jKpUlEPvCRZQ5kvPxhSABQ3tFJF/1i6nAA8EiUT84BoJBsCmw1Hg8wzV7IUKeHRli7grDpZeuMJuJnSSrOjvEO0tZQMwlItHk4w4CI0aP+skWq03qeA8YGk28M/XeJEaggUH/mMQs8roHNCbwKS4GsFWkUXKRqTdN/pzaGeusKRPBHRlYfEoEkDaJSnQqkxl4TeUJoTYQGdMjC51oRBgsNFEBKdgPO2mURdOgrZxZK5rSUa6d2JfvYVOMMzjAS0OBAFxwHMmOIY4pWADFVW7KHsEPWxQibd6Is947twJBHRDVENt4BZ6BeHtncj1Ac6fagFhNbEfOLH0bQR2nXbjvvE2fgjKb/mHxyYwJIG8TmcUvb5wcihWQe06/vrLWiMSoXku+vZgKitrQa+MoLdTYHqr8/6xE4NZTdKwi3/zFkpdymHpSH0fOUpYKl0k1rXGG1DKrUuvzjpsnYsafLn8J6zR/ZHxmowDe3fpb/rCQZbOQfnJNN1wmKAR8MbaYao1NxwxuPl8CX+3CM4C0CEu9mv+4BkS68CE/bjuo3s6wHRHjnkyNGcqq/rLzY7c4N7A89mOAmngc/0xwgN93PmwHU/rnjThsH+cbvCd148Oz/GaCCVH7DLNgUAnWRvQ6sCafvNWD3uH4O/mZy2yLySs6WFwMtBWCp0Lvfjy48RIk4lTft/jFATERsLgDCS3ai7DqcOscQIVM8iOuV7985p2FLQOmdccO8sGopRkFf3+sQlG2PHjjGBjwWuFwbQNxJMvBcmadP8A5ijvi8nQN/jEgqGbDqanTnJDFS6nME7xeIhLLOYdySOnxhNUXQHA0YJyaLc5dUaB5zv+Mczak2N94SV053r8eN4tlbofZ95sVIZtfLxkhUbrVLvjLSkoM1gYGRupp+8uUs1W69YyAwk5BgQLZLyx5p40zHOZEuaPLXbtjXho307SgNNtwgE7bwY9bQIG8gi9ipPoImbAgolASF5I2pg0kN2dC7LBDb04sQ7Ss0IBK2N8RPCgHKI4VapSU0e82Ua2jTTVeV0f7Z0sHAQvCGmc0Sc4/UACtbWnW+/bkRIJJobW7n59BuiPMKmHPc/zhK8FI5UpvudmRkteX48PP3jxAkaE7utcfX3lC0qQ8jq6v9mAQDsllvnTOsalC0B+HY+sMy3OkJOdtH+mXAJ2OP4/r5yYACNBH4GzGeAE3Rvuk+pmzc5C6eR4cBoA883AuZ+c6IuXJ0AyWi123VcPotFQE9WmIBwiqD/54y0KUanyTVR/VyehIu2g0Ifi/eDbzXp/GAlkPlxAHDvnAFg3V3gLjYp1vNBJl2s8/jISnSByxGGJqamQVBp7uh/WTjBWh7eeMKBg0XswaFeiw/8AuaagNw/LiZadoUG89i4yKWtUA0TyNDs45uJDisYPjQV4nyMOs+OoNn7QxHwobCrz1ktn07gmuThGmu8QIMwFuJE8b5xygUmhBr85V1AOdPRfifjAABrmKdGI39Ehr4zaJnh+C3EabyMFUQ8bTUx3wSl4LvZvJdNIGlvfcxTTWqravplis34MP0/YSm0vHlr4cf7DIF9V985JQCCw8BKxi7187wxsXYcYJBjmft3xgrUNc6cMlAEibH44yAmAq33rDJ8JsY6BFglf9YYRq8hQMR7bNjS5tQ4O5e5iKEk2hA8YQB2JKAngsNmPzpeVlksbZadhdttI4cKEyxdBUccU0jlGFqEJyDwFa5gRzcFgC2tBOSGjX0YDYgdg0IABeNmtDREWFsj2dENH+M0pKylju610c6wbNEKXo8DVf1k1kklN+dSNDu9bOcPhe3WPb5rf0YrUuxU74cZlBXh2eh/OT5of5fFKPF4dYpCjYCLoGu2YOGoGG8XkdPnx9I5Ri/0X1kKgRYQey07vOVEaTRk9yc/WBo1mgMftnPeFrAQBdnvN8gVOBu761ziC2Q6h2vOvX97yYnS+n4y3l8gRy41dnWjlyIA9/tjRXT1Uwk5HicCh7DQa+A+sagIkSa2TjAd8n72wl1j8TEhVPxgmGZ3MADeeP9c3Eu3JHf4MQrIohgQhv1MGdHaVMUop/hxRzLYyXuDrOYRSJh2oJ+n85QM0oz74xyRDhdP58TNZ0KuhOD7uNlBF0329ZDsGQCKfKG/I+MErwU263l32ud4iBW7t+nX5wpEQortY8/HWPEhS3sptecJUvtp95SUXfKfWJglHmKiH/LA1CLaqeQP+YdJV/j+84ICh5aI68cZAx7Qo/u76zavE7hoj7PScZozBUOvxMGWBCiB5eHrXM3zlDpq6UTlEL6I8ZBbSjHht179cYqk7qIuz16/pnFAPcDUTzpwWuzdW3wYQKhtt4+sJTTSGH41x1jcI4sbb48/eXRU2/wDZwBCRKxA/sxSgJpNMtvxuIB/vFt85bo+t4OMUclV+P/c4EQJ3MEYoJsElyVPNIPRwBpTRWRjTHRRPA70CeyRUaXKMxI3tpILpjS8xJm2/REsiIuG6th0mckMYQRJZda/1jgHaKvmabR3xrnIprwrRtL6/gywJRJN0WL0P24YXPEI5RbVnc36wCqhoAAHTrnmU8YDDgpAtTalfO1vnrERAQagHvlDTqZq1AAGOqLx8T/WEyuF2gPtT+8YbOqUATiH99bxslXAKeCuuU15esr8Qqpzskm/D/OLHJUUHu9n74+MiIAoHCZruY3oCYfkg1fh6nxic/ssTnivHrDLiIShzwL1gEJ18XmeMZS2nBltJngwgibyxjPNRgrvDBG2cphzzHa/MOMClVTUui551y8GFSK6V5ccJHomvziU0X2YScnW9GNw6+AfmnjG0NGTceMHgC2PWX6q2aA+LmwVWyrPjfGIeBopqvl3MY65A6adzHW8AAvvORmALvj8Yuk+YPOI3Vi3kEfmuOAU2goLyMCI1FE0YSQ3qlah/KZtm5F2jmHb8YQXoNI0p9OsVULteplIdkgf5zS5ABEL5HiP6wqRTMSlWdXHJo33+cBA9K8rxzhzxUPZJffH9uKW6js4SrJxxrRS42pthH+D9YdM3eAcG3zhmwER4MK0cAveOIZYavPG33nA1RtiX678dYtBAtQXJPvACKheY7jx+85iomjTzcnBvdO7D5xJCGUqX1g1K1a2T7wYdATAfjW8mG9KBB40YrZ4nQPP3lkdzRK+cIQ7lsa+DC5NjNlULQ2RqNAYKZROiaaAx62fkqlN7KEQWwkMN7POUkqXAACrt0BvxlI4NTR+O8XX5FjT7xzXLs3y9/vGN61O/USpNc/WMjeSixcyx4/vO+v0ik8a2M8YalziLw4/JhpHoBPRK358YnR2u9Gfn+cMGWF5E6Anrk6wDK+dhf4Yoa6lfiomAiXKj05yZArR9A/nDFSNXNNP1yYV4ZYL7TTjw+3b9G87PJyA9Bp88/PGF+2RzOpGz+95ajEGoBY/iZE0pUQflHUyLq8LvAqoPnBaoXjjKBU8c4I0b5AxUsw9c43Vw1ogoLQnWCL2dy3CHhtHB+0MsD5JE53t4+PONyGgSB5scN+c10zk1qu/GLyNCNIDljPjEIz8HbxMXmHCJ84xEVq2PlP1gpzYOA9a/8w2g7IDoDj7cq8vQQB4MEwmbSKdL0cB6cQr8lQqtxzB0d47UEJcutTpm9IuvSmc2R6BoHLGf+r0P6Ug2m6deP4xKrRCPalkXqk+Ac08oHpq1O+esayrZFHvXRZk9Cbl4xXwfRzdHyL+8SWUV2Xgr7kwAndV065xAd5+HB/vIemggpLxR+ce0avMbfjy68+8VINoSPkVf8YCRToJjqXg+MNKzKSJGvx5/tHSRIbR8+f5wLKe0aYsAhvg3xiYIO91X5w3YRK7cVJTZ5D/Rm1vW6vzxgi3eU59XIdo0tF/5m6XQRn1TG7L2GlMBA2Duu/xigABoOs9eMpDIR3gFXYd8q0HKpUjcH2k0UPGiZp10KB81eOX4PwlFe0E6r1myFmOv+QwWDKv4yO8IOqtTQ4894npULvHNYu8thf3c2IFFMPrEsi5A1OU/vGK8xKQqGxe+5gwOTYt+MnHXYG0jcP06r/xhN6SCcClhwg/xifbgDX99ZyXZ5twO/UTe2MUoNv8AnFQKF8/wyPNt5FXEoRE04PFwrdvjnFkEsQGy/wDvrAh4ErY/GLwfP4+bgkROVWzzjXWvZ7+Mfem+V+sPRjSBHlesgwh6c/jA82d8/kwA7VZq1kMbqIgwlJVEIY0uI7GBjTsZ0N3NZGBkbwvtvHBQv5xcAWpN6T/eblFyif4xQGEkyDslODh+M56Oa6HaweejvLbZqN2R/k6xBC4GRQFnkvw+muMxbI8KIHirvXfOaZoCehZfld/rEXglFcaY7wgAxundC/49YhsGeEw30suVN8cdZfKWo8888k384gAdCAwvOLDXsra2b+pghVPKDlJOdcYNE0FtqPg1TnBQ/WQz97x3fSnQdECPP1hP+QlFeXTs4wsA7BhipClKjs/WNSR2sXIQ1JCphDgnQf5uaE7wbT7xToVZQ4BUSPlcGS+dTA+cDCs8buTJJwLa/nHaIzz9MTYFFLsLv+P3gYiisW226Of4cP7eLyOxWc7/AJxBdsrfkOn+AxZ8dK6bmjMVr+QhdelycZBL+S8afE04WAhNFm+fmTCnWUZFd3ejZ+8dVIASJTkbcrMUJKlMD5fh9YC2FSwO+3e/xgOWAkccieMDoiFbkPJMd+sl4nr/ANyclWCEEP6GsBuCs+/xmiNtJTxkZr2wsVnnETZ4Vg0ParUf4wYDH2YEgzia/wAYeh4hF/VMqn4g/WAZ688X6mIir0qJg5Fd06xVBpv+S5ztE/thrulb/jGbpnGLOE7KODF5Ht+cCoV5G9v1h5muvOhz98ZG6YlvLovPX6yioIX05dt4qxBIA8bOffP/AGUCwpA+guXxuKnXutYzY0GLYso9/wDMeaIaHXbJu4WQGiz9L1MU6QzSvO2+F1bM2zbNSX43P84G7ojwVDY1wqcdYO4DrAdVQiAXrInFQOG1W9p9x3xlSUISrxR2WGe8OTU0SgiH01DvD2HJtxP64YRoQ5Q2vXx7w2aLSzX2/wCMhyGFcKTnGQXiARGHh3+8q0HDNj1ZjkrZTf8AzKYz4cs4nE53jGYvRAzhvtYc/WHS+4AIvxx4PWHTNhtSdw9H7wRlulQpUJk+TwBXg3zr4+c0l8nJQ94IAYkUae8FpZNJXpmEE15U+OTEoqmwz994gJd0G8+JLiwfaPX7xcMazgRwFF7L28YbASgLYvN2d3RiOlVoTY7gN3hEobrRHZG3CUQRIG8lJOfy77EjoMkXseE3+cCJovhjfAX+94oNsvEAjoPq+8YGqOrKeiayDMb3f4HfOVCJUUSG9P8AvNjrAbYHl+sT6mtHU8vGv7vHFBItR+v7vBdcFKB/mfOFR4RwX9/xiKtNuk38PP6zkT0g5nnlgtCLE17rJPhGQ/N7wU9hVJflwhH1sYevH/mElAGxp+/OAsUppQfeEsD3pz8Y+xnISvjxiqNAolzWQm5EwTazlY3GGADmLgCg6tf8YI3VSu/eIbS9v8YQYzgrkhbG5dXGngJA/K8f8zmQHOTcvzOc5doEBtEVOE/eMe2htJJJeZ847iRKPO6s84Q2g7KPJeQ8HnBFzMqD9fWAooTuuu0ifj1jYCjeprnZlo9cCQ8+8YIHLQLfn6yH3IlwtkNqNlOTCgOuO9/GHA20g0YAHSjpBx/n+cr3QUhEDaRacdzUx2iUrF2NBTmQ2ax8wrbHm5OQINNp6co4p3FPvKRkgHdhvnBXVexBkAHE3G+vLsx23ob6HM+Q/OOTy7Uv0xKeNpRH1cIJg7kD7mUtXNC3AB5vDejWHATZJautns/jOiqpQN+tec3ByZeX1PMmHoRSk9DpS649ecMhw3nPrWCELCjxtYRyILjI0Tnnr+cagpahrfuzKpYgUkHb24oqLFBD7yINMBUIvdtnWeBKJIeS7x2kYiD9JiiBCbV9ef8AeMHsoE76vGNtWhSYnkdzt6yaG2CyePXeIQXI2Ot/4wVSrZZgQx867ddGBRk5IXj/AHg66aN76nOVpKokF5DnnDipUjvWMlwulp3098fvNxGgNSHr8fxjxr4d4KheRz74/GEU7IQR/wDcCpiAls+d+sNc03sifJ+cXNEgIfyxSVmq/t/OslcFojU1ziytrq4N/wAZHFATQTxcOhE2Qu5vDQnOwD5wS8Dv3hxCJNCh53lpkdqg+J4zTnJAMPxk5FXbGPn85uXqh/piLDerxjZjvgwrQspDlgMVgvYfpyG6wE628ThxZRRK0loxNIvNwiVg31FmifNbydYn1Yq7uucmgR+7/wCZIVWhqfjF6qcMHAdfWOCtHdAdb3jiFOQxPcxVYkMOXadGnARXB0Vk92TBXUqBH0vPnAOqGwonuYV3m6Anxpr4ykM1hoBsgXfz3M2fIvLndN7Bzc9FtR0ILtHrjEj1SLR3DinT/wBxSNI0I9jd83nAfWvZxsN/xhJWyJ4Tj85wV3BDDXny3rAFvYwZNnUxIrd5F1d97MZuuxDtPBrjAYA0tocMvsx1FxkE+f8APjAHwCK0ncQ9ZQpXz+Soc/GXuic+eqXv/mUEvYp8wesEOK2LGoaTeJCeaj9C/v17wkGI5290f84Qq3Ygk1zHP24sATiu3vLPaF20/wBZgooXSiHab63m4poHS8fu5I17AkbrgzvYh0zzs5xG5Gt2yTgX/eSUYBUii7G29B24LSG6t384puBCrZkRKK5kOvvDrQCyEuG7rIE1xBEAhEI0/OIEutkLU/nCkJJQYNHL6mDfY0LyL/fzgLY5atuDPAFKLj2hVl8sCNTO42ZXkOKbP1lh2A+RhQ1BCtwihDwSOWFDZHk6wI4puFPGCBDNeHv5+MIIlhAojf3/AExAxukGOYaPxh9RAUUX+/4wwsJqN/dyDXbYLrCAKG1gyA/IDkwIurOMgWkOh2zDthGo5x/AUkqP3kDSO+5hGBUXofPrCbe4jXv65zUDwdXBIkuwbwJuh3j5n9/nB8EKjP08eMTO6rRp9YJG/Cn5zYkdov4ed4eU2DgLpD2vrJoIrT44e82byvHXNUjol8ZF0GLoJeR064+sYVp0gD3wLvAsUSA4Yya8uAxBIuy6D+Q+8Ng+ABgn0F5onV9qYh6FO8Aov6Y8qarBepeDleesOHOCldfj+M2KHUr0MRL6yH5pucmKIJYaPex+cMFoQYm361ciZGreiCIQ15mNWDVAUeF8f6yOIimTXjXjNim/W3dn98448EhfMf2ZEtgE/wAno+cCUFNuo73P4zkDXfh89+cT0nSpLNb/AB+c9HDri3Qa1y84KpTnQzrRj7Dzwh883G1PYafjePyhKUz8m+sY+c4X4YpvciHE/Uwxp7lVPOJhgl2RytgIZ8swhICADG+f4xQanUi+BRxgWlf/ABlCRaCZRNz95AqyO3L8YgkAsbtMSeOjlVySII2zb33gtFy3tecQlI1NTzgmlXkNF4MoKm+T/X91jLtUZ5OHDUB1fLxinc8ixcUgISoW4oacFd348by64Vo4msYAUhK/4ZIHCY2NPE7zR1CW05tSUsCB8ZFaIul18YgK6WdX/POPChGro6MOFxeKk+/rCIF2R2zXL9BMYOUPw+sV9gPHTFnKSfP1ivjqBvNoFn2r36mEnUDqDzMaQiFm/wAmRZMkF+MRyuLe+NdEsSV/3gXakqRtZ/fGMRqA7ouxHXi+r5wAyZ801r6cp1ak7JIGoML/ADkPASg1yBwE/wBY7QFW4Gqzv/eUhyBRR4nxnn5dNrxzz5xutMhXrXJgvDlQU5JZ32dZt+pCx4Pwv4x3woJRH+vxlCXXnQH7694xmhx6flx4yF/U5fjvHVCWzA9g9/8AMD0YghW2BtvX84EN/qSLabMv0ypol3uOtM4yitzC6htp3x34MsigYCaK3j0mONQG0/OAqJ2G0blGgrg7+dZTtBzGvnFFQYb0el+HBkUachrx1rB61CIE7m9ZfXq0D9+rlgqzd7K5patA0Xuc4hYe0t8b36yFkbxzv+cZSAOe/fE+sIw7TSGcNA2hNzi/jHUPg9H/AHrDxnkDb/dfziEEXYqd9eJjUJV9A1/jF1AhXgW79U/ZjArY9DnX8mOOq1DxvswKQ5BOh/jrKwi6FG6esQicIBCvyO+9Zbspwxvn/GJFGg2P31xhiJZBzrin9c61XpXr7xcTDILCY0oNFXk3/WaPDuCy+PjFTGjY27/d3kJuVJI8hvzkMkADXR++sj3CSjTvhwIIQ3OT+/5xgxDndyDG6fUZ3lx83OA+MhUBoOCdGaFQIPrxiEF70wyEY7eDirnh4QNdmG6VodutY5hpQG3Rm2umgjJm5LRlq5fNEq2fjLwiOhJx/wAyPtUL05cchUo64fnEa0Gm7iUhbTx/zNIXXEaYOwKbqbuHYRYEO6/fODC+7RU/PvEg8EBqXdPzkpEgA7ayHUPtkgaeIWnqBtPVFNqNKxI5TbNa940wN02B5+JicZJpDelOHbrHVAX5UTr5wdFHdw2C9Ef6YQTgdFe/4zZ8EWs6d4L8E8g/887ypbqOc52NXGD2oA9ixvRc1kEB7UR1rj9mMwVWynEeeJ/GEJts0nhTsp6wFlsKqI87wOIDIhOxvjBzpxAK11HWn6cOqf5VSu5h4cupaeQ/GMQhtGuXjrLMhoEB79YUJQUOGl3o+cWccRinPDN984V3veCvN0fvAvZqqlv3/dYeS1VVP5T9Y4ag2cOVDBD1LhQRmyj+Xk/xmnhULd1/vnN4Joh20/5+8rMKixU4/Wv+4nNwsPkxfs+zP2LgBnt04oVZENNyfnucYiGCa0vGtJPsx7ZbkrzJO3/vjC0whhqRdd/PzgJkXYVlmn6vnEwUJW5qWHlvPreQ0EOD1r8azeFDb+vrEBQl4OHrl5xCrMgVw7+OsMCgboechB8LZYf6wCmUlfH

556+ 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"/>

557+

558+ Example content:

559+ 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.

560+

561+ 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.

562+

563+ 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.

564+

565+ <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>

569+ More example files: <a href="https://www.online-convert.com/file-type" target="_blank">https://www.online-convert.com/file-type</a>

570+ Text of "Example content": <a href="https://en.wikipedia.org/wiki/John_Doe" target="_blank">Wikipedia</a>

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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"/>

574+

575+ Feel free to use and share the file according to license above.

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.yamlnew file+737

@@ -0,0 +1,737 @@

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.yamlnew file+499