git.iko.soy/crush
on main help sign in
fix(tools): switch bufio scanner for reader (#2884)
6f91b0cKieran Klukas
internal/agent/testdata/TestCoderAgent/glm-5.1/bash_tool.yaml+361−243
compare with main
unifiedsplit
@@ -25,371 +25,463 @@ interactions:
25 content_length: -1
25 content_length: -1
26 uncompressed: true
26 uncompressed: true
27 body: |+
27 body: |+
28− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
28+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
29
29
30− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"User"},"finish_reason":null}]}
30+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
31
31
32− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" wants"},"finish_reason":null}]}
32+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
33
33
34− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
34+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" says"},"finish_reason":null}]}
35
35
36− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
36+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
37
37
38− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
38+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
39
39
40− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
40+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Generate"},"finish_reason":null}]}
41
41
42− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
42+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
43
43
44− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
44+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
45
45
46− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
46+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
47
47
48− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Must"},"finish_reason":null}]}
48+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
49
49
50− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
50+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
51
51
52− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ≤"},"finish_reason":null}]}
52+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" following"},"finish_reason":null}]}
53
53
54− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
54+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
55
55
56− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
56+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
57
57
58− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
58+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" use"},"finish_reason":null}]}
59
59
60− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" one"},"finish_reason":null}]}
60+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" bash"},"finish_reason":null}]}
61
61
62− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
62+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"..."},"finish_reason":null}]}
63
63
64− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
64+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
65
65
66− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" no"},"finish_reason":null}]}
66+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" The"},"finish_reason":null}]}
67
67
68− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
68+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" instruction"},"finish_reason":null}]}
69
69
70− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" or"},"finish_reason":null}]}
70+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
71
71
72− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" col"},"finish_reason":null}]}
72+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" produce"},"finish_reason":null}]}
73
73
74− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ons"},"finish_reason":null}]}
74+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
75
75
76− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
76+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" short"},"finish_reason":null}]}
77
77
78− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Summ"},"finish_reason":null}]}
78+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
79
79
80− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ar"},"finish_reason":null}]}
80+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
81
81
82− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ize"},"finish_reason":null}]}
82+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" same"},"finish_reason":null}]}
83
83
84− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
84+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" language"},"finish_reason":null}]}
85
85
86− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
86+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
87
87
88− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Create"},"finish_reason":null}]}
88+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"English"},"finish_reason":null}]}
89
89
90− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" test"},"finish_reason":null}]}
90+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"),"},"finish_reason":null}]}
91
91
92− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".txt"},"finish_reason":null}]}
92+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \u003c="},"finish_reason":null}]}
93
93
94− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
94+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
95
95
96− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" hello"},"finish_reason":null}]}
96+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
97
97
98− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" bash"},"finish_reason":null}]}
98+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
99
99
100− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" using"},"finish_reason":null}]}
100+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" one"},"finish_reason":null}]}
101
101
102− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" bash"},"finish_reason":null}]}
102+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
103
103
104− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" without"},"finish_reason":null}]}
104+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
105
105
106− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" timestamp"},"finish_reason":null}]}
106+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" no"},"finish_reason":null}]}
107
107
108− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
108+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
109
109
110− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Need"},"finish_reason":null}]}
110+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" or"},"finish_reason":null}]}
111
111
112− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" short"},"finish_reason":null}]}
112+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" col"},"finish_reason":null}]}
113
113
114− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
114+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ons"},"finish_reason":null}]}
115
115
116− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Maybe"},"finish_reason":null}]}
116+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
117
117
118− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
118+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Summ"},"finish_reason":null}]}
119
119
120− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"B"},"finish_reason":null}]}
120+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ar"},"finish_reason":null}]}
121
121
122− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ash"},"finish_reason":null}]}
122+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ize"},"finish_reason":null}]}
123
123
124− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" command"},"finish_reason":null}]}
124+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
125
125
126− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
126+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Something"},"finish_reason":null}]}
127
127
128− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" create"},"finish_reason":null}]}
128+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" like"},"finish_reason":null}]}
129
129
130− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" test"},"finish_reason":null}]}
130+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
131
131
132− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".txt"},"finish_reason":null}]}
132+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Bash"},"finish_reason":null}]}
133
133
134− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
134+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" command"},"finish_reason":null}]}
135
135
136− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" hello"},"finish_reason":null}]}
136+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
137
137
138− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" bash"},"finish_reason":null}]}
138+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" create"},"finish_reason":null}]}
139
139
140− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
140+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" test"},"finish_reason":null}]}
141
141
142− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
142+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".txt"},"finish_reason":null}]}
143
143
144− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" under"},"finish_reason":null}]}
144+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
145
145
146− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
146+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" hello"},"finish_reason":null}]}
147
147
148− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
148+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
149
149
150− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"?"},"finish_reason":null}]}
150+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
151
151
152− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
152+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Must"},"finish_reason":null}]}
153
153
154− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
154+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
155
155
156− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
156+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" under"},"finish_reason":null}]}
157
157
158− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
158+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
159
159
160− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"B"},"finish_reason":null}]}
160+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
161
161
162− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ash"},"finish_reason":null}]}
162+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
163
163
164− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" command"},"finish_reason":null}]}
164+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
165
165
166− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
166+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Let's"},"finish_reason":null}]}
167
167
168− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" create"},"finish_reason":null}]}
168+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
169
169
170− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" test"},"finish_reason":null}]}
170+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
171
171
172− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".txt"},"finish_reason":null}]}
172+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
173
173
174− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
174+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"B"},"finish_reason":null}]}
175
175
176− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" hello"},"finish_reason":null}]}
176+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ash"},"finish_reason":null}]}
177
177
178− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" bash"},"finish_reason":null}]}
178+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" create"},"finish_reason":null}]}
179
179
180− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
180+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" test"},"finish_reason":null}]}
181
181
182− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ="},"finish_reason":null}]}
182+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".txt"},"finish_reason":null}]}
183
183
184− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" let's"},"finish_reason":null}]}
184+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
185
185
186− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
186+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" hello"},"finish_reason":null}]}
187
187
188− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
188+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
189
189
190− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Bash"},"finish_reason":null}]}
190+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
191
191
192− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
192+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that's"},"finish_reason":null}]}
193
193
194− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
194+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
195
195
196− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")+"},"finish_reason":null}]}
196+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"38"},"finish_reason":null}]}
197
197
198− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"space"},"finish_reason":null}]}
198+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"?"},"finish_reason":null}]}
199
199
200− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
200+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Let's"},"finish_reason":null}]}
201
201
202− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
202+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
203
203
204− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
204+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
205
205
206− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
206+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Bash"},"finish_reason":null}]}
207
207
208− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" command"},"finish_reason":null}]}
208+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
209
209
210− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
210+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
211
211
212− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
212+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")+"},"finish_reason":null}]}
213
213
214− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
214+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"space"},"finish_reason":null}]}
215
215
216− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"12"},"finish_reason":null}]}
216+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
217
217
218− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
218+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"create"},"finish_reason":null}]}
219
219
220− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
220+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
221
221
222− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
222+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
223
223
224− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"13"},"finish_reason":null}]}
224+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
225
225
226− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
226+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
227
227
228− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
228+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"?"},"finish_reason":null}]}
229
229
230− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
230+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Actually"},"finish_reason":null}]}
231
231
232− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
232+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
233
233
234− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
234+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" letters"},"finish_reason":null}]}
235
235
236− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"15"},"finish_reason":null}]}
236+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
237
237
238− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
238+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
239
239
240− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
240+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"B"},"finish_reason":null}]}
241
241
242− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
242+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ash"},"finish_reason":null}]}
243
243
244− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"16"},"finish_reason":null}]}
244+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" create"},"finish_reason":null}]}
245
245
246− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
246+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" test"},"finish_reason":null}]}
247
247
248− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" create"},"finish_reason":null}]}
248+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".txt"},"finish_reason":null}]}
249
249
250− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
250+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
251
251
252− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
252+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" hello"},"finish_reason":null}]}
253
253
254− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
254+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
255
255
256− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"22"},"finish_reason":null}]}
256+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
257
257
258− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
258+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Let's"},"finish_reason":null}]}
259
259
260− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
260+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
261
261
262− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
262+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
263
263
264− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"23"},"finish_reason":null}]}
264+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
265
265
266− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
266+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" B"},"finish_reason":null}]}
267
267
268− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" test"},"finish_reason":null}]}
268+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
269
269
270− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".txt"},"finish_reason":null}]}
270+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
271
271
272− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
272+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")a"},"finish_reason":null}]}
273
273
274− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"8"},"finish_reason":null}]}
274+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
275
275
276− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
276+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"s"},"finish_reason":null}]}
277
277
278− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"31"},"finish_reason":null}]}
278+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
279
279
280− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
280+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"h"},"finish_reason":null}]}
281
281
282− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
282+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
283
283
284− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
284+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
285
285
286− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"32"},"finish_reason":null}]}
286+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
287
287
288− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
288+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" c"},"finish_reason":null}]}
289
289
290− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
290+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
291
291
292− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
292+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"r"},"finish_reason":null}]}
293
293
294− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
294+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
295
295
296− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
296+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"e"},"finish_reason":null}]}
297
297
298− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"36"},"finish_reason":null}]}
298+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"8"},"finish_reason":null}]}
299
299
300− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
300+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"a"},"finish_reason":null}]}
301
301
302− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
302+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"9"},"finish_reason":null}]}
303
303
304− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
304+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"t"},"finish_reason":null}]}
305
305
306− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"37"},"finish_reason":null}]}
306+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"10"},"finish_reason":null}]}
307
307
308− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
308+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"e"},"finish_reason":null}]}
309
309
310− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" hello"},"finish_reason":null}]}
310+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"11"},"finish_reason":null}]}
311
311
312− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
312+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
313
313
314− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
314+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"12"},"finish_reason":null}]}
315
315
316− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
316+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" t"},"finish_reason":null}]}
317
317
318− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"42"},"finish_reason":null}]}
318+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"13"},"finish_reason":null}]}
319
319
320− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
320+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"e"},"finish_reason":null}]}
321
321
322− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
322+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"14"},"finish_reason":null}]}
323
323
324− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
324+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"s"},"finish_reason":null}]}
325
325
326− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"43"},"finish_reason":null}]}
326+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"15"},"finish_reason":null}]}
327
327
328− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
328+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"t"},"finish_reason":null}]}
329
329
330− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" bash"},"finish_reason":null}]}
330+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"16"},"finish_reason":null}]}
331
331
332− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
332+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
333
333
334− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
334+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"17"},"finish_reason":null}]}
335
335
336− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
336+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"t"},"finish_reason":null}]}
337
337
338− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"47"},"finish_reason":null}]}
338+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"18"},"finish_reason":null}]}
339
339
340− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
340+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"x"},"finish_reason":null}]}
341
341
342− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
342+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"19"},"finish_reason":null}]}
343
343
344− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
344+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"t"},"finish_reason":null}]}
345
345
346− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"47"},"finish_reason":null}]}
346+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"20"},"finish_reason":null}]}
347
347
348− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
348+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
349
349
350− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" okay"},"finish_reason":null}]}
350+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"21"},"finish_reason":null}]}
351
351
352− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
352+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"w"},"finish_reason":null}]}
353
353
354− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" No"},"finish_reason":null}]}
354+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"22"},"finish_reason":null}]}
355
355
356− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
356+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"i"},"finish_reason":null}]}
357
357
358− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"/"},"finish_reason":null}]}
358+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"23"},"finish_reason":null}]}
359
359
360− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"col"},"finish_reason":null}]}
360+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"t"},"finish_reason":null}]}
361
361
362− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ons"},"finish_reason":null}]}
362+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"24"},"finish_reason":null}]}
363
363
364− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
364+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"h"},"finish_reason":null}]}
365
365
366− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Good"},"finish_reason":null}]}
366+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"25"},"finish_reason":null}]}
367
367
368− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
368+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
369
369
370− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"B"},"finish_reason":null}]}
370+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"26"},"finish_reason":null}]}
371
371
372− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"ash"},"finish_reason":null}]}
372+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"h"},"finish_reason":null}]}
373
373
374− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" command"},"finish_reason":null}]}
374+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"27"},"finish_reason":null}]}
375
375
376− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" to"},"finish_reason":null}]}
376+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"e"},"finish_reason":null}]}
377
377
378− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" create"},"finish_reason":null}]}
378+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"28"},"finish_reason":null}]}
379
379
380− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" test"},"finish_reason":null}]}
380+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"l"},"finish_reason":null}]}
381
381
382− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":".txt"},"finish_reason":null}]}
382+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"29"},"finish_reason":null}]}
383
383
384− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" with"},"finish_reason":null}]}
384+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"l"},"finish_reason":null}]}
385
385
386− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" hello"},"finish_reason":null}]}
386+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"30"},"finish_reason":null}]}
387
387
388− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" bash"},"finish_reason":null}]}
388+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"o"},"finish_reason":null}]}
389
389
390− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
390+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"31"},"finish_reason":null}]}
391
391
392+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
393+
394+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"32"},"finish_reason":null}]}
395+
396+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"c"},"finish_reason":null}]}
397+
398+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"33"},"finish_reason":null}]}
399+
400+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"o"},"finish_reason":null}]}
401+
402+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"34"},"finish_reason":null}]}
403+
404+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"n"},"finish_reason":null}]}
405+
406+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"35"},"finish_reason":null}]}
407+
408+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"t"},"finish_reason":null}]}
409+
410+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"36"},"finish_reason":null}]}
411+
412+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"e"},"finish_reason":null}]}
413+
414+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"37"},"finish_reason":null}]}
415+
416+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"n"},"finish_reason":null}]}
417+
418+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"38"},"finish_reason":null}]}
419+
420+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"t"},"finish_reason":null}]}
421+
422+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"39"},"finish_reason":null}]}
423+
424+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
425+
426+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
427+
428+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
429+
430+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"39"},"finish_reason":null}]}
431+
432+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
433+
434+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
435+
436+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Good"},"finish_reason":null}]}
437+
438+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
439+
440+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" No"},"finish_reason":null}]}
441+
442+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" colon"},"finish_reason":null}]}
443+
444+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
445+
446+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" no"},"finish_reason":null}]}
447+
448+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
449+
450+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
451+
452+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
453+
454+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" fine"},"finish_reason":null}]}
455+
456+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".\n\n"},"finish_reason":null}]}
457+
458+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Return"},"finish_reason":null}]}
459+
460+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" just"},"finish_reason":null}]}
461+
462+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that"},"finish_reason":null}]}
463+
464+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
465+
466+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"B"},"finish_reason":null}]}
467+
468+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"ash"},"finish_reason":null}]}
469+
470+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" create"},"finish_reason":null}]}
471+
472+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" test"},"finish_reason":null}]}
473+
474+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":".txt"},"finish_reason":null}]}
475+
476+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" with"},"finish_reason":null}]}
477+
478+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" hello"},"finish_reason":null}]}
479+
480+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" content"},"finish_reason":null}]}
481+
482+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
483+
392− data: {"id":"chatcmpl-c4e5208ce189f5ae587688b7","object":"chat.completion.chunk","created":1778601691,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":31,"completion_tokens":190,"total_tokens":413,"prompt_tokens_details":{"cached_tokens":192}}}
484+ data: {"id":"chatcmpl-5177570c0b1bb913dbd9e57a","object":"chat.completion.chunk","created":1778602892,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":31,"completion_tokens":236,"total_tokens":459,"prompt_tokens_details":{"cached_tokens":192}}}
393
485
394 data: [DONE]
486 data: [DONE]
395
487
@@ -398,7 +490,7 @@ interactions:
398 - text/event-stream
490 - text/event-stream
399 status: 200 OK
491 status: 200 OK
400 code: 200
492 code: 200
401− duration: 452.47ms
493+ duration: 507.14075ms
402- id: 1
494- id: 1
403 request:
495 request:
404 proto: HTTP/1.1
496 proto: HTTP/1.1
@@ -423,55 +515,101 @@ interactions:
423 content_length: -1
515 content_length: -1
424 uncompressed: true
516 uncompressed: true
425 body: |+
517 body: |+
426− data: {"id":"chatcmpl-452f541934d95f102a74b380","object":"chat.completion.chunk","created":1778601694,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
518+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
519+
520+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
521+
522+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
523+
524+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" wants me"},"finish_reason":null}]}
525+
526+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" to create"},"finish_reason":null}]}
527+
528+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" a file"},"finish_reason":null}]}
529+
530+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" named"},"finish_reason":null}]}
531+
532+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" test"},"finish_reason":null}]}
533+
534+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":".txt with"},"finish_reason":null}]}
535+
536+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" content '"},"finish_reason":null}]}
537+
538+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"hello bash"},"finish_reason":null}]}
539+
540+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"' without"},"finish_reason":null}]}
541+
542+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" printing"},"finish_reason":null}]}
543+
544+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" its"},"finish_reason":null}]}
545+
546+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" timestamp. I"},"finish_reason":null}]}
427
547
428− data: {"id":"chatcmpl-452f541934d95f102a74b380","object":"chat.completion.chunk","created":1778601694,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_1a51a6006cb9443db0b7bcb2","type":"function","index":0,"function":{"name":"bash","arguments":""}}]},"finish_reason":null}]}
548+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"'ll use"},"finish_reason":null}]}
429
549
430− data: {"id":"chatcmpl-452f541934d95f102a74b380","object":"chat.completion.chunk","created":1778601694,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
550+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" the bash"},"finish_reason":null}]}
431
551
432− data: {"id":"chatcmpl-452f541934d95f102a74b380","object":"chat.completion.chunk","created":1778601694,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
552+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" tool"},"finish_reason":null}]}
433
553
434− data: {"id":"chatcmpl-452f541934d95f102a74b380","object":"chat.completion.chunk","created":1778601694,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"command\": "}}]},"finish_reason":null}]}
554+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" to do"},"finish_reason":null}]}
435
555
436− data: {"id":"chatcmpl-452f541934d95f102a74b380","object":"chat.completion.chunk","created":1778601694,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"touch -"}}]},"finish_reason":null}]}
556+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" this."},"finish_reason":null}]}
437
557
438− data: {"id":"chatcmpl-452f541934d95f102a74b380","object":"chat.completion.chunk","created":1778601694,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"t"}}]},"finish_reason":null}]}
558+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_d25ca3324611465a8c0414e8","type":"function","index":0,"function":{"name":"bash","arguments":""}}]},"finish_reason":null}]}
439
559
440− data: {"id":"chatcmpl-452f541934d95f102a74b380","object":"chat.completion.chunk","created":1778601694,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" 19"}}]},"finish_reason":null}]}
560+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
441
561
442− data: {"id":"chatcmpl-452f541934d95f102a74b380","object":"chat.completion.chunk","created":1778601694,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"7001"}}]},"finish_reason":null}]}
562+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
443
563
444− data: {"id":"chatcmpl-452f541934d95f102a74b380","object":"chat.completion.chunk","created":1778601694,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"010"}}]},"finish_reason":null}]}
564+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"command\": "}}]},"finish_reason":null}]}
445
565
446− data: {"id":"chatcmpl-452f541934d95f102a74b380","object":"chat.completion.chunk","created":1778601694,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"000 test"}}]},"finish_reason":null}]}
566+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"printf"}}]},"finish_reason":null}]}
447
567
448− data: {"id":"chatcmpl-452f541934d95f102a74b380","object":"chat.completion.chunk","created":1778601694,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".txt"}}]},"finish_reason":null}]}
568+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" '"}}]},"finish_reason":null}]}
449
569
450− data: {"id":"chatcmpl-452f541934d95f102a74b380","object":"chat.completion.chunk","created":1778601694,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \u0026\u0026 echo '"}}]},"finish_reason":null}]}
570+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"hello bash"}}]},"finish_reason":null}]}
451
571
452− data: {"id":"chatcmpl-452f541934d95f102a74b380","object":"chat.completion.chunk","created":1778601694,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"hello bash"}}]},"finish_reason":null}]}
572+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"' \u003e"}}]},"finish_reason":null}]}
453
573
454− data: {"id":"chatcmpl-452f541934d95f102a74b380","object":"chat.completion.chunk","created":1778601694,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"' \u003e test"}}]},"finish_reason":null}]}
574+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" /tmp"}}]},"finish_reason":null}]}
455
575
456− data: {"id":"chatcmpl-452f541934d95f102a74b380","object":"chat.completion.chunk","created":1778601694,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".txt\""}}]},"finish_reason":null}]}
576+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/c"}}]},"finish_reason":null}]}
457
577
458− data: {"id":"chatcmpl-452f541934d95f102a74b380","object":"chat.completion.chunk","created":1778601694,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":", "}}]},"finish_reason":null}]}
578+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"rush"}}]},"finish_reason":null}]}
459
579
460− data: {"id":"chatcmpl-452f541934d95f102a74b380","object":"chat.completion.chunk","created":1778601694,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"description\": "}}]},"finish_reason":null}]}
580+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}]}
461
581
462− data: {"id":"chatcmpl-452f541934d95f102a74b380","object":"chat.completion.chunk","created":1778601694,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"Create test"}}]},"finish_reason":null}]}
582+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}]}
463
583
464− data: {"id":"chatcmpl-452f541934d95f102a74b380","object":"chat.completion.chunk","created":1778601694,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".txt with content"}}]},"finish_reason":null}]}
584+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}]}
465
585
466− data: {"id":"chatcmpl-452f541934d95f102a74b380","object":"chat.completion.chunk","created":1778601694,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" and zero"}}]},"finish_reason":null}]}
586+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}]}
467
587
468− data: {"id":"chatcmpl-452f541934d95f102a74b380","object":"chat.completion.chunk","created":1778601694,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" timestamp\""}}]},"finish_reason":null}]}
588+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/glm"}}]},"finish_reason":null}]}
469
589
470− data: {"id":"chatcmpl-452f541934d95f102a74b380","object":"chat.completion.chunk","created":1778601694,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
590+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-5"}}]},"finish_reason":null}]}
471
591
472− data: {"id":"chatcmpl-452f541934d95f102a74b380","object":"chat.completion.chunk","created":1778601694,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
592+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".1"}}]},"finish_reason":null}]}
473
593
594+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/bash_tool"}}]},"finish_reason":null}]}
595+
596+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/test.txt"}}]},"finish_reason":null}]}
597+
598+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\", "}}]},"finish_reason":null}]}
599+
600+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"description\": "}}]},"finish_reason":null}]}
601+
602+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"Create test"}}]},"finish_reason":null}]}
603+
604+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".txt with content"}}]},"finish_reason":null}]}
605+
606+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\""}}]},"finish_reason":null}]}
607+
608+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
609+
610+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
611+
474− data: {"id":"chatcmpl-452f541934d95f102a74b380","object":"chat.completion.chunk","created":1778601694,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7776,"completion_tokens":43,"total_tokens":7819,"completion_tokens_details":{"reasoning_tokens":42}}}
612+ data: {"id":"chatcmpl-e3e64c8842e0655f010052ff","object":"chat.completion.chunk","created":1778602898,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":736,"completion_tokens":76,"total_tokens":7852,"prompt_tokens_details":{"cached_tokens":7040},"completion_tokens_details":{"reasoning_tokens":32}}}
475
613
476 data: [DONE]
614 data: [DONE]
477
615
@@ -480,15 +618,15 @@ interactions:
480 - text/event-stream
618 - text/event-stream
481 status: 200 OK
619 status: 200 OK
482 code: 200
620 code: 200
483− duration: 3.634534167s
621+ duration: 6.870477083s
484- id: 2
622- id: 2
485 request:
623 request:
486 proto: HTTP/1.1
624 proto: HTTP/1.1
487 proto_major: 1
625 proto_major: 1
488 proto_minor: 1
626 proto_minor: 1
489− content_length: 34142
627+ content_length: 34305
490 host: ""
628 host: ""
491− 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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\",\"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_1a51a6006cb9443db0b7bcb2\",\"function\":{\"arguments\":\"{\\\"command\\\": \\\"touch -t 197001010000 test.txt && echo 'hello bash' > test.txt\\\", \\\"description\\\": \\\"Create test.txt with content and zero timestamp\\\"}\",\"name\":\"bash\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"no output\",\"tool_call_id\":\"call_1a51a6006cb9443db0b7bcb2\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
629+ 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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\",\"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_d25ca3324611465a8c0414e8\",\"function\":{\"arguments\":\"{\\\"command\\\": \\\"printf 'hello bash' > /tmp/crush-test/TestCoderAgent/glm-5.1/bash_tool/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' without printing its timestamp. I'll use the bash tool to do this.\"},{\"content\":\"no output\",\"tool_call_id\":\"call_d25ca3324611465a8c0414e8\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
492 headers:
630 headers:
493 Accept:
631 Accept:
494 - application/json
632 - application/json
@@ -505,45 +643,25 @@ interactions:
505 content_length: -1
643 content_length: -1
506 uncompressed: true
644 uncompressed: true
507 body: |+
645 body: |+
508− data: {"id":"chatcmpl-590f5fe0db64d1bca1aad6e6","object":"chat.completion.chunk","created":1778601703,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
646+ data: {"id":"chatcmpl-849c71419bf3bc5f48eab3ae","object":"chat.completion.chunk","created":1778602906,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
509−
510− data: {"id":"chatcmpl-590f5fe0db64d1bca1aad6e6","object":"chat.completion.chunk","created":1778601703,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Done"},"finish_reason":null}]}
511−
512− data: {"id":"chatcmpl-590f5fe0db64d1bca1aad6e6","object":"chat.completion.chunk","created":1778601703,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":". Created"},"finish_reason":null}]}
513−
514− data: {"id":"chatcmpl-590f5fe0db64d1bca1aad6e6","object":"chat.completion.chunk","created":1778601703,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `test"},"finish_reason":null}]}
515−
516− data: {"id":"chatcmpl-590f5fe0db64d1bca1aad6e6","object":"chat.completion.chunk","created":1778601703,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":".txt"},"finish_reason":null}]}
517−
518− data: {"id":"chatcmpl-590f5fe0db64d1bca1aad6e6","object":"chat.completion.chunk","created":1778601703,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"` with content"},"finish_reason":null}]}
519−
520− data: {"id":"chatcmpl-590f5fe0db64d1bca1aad6e6","object":"chat.completion.chunk","created":1778601703,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `"},"finish_reason":null}]}
521−
522− data: {"id":"chatcmpl-590f5fe0db64d1bca1aad6e6","object":"chat.completion.chunk","created":1778601703,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"hello bash"},"finish_reason":null}]}
523−
524− data: {"id":"chatcmpl-590f5fe0db64d1bca1aad6e6","object":"chat.completion.chunk","created":1778601703,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"` and timestamp"},"finish_reason":null}]}
525−
526− data: {"id":"chatcmpl-590f5fe0db64d1bca1aad6e6","object":"chat.completion.chunk","created":1778601703,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" set"},"finish_reason":null}]}
527−
528− data: {"id":"chatcmpl-590f5fe0db64d1bca1aad6e6","object":"chat.completion.chunk","created":1778601703,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" to"},"finish_reason":null}]}
529
647
530− data: {"id":"chatcmpl-590f5fe0db64d1bca1aad6e6","object":"chat.completion.chunk","created":1778601703,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" epoch ("},"finish_reason":null}]}
648+ data: {"id":"chatcmpl-849c71419bf3bc5f48eab3ae","object":"chat.completion.chunk","created":1778602906,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Created"},"finish_reason":null}]}
531
649
532− data: {"id":"chatcmpl-590f5fe0db64d1bca1aad6e6","object":"chat.completion.chunk","created":1778601703,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"197"},"finish_reason":null}]}
650+ data: {"id":"chatcmpl-849c71419bf3bc5f48eab3ae","object":"chat.completion.chunk","created":1778602906,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `"},"finish_reason":null}]}
533
651
534− data: {"id":"chatcmpl-590f5fe0db64d1bca1aad6e6","object":"chat.completion.chunk","created":1778601703,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"0-"},"finish_reason":null}]}
652+ data: {"id":"chatcmpl-849c71419bf3bc5f48eab3ae","object":"chat.completion.chunk","created":1778602906,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"test.txt"},"finish_reason":null}]}
535
653
536− data: {"id":"chatcmpl-590f5fe0db64d1bca1aad6e6","object":"chat.completion.chunk","created":1778601703,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"01-01"},"finish_reason":null}]}
654+ data: {"id":"chatcmpl-849c71419bf3bc5f48eab3ae","object":"chat.completion.chunk","created":1778602906,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"` with"},"finish_reason":null}]}
537
655
538− data: {"id":"chatcmpl-590f5fe0db64d1bca1aad6e6","object":"chat.completion.chunk","created":1778601703,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" "},"finish_reason":null}]}
656+ data: {"id":"chatcmpl-849c71419bf3bc5f48eab3ae","object":"chat.completion.chunk","created":1778602906,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" content `"},"finish_reason":null}]}
539
657
540− data: {"id":"chatcmpl-590f5fe0db64d1bca1aad6e6","object":"chat.completion.chunk","created":1778601703,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"00:"},"finish_reason":null}]}
658+ data: {"id":"chatcmpl-849c71419bf3bc5f48eab3ae","object":"chat.completion.chunk","created":1778602906,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"hello bash"},"finish_reason":null}]}
541
659
542− data: {"id":"chatcmpl-590f5fe0db64d1bca1aad6e6","object":"chat.completion.chunk","created":1778601703,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"00)."},"finish_reason":null}]}
660+ data: {"id":"chatcmpl-849c71419bf3bc5f48eab3ae","object":"chat.completion.chunk","created":1778602906,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`."},"finish_reason":null}]}
543
661
544− data: {"id":"chatcmpl-590f5fe0db64d1bca1aad6e6","object":"chat.completion.chunk","created":1778601703,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
662+ data: {"id":"chatcmpl-849c71419bf3bc5f48eab3ae","object":"chat.completion.chunk","created":1778602906,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
545
663
546− data: {"id":"chatcmpl-590f5fe0db64d1bca1aad6e6","object":"chat.completion.chunk","created":1778601703,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7825,"completion_tokens":33,"total_tokens":7858,"completion_tokens_details":{"reasoning_tokens":32}}}
664+ data: {"id":"chatcmpl-849c71419bf3bc5f48eab3ae","object":"chat.completion.chunk","created":1778602906,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":82,"completion_tokens":13,"total_tokens":7839,"prompt_tokens_details":{"cached_tokens":7744},"completion_tokens_details":{"reasoning_tokens":12}}}
547
665
548 data: [DONE]
666 data: [DONE]
549
667
@@ -552,4 +670,4 @@ interactions:
552 - text/event-stream
670 - text/event-stream
553 status: 200 OK
671 status: 200 OK
554 code: 200
672 code: 200
555− duration: 7.757482958s
673+ duration: 5.924362291s
internal/agent/testdata/TestCoderAgent/glm-5.1/download_tool.yaml+345−149
@@ -25,171 +25,389 @@ interactions:
25 content_length: -1
25 content_length: -1
26 uncompressed: true
26 uncompressed: true
27 body: |+
27 body: |+
28− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
28+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
29
29
30− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"User"},"finish_reason":null}]}
30+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"We"},"finish_reason":null}]}
31
31
32− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" asks"},"finish_reason":null}]}
32+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" need"},"finish_reason":null}]}
33
33
34− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
34+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
35
35
36− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
36+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" produce"},"finish_reason":null}]}
37
37
38− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Generate"},"finish_reason":null}]}
38+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
39
39
40− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
40+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" short"},"finish_reason":null}]}
41
41
42− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
42+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
43
43
44− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
44+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
45
45
46− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
46+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" same"},"finish_reason":null}]}
47
47
48− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
48+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" language"},"finish_reason":null}]}
49
49
50− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" following"},"finish_reason":null}]}
50+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
51
51
52− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
52+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"English"},"finish_reason":null}]}
53
53
54− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
54+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")."},"finish_reason":null}]}
55
55
56− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" download"},"finish_reason":null}]}
56+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Summ"},"finish_reason":null}]}
57
57
58− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
58+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ar"},"finish_reason":null}]}
59
59
60− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" file"},"finish_reason":null}]}
60+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ize"},"finish_reason":null}]}
61
61
62− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" from"},"finish_reason":null}]}
62+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
63
63
64− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" https"},"finish_reason":null}]}
64+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
65
65
66− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"://"},"finish_reason":null}]}
66+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"download"},"finish_reason":null}]}
67
67
68− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"example"},"finish_reason":null}]}
68+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
69
69
70− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"-files"},"finish_reason":null}]}
70+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" file"},"finish_reason":null}]}
71
71
72− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".online"},"finish_reason":null}]}
72+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" from"},"finish_reason":null}]}
73
73
74− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"-con"},"finish_reason":null}]}
74+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" URL"},"finish_reason":null}]}
75
75
76− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"vert"},"finish_reason":null}]}
76+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
77
77
78− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".com"},"finish_reason":null}]}
78+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" save"},"finish_reason":null}]}
79
79
80− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"/document"},"finish_reason":null}]}
80+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" it"},"finish_reason":null}]}
81
81
82− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"/t"},"finish_reason":null}]}
82+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" as"},"finish_reason":null}]}
83
83
84− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"xt"},"finish_reason":null}]}
84+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" example"},"finish_reason":null}]}
85
85
86− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"/example"},"finish_reason":null}]}
86+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".txt"},"finish_reason":null}]}
87
87
88− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".txt"},"finish_reason":null}]}
88+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
89
89
90− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
90+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Title"},"finish_reason":null}]}
91
91
92− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" save"},"finish_reason":null}]}
92+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" within"},"finish_reason":null}]}
93
93
94− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" it"},"finish_reason":null}]}
94+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
95
95
96− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" as"},"finish_reason":null}]}
96+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
97
97
98− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" example"},"finish_reason":null}]}
98+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
99
99
100− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".txt"},"finish_reason":null}]}
100+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
101
101
102− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
102+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Maybe"},"finish_reason":null}]}
103
103
104− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Need"},"finish_reason":null}]}
104+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
105
105
106− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
106+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
107
107
108− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" short"},"finish_reason":null}]}
108+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Download"},"finish_reason":null}]}
109
109
110− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
110+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" example"},"finish_reason":null}]}
111
111
112− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \u003c="},"finish_reason":null}]}
112+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".txt"},"finish_reason":null}]}
113
113
114− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
114+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" from"},"finish_reason":null}]}
115
115
116− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
116+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" URL"},"finish_reason":null}]}
117
117
118− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
118+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
119
119
120− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" summarize"},"finish_reason":null}]}
120+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Save"},"finish_reason":null}]}
121
121
122− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
122+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Loc"},"finish_reason":null}]}
123
123
124− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Title"},"finish_reason":null}]}
124+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ally"},"finish_reason":null}]}
125
125
126− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" could"},"finish_reason":null}]}
126+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
127
127
128− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
128+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
129
129
130− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
130+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
131
131
132− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Download"},"finish_reason":null}]}
132+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
133
133
134− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
134+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Let's"},"finish_reason":null}]}
135
135
136− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Save"},"finish_reason":null}]}
136+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
137
137
138− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" example"},"finish_reason":null}]}
138+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
139
139
140− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".txt"},"finish_reason":null}]}
140+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
141
141
142− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" from"},"finish_reason":null}]}
142+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Download"},"finish_reason":null}]}
143
143
144− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" URL"},"finish_reason":null}]}
144+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" example"},"finish_reason":null}]}
145
145
146− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
146+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".txt"},"finish_reason":null}]}
147
147
148− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
148+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" from"},"finish_reason":null}]}
149
149
150− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" under"},"finish_reason":null}]}
150+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" URL"},"finish_reason":null}]}
151
151
152− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
152+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
153
153
154− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
154+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Save"},"finish_reason":null}]}
155
155
156− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
156+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Loc"},"finish_reason":null}]}
157
157
158− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" No"},"finish_reason":null}]}
158+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ally"},"finish_reason":null}]}
159
159
160− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
160+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
161
161
162− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
162+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Characters"},"finish_reason":null}]}
163
163
164− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" no"},"finish_reason":null}]}
164+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
165
165
166− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" colon"},"finish_reason":null}]}
166+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" including"},"finish_reason":null}]}
167
167
168− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
168+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" spaces"},"finish_reason":null}]}
169
169
170− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" One"},"finish_reason":null}]}
170+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
171
171
172− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
172+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" D"},"finish_reason":null}]}
173
173
174− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
174+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
175
175
176− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Download"},"finish_reason":null}]}
176+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
177
177
178− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" and"},"finish_reason":null}]}
178+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
179
179
180− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Save"},"finish_reason":null}]}
180+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" o"},"finish_reason":null}]}
181
181
182− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" example"},"finish_reason":null}]}
182+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
183
183
184− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":".txt"},"finish_reason":null}]}
184+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" w"},"finish_reason":null}]}
185
185
186− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" from"},"finish_reason":null}]}
186+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
187
187
188− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" URL"},"finish_reason":null}]}
188+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" n"},"finish_reason":null}]}
189
189
190− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
190+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
191
191
192− data: {"id":"chatcmpl-e4df7b056dc1c95101c2a8f0","object":"chat.completion.chunk","created":1778601704,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":34,"completion_tokens":90,"total_tokens":316,"prompt_tokens_details":{"cached_tokens":192}}}
192+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" l"},"finish_reason":null}]}
193+
194+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
195+
196+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" o"},"finish_reason":null}]}
197+
198+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
199+
200+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
201+
202+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
203+
204+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" d"},"finish_reason":null}]}
205+
206+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"8"},"finish_reason":null}]}
207+
208+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
209+
210+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"9"},"finish_reason":null}]}
211+
212+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" e"},"finish_reason":null}]}
213+
214+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"10"},"finish_reason":null}]}
215+
216+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" x"},"finish_reason":null}]}
217+
218+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"11"},"finish_reason":null}]}
219+
220+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
221+
222+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"12"},"finish_reason":null}]}
223+
224+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" m"},"finish_reason":null}]}
225+
226+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"13"},"finish_reason":null}]}
227+
228+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" p"},"finish_reason":null}]}
229+
230+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"14"},"finish_reason":null}]}
231+
232+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" l"},"finish_reason":null}]}
233+
234+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"15"},"finish_reason":null}]}
235+
236+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" e"},"finish_reason":null}]}
237+
238+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"16"},"finish_reason":null}]}
239+
240+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ."},"finish_reason":null}]}
241+
242+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"17"},"finish_reason":null}]}
243+
244+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" t"},"finish_reason":null}]}
245+
246+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"18"},"finish_reason":null}]}
247+
248+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" x"},"finish_reason":null}]}
249+
250+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"19"},"finish_reason":null}]}
251+
252+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" t"},"finish_reason":null}]}
253+
254+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"20"},"finish_reason":null}]}
255+
256+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
257+
258+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"21"},"finish_reason":null}]}
259+
260+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" f"},"finish_reason":null}]}
261+
262+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"22"},"finish_reason":null}]}
263+
264+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" r"},"finish_reason":null}]}
265+
266+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"23"},"finish_reason":null}]}
267+
268+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" o"},"finish_reason":null}]}
269+
270+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"24"},"finish_reason":null}]}
271+
272+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" m"},"finish_reason":null}]}
273+
274+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"25"},"finish_reason":null}]}
275+
276+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
277+
278+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"26"},"finish_reason":null}]}
279+
280+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" U"},"finish_reason":null}]}
281+
282+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"27"},"finish_reason":null}]}
283+
284+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" R"},"finish_reason":null}]}
285+
286+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"28"},"finish_reason":null}]}
287+
288+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" L"},"finish_reason":null}]}
289+
290+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"29"},"finish_reason":null}]}
291+
292+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
293+
294+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"30"},"finish_reason":null}]}
295+
296+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
297+
298+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"31"},"finish_reason":null}]}
299+
300+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" n"},"finish_reason":null}]}
301+
302+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"32"},"finish_reason":null}]}
303+
304+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" d"},"finish_reason":null}]}
305+
306+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"33"},"finish_reason":null}]}
307+
308+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
309+
310+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"34"},"finish_reason":null}]}
311+
312+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" S"},"finish_reason":null}]}
313+
314+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"35"},"finish_reason":null}]}
315+
316+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
317+
318+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"36"},"finish_reason":null}]}
319+
320+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" v"},"finish_reason":null}]}
321+
322+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"37"},"finish_reason":null}]}
323+
324+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" e"},"finish_reason":null}]}
325+
326+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"38"},"finish_reason":null}]}
327+
328+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
329+
330+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"39"},"finish_reason":null}]}
331+
332+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" L"},"finish_reason":null}]}
333+
334+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"40"},"finish_reason":null}]}
335+
336+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" o"},"finish_reason":null}]}
337+
338+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"41"},"finish_reason":null}]}
339+
340+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" c"},"finish_reason":null}]}
341+
342+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"42"},"finish_reason":null}]}
343+
344+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
345+
346+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"43"},"finish_reason":null}]}
347+
348+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" l"},"finish_reason":null}]}
349+
350+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"44"},"finish_reason":null}]}
351+
352+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" l"},"finish_reason":null}]}
353+
354+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"45"},"finish_reason":null}]}
355+
356+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" y"},"finish_reason":null}]}
357+
358+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"46"},"finish_reason":null}]}
359+
360+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" =\u003e"},"finish_reason":null}]}
361+
362+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
363+
364+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"46"},"finish_reason":null}]}
365+
366+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
367+
368+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
369+
370+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" fine"},"finish_reason":null}]}
371+
372+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" under"},"finish_reason":null}]}
373+
374+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
375+
376+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
377+
378+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".\n\n"},"finish_reason":null}]}
379+
380+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Return"},"finish_reason":null}]}
381+
382+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" only"},"finish_reason":null}]}
383+
384+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that"},"finish_reason":null}]}
385+
386+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
387+
388+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
389+
390+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Download"},"finish_reason":null}]}
391+
392+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" example"},"finish_reason":null}]}
393+
394+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":".txt"},"finish_reason":null}]}
395+
396+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" from"},"finish_reason":null}]}
397+
398+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" URL"},"finish_reason":null}]}
399+
400+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" and"},"finish_reason":null}]}
401+
402+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Save"},"finish_reason":null}]}
403+
404+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Loc"},"finish_reason":null}]}
405+
406+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"ally"},"finish_reason":null}]}
407+
408+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
409+
410+ data: {"id":"chatcmpl-ba361be141c10de914be5763","object":"chat.completion.chunk","created":1778602907,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":34,"completion_tokens":199,"total_tokens":425,"prompt_tokens_details":{"cached_tokens":192}}}
193
411
194 data: [DONE]
412 data: [DONE]
195
413
@@ -198,7 +416,7 @@ interactions:
198 - text/event-stream
416 - text/event-stream
199 status: 200 OK
417 status: 200 OK
200 code: 200
418 code: 200
201− duration: 467.600875ms
419+ duration: 482.208583ms
202- id: 1
420- id: 1
203 request:
421 request:
204 proto: HTTP/1.1
422 proto: HTTP/1.1
@@ -223,85 +441,61 @@ interactions:
223 content_length: -1
441 content_length: -1
224 uncompressed: true
442 uncompressed: true
225 body: |+
443 body: |+
226− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
444+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
227−
228− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
229−
230− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
231−
232− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" wants to download"},"finish_reason":null}]}
233−
234− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" a file from"},"finish_reason":null}]}
235−
236− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" a URL"},"finish_reason":null}]}
237−
238− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" and save"},"finish_reason":null}]}
239
445
240− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" it as"},"finish_reason":null}]}
446+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_a15b617656dd48cdb460d8ab","type":"function","index":0,"function":{"name":"download","arguments":""}}]},"finish_reason":null}]}
241
447
242− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" example.txt"},"finish_reason":null}]}
448+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
243
449
244− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":". I"},"finish_reason":null}]}
450+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
245
451
246− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"'ll use the"},"finish_reason":null}]}
452+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"file_path\": \"/tmp"}}]},"finish_reason":null}]}
247
453
248− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" download tool for"},"finish_reason":null}]}
454+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/c"}}]},"finish_reason":null}]}
249
455
250− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" this."},"finish_reason":null}]}
456+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"rush-test"}}]},"finish_reason":null}]}
251
457
252− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_8e6a731f0e0a47a1b0017417","type":"function","index":0,"function":{"name":"download","arguments":""}}]},"finish_reason":null}]}
458+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}]}
253
459
254− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
460+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}]}
255
461
256− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
462+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}]}
257
463
258− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"file_path\": "}}]},"finish_reason":null}]}
464+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/glm"}}]},"finish_reason":null}]}
259
465
260− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/tmp/c"}}]},"finish_reason":null}]}
466+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-5"}}]},"finish_reason":null}]}
261
467
262− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"rush"}}]},"finish_reason":null}]}
468+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".1/download"}}]},"finish_reason":null}]}
263
469
264− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}]}
470+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}]}
265
471
266− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}]}
472+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/example.txt"}}]},"finish_reason":null}]}
267
473
268− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}]}
474+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\", "}}]},"finish_reason":null}]}
269
475
270− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}]}
476+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"url\": "}}]},"finish_reason":null}]}
271
477
272− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/glm"}}]},"finish_reason":null}]}
478+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"https://example"}}]},"finish_reason":null}]}
273
479
274− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-5"}}]},"finish_reason":null}]}
480+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-files"}}]},"finish_reason":null}]}
275
481
276− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".1"}}]},"finish_reason":null}]}
482+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".online"}}]},"finish_reason":null}]}
277
483
278− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/download_tool"}}]},"finish_reason":null}]}
484+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-convert"}}]},"finish_reason":null}]}
279
485
280− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/example.txt\""}}]},"finish_reason":null}]}
486+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".com/document"}}]},"finish_reason":null}]}
281
487
282− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":", "}}]},"finish_reason":null}]}
488+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/t"}}]},"finish_reason":null}]}
283
489
284− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"url\": "}}]},"finish_reason":null}]}
490+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"xt"}}]},"finish_reason":null}]}
285
491
286− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"https://example"}}]},"finish_reason":null}]}
492+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/example.txt\""}}]},"finish_reason":null}]}
287
493
288− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-files"}}]},"finish_reason":null}]}
494+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
289
495
290− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".online-"}}]},"finish_reason":null}]}
496+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
291
497
292− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"convert.com/document"}}]},"finish_reason":null}]}
293−
294− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/t"}}]},"finish_reason":null}]}
295−
296− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"xt/example"}}]},"finish_reason":null}]}
297−
298− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".txt\""}}]},"finish_reason":null}]}
299−
300− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
301−
302− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
303−
304− data: {"id":"chatcmpl-1fc54652250a944af3fd063f","object":"chat.completion.chunk","created":1778601708,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7779,"completion_tokens":72,"total_tokens":7851,"completion_tokens_details":{"reasoning_tokens":26}}}
498+ data: {"id":"chatcmpl-56a120a873ddf166c2339f99","object":"chat.completion.chunk","created":1778602911,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":739,"completion_tokens":46,"total_tokens":7825,"prompt_tokens_details":{"cached_tokens":7040},"completion_tokens_details":{"reasoning_tokens":45}}}
305
499
306 data: [DONE]
500 data: [DONE]
307
501
@@ -310,7 +504,7 @@ interactions:
310 - text/event-stream
504 - text/event-stream
311 status: 200 OK
505 status: 200 OK
312 code: 200
506 code: 200
313− duration: 4.006941625s
507+ duration: 4.397847291s
314- id: 2
508- id: 2
315 request:
509 request:
316 proto: HTTP/1.1
510 proto: HTTP/1.1
@@ -356,15 +550,15 @@ interactions:
356 - text/plain; charset=UTF-8
550 - text/plain; charset=UTF-8
357 status: 200 OK
551 status: 200 OK
358 code: 200
552 code: 200
359− duration: 678.656667ms
553+ duration: 1.709496s
360- id: 3
554- id: 3
361 request:
555 request:
362 proto: HTTP/1.1
556 proto: HTTP/1.1
363 proto_major: 1
557 proto_major: 1
364 proto_minor: 1
558 proto_minor: 1
365− content_length: 34399
559+ content_length: 34267
366 host: ""
560 host: ""
367− 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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\",\"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_8e6a731f0e0a47a1b0017417\",\"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. I'll use the download tool for this.\"},{\"content\":\"Successfully downloaded 2574 bytes to example.txt (Content-Type: text/plain; charset=UTF-8)\",\"tool_call_id\":\"call_8e6a731f0e0a47a1b0017417\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
561+ 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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\",\"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_a15b617656dd48cdb460d8ab\",\"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\"},{\"content\":\"Successfully downloaded 2574 bytes to example.txt (Content-Type: text/plain; charset=UTF-8)\",\"tool_call_id\":\"call_a15b617656dd48cdb460d8ab\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
368 headers:
562 headers:
369 Accept:
563 Accept:
370 - application/json
564 - application/json
@@ -381,21 +575,23 @@ interactions:
381 content_length: -1
575 content_length: -1
382 uncompressed: true
576 uncompressed: true
383 body: |+
577 body: |+
384− data: {"id":"chatcmpl-2fbaf1aacf59e1aafe55e635","object":"chat.completion.chunk","created":1778601713,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
578+ data: {"id":"chatcmpl-d5e1ff21498ba1c8d7f74995","object":"chat.completion.chunk","created":1778602916,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
579+
580+ data: {"id":"chatcmpl-d5e1ff21498ba1c8d7f74995","object":"chat.completion.chunk","created":1778602916,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Download"},"finish_reason":null}]}
385
581
386− data: {"id":"chatcmpl-2fbaf1aacf59e1aafe55e635","object":"chat.completion.chunk","created":1778601713,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Download"},"finish_reason":null}]}
582+ data: {"id":"chatcmpl-d5e1ff21498ba1c8d7f74995","object":"chat.completion.chunk","created":1778602916,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"ed and"},"finish_reason":null}]}
387
583
388− data: {"id":"chatcmpl-2fbaf1aacf59e1aafe55e635","object":"chat.completion.chunk","created":1778601713,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"ed and"},"finish_reason":null}]}
584+ data: {"id":"chatcmpl-d5e1ff21498ba1c8d7f74995","object":"chat.completion.chunk","created":1778602916,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" saved as"},"finish_reason":null}]}
389
585
390− data: {"id":"chatcmpl-2fbaf1aacf59e1aafe55e635","object":"chat.completion.chunk","created":1778601713,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" saved as `"},"finish_reason":null}]}
586+ data: {"id":"chatcmpl-d5e1ff21498ba1c8d7f74995","object":"chat.completion.chunk","created":1778602916,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `example"},"finish_reason":null}]}
391
587
392− data: {"id":"chatcmpl-2fbaf1aacf59e1aafe55e635","object":"chat.completion.chunk","created":1778601713,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"example.txt"},"finish_reason":null}]}
588+ data: {"id":"chatcmpl-d5e1ff21498ba1c8d7f74995","object":"chat.completion.chunk","created":1778602916,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":".txt"},"finish_reason":null}]}
393
589
394− data: {"id":"chatcmpl-2fbaf1aacf59e1aafe55e635","object":"chat.completion.chunk","created":1778601713,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`."},"finish_reason":null}]}
590+ data: {"id":"chatcmpl-d5e1ff21498ba1c8d7f74995","object":"chat.completion.chunk","created":1778602916,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`."},"finish_reason":null}]}
395
591
396− data: {"id":"chatcmpl-2fbaf1aacf59e1aafe55e635","object":"chat.completion.chunk","created":1778601713,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
592+ data: {"id":"chatcmpl-d5e1ff21498ba1c8d7f74995","object":"chat.completion.chunk","created":1778602916,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
397
593
398− data: {"id":"chatcmpl-2fbaf1aacf59e1aafe55e635","object":"chat.completion.chunk","created":1778601713,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7851,"completion_tokens":11,"total_tokens":7862,"completion_tokens_details":{"reasoning_tokens":10}}}
594+ data: {"id":"chatcmpl-d5e1ff21498ba1c8d7f74995","object":"chat.completion.chunk","created":1778602916,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7851,"completion_tokens":11,"total_tokens":7862,"completion_tokens_details":{"reasoning_tokens":10}}}
399
595
400 data: [DONE]
596 data: [DONE]
401
597
@@ -404,4 +600,4 @@ interactions:
404 - text/event-stream
600 - text/event-stream
405 status: 200 OK
601 status: 200 OK
406 code: 200
602 code: 200
407− duration: 4.159503041s
603+ duration: 3.135074417s
internal/agent/testdata/TestCoderAgent/glm-5.1/fetch_tool.yaml+466−252
@@ -25,421 +25,619 @@ interactions:
25 content_length: -1
25 content_length: -1
26 uncompressed: true
26 uncompressed: true
27 body: |+
27 body: |+
28− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
28+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
29
29
30− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
30+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
31
31
32− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
32+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
33
33
34− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
34+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" asks"},"finish_reason":null}]}
35
35
36− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
36+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
37
37
38− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Generate"},"finish_reason":null}]}
38+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
39
39
40− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
40+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Generate"},"finish_reason":null}]}
41
41
42− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
42+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
43
43
44− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
44+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
45
45
46− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
46+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
47
47
48− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
48+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
49
49
50− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" following"},"finish_reason":null}]}
50+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
51
51
52− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
52+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" following"},"finish_reason":null}]}
53
53
54− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
54+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
55
55
56− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" fetch"},"finish_reason":null}]}
56+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
57
57
58− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
58+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" fetch"},"finish_reason":null}]}
59
59
60− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
60+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
61
61
62− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" from"},"finish_reason":null}]}
62+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
63
63
64− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" https"},"finish_reason":null}]}
64+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" from"},"finish_reason":null}]}
65
65
66− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"://"},"finish_reason":null}]}
66+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" https"},"finish_reason":null}]}
67
67
68− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"example"},"finish_reason":null}]}
68+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"://"},"finish_reason":null}]}
69
69
70− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"-files"},"finish_reason":null}]}
70+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"example"},"finish_reason":null}]}
71
71
72− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".online"},"finish_reason":null}]}
72+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"-files"},"finish_reason":null}]}
73
73
74− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"-con"},"finish_reason":null}]}
74+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".online"},"finish_reason":null}]}
75
75
76− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"vert"},"finish_reason":null}]}
76+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"-con"},"finish_reason":null}]}
77
77
78− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".com"},"finish_reason":null}]}
78+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"vert"},"finish_reason":null}]}
79
79
80− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"/"},"finish_reason":null}]}
80+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".com"},"finish_reason":null}]}
81
81
82− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"website"},"finish_reason":null}]}
82+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"/"},"finish_reason":null}]}
83
83
84− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"/html"},"finish_reason":null}]}
84+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"website"},"finish_reason":null}]}
85
85
86− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"/example"},"finish_reason":null}]}
86+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"/html"},"finish_reason":null}]}
87
87
88− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".html"},"finish_reason":null}]}
88+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"/example"},"finish_reason":null}]}
89
89
90− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
90+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".html"},"finish_reason":null}]}
91
91
92− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" tell"},"finish_reason":null}]}
92+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
93
93
94− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" me"},"finish_reason":null}]}
94+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" tell"},"finish_reason":null}]}
95
95
96− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" if"},"finish_reason":null}]}
96+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" me"},"finish_reason":null}]}
97
97
98− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" it"},"finish_reason":null}]}
98+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" if"},"finish_reason":null}]}
99
99
100− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" contains"},"finish_reason":null}]}
100+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" it"},"finish_reason":null}]}
101
101
102− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
102+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" contains"},"finish_reason":null}]}
103
103
104− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" word"},"finish_reason":null}]}
104+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
105
105
106− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
106+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" word"},"finish_reason":null}]}
107
107
108− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"John"},"finish_reason":null}]}
108+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
109
109
110− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Doe"},"finish_reason":null}]}
110+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"John"},"finish_reason":null}]}
111
111
112− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'"},"finish_reason":null}]}
112+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Doe"},"finish_reason":null}]}
113
113
114− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
114+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'"},"finish_reason":null}]}
115
115
116− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Need"},"finish_reason":null}]}
116+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
117
117
118− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
118+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" We"},"finish_reason":null}]}
119
119
120− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" short"},"finish_reason":null}]}
120+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" need"},"finish_reason":null}]}
121
121
122− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
122+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
123
123
124− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
124+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" produce"},"finish_reason":null}]}
125
125
126− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \u003c="},"finish_reason":null}]}
126+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
127
127
128− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
128+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" short"},"finish_reason":null}]}
129
129
130− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
130+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
131
131
132− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
132+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
133
133
134− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" same"},"finish_reason":null}]}
134+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" same"},"finish_reason":null}]}
135
135
136− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" language"},"finish_reason":null}]}
136+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" language"},"finish_reason":null}]}
137
137
138− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
138+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
139
139
140− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"English"},"finish_reason":null}]}
140+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"English"},"finish_reason":null}]}
141
141
142− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")."},"finish_reason":null}]}
142+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")."},"finish_reason":null}]}
143
143
144− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Summ"},"finish_reason":null}]}
144+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Must"},"finish_reason":null}]}
145
145
146− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ar"},"finish_reason":null}]}
146+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
147
147
148− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ize"},"finish_reason":null}]}
148+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \u003c="},"finish_reason":null}]}
149
149
150− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
150+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
151
151
152− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
152+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
153
153
154− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Check"},"finish_reason":null}]}
154+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
155
155
156− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" if"},"finish_reason":null}]}
156+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" one"},"finish_reason":null}]}
157
157
158− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" example"},"finish_reason":null}]}
158+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
159
159
160− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".html"},"finish_reason":null}]}
160+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
161
161
162− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" contains"},"finish_reason":null}]}
162+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" no"},"finish_reason":null}]}
163
163
164− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
164+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
165
165
166− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"John"},"finish_reason":null}]}
166+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" or"},"finish_reason":null}]}
167
167
168− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Doe"},"finish_reason":null}]}
168+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" col"},"finish_reason":null}]}
169
169
170− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'"},"finish_reason":null}]}
170+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ons"},"finish_reason":null}]}
171
171
172− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
172+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".\n\n"},"finish_reason":null}]}
173
173
174− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Title"},"finish_reason":null}]}
174+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Possible"},"finish_reason":null}]}
175
175
176− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" could"},"finish_reason":null}]}
176+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
177
177
178− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
178+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
179
179
180− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
180+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
181
181
182− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
182+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Check"},"finish_reason":null}]}
183
183
184− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Check"},"finish_reason":null}]}
184+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
185
185
186− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
186+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
187
187
188− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
188+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"John"},"finish_reason":null}]}
189
189
190− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"John"},"finish_reason":null}]}
190+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Doe"},"finish_reason":null}]}
191
191
192− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Doe"},"finish_reason":null}]}
192+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'"},"finish_reason":null}]}
193
193
194− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'"},"finish_reason":null}]}
194+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
195
195
196− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
196+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Example"},"finish_reason":null}]}
197
197
198− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" example"},"finish_reason":null}]}
198+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" HTML"},"finish_reason":null}]}
199
199
200− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".html"},"finish_reason":null}]}
200+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Page"},"finish_reason":null}]}
201
201
202− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
202+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
203
203
204− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
204+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
205
205
206− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
206+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
207
207
208− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
208+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
209
209
210− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
210+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" let's"},"finish_reason":null}]}
211
211
212− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Check"},"finish_reason":null}]}
212+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
213
213
214− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
214+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
215
215
216− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
216+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
217
217
218− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"John"},"finish_reason":null}]}
218+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Check"},"finish_reason":null}]}
219
219
220− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Doe"},"finish_reason":null}]}
220+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
221
221
222− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'"},"finish_reason":null}]}
222+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
223
223
224− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
224+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"John"},"finish_reason":null}]}
225
225
226− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" example"},"finish_reason":null}]}
226+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Doe"},"finish_reason":null}]}
227
227
228− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".html"},"finish_reason":null}]}
228+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'"},"finish_reason":null}]}
229
229
230− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
230+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
231
231
232− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" length"},"finish_reason":null}]}
232+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Example"},"finish_reason":null}]}
233
233
234− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
234+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" HTML"},"finish_reason":null}]}
235
235
236− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Let's"},"finish_reason":null}]}
236+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Page"},"finish_reason":null}]}
237
237
238− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
238+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
239
239
240− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
240+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
241
241
242− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" C"},"finish_reason":null}]}
242+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
243
243
244− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
244+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"38"},"finish_reason":null}]}
245
245
246− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
246+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
247
247
248− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
248+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
249
249
250− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"h"},"finish_reason":null}]}
250+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"including"},"finish_reason":null}]}
251
251
252− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
252+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" spaces"},"finish_reason":null}]}
253
253
254− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"e"},"finish_reason":null}]}
254+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")."},"finish_reason":null}]}
255
255
256− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
256+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" No"},"finish_reason":null}]}
257
257
258− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"c"},"finish_reason":null}]}
258+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
259
259
260− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
260+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"?"},"finish_reason":null}]}
261
261
262− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"k"},"finish_reason":null}]}
262+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" It"},"finish_reason":null}]}
263
263
264− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
264+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" includes"},"finish_reason":null}]}
265
265
266− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
266+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" single"},"finish_reason":null}]}
267
267
268− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"space"},"finish_reason":null}]}
268+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
269
269
270− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
270+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" around"},"finish_reason":null}]}
271
271
272− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
272+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" John"},"finish_reason":null}]}
273
273
274− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"f"},"finish_reason":null}]}
274+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Doe"},"finish_reason":null}]}
275
275
276− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
276+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
277
277
278− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"o"},"finish_reason":null}]}
278+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
279
279
280− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"8"},"finish_reason":null}]}
280+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" okay"},"finish_reason":null}]}
281
281
282− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"r"},"finish_reason":null}]}
282+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"?"},"finish_reason":null}]}
283
283
284− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"9"},"finish_reason":null}]}
284+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Title"},"finish_reason":null}]}
285
285
286− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
286+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" should"},"finish_reason":null}]}
287
287
288− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"space"},"finish_reason":null}]}
288+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" not"},"finish_reason":null}]}
289
289
290− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"10"},"finish_reason":null}]}
290+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" have"},"finish_reason":null}]}
291
291
292− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")'"},"finish_reason":null}]}
292+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
293
293
294− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"11"},"finish_reason":null}]}
294+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"?"},"finish_reason":null}]}
295
295
296− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"J"},"finish_reason":null}]}
296+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Not"},"finish_reason":null}]}
297
297
298− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"12"},"finish_reason":null}]}
298+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" required"},"finish_reason":null}]}
299
299
300− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"o"},"finish_reason":null}]}
300+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
301
301
302− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"13"},"finish_reason":null}]}
302+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" avoid"},"finish_reason":null}]}
303
303
304− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"h"},"finish_reason":null}]}
304+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
305
305
306− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"14"},"finish_reason":null}]}
306+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
307
307
308− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"n"},"finish_reason":null}]}
308+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" but"},"finish_reason":null}]}
309
309
310− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"15"},"finish_reason":null}]}
310+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" possibly"},"finish_reason":null}]}
311
311
312− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
312+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" okay"},"finish_reason":null}]}
313
313
314− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"space"},"finish_reason":null}]}
314+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
315
315
316− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"16"},"finish_reason":null}]}
316+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" They"},"finish_reason":null}]}
317
317
318− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"D"},"finish_reason":null}]}
318+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" said"},"finish_reason":null}]}
319
319
320− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"17"},"finish_reason":null}]}
320+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" not"},"finish_reason":null}]}
321
321
322− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"o"},"finish_reason":null}]}
322+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
323
323
324− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"18"},"finish_reason":null}]}
324+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" use"},"finish_reason":null}]}
325
325
326− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"e"},"finish_reason":null}]}
326+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
327
327
328− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'"},"finish_reason":null}]}
328+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" or"},"finish_reason":null}]}
329
329
330− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"19"},"finish_reason":null}]}
330+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" col"},"finish_reason":null}]}
331
331
332− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
332+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ons"},"finish_reason":null}]}
333
333
334− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"space"},"finish_reason":null}]}
334+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
335
335
336− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"20"},"finish_reason":null}]}
336+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Actually"},"finish_reason":null}]}
337
337
338− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")i"},"finish_reason":null}]}
338+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" rule"},"finish_reason":null}]}
339
339
340− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"21"},"finish_reason":null}]}
340+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
341
341
342− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"n"},"finish_reason":null}]}
342+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
343
343
344− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"22"},"finish_reason":null}]}
344+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Do"},"finish_reason":null}]}
345
345
346− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
346+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" not"},"finish_reason":null}]}
347
347
348− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"space"},"finish_reason":null}]}
348+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" use"},"finish_reason":null}]}
349
349
350− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"23"},"finish_reason":null}]}
350+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
351
351
352− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")e"},"finish_reason":null}]}
352+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" or"},"finish_reason":null}]}
353
353
354− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"24"},"finish_reason":null}]}
354+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" col"},"finish_reason":null}]}
355
355
356− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"x"},"finish_reason":null}]}
356+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ons"},"finish_reason":null}]}
357
357
358− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"25"},"finish_reason":null}]}
358+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
359
359
360− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"a"},"finish_reason":null}]}
360+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" So"},"finish_reason":null}]}
361
361
362− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"26"},"finish_reason":null}]}
362+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" we"},"finish_reason":null}]}
363
363
364− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"m"},"finish_reason":null}]}
364+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" cannot"},"finish_reason":null}]}
365
365
366− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"27"},"finish_reason":null}]}
366+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" have"},"finish_reason":null}]}
367
367
368− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"p"},"finish_reason":null}]}
368+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
369
369
370− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"28"},"finish_reason":null}]}
370+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
371
371
372− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"l"},"finish_reason":null}]}
372+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Remove"},"finish_reason":null}]}
373
373
374− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"29"},"finish_reason":null}]}
374+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
375
375
376− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"e"},"finish_reason":null}]}
376+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
377
377
378− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"30"},"finish_reason":null}]}
378+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
379
379
380− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
380+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Check"},"finish_reason":null}]}
381
381
382− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"31"},"finish_reason":null}]}
382+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
383
383
384− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"h"},"finish_reason":null}]}
384+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" John"},"finish_reason":null}]}
385
385
386− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"32"},"finish_reason":null}]}
386+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Doe"},"finish_reason":null}]}
387
387
388− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"t"},"finish_reason":null}]}
388+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
389
389
390− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"33"},"finish_reason":null}]}
390+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Example"},"finish_reason":null}]}
391
391
392− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"m"},"finish_reason":null}]}
392+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" HTML"},"finish_reason":null}]}
393
393
394− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"34"},"finish_reason":null}]}
394+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Page"},"finish_reason":null}]}
395
395
396− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"l"},"finish_reason":null}]}
396+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
397
397
398− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"35"},"finish_reason":null}]}
398+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
399
399
400− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
400+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
401
401
402− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
402+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Let's"},"finish_reason":null}]}
403
403
404− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
404+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
405
405
406− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"35"},"finish_reason":null}]}
406+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
407
407
408− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
408+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
409
409
410− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
410+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
411
411
412− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" okay"},"finish_reason":null}]}
412+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Check"},"finish_reason":null}]}
413
413
414− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
414+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
415
415
416− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Provide"},"finish_reason":null}]}
416+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" John"},"finish_reason":null}]}
417
417
418− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that"},"finish_reason":null}]}
418+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Doe"},"finish_reason":null}]}
419
419
420− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".\n\n"},"finish_reason":null}]}
420+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
421
421
422− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Check"},"finish_reason":null}]}
422+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Example"},"finish_reason":null}]}
423
423
424− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" for"},"finish_reason":null}]}
424+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" HTML"},"finish_reason":null}]}
425
425
426− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" '"},"finish_reason":null}]}
426+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Page"},"finish_reason":null}]}
427
427
428− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"John"},"finish_reason":null}]}
428+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
429
429
430− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Doe"},"finish_reason":null}]}
430+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" length"},"finish_reason":null}]}
431
431
432− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"'"},"finish_reason":null}]}
432+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
433
433
434− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" in"},"finish_reason":null}]}
434+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
435
435
436− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" example"},"finish_reason":null}]}
436+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" letters"},"finish_reason":null}]}
437
437
438− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":".html"},"finish_reason":null}]}
438+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
439
439
440− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
440+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Check"},"finish_reason":null}]}
441
441
442− data: {"id":"chatcmpl-f0927d49937b379d557ec87f","object":"chat.completion.chunk","created":1778601714,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":167,"completion_tokens":215,"total_tokens":446,"prompt_tokens_details":{"cached_tokens":64}}}
442+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
443+
444+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
445+
446+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
447+
448+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" +"},"finish_reason":null}]}
449+
450+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
451+
452+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ="},"finish_reason":null}]}
453+
454+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
455+
456+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":";"},"finish_reason":null}]}
457+
458+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
459+
460+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
461+
462+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
463+
464+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
465+
466+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" -\u003e"},"finish_reason":null}]}
467+
468+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"9"},"finish_reason":null}]}
469+
470+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":";"},"finish_reason":null}]}
471+
472+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
473+
474+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
475+
476+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"10"},"finish_reason":null}]}
477+
478+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":";"},"finish_reason":null}]}
479+
480+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" John"},"finish_reason":null}]}
481+
482+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
483+
484+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
485+
486+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
487+
488+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"14"},"finish_reason":null}]}
489+
490+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":";"},"finish_reason":null}]}
491+
492+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
493+
494+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
495+
496+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"15"},"finish_reason":null}]}
497+
498+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":";"},"finish_reason":null}]}
499+
500+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Doe"},"finish_reason":null}]}
501+
502+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
503+
504+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
505+
506+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
507+
508+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"18"},"finish_reason":null}]}
509+
510+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":";"},"finish_reason":null}]}
511+
512+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
513+
514+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
515+
516+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"19"},"finish_reason":null}]}
517+
518+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":";"},"finish_reason":null}]}
519+
520+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
521+
522+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
523+
524+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
525+
526+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
527+
528+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"21"},"finish_reason":null}]}
529+
530+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":";"},"finish_reason":null}]}
531+
532+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
533+
534+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
535+
536+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"22"},"finish_reason":null}]}
537+
538+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":";"},"finish_reason":null}]}
539+
540+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Example"},"finish_reason":null}]}
541+
542+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
543+
544+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
545+
546+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
547+
548+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"29"},"finish_reason":null}]}
549+
550+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":";"},"finish_reason":null}]}
551+
552+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
553+
554+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
555+
556+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"30"},"finish_reason":null}]}
557+
558+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":";"},"finish_reason":null}]}
559+
560+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" HTML"},"finish_reason":null}]}
561+
562+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
563+
564+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
565+
566+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
567+
568+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"34"},"finish_reason":null}]}
569+
570+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":";"},"finish_reason":null}]}
571+
572+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
573+
574+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
575+
576+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"35"},"finish_reason":null}]}
577+
578+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":";"},"finish_reason":null}]}
579+
580+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Page"},"finish_reason":null}]}
581+
582+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
583+
584+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
585+
586+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
587+
588+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"39"},"finish_reason":null}]}
589+
590+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
591+
592+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" So"},"finish_reason":null}]}
593+
594+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
595+
596+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"39"},"finish_reason":null}]}
597+
598+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
599+
600+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
601+
602+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" no"},"finish_reason":null}]}
603+
604+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
605+
606+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".\n\n"},"finish_reason":null}]}
607+
608+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"That"},"finish_reason":null}]}
609+
610+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" fits"},"finish_reason":null}]}
611+
612+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
613+
614+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Return"},"finish_reason":null}]}
615+
616+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that"},"finish_reason":null}]}
617+
618+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" exactly"},"finish_reason":null}]}
619+
620+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
621+
622+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Check"},"finish_reason":null}]}
623+
624+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" for"},"finish_reason":null}]}
625+
626+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" John"},"finish_reason":null}]}
627+
628+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Doe"},"finish_reason":null}]}
629+
630+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" in"},"finish_reason":null}]}
631+
632+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Example"},"finish_reason":null}]}
633+
634+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" HTML"},"finish_reason":null}]}
635+
636+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Page"},"finish_reason":null}]}
637+
638+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
639+
640+ data: {"id":"chatcmpl-f81138bfe8a0019567efdd49","object":"chat.completion.chunk","created":1778602917,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":51,"completion_tokens":314,"total_tokens":541,"prompt_tokens_details":{"cached_tokens":176}}}
443
641
444 data: [DONE]
642 data: [DONE]
445
643
@@ -448,7 +646,7 @@ interactions:
448 - text/event-stream
646 - text/event-stream
449 status: 200 OK
647 status: 200 OK
450 code: 200
648 code: 200
451− duration: 597.545416ms
649+ duration: 494.272708ms
452- id: 1
650- id: 1
453 request:
651 request:
454 proto: HTTP/1.1
652 proto: HTTP/1.1
@@ -473,61 +671,65 @@ interactions:
473 content_length: -1
671 content_length: -1
474 uncompressed: true
672 uncompressed: true
475 body: |+
673 body: |+
476− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
674+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
675+
676+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
677+
678+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
477
679
478− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
680+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" wants me"},"finish_reason":null}]}
479
681
480− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
682+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" to fetch"},"finish_reason":null}]}
481
683
482− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" wants me to fetch"},"finish_reason":null}]}
684+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" content from a"},"finish_reason":null}]}
483
685
484− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
686+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" URL and check"},"finish_reason":null}]}
485
687
486− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" from a URL and"},"finish_reason":null}]}
688+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" if it"},"finish_reason":null}]}
487
689
488− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" check"},"finish_reason":null}]}
690+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" contains the"},"finish_reason":null}]}
489
691
490− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" if it"},"finish_reason":null}]}
692+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" word '"},"finish_reason":null}]}
491
693
492− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" contains the word '"},"finish_reason":null}]}
694+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"John Doe"},"finish_reason":null}]}
493
695
494− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"John Doe"},"finish_reason":null}]}
696+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"'."},"finish_reason":null}]}
495
697
496− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"'."},"finish_reason":null}]}
698+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_3eb473bfbb9f4ca18112f6c2","type":"function","index":0,"function":{"name":"fetch","arguments":""}}]},"finish_reason":null}]}
497
699
498− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_ee068c7ab33d4d7ca7398937","type":"function","index":0,"function":{"name":"fetch","arguments":""}}]},"finish_reason":null}]}
700+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
499
701
500− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
702+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
501
703
502− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
704+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"format\": "}}]},"finish_reason":null}]}
503
705
504− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"format\": "}}]},"finish_reason":null}]}
706+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"text\", "}}]},"finish_reason":null}]}
505
707
506− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"text\""}}]},"finish_reason":null}]}
708+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"url\": "}}]},"finish_reason":null}]}
507
709
508− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":", \"url\": "}}]},"finish_reason":null}]}
710+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"https"}}]},"finish_reason":null}]}
509
711
510− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"https://example"}}]},"finish_reason":null}]}
712+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"://example"}}]},"finish_reason":null}]}
511
713
512− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-files"}}]},"finish_reason":null}]}
714+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-files"}}]},"finish_reason":null}]}
513
715
514− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".online"}}]},"finish_reason":null}]}
716+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".online"}}]},"finish_reason":null}]}
515
717
516− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-convert.com"}}]},"finish_reason":null}]}
718+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}]}
517
719
518− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/website"}}]},"finish_reason":null}]}
720+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"convert.com"}}]},"finish_reason":null}]}
519
721
520− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/html"}}]},"finish_reason":null}]}
722+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/website"}}]},"finish_reason":null}]}
521
723
522− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/example.html"}}]},"finish_reason":null}]}
724+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/html/example"}}]},"finish_reason":null}]}
523
725
524− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\""}}]},"finish_reason":null}]}
726+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".html\""}}]},"finish_reason":null}]}
525
727
526− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
728+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
527
729
528− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
730+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
529
731
530− data: {"id":"chatcmpl-0367ea5f9721db65227d2560","object":"chat.completion.chunk","created":1778601718,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7786,"completion_tokens":50,"total_tokens":7836,"completion_tokens_details":{"reasoning_tokens":21}}}
732+ data: {"id":"chatcmpl-509896ec2c0018c3bafd2c2b","object":"chat.completion.chunk","created":1778602920,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7786,"completion_tokens":50,"total_tokens":7836,"completion_tokens_details":{"reasoning_tokens":21}}}
531
733
532 data: [DONE]
734 data: [DONE]
533
735
@@ -536,7 +738,7 @@ interactions:
536 - text/event-stream
738 - text/event-stream
537 status: 200 OK
739 status: 200 OK
538 code: 200
740 code: 200
539− duration: 5.000877791s
741+ duration: 3.701119875s
540- id: 2
742- id: 2
541 request:
743 request:
542 proto: HTTP/1.1
744 proto: HTTP/1.1
@@ -607,7 +809,7 @@ interactions:
607 - text/html; charset=UTF-8
809 - text/html; charset=UTF-8
608 status: 200 OK
810 status: 200 OK
609 code: 200
811 code: 200
610− duration: 158.890875ms
812+ duration: 160.953ms
611- id: 3
813- id: 3
612 request:
814 request:
613 proto: HTTP/1.1
815 proto: HTTP/1.1
@@ -615,7 +817,7 @@ interactions:
615 proto_minor: 1
817 proto_minor: 1
616 content_length: 34346
818 content_length: 34346
617 host: ""
819 host: ""
618− 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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\",\"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_ee068c7ab33d4d7ca7398937\",\"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_ee068c7ab33d4d7ca7398937\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
820+ 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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\",\"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_3eb473bfbb9f4ca18112f6c2\",\"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_3eb473bfbb9f4ca18112f6c2\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
619 headers:
821 headers:
620 Accept:
822 Accept:
621 - application/json
823 - application/json
@@ -632,27 +834,39 @@ interactions:
632 content_length: -1
834 content_length: -1
633 uncompressed: true
835 uncompressed: true
634 body: |+
836 body: |+
635− data: {"id":"chatcmpl-2f895e7d8be2f4beffa3c809","object":"chat.completion.chunk","created":1778601723,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
837+ data: {"id":"chatcmpl-7714e100521a3da20cbf625b","object":"chat.completion.chunk","created":1778602924,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
838+
839+ data: {"id":"chatcmpl-7714e100521a3da20cbf625b","object":"chat.completion.chunk","created":1778602924,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
840+
841+ data: {"id":"chatcmpl-7714e100521a3da20cbf625b","object":"chat.completion.chunk","created":1778602924,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" fetched"},"finish_reason":null}]}
842+
843+ data: {"id":"chatcmpl-7714e100521a3da20cbf625b","object":"chat.completion.chunk","created":1778602924,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" content doesn"},"finish_reason":null}]}
844+
845+ data: {"id":"chatcmpl-7714e100521a3da20cbf625b","object":"chat.completion.chunk","created":1778602924,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"'t contain"},"finish_reason":null}]}
846+
847+ data: {"id":"chatcmpl-7714e100521a3da20cbf625b","object":"chat.completion.chunk","created":1778602924,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" the word"},"finish_reason":null}]}
848+
849+ data: {"id":"chatcmpl-7714e100521a3da20cbf625b","object":"chat.completion.chunk","created":1778602924,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
636
850
637− data: {"id":"chatcmpl-2f895e7d8be2f4beffa3c809","object":"chat.completion.chunk","created":1778601723,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"The"},"finish_reason":null}]}
851+ data: {"id":"chatcmpl-7714e100521a3da20cbf625b","object":"chat.completion.chunk","created":1778602924,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"John Doe"},"finish_reason":null}]}
638
852
639− data: {"id":"chatcmpl-2f895e7d8be2f4beffa3c809","object":"chat.completion.chunk","created":1778601723,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" fetched"},"finish_reason":null}]}
853+ data: {"id":"chatcmpl-7714e100521a3da20cbf625b","object":"chat.completion.chunk","created":1778602924,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"'."},"finish_reason":null}]}
640
854
641− data: {"id":"chatcmpl-2f895e7d8be2f4beffa3c809","object":"chat.completion.chunk","created":1778601723,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" content does"},"finish_reason":null}]}
855+ data: {"id":"chatcmpl-7714e100521a3da20cbf625b","object":"chat.completion.chunk","created":1778602924,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"No"},"finish_reason":null}]}
642
856
643− data: {"id":"chatcmpl-2f895e7d8be2f4beffa3c809","object":"chat.completion.chunk","created":1778601723,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" **"},"finish_reason":null}]}
857+ data: {"id":"chatcmpl-7714e100521a3da20cbf625b","object":"chat.completion.chunk","created":1778602924,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":", the fetched"},"finish_reason":null}]}
644
858
645− data: {"id":"chatcmpl-2f895e7d8be2f4beffa3c809","object":"chat.completion.chunk","created":1778601723,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"not** contain"},"finish_reason":null}]}
859+ data: {"id":"chatcmpl-7714e100521a3da20cbf625b","object":"chat.completion.chunk","created":1778602924,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" content does"},"finish_reason":null}]}
646
860
647− data: {"id":"chatcmpl-2f895e7d8be2f4beffa3c809","object":"chat.completion.chunk","created":1778601723,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" the word \""},"finish_reason":null}]}
861+ data: {"id":"chatcmpl-7714e100521a3da20cbf625b","object":"chat.completion.chunk","created":1778602924,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" not contain the"},"finish_reason":null}]}
648
862
649− data: {"id":"chatcmpl-2f895e7d8be2f4beffa3c809","object":"chat.completion.chunk","created":1778601723,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"John Doe"},"finish_reason":null}]}
863+ data: {"id":"chatcmpl-7714e100521a3da20cbf625b","object":"chat.completion.chunk","created":1778602924,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" word \""},"finish_reason":null}]}
650
864
651− data: {"id":"chatcmpl-2f895e7d8be2f4beffa3c809","object":"chat.completion.chunk","created":1778601723,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"\"."},"finish_reason":null}]}
865+ data: {"id":"chatcmpl-7714e100521a3da20cbf625b","object":"chat.completion.chunk","created":1778602924,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"John Doe\"."},"finish_reason":null}]}
652
866
653− data: {"id":"chatcmpl-2f895e7d8be2f4beffa3c809","object":"chat.completion.chunk","created":1778601723,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
867+ data: {"id":"chatcmpl-7714e100521a3da20cbf625b","object":"chat.completion.chunk","created":1778602924,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
654
868
655− data: {"id":"chatcmpl-2f895e7d8be2f4beffa3c809","object":"chat.completion.chunk","created":1778601723,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7843,"completion_tokens":16,"total_tokens":7859,"completion_tokens_details":{"reasoning_tokens":15}}}
869+ data: {"id":"chatcmpl-7714e100521a3da20cbf625b","object":"chat.completion.chunk","created":1778602924,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7843,"completion_tokens":28,"total_tokens":7871,"completion_tokens_details":{"reasoning_tokens":12}}}
656
870
657 data: [DONE]
871 data: [DONE]
658
872
@@ -661,4 +875,4 @@ interactions:
661 - text/event-stream
875 - text/event-stream
662 status: 200 OK
876 status: 200 OK
663 code: 200
877 code: 200
664− duration: 2.902633375s
878+ duration: 2.717033708s
internal/agent/testdata/TestCoderAgent/glm-5.1/glob_tool.yaml+260−130
@@ -25,209 +25,299 @@ interactions:
25 content_length: -1
25 content_length: -1
26 uncompressed: true
26 uncompressed: true
27 body: |+
27 body: |+
28− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
28+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
29
29
30− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
30+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
31
31
32− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
32+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
33
33
34− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ask"},"finish_reason":null}]}
34+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" wants"},"finish_reason":null}]}
35
35
36− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
36+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
37
37
38− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Generate"},"finish_reason":null}]}
38+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
39
39
40− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
40+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
41
41
42− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
42+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
43
43
44− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
44+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
45
45
46− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
46+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"use"},"finish_reason":null}]}
47
47
48− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
48+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" glob"},"finish_reason":null}]}
49
49
50− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" following"},"finish_reason":null}]}
50+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
51
51
52− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
52+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" find"},"finish_reason":null}]}
53
53
54− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
54+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" all"},"finish_reason":null}]}
55
55
56− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" use"},"finish_reason":null}]}
56+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ."},"finish_reason":null}]}
57
57
58− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" glob"},"finish_reason":null}]}
58+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"go"},"finish_reason":null}]}
59
59
60− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
60+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
61
61
62− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" find"},"finish_reason":null}]}
62+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
63
63
64− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" all"},"finish_reason":null}]}
64+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
65
65
66− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ."},"finish_reason":null}]}
66+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" current"},"finish_reason":null}]}
67
67
68− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"go"},"finish_reason":null}]}
68+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" directory"},"finish_reason":null}]}
69
69
70− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
70+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
71
71
72− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
72+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" It"},"finish_reason":null}]}
73
73
74− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
74+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" is"},"finish_reason":null}]}
75
75
76− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" current"},"finish_reason":null}]}
76+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" English"},"finish_reason":null}]}
77
77
78− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" directory"},"finish_reason":null}]}
78+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
79
79
80− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
80+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Title"},"finish_reason":null}]}
81
81
82− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Need"},"finish_reason":null}]}
82+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" under"},"finish_reason":null}]}
83
83
84− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
84+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
85
85
86− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" produce"},"finish_reason":null}]}
86+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
87
87
88− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
88+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
89
89
90− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" short"},"finish_reason":null}]}
90+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
91
91
92− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
92+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Something"},"finish_reason":null}]}
93
93
94− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
94+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" like"},"finish_reason":null}]}
95
95
96− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" same"},"finish_reason":null}]}
96+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
97
97
98− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" language"},"finish_reason":null}]}
98+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Using"},"finish_reason":null}]}
99
99
100− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
100+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" glob"},"finish_reason":null}]}
101
101
102− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"English"},"finish_reason":null}]}
102+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
103
103
104− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")."},"finish_reason":null}]}
104+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" locate"},"finish_reason":null}]}
105
105
106− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Should"},"finish_reason":null}]}
106+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" all"},"finish_reason":null}]}
107
107
108− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
108+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ."},"finish_reason":null}]}
109
109
110− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \u003c="},"finish_reason":null}]}
110+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"go"},"finish_reason":null}]}
111
111
112− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
112+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
113
113
114− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
114+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
115
115
116− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
116+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
117
117
118− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Summ"},"finish_reason":null}]}
118+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
119
119
120− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ar"},"finish_reason":null}]}
120+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
121
121
122− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ize"},"finish_reason":null}]}
122+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
123
123
124− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
124+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Using"},"finish_reason":null}]}
125
125
126− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
126+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" glob"},"finish_reason":null}]}
127
127
128− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Find"},"finish_reason":null}]}
128+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
129
129
130− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" all"},"finish_reason":null}]}
130+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" locate"},"finish_reason":null}]}
131
131
132− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ."},"finish_reason":null}]}
132+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" all"},"finish_reason":null}]}
133
133
134− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"go"},"finish_reason":null}]}
134+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ."},"finish_reason":null}]}
135
135
136− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
136+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"go"},"finish_reason":null}]}
137
137
138− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
138+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
139
139
140− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" glob"},"finish_reason":null}]}
140+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
141
141
142− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
142+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" length"},"finish_reason":null}]}
143
143
144− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Maybe"},"finish_reason":null}]}
144+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"?"},"finish_reason":null}]}
145
145
146− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
146+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Let's"},"finish_reason":null}]}
147
147
148− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Using"},"finish_reason":null}]}
148+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
149
149
150− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" glob"},"finish_reason":null}]}
150+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
151
151
152− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
152+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Using"},"finish_reason":null}]}
153
153
154− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" locate"},"finish_reason":null}]}
154+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
155
155
156− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ."},"finish_reason":null}]}
156+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
157
157
158− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"go"},"finish_reason":null}]}
158+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
159
159
160− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
160+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
161
161
162− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
162+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
163
163
164− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
164+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
165
165
166− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
166+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
167
167
168− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
168+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
169
169
170− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Using"},"finish_reason":null}]}
170+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" glob"},"finish_reason":null}]}
171
171
172− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" glob"},"finish_reason":null}]}
172+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
173
173
174− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
174+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
175
175
176− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" locate"},"finish_reason":null}]}
176+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" =\u003e"},"finish_reason":null}]}
177
177
178− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ."},"finish_reason":null}]}
178+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"10"},"finish_reason":null}]}
179
179
180− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"go"},"finish_reason":null}]}
180+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
181
181
182− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
182+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
183
183
184− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
184+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
185
185
186− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ="},"finish_reason":null}]}
186+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"11"},"finish_reason":null}]}
187
187
188− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
188+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
189
189
190− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"30"},"finish_reason":null}]}
190+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
191
191
192− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
192+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
193
193
194− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
194+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
195
195
196− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" OK"},"finish_reason":null}]}
196+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" =\u003e"},"finish_reason":null}]}
197
197
198− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
198+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"13"},"finish_reason":null}]}
199
199
200− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Return"},"finish_reason":null}]}
200+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
201
201
202− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" as"},"finish_reason":null}]}
202+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
203
203
204− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" single"},"finish_reason":null}]}
204+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
205
205
206− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
206+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"14"},"finish_reason":null}]}
207
207
208− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" no"},"finish_reason":null}]}
208+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
209
209
210− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
210+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" locate"},"finish_reason":null}]}
211
211
212− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
212+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
213
213
214− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Using"},"finish_reason":null}]}
214+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
215
215
216− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" glob"},"finish_reason":null}]}
216+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" =\u003e"},"finish_reason":null}]}
217
217
218− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" to"},"finish_reason":null}]}
218+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"20"},"finish_reason":null}]}
219
219
220− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" locate"},"finish_reason":null}]}
220+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
221
221
222− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" ."},"finish_reason":null}]}
222+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
223
223
224− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"go"},"finish_reason":null}]}
224+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
225
225
226− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" files"},"finish_reason":null}]}
226+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"21"},"finish_reason":null}]}
227
227
228− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
228+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
229
229
230+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" all"},"finish_reason":null}]}
231+
232+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
233+
234+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
235+
236+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" =\u003e"},"finish_reason":null}]}
237+
238+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"24"},"finish_reason":null}]}
239+
240+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
241+
242+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
243+
244+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
245+
246+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"25"},"finish_reason":null}]}
247+
248+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
249+
250+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ."},"finish_reason":null}]}
251+
252+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"go"},"finish_reason":null}]}
253+
254+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
255+
256+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
257+
258+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" =\u003e"},"finish_reason":null}]}
259+
260+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"28"},"finish_reason":null}]}
261+
262+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
263+
264+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
265+
266+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
267+
268+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"29"},"finish_reason":null}]}
269+
270+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
271+
272+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
273+
274+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
275+
276+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
277+
278+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" =\u003e"},"finish_reason":null}]}
279+
280+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"34"},"finish_reason":null}]}
281+
282+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
283+
284+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Under"},"finish_reason":null}]}
285+
286+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
287+
288+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
289+
290+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
291+
292+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Good"},"finish_reason":null}]}
293+
294+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
295+
296+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Return"},"finish_reason":null}]}
297+
298+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that"},"finish_reason":null}]}
299+
300+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
301+
302+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Using"},"finish_reason":null}]}
303+
304+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" glob"},"finish_reason":null}]}
305+
306+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" to"},"finish_reason":null}]}
307+
308+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" locate"},"finish_reason":null}]}
309+
310+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" all"},"finish_reason":null}]}
311+
312+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" ."},"finish_reason":null}]}
313+
314+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"go"},"finish_reason":null}]}
315+
316+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" files"},"finish_reason":null}]}
317+
318+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
319+
230− data: {"id":"chatcmpl-832c23734a41e749ff8db8ed","object":"chat.completion.chunk","created":1778601724,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":23,"completion_tokens":109,"total_tokens":324,"prompt_tokens_details":{"cached_tokens":192}}}
320+ data: {"id":"chatcmpl-237115a5290300c92c01c6c6","object":"chat.completion.chunk","created":1778602925,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":23,"completion_tokens":154,"total_tokens":369,"prompt_tokens_details":{"cached_tokens":192}}}
231
321
232 data: [DONE]
322 data: [DONE]
233
323
@@ -236,7 +326,7 @@ interactions:
236 - text/event-stream
326 - text/event-stream
237 status: 200 OK
327 status: 200 OK
238 code: 200
328 code: 200
239− duration: 445.594917ms
329+ duration: 557.906084ms
240- id: 1
330- id: 1
241 request:
331 request:
242 proto: HTTP/1.1
332 proto: HTTP/1.1
@@ -261,33 +351,71 @@ interactions:
261 content_length: -1
351 content_length: -1
262 uncompressed: true
352 uncompressed: true
263 body: |+
353 body: |+
264− data: {"id":"chatcmpl-ff98cd358f55061c688302dd","object":"chat.completion.chunk","created":1778601726,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
354+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
355+
356+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
357+
358+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
359+
360+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" wants to"},"finish_reason":null}]}
361+
362+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" use glob"},"finish_reason":null}]}
265
363
266− data: {"id":"chatcmpl-ff98cd358f55061c688302dd","object":"chat.completion.chunk","created":1778601726,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"Simple"},"finish_reason":null}]}
364+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" to find all"},"finish_reason":null}]}
267
365
268− data: {"id":"chatcmpl-ff98cd358f55061c688302dd","object":"chat.completion.chunk","created":1778601726,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" glob"},"finish_reason":null}]}
366+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" .go"},"finish_reason":null}]}
269
367
270− data: {"id":"chatcmpl-ff98cd358f55061c688302dd","object":"chat.completion.chunk","created":1778601726,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" request"},"finish_reason":null}]}
368+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" files in"},"finish_reason":null}]}
271
369
272− data: {"id":"chatcmpl-ff98cd358f55061c688302dd","object":"chat.completion.chunk","created":1778601726,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
370+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" the current directory"},"finish_reason":null}]}
273
371
274− data: {"id":"chatcmpl-ff98cd358f55061c688302dd","object":"chat.completion.chunk","created":1778601726,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_93398c73218c40abab6ccf80","type":"function","index":0,"function":{"name":"glob","arguments":""}}]},"finish_reason":null}]}
372+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
275
373
276− data: {"id":"chatcmpl-ff98cd358f55061c688302dd","object":"chat.completion.chunk","created":1778601726,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
374+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_527f3eeb6c7c4b6cb849fa69","type":"function","index":0,"function":{"name":"glob","arguments":""}}]},"finish_reason":null}]}
277
375
278− data: {"id":"chatcmpl-ff98cd358f55061c688302dd","object":"chat.completion.chunk","created":1778601726,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
376+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
279
377
280− data: {"id":"chatcmpl-ff98cd358f55061c688302dd","object":"chat.completion.chunk","created":1778601726,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"pattern\": "}}]},"finish_reason":null}]}
378+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
281
379
282− data: {"id":"chatcmpl-ff98cd358f55061c688302dd","object":"chat.completion.chunk","created":1778601726,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"**/*."}}]},"finish_reason":null}]}
380+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"path\": "}}]},"finish_reason":null}]}
283
381
284− data: {"id":"chatcmpl-ff98cd358f55061c688302dd","object":"chat.completion.chunk","created":1778601726,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go\""}}]},"finish_reason":null}]}
382+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/tmp"}}]},"finish_reason":null}]}
285
383
286− data: {"id":"chatcmpl-ff98cd358f55061c688302dd","object":"chat.completion.chunk","created":1778601726,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
384+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/c"}}]},"finish_reason":null}]}
287
385
288− data: {"id":"chatcmpl-ff98cd358f55061c688302dd","object":"chat.completion.chunk","created":1778601726,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
386+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"rush"}}]},"finish_reason":null}]}
289
387
388+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}]}
389+
390+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}]}
391+
392+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}]}
393+
394+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}]}
395+
396+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/glm"}}]},"finish_reason":null}]}
397+
398+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-5"}}]},"finish_reason":null}]}
399+
400+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".1"}}]},"finish_reason":null}]}
401+
402+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/glob"}}]},"finish_reason":null}]}
403+
404+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}]}
405+
406+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\", "}}]},"finish_reason":null}]}
407+
408+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"pattern\": "}}]},"finish_reason":null}]}
409+
410+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"*.go"}}]},"finish_reason":null}]}
411+
412+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\""}}]},"finish_reason":null}]}
413+
414+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
415+
416+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
417+
290− data: {"id":"chatcmpl-ff98cd358f55061c688302dd","object":"chat.completion.chunk","created":1778601726,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7769,"completion_tokens":17,"total_tokens":7786,"completion_tokens_details":{"reasoning_tokens":4}}}
418+ data: {"id":"chatcmpl-b915be925af8f26fa3f5cdb1","object":"chat.completion.chunk","created":1778602928,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":729,"completion_tokens":50,"total_tokens":7819,"prompt_tokens_details":{"cached_tokens":7040},"completion_tokens_details":{"reasoning_tokens":17}}}
291
419
292 data: [DONE]
420 data: [DONE]
293
421
@@ -296,15 +424,15 @@ interactions:
296 - text/event-stream
424 - text/event-stream
297 status: 200 OK
425 status: 200 OK
298 code: 200
426 code: 200
299− duration: 3.008176292s
427+ duration: 3.012647542s
300- id: 2
428- id: 2
301 request:
429 request:
302 proto: HTTP/1.1
430 proto: HTTP/1.1
303 proto_major: 1
431 proto_major: 1
304 proto_minor: 1
432 proto_minor: 1
305− content_length: 34068
433+ content_length: 34183
306 host: ""
434 host: ""
307− 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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\",\"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_93398c73218c40abab6ccf80\",\"function\":{\"arguments\":\"{\\\"pattern\\\": \\\"**/*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"Simple glob request.\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/glm-5.1/glob_tool/main.go\",\"tool_call_id\":\"call_93398c73218c40abab6ccf80\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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\",\"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_527f3eeb6c7c4b6cb849fa69\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/glob_tool\\\", \\\"pattern\\\": \\\"*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"The user wants to use glob to find all .go files in the current directory.\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/glm-5.1/glob_tool/main.go\",\"tool_call_id\":\"call_527f3eeb6c7c4b6cb849fa69\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
308 headers:
436 headers:
309 Accept:
437 Accept:
310 - application/json
438 - application/json
@@ -321,23 +449,25 @@ interactions:
321 content_length: -1
449 content_length: -1
322 uncompressed: true
450 uncompressed: true
323 body: |+
451 body: |+
324− data: {"id":"chatcmpl-b9e97a652a8e2fc7b0993d7f","object":"chat.completion.chunk","created":1778601730,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
452+ data: {"id":"chatcmpl-662697b1c74c6e5318b64d67","object":"chat.completion.chunk","created":1778602932,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
453+
454+ data: {"id":"chatcmpl-662697b1c74c6e5318b64d67","object":"chat.completion.chunk","created":1778602932,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Found"},"finish_reason":null}]}
325
455
326− data: {"id":"chatcmpl-b9e97a652a8e2fc7b0993d7f","object":"chat.completion.chunk","created":1778601730,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Found"},"finish_reason":null}]}
456+ data: {"id":"chatcmpl-662697b1c74c6e5318b64d67","object":"chat.completion.chunk","created":1778602932,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" 1 `."},"finish_reason":null}]}
327
457
328− data: {"id":"chatcmpl-b9e97a652a8e2fc7b0993d7f","object":"chat.completion.chunk","created":1778601730,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" "},"finish_reason":null}]}
458+ data: {"id":"chatcmpl-662697b1c74c6e5318b64d67","object":"chat.completion.chunk","created":1778602932,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"go"},"finish_reason":null}]}
329
459
330− data: {"id":"chatcmpl-b9e97a652a8e2fc7b0993d7f","object":"chat.completion.chunk","created":1778601730,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"1 `."},"finish_reason":null}]}
460+ data: {"id":"chatcmpl-662697b1c74c6e5318b64d67","object":"chat.completion.chunk","created":1778602932,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"` file"},"finish_reason":null}]}
331
461
332− data: {"id":"chatcmpl-b9e97a652a8e2fc7b0993d7f","object":"chat.completion.chunk","created":1778601730,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"go`"},"finish_reason":null}]}
462+ data: {"id":"chatcmpl-662697b1c74c6e5318b64d67","object":"chat.completion.chunk","created":1778602932,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":": `"},"finish_reason":null}]}
333
463
334− data: {"id":"chatcmpl-b9e97a652a8e2fc7b0993d7f","object":"chat.completion.chunk","created":1778601730,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" file: `main"},"finish_reason":null}]}
464+ data: {"id":"chatcmpl-662697b1c74c6e5318b64d67","object":"chat.completion.chunk","created":1778602932,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"main.go"},"finish_reason":null}]}
335
465
336− data: {"id":"chatcmpl-b9e97a652a8e2fc7b0993d7f","object":"chat.completion.chunk","created":1778601730,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":".go`"},"finish_reason":null}]}
466+ data: {"id":"chatcmpl-662697b1c74c6e5318b64d67","object":"chat.completion.chunk","created":1778602932,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`"},"finish_reason":null}]}
337
467
338− data: {"id":"chatcmpl-b9e97a652a8e2fc7b0993d7f","object":"chat.completion.chunk","created":1778601730,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
468+ data: {"id":"chatcmpl-662697b1c74c6e5318b64d67","object":"chat.completion.chunk","created":1778602932,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
339
469
340− data: {"id":"chatcmpl-b9e97a652a8e2fc7b0993d7f","object":"chat.completion.chunk","created":1778601730,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7804,"completion_tokens":14,"total_tokens":7818,"completion_tokens_details":{"reasoning_tokens":13}}}
470+ data: {"id":"chatcmpl-662697b1c74c6e5318b64d67","object":"chat.completion.chunk","created":1778602932,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7824,"completion_tokens":14,"total_tokens":7838,"completion_tokens_details":{"reasoning_tokens":13}}}
341
471
342 data: [DONE]
472 data: [DONE]
343
473
@@ -346,4 +476,4 @@ interactions:
346 - text/event-stream
476 - text/event-stream
347 status: 200 OK
477 status: 200 OK
348 code: 200
478 code: 200
349− duration: 3.883457292s
479+ duration: 3.09175425s
internal/agent/testdata/TestCoderAgent/glm-5.1/grep_tool.yaml+202−132
@@ -25,157 +25,241 @@ interactions:
25 content_length: -1
25 content_length: -1
26 uncompressed: true
26 uncompressed: true
27 body: |+
27 body: |+
28− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
28+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
29
29
30− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"User"},"finish_reason":null}]}
30+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"We"},"finish_reason":null}]}
31
31
32− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" wants"},"finish_reason":null}]}
32+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" need"},"finish_reason":null}]}
33
33
34− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
34+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
35
35
36− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
36+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" produce"},"finish_reason":null}]}
37
37
38− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
38+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
39
39
40− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
40+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" short"},"finish_reason":null}]}
41
41
42− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
42+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
43
43
44− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
44+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
45
45
46− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
46+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" same"},"finish_reason":null}]}
47
47
48− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Must"},"finish_reason":null}]}
48+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" language"},"finish_reason":null}]}
49
49
50− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
50+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
51
51
52− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" under"},"finish_reason":null}]}
52+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"English"},"finish_reason":null}]}
53
53
54− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
54+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")."},"finish_reason":null}]}
55
55
56− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
56+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Summ"},"finish_reason":null}]}
57
57
58− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
58+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ar"},"finish_reason":null}]}
59
59
60− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
60+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ize"},"finish_reason":null}]}
61
61
62− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" one"},"finish_reason":null}]}
62+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
63
63
64− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
64+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
65
65
66− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
66+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"use"},"finish_reason":null}]}
67
67
68− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" same"},"finish_reason":null}]}
68+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" grep"},"finish_reason":null}]}
69
69
70− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" language"},"finish_reason":null}]}
70+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
71
71
72− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
72+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" search"},"finish_reason":null}]}
73
73
74− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"English"},"finish_reason":null}]}
74+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
75
75
76− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")."},"finish_reason":null}]}
76+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
77
77
78− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Summ"},"finish_reason":null}]}
78+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" word"},"finish_reason":null}]}
79
79
80− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ar"},"finish_reason":null}]}
80+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
81
81
82− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ize"},"finish_reason":null}]}
82+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"package"},"finish_reason":null}]}
83
83
84− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
84+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'"},"finish_reason":null}]}
85
85
86− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
86+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
87
87
88− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"using"},"finish_reason":null}]}
88+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" go"},"finish_reason":null}]}
89
89
90− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" grep"},"finish_reason":null}]}
90+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
91
91
92− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
92+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
93
93
94− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" find"},"finish_reason":null}]}
94+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Title"},"finish_reason":null}]}
95
95
96− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
96+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" length"},"finish_reason":null}]}
97
97
98− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"package"},"finish_reason":null}]}
98+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \u003c="},"finish_reason":null}]}
99
99
100− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'"},"finish_reason":null}]}
100+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
101
101
102− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
102+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
103
103
104− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Go"},"finish_reason":null}]}
104+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
105
105
106− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
106+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Maybe"},"finish_reason":null}]}
107
107
108− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
108+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
109
109
110− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Title"},"finish_reason":null}]}
110+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"G"},"finish_reason":null}]}
111
111
112− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" maybe"},"finish_reason":null}]}
112+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"rep"},"finish_reason":null}]}
113
113
114− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
114+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
115
115
116− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"G"},"finish_reason":null}]}
116+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
117
117
118− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"rep"},"finish_reason":null}]}
118+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"package"},"finish_reason":null}]}
119
119
120− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
120+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'"},"finish_reason":null}]}
121
121
122− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
122+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
123
123
124− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"package"},"finish_reason":null}]}
124+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Go"},"finish_reason":null}]}
125
125
126− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'"},"finish_reason":null}]}
126+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
127
127
128− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
128+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
129
129
130− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Go"},"finish_reason":null}]}
130+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
131
131
132− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" source"},"finish_reason":null}]}
132+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
133
133
134− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
134+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"26"},"finish_reason":null}]}
135
135
136− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
136+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
137
137
138− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
138+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
139
139
140− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
140+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" No"},"finish_reason":null}]}
141
141
142− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"33"},"finish_reason":null}]}
142+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
143
143
144− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
144+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"?"},"finish_reason":null}]}
145
145
146− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
146+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Actually"},"finish_reason":null}]}
147
147
148− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Should"},"finish_reason":null}]}
148+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" we"},"finish_reason":null}]}
149
149
150− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
150+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" can"},"finish_reason":null}]}
151
151
152− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" okay"},"finish_reason":null}]}
152+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" include"},"finish_reason":null}]}
153
153
154− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
154+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
155
155
156− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"G"},"finish_reason":null}]}
156+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"?"},"finish_reason":null}]}
157
157
158− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"rep"},"finish_reason":null}]}
158+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" The"},"finish_reason":null}]}
159
159
160− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" for"},"finish_reason":null}]}
160+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" rule"},"finish_reason":null}]}
161
161
162− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" “"},"finish_reason":null}]}
162+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
163
163
164− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"package"},"finish_reason":null}]}
164+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Do"},"finish_reason":null}]}
165
165
166− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"”"},"finish_reason":null}]}
166+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" not"},"finish_reason":null}]}
167
167
168− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" in"},"finish_reason":null}]}
168+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" use"},"finish_reason":null}]}
169
169
170− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Go"},"finish_reason":null}]}
170+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
171
171
172− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" source"},"finish_reason":null}]}
172+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" or"},"finish_reason":null}]}
173
173
174− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" files"},"finish_reason":null}]}
174+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" col"},"finish_reason":null}]}
175
175
176− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
176+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ons"},"finish_reason":null}]}
177
177
178+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
179+
180+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" So"},"finish_reason":null}]}
181+
182+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" cannot"},"finish_reason":null}]}
183+
184+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" use"},"finish_reason":null}]}
185+
186+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" single"},"finish_reason":null}]}
187+
188+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
189+
190+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" maybe"},"finish_reason":null}]}
191+
192+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" considered"},"finish_reason":null}]}
193+
194+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
195+
196+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
197+
198+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Should"},"finish_reason":null}]}
199+
200+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" avoid"},"finish_reason":null}]}
201+
202+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
203+
204+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
205+
206+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" So"},"finish_reason":null}]}
207+
208+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
209+
210+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"G"},"finish_reason":null}]}
211+
212+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"rep"},"finish_reason":null}]}
213+
214+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
215+
216+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" package"},"finish_reason":null}]}
217+
218+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
219+
220+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Go"},"finish_reason":null}]}
221+
222+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
223+
224+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
225+
226+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
227+
228+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" fine"},"finish_reason":null}]}
229+
230+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
231+
232+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Under"},"finish_reason":null}]}
233+
234+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
235+
236+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
237+
238+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
239+
240+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" One"},"finish_reason":null}]}
241+
242+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
243+
244+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
245+
246+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"G"},"finish_reason":null}]}
247+
248+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"rep"},"finish_reason":null}]}
249+
250+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" for"},"finish_reason":null}]}
251+
252+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" package"},"finish_reason":null}]}
253+
254+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" in"},"finish_reason":null}]}
255+
256+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Go"},"finish_reason":null}]}
257+
258+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" files"},"finish_reason":null}]}
259+
260+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
261+
178− data: {"id":"chatcmpl-dd995ea66dc2661213ac8d4b","object":"chat.completion.chunk","created":1778601731,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":24,"completion_tokens":83,"total_tokens":299,"prompt_tokens_details":{"cached_tokens":192}}}
262+ data: {"id":"chatcmpl-5344edabe33638fa892c5942","object":"chat.completion.chunk","created":1778602933,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":24,"completion_tokens":125,"total_tokens":341,"prompt_tokens_details":{"cached_tokens":192}}}
179
263
180 data: [DONE]
264 data: [DONE]
181
265
@@ -184,7 +268,7 @@ interactions:
184 - text/event-stream
268 - text/event-stream
185 status: 200 OK
269 status: 200 OK
186 code: 200
270 code: 200
187− duration: 428.985583ms
271+ duration: 499.148667ms
188- id: 1
272- id: 1
189 request:
273 request:
190 proto: HTTP/1.1
274 proto: HTTP/1.1
@@ -209,69 +293,53 @@ interactions:
209 content_length: -1
293 content_length: -1
210 uncompressed: true
294 uncompressed: true
211 body: |+
295 body: |+
212− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
296+ data: {"id":"chatcmpl-b8f3de607df1fdc77a2c59e9","object":"chat.completion.chunk","created":1778602937,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
213−
214− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"Search"},"finish_reason":null}]}
215−
216− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
217−
218− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" 'package"},"finish_reason":null}]}
219
297
220− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"' in Go"},"finish_reason":null}]}
298+ data: {"id":"chatcmpl-b8f3de607df1fdc77a2c59e9","object":"chat.completion.chunk","created":1778602937,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
221
299
222− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" files in"},"finish_reason":null}]}
300+ data: {"id":"chatcmpl-b8f3de607df1fdc77a2c59e9","object":"chat.completion.chunk","created":1778602937,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
223
301
224− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" the current"},"finish_reason":null}]}
302+ data: {"id":"chatcmpl-b8f3de607df1fdc77a2c59e9","object":"chat.completion.chunk","created":1778602937,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" wants me"},"finish_reason":null}]}
225
303
226− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" directory"},"finish_reason":null}]}
304+ data: {"id":"chatcmpl-b8f3de607df1fdc77a2c59e9","object":"chat.completion.chunk","created":1778602937,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" to search"},"finish_reason":null}]}
227
305
228− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
306+ data: {"id":"chatcmpl-b8f3de607df1fdc77a2c59e9","object":"chat.completion.chunk","created":1778602937,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" for the"},"finish_reason":null}]}
229
307
230− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_6e6529e4c8054555bcb2df8d","type":"function","index":0,"function":{"name":"grep","arguments":""}}]},"finish_reason":null}]}
308+ data: {"id":"chatcmpl-b8f3de607df1fdc77a2c59e9","object":"chat.completion.chunk","created":1778602937,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" word '"},"finish_reason":null}]}
231
309
232− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
310+ data: {"id":"chatcmpl-b8f3de607df1fdc77a2c59e9","object":"chat.completion.chunk","created":1778602937,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"package' in"},"finish_reason":null}]}
233
311
234− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
312+ data: {"id":"chatcmpl-b8f3de607df1fdc77a2c59e9","object":"chat.completion.chunk","created":1778602937,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" Go files"},"finish_reason":null}]}
235
313
236− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"include\": "}}]},"finish_reason":null}]}
314+ data: {"id":"chatcmpl-b8f3de607df1fdc77a2c59e9","object":"chat.completion.chunk","created":1778602937,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" using"},"finish_reason":null}]}
237
315
238− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"*.go"}}]},"finish_reason":null}]}
316+ data: {"id":"chatcmpl-b8f3de607df1fdc77a2c59e9","object":"chat.completion.chunk","created":1778602937,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" the grep"},"finish_reason":null}]}
239
317
240− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\", "}}]},"finish_reason":null}]}
318+ data: {"id":"chatcmpl-b8f3de607df1fdc77a2c59e9","object":"chat.completion.chunk","created":1778602937,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" tool."},"finish_reason":null}]}
241
319
242− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"path\": \"/tmp"}}]},"finish_reason":null}]}
320+ data: {"id":"chatcmpl-b8f3de607df1fdc77a2c59e9","object":"chat.completion.chunk","created":1778602937,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_c590992499e3426a8c96f534","type":"function","index":0,"function":{"name":"grep","arguments":""}}]},"finish_reason":null}]}
243
321
244− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/c"}}]},"finish_reason":null}]}
322+ data: {"id":"chatcmpl-b8f3de607df1fdc77a2c59e9","object":"chat.completion.chunk","created":1778602937,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
245
323
246− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"rush"}}]},"finish_reason":null}]}
324+ data: {"id":"chatcmpl-b8f3de607df1fdc77a2c59e9","object":"chat.completion.chunk","created":1778602937,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
247
325
248− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}]}
326+ data: {"id":"chatcmpl-b8f3de607df1fdc77a2c59e9","object":"chat.completion.chunk","created":1778602937,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"include\": "}}]},"finish_reason":null}]}
249
327
250− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}]}
328+ data: {"id":"chatcmpl-b8f3de607df1fdc77a2c59e9","object":"chat.completion.chunk","created":1778602937,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"*."}}]},"finish_reason":null}]}
251
329
252− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}]}
330+ data: {"id":"chatcmpl-b8f3de607df1fdc77a2c59e9","object":"chat.completion.chunk","created":1778602937,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go\""}}]},"finish_reason":null}]}
253
331
254− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}]}
332+ data: {"id":"chatcmpl-b8f3de607df1fdc77a2c59e9","object":"chat.completion.chunk","created":1778602937,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":", "}}]},"finish_reason":null}]}
255
333
256− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/glm"}}]},"finish_reason":null}]}
334+ data: {"id":"chatcmpl-b8f3de607df1fdc77a2c59e9","object":"chat.completion.chunk","created":1778602937,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"pattern\": "}}]},"finish_reason":null}]}
257
335
258− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-5."}}]},"finish_reason":null}]}
336+ data: {"id":"chatcmpl-b8f3de607df1fdc77a2c59e9","object":"chat.completion.chunk","created":1778602937,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"package\""}}]},"finish_reason":null}]}
259
337
260− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"1/g"}}]},"finish_reason":null}]}
338+ data: {"id":"chatcmpl-b8f3de607df1fdc77a2c59e9","object":"chat.completion.chunk","created":1778602937,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
261
339
262− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"rep_tool"}}]},"finish_reason":null}]}
340+ data: {"id":"chatcmpl-b8f3de607df1fdc77a2c59e9","object":"chat.completion.chunk","created":1778602937,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
263
341
264− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\", "}}]},"finish_reason":null}]}
265−
266− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"pattern\": "}}]},"finish_reason":null}]}
267−
268− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"package\""}}]},"finish_reason":null}]}
269−
270− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
271−
272− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
273−
274− data: {"id":"chatcmpl-de353447d4e7480858e0d2a1","object":"chat.completion.chunk","created":1778601733,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":730,"completion_tokens":52,"total_tokens":7822,"prompt_tokens_details":{"cached_tokens":7040},"completion_tokens_details":{"reasoning_tokens":13}}}
342+ data: {"id":"chatcmpl-b8f3de607df1fdc77a2c59e9","object":"chat.completion.chunk","created":1778602937,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":730,"completion_tokens":38,"total_tokens":7808,"prompt_tokens_details":{"cached_tokens":7040},"completion_tokens_details":{"reasoning_tokens":20}}}
275
343
276 data: [DONE]
344 data: [DONE]
277
345
@@ -280,15 +348,15 @@ interactions:
280 - text/event-stream
348 - text/event-stream
281 status: 200 OK
349 status: 200 OK
282 code: 200
350 code: 200
283− duration: 2.815924666s
351+ duration: 5.028893875s
284- id: 2
352- id: 2
285 request:
353 request:
286 proto: HTTP/1.1
354 proto: HTTP/1.1
287 proto_major: 1
355 proto_major: 1
288 proto_minor: 1
356 proto_minor: 1
289− content_length: 34243
357+ content_length: 34204
290 host: ""
358 host: ""
291− 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</editing_files>\\n\\n<whitespace_and_exact_matching>\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n</whitespace_and_exact_matching>\\n\\n<task_completion>\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n</task_completion>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences\\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n<bash_commands>\\n**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/glm-5.1/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n<available_skills>\\n <skill>\\n <name>crush-hooks</name>\\n <description>Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.</description>\\n <location>crush://skills/crush-hooks/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n <skill>\\n <name>jq</name>\\n <description>Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.</description>\\n <location>crush://skills/jq/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n</available_skills>\\n\\n<skills_usage>\\nThe `<description>` of each skill is a TRIGGER — it tells you *when* a skill applies. It is NOT a specification of what the skill does or how to do it. The procedure, scripts, commands, references, and required flags live only in the SKILL.md body. You do not know what a skill actually does until you have read its SKILL.md.\\n\\nMANDATORY activation flow:\\n1. Scan `<available_skills>` against the current user task.\\n2. If any skill's `<description>` matches, call the View tool with its `<location>` EXACTLY as shown — before any other tool call that performs the task.\\n3. Read the entire SKILL.md and follow its instructions.\\n4. Only then execute the task, using the skill's prescribed commands/tools.\\n\\nDo NOT skip step 2 because you think you already know how to do the task. Do NOT infer a skill's behavior from its name or description. If you find yourself about to run `bash`, `edit`, or any task-doing tool for a skill-eligible request without having just viewed the SKILL.md, stop and load the skill first.\\n\\nBuiltin skills (type=builtin) use virtual `crush://skills/...` location identifiers. The \\\"crush://\\\" prefix is NOT a URL, network address, or MCP resource — it is a special internal identifier the View tool understands natively. Pass the `<location>` verbatim to View.\\n\\nDo not use MCP tools (including read_mcp_resource) to load skills.\\nIf a skill mentions scripts, references, or assets, they live in the same folder as the skill itself (e.g., scripts/, references/, assets/ subdirectories within the skill's folder).\\n</skills_usage>\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"<system_reminder>This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.</system_reminder>\",\"role\":\"user\"},{\"content\":\"use grep to search for the word 'package' in go files\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_6e6529e4c8054555bcb2df8d\",\"function\":{\"arguments\":\"{\\\"include\\\": \\\"*.go\\\", \\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/grep_tool\\\", \\\"pattern\\\": \\\"package\\\"}\",\"name\":\"grep\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"Search for 'package' in Go files in the current directory.\"},{\"content\":\"Found 1 matches\\n/tmp/crush-test/TestCoderAgent/glm-5.1/grep_tool/main.go:\\n Line 1, Char 1: package main\\n\",\"tool_call_id\":\"call_6e6529e4c8054555bcb2df8d\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
359+ 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</editing_files>\\n\\n<whitespace_and_exact_matching>\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n</whitespace_and_exact_matching>\\n\\n<task_completion>\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n</task_completion>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences\\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n<bash_commands>\\n**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/glm-5.1/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n<available_skills>\\n <skill>\\n <name>crush-hooks</name>\\n <description>Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.</description>\\n <location>crush://skills/crush-hooks/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n <skill>\\n <name>jq</name>\\n <description>Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.</description>\\n <location>crush://skills/jq/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n</available_skills>\\n\\n<skills_usage>\\nThe `<description>` of each skill is a TRIGGER — it tells you *when* a skill applies. It is NOT a specification of what the skill does or how to do it. The procedure, scripts, commands, references, and required flags live only in the SKILL.md body. You do not know what a skill actually does until you have read its SKILL.md.\\n\\nMANDATORY activation flow:\\n1. Scan `<available_skills>` against the current user task.\\n2. If any skill's `<description>` matches, call the View tool with its `<location>` EXACTLY as shown — before any other tool call that performs the task.\\n3. Read the entire SKILL.md and follow its instructions.\\n4. Only then execute the task, using the skill's prescribed commands/tools.\\n\\nDo NOT skip step 2 because you think you already know how to do the task. Do NOT infer a skill's behavior from its name or description. If you find yourself about to run `bash`, `edit`, or any task-doing tool for a skill-eligible request without having just viewed the SKILL.md, stop and load the skill first.\\n\\nBuiltin skills (type=builtin) use virtual `crush://skills/...` location identifiers. The \\\"crush://\\\" prefix is NOT a URL, network address, or MCP resource — it is a special internal identifier the View tool understands natively. Pass the `<location>` verbatim to View.\\n\\nDo not use MCP tools (including read_mcp_resource) to load skills.\\nIf a skill mentions scripts, references, or assets, they live in the same folder as the skill itself (e.g., scripts/, references/, assets/ subdirectories within the skill's folder).\\n</skills_usage>\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"<system_reminder>This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.</system_reminder>\",\"role\":\"user\"},{\"content\":\"use grep to search for the word 'package' in go files\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_c590992499e3426a8c96f534\",\"function\":{\"arguments\":\"{\\\"include\\\": \\\"*.go\\\", \\\"pattern\\\": \\\"package\\\"}\",\"name\":\"grep\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"The user wants me to search for the word 'package' in Go files using the grep tool.\"},{\"content\":\"Found 1 matches\\n/tmp/crush-test/TestCoderAgent/glm-5.1/grep_tool/main.go:\\n Line 1, Char 1: package main\\n\",\"tool_call_id\":\"call_c590992499e3426a8c96f534\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
292 headers:
360 headers:
293 Accept:
361 Accept:
294 - application/json
362 - application/json
@@ -305,27 +373,29 @@ interactions:
305 content_length: -1
373 content_length: -1
306 uncompressed: true
374 uncompressed: true
307 body: |+
375 body: |+
308− data: {"id":"chatcmpl-ab3020d8b997a66d8be305a7","object":"chat.completion.chunk","created":1778601736,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
376+ data: {"id":"chatcmpl-b2b4e1097beee00d4c336a57","object":"chat.completion.chunk","created":1778602942,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
377+
378+ data: {"id":"chatcmpl-b2b4e1097beee00d4c336a57","object":"chat.completion.chunk","created":1778602942,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Found"},"finish_reason":null}]}
309
379
310− data: {"id":"chatcmpl-ab3020d8b997a66d8be305a7","object":"chat.completion.chunk","created":1778601736,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Found"},"finish_reason":null}]}
380+ data: {"id":"chatcmpl-b2b4e1097beee00d4c336a57","object":"chat.completion.chunk","created":1778602942,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" 1 match"},"finish_reason":null}]}
311
381
312− data: {"id":"chatcmpl-ab3020d8b997a66d8be305a7","object":"chat.completion.chunk","created":1778601736,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" 1"},"finish_reason":null}]}
382+ data: {"id":"chatcmpl-b2b4e1097beee00d4c336a57","object":"chat.completion.chunk","created":1778602942,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}]}
313
383
314− data: {"id":"chatcmpl-ab3020d8b997a66d8be305a7","object":"chat.completion.chunk","created":1778601736,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" match in"},"finish_reason":null}]}
384+ data: {"id":"chatcmpl-b2b4e1097beee00d4c336a57","object":"chat.completion.chunk","created":1778602942,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `main"},"finish_reason":null}]}
315
385
316− data: {"id":"chatcmpl-ab3020d8b997a66d8be305a7","object":"chat.completion.chunk","created":1778601736,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `"},"finish_reason":null}]}
386+ data: {"id":"chatcmpl-b2b4e1097beee00d4c336a57","object":"chat.completion.chunk","created":1778602942,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}]}
317
387
318− data: {"id":"chatcmpl-ab3020d8b997a66d8be305a7","object":"chat.completion.chunk","created":1778601736,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"main.go:1"},"finish_reason":null}]}
388+ data: {"id":"chatcmpl-b2b4e1097beee00d4c336a57","object":"chat.completion.chunk","created":1778602942,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":":1"},"finish_reason":null}]}
319
389
320− data: {"id":"chatcmpl-ab3020d8b997a66d8be305a7","object":"chat.completion.chunk","created":1778601736,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"` — `"},"finish_reason":null}]}
390+ data: {"id":"chatcmpl-b2b4e1097beee00d4c336a57","object":"chat.completion.chunk","created":1778602942,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"` — `"},"finish_reason":null}]}
321
391
322− data: {"id":"chatcmpl-ab3020d8b997a66d8be305a7","object":"chat.completion.chunk","created":1778601736,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"package"},"finish_reason":null}]}
392+ data: {"id":"chatcmpl-b2b4e1097beee00d4c336a57","object":"chat.completion.chunk","created":1778602942,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"package main"},"finish_reason":null}]}
323
393
324− data: {"id":"chatcmpl-ab3020d8b997a66d8be305a7","object":"chat.completion.chunk","created":1778601736,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" main`."},"finish_reason":null}]}
394+ data: {"id":"chatcmpl-b2b4e1097beee00d4c336a57","object":"chat.completion.chunk","created":1778602942,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`"},"finish_reason":null}]}
325
395
326− data: {"id":"chatcmpl-ab3020d8b997a66d8be305a7","object":"chat.completion.chunk","created":1778601736,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
396+ data: {"id":"chatcmpl-b2b4e1097beee00d4c336a57","object":"chat.completion.chunk","created":1778602942,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
327
397
328− data: {"id":"chatcmpl-ab3020d8b997a66d8be305a7","object":"chat.completion.chunk","created":1778601736,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":105,"completion_tokens":18,"total_tokens":7867,"prompt_tokens_details":{"cached_tokens":7744},"completion_tokens_details":{"reasoning_tokens":17}}}
398+ data: {"id":"chatcmpl-b2b4e1097beee00d4c336a57","object":"chat.completion.chunk","created":1778602942,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7828,"completion_tokens":18,"total_tokens":7846,"completion_tokens_details":{"reasoning_tokens":17}}}
329
399
330 data: [DONE]
400 data: [DONE]
331
401
@@ -334,4 +404,4 @@ interactions:
334 - text/event-stream
404 - text/event-stream
335 status: 200 OK
405 status: 200 OK
336 code: 200
406 code: 200
337− duration: 1.829357958s
407+ duration: 3.987487125s
internal/agent/testdata/TestCoderAgent/glm-5.1/ls_tool.yaml+92−112
@@ -25,137 +25,141 @@ interactions:
25 content_length: -1
25 content_length: -1
26 uncompressed: true
26 uncompressed: true
27 body: |+
27 body: |+
28− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
28+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
29
29
30− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"User"},"finish_reason":null}]}
30+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
31
31
32− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" asks"},"finish_reason":null}]}
32+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
33
33
34− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
34+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" wants"},"finish_reason":null}]}
35
35
36− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
36+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
37
37
38− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Generate"},"finish_reason":null}]}
38+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
39
39
40− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
40+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
41
41
42− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
42+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
43
43
44− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
44+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
45
45
46− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
46+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" given"},"finish_reason":null}]}
47
47
48− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
48+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
49
49
50− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" following"},"finish_reason":null}]}
50+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
51
51
52− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
52+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
53
53
54− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
54+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"use"},"finish_reason":null}]}
55
55
56− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" use"},"finish_reason":null}]}
56+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ls"},"finish_reason":null}]}
57
57
58− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ls"},"finish_reason":null}]}
58+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
59
59
60− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
60+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" list"},"finish_reason":null}]}
61
61
62− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" list"},"finish_reason":null}]}
62+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
63
63
64− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
64+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
65
65
66− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
66+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
67
67
68− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
68+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
69
69
70− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
70+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" current"},"finish_reason":null}]}
71
71
72− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" current"},"finish_reason":null}]}
72+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" directory"},"finish_reason":null}]}
73
73
74− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" directory"},"finish_reason":null}]}
74+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
75
75
76− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
76+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Should"},"finish_reason":null}]}
77
77
78− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Need"},"finish_reason":null}]}
78+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
79
79
80− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
80+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" short"},"finish_reason":null}]}
81
81
82− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
82+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
83
83
84− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
84+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" under"},"finish_reason":null}]}
85
85
86− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" same"},"finish_reason":null}]}
86+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
87
87
88− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" language"},"finish_reason":null}]}
88+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
89
89
90− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
90+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
91
91
92− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"English"},"finish_reason":null}]}
92+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
93
93
94− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")."},"finish_reason":null}]}
94+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" one"},"finish_reason":null}]}
95
95
96− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Max"},"finish_reason":null}]}
96+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
97
97
98− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
98+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
99
99
100− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
100+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" no"},"finish_reason":null}]}
101
101
102− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
102+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
103
103
104− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
104+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" or"},"finish_reason":null}]}
105
105
106− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Something"},"finish_reason":null}]}
106+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" col"},"finish_reason":null}]}
107
107
108− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" like"},"finish_reason":null}]}
108+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ons"},"finish_reason":null}]}
109
109
110− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
110+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
111
111
112− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Listing"},"finish_reason":null}]}
112+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" summary"},"finish_reason":null}]}
113
113
114− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Files"},"finish_reason":null}]}
114+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
115
115
116− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
116+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Title"},"finish_reason":null}]}
117
117
118− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ls"},"finish_reason":null}]}
118+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" could"},"finish_reason":null}]}
119
119
120− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
120+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
121
121
122− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
122+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
123
123
124− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" under"},"finish_reason":null}]}
124+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Listing"},"finish_reason":null}]}
125
125
126− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
126+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Files"},"finish_reason":null}]}
127
127
128− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
128+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
129
129
130− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
130+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ls"},"finish_reason":null}]}
131
131
132− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Return"},"finish_reason":null}]}
132+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
133
133
134− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" just"},"finish_reason":null}]}
134+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
135
135
136− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" one"},"finish_reason":null}]}
136+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" under"},"finish_reason":null}]}
137
137
138− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
138+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
139
139
140− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
140+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
141
141
142− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" no"},"finish_reason":null}]}
142+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
143
143
144− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
144+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
145
145
146− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
146+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Return"},"finish_reason":null}]}
147
147
148− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Listing"},"finish_reason":null}]}
148+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that"},"finish_reason":null}]}
149
149
150− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Files"},"finish_reason":null}]}
150+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
151
151
152− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" with"},"finish_reason":null}]}
152+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Listing"},"finish_reason":null}]}
153
153
154− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" ls"},"finish_reason":null}]}
154+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Files"},"finish_reason":null}]}
155
155
156− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
156+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" with"},"finish_reason":null}]}
157
157
158+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" ls"},"finish_reason":null}]}
159+
160+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
161+
158− data: {"id":"chatcmpl-5257bdd2dd07faca3a39a451","object":"chat.completion.chunk","created":1778601737,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":33,"completion_tokens":73,"total_tokens":282,"prompt_tokens_details":{"cached_tokens":176}}}
162+ data: {"id":"chatcmpl-534f73b44615e15b12b916f0","object":"chat.completion.chunk","created":1778602942,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":21,"completion_tokens":75,"total_tokens":288,"prompt_tokens_details":{"cached_tokens":192}}}
159
163
160 data: [DONE]
164 data: [DONE]
161
165
@@ -164,7 +168,7 @@ interactions:
164 - text/event-stream
168 - text/event-stream
165 status: 200 OK
169 status: 200 OK
166 code: 200
170 code: 200
167− duration: 536.305667ms
171+ duration: 481.844334ms
168- id: 1
172- id: 1
169 request:
173 request:
170 proto: HTTP/1.1
174 proto: HTTP/1.1
@@ -189,41 +193,17 @@ interactions:
189 content_length: -1
193 content_length: -1
190 uncompressed: true
194 uncompressed: true
191 body: |+
195 body: |+
192− data: {"id":"chatcmpl-cc9eaa6841f50bdb2bb1138a","object":"chat.completion.chunk","created":1778601741,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
196+ data: {"id":"chatcmpl-6c6dfce3d308e14ffba6487b","object":"chat.completion.chunk","created":1778602946,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
193−
194− data: {"id":"chatcmpl-cc9eaa6841f50bdb2bb1138a","object":"chat.completion.chunk","created":1778601741,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_b71d148a2ebc4ca6a2f3a4e2","type":"function","index":0,"function":{"name":"ls","arguments":""}}]},"finish_reason":null}]}
195−
196− data: {"id":"chatcmpl-cc9eaa6841f50bdb2bb1138a","object":"chat.completion.chunk","created":1778601741,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
197−
198− data: {"id":"chatcmpl-cc9eaa6841f50bdb2bb1138a","object":"chat.completion.chunk","created":1778601741,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
199−
200− data: {"id":"chatcmpl-cc9eaa6841f50bdb2bb1138a","object":"chat.completion.chunk","created":1778601741,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"path\": "}}]},"finish_reason":null}]}
201−
202− data: {"id":"chatcmpl-cc9eaa6841f50bdb2bb1138a","object":"chat.completion.chunk","created":1778601741,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/tmp/c"}}]},"finish_reason":null}]}
203−
204− data: {"id":"chatcmpl-cc9eaa6841f50bdb2bb1138a","object":"chat.completion.chunk","created":1778601741,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"rush"}}]},"finish_reason":null}]}
205−
206− data: {"id":"chatcmpl-cc9eaa6841f50bdb2bb1138a","object":"chat.completion.chunk","created":1778601741,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test/Test"}}]},"finish_reason":null}]}
207−
208− data: {"id":"chatcmpl-cc9eaa6841f50bdb2bb1138a","object":"chat.completion.chunk","created":1778601741,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}]}
209−
210− data: {"id":"chatcmpl-cc9eaa6841f50bdb2bb1138a","object":"chat.completion.chunk","created":1778601741,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent/g"}}]},"finish_reason":null}]}
211−
212− data: {"id":"chatcmpl-cc9eaa6841f50bdb2bb1138a","object":"chat.completion.chunk","created":1778601741,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"lm-"}}]},"finish_reason":null}]}
213−
214− data: {"id":"chatcmpl-cc9eaa6841f50bdb2bb1138a","object":"chat.completion.chunk","created":1778601741,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5."}}]},"finish_reason":null}]}
215−
216− data: {"id":"chatcmpl-cc9eaa6841f50bdb2bb1138a","object":"chat.completion.chunk","created":1778601741,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"1/ls"}}]},"finish_reason":null}]}
217
197
218− data: {"id":"chatcmpl-cc9eaa6841f50bdb2bb1138a","object":"chat.completion.chunk","created":1778601741,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}]}
198+ data: {"id":"chatcmpl-6c6dfce3d308e14ffba6487b","object":"chat.completion.chunk","created":1778602946,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_9f47b2a8049648eba6e14139","type":"function","index":0,"function":{"name":"ls","arguments":""}}]},"finish_reason":null}]}
219
199
220− data: {"id":"chatcmpl-cc9eaa6841f50bdb2bb1138a","object":"chat.completion.chunk","created":1778601741,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\""}}]},"finish_reason":null}]}
200+ data: {"id":"chatcmpl-6c6dfce3d308e14ffba6487b","object":"chat.completion.chunk","created":1778602946,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
221
201
222− data: {"id":"chatcmpl-cc9eaa6841f50bdb2bb1138a","object":"chat.completion.chunk","created":1778601741,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
202+ data: {"id":"chatcmpl-6c6dfce3d308e14ffba6487b","object":"chat.completion.chunk","created":1778602946,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{}"}}]},"finish_reason":null}]}
223
203
224− data: {"id":"chatcmpl-cc9eaa6841f50bdb2bb1138a","object":"chat.completion.chunk","created":1778601741,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
204+ data: {"id":"chatcmpl-6c6dfce3d308e14ffba6487b","object":"chat.completion.chunk","created":1778602946,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
225
205
226− data: {"id":"chatcmpl-cc9eaa6841f50bdb2bb1138a","object":"chat.completion.chunk","created":1778601741,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7767,"completion_tokens":26,"total_tokens":7793,"completion_tokens_details":{"reasoning_tokens":25}}}
206+ data: {"id":"chatcmpl-6c6dfce3d308e14ffba6487b","object":"chat.completion.chunk","created":1778602946,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":727,"completion_tokens":5,"total_tokens":7772,"prompt_tokens_details":{"cached_tokens":7040},"completion_tokens_details":{"reasoning_tokens":4}}}
227
207
228 data: [DONE]
208 data: [DONE]
229
209
@@ -232,15 +212,15 @@ interactions:
232 - text/event-stream
212 - text/event-stream
233 status: 200 OK
213 status: 200 OK
234 code: 200
214 code: 200
235− duration: 4.996589333s
215+ duration: 4.089139708s
236- id: 2
216- id: 2
237 request:
217 request:
238 proto: HTTP/1.1
218 proto: HTTP/1.1
239 proto_major: 1
219 proto_major: 1
240 proto_minor: 1
220 proto_minor: 1
241− content_length: 34073
221+ content_length: 34013
242 host: ""
222 host: ""
243− 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</editing_files>\\n\\n<whitespace_and_exact_matching>\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n</whitespace_and_exact_matching>\\n\\n<task_completion>\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n</task_completion>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences\\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n<bash_commands>\\n**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/glm-5.1/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n<available_skills>\\n <skill>\\n <name>crush-hooks</name>\\n <description>Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.</description>\\n <location>crush://skills/crush-hooks/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n <skill>\\n <name>jq</name>\\n <description>Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.</description>\\n <location>crush://skills/jq/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n</available_skills>\\n\\n<skills_usage>\\nThe `<description>` of each skill is a TRIGGER — it tells you *when* a skill applies. It is NOT a specification of what the skill does or how to do it. The procedure, scripts, commands, references, and required flags live only in the SKILL.md body. You do not know what a skill actually does until you have read its SKILL.md.\\n\\nMANDATORY activation flow:\\n1. Scan `<available_skills>` against the current user task.\\n2. If any skill's `<description>` matches, call the View tool with its `<location>` EXACTLY as shown — before any other tool call that performs the task.\\n3. Read the entire SKILL.md and follow its instructions.\\n4. Only then execute the task, using the skill's prescribed commands/tools.\\n\\nDo NOT skip step 2 because you think you already know how to do the task. Do NOT infer a skill's behavior from its name or description. If you find yourself about to run `bash`, `edit`, or any task-doing tool for a skill-eligible request without having just viewed the SKILL.md, stop and load the skill first.\\n\\nBuiltin skills (type=builtin) use virtual `crush://skills/...` location identifiers. The \\\"crush://\\\" prefix is NOT a URL, network address, or MCP resource — it is a special internal identifier the View tool understands natively. Pass the `<location>` verbatim to View.\\n\\nDo not use MCP tools (including read_mcp_resource) to load skills.\\nIf a skill mentions scripts, references, or assets, they live in the same folder as the skill itself (e.g., scripts/, references/, assets/ subdirectories within the skill's folder).\\n</skills_usage>\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"<system_reminder>This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.</system_reminder>\",\"role\":\"user\"},{\"content\":\"use ls to list the files in the current directory\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_b71d148a2ebc4ca6a2f3a4e2\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/ls_tool\\\"}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/glm-5.1/ls_tool/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_b71d148a2ebc4ca6a2f3a4e2\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
223+ 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</editing_files>\\n\\n<whitespace_and_exact_matching>\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n</whitespace_and_exact_matching>\\n\\n<task_completion>\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n</task_completion>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences\\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n<bash_commands>\\n**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/glm-5.1/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n<available_skills>\\n <skill>\\n <name>crush-hooks</name>\\n <description>Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.</description>\\n <location>crush://skills/crush-hooks/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n <skill>\\n <name>jq</name>\\n <description>Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.</description>\\n <location>crush://skills/jq/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n</available_skills>\\n\\n<skills_usage>\\nThe `<description>` of each skill is a TRIGGER — it tells you *when* a skill applies. It is NOT a specification of what the skill does or how to do it. The procedure, scripts, commands, references, and required flags live only in the SKILL.md body. You do not know what a skill actually does until you have read its SKILL.md.\\n\\nMANDATORY activation flow:\\n1. Scan `<available_skills>` against the current user task.\\n2. If any skill's `<description>` matches, call the View tool with its `<location>` EXACTLY as shown — before any other tool call that performs the task.\\n3. Read the entire SKILL.md and follow its instructions.\\n4. Only then execute the task, using the skill's prescribed commands/tools.\\n\\nDo NOT skip step 2 because you think you already know how to do the task. Do NOT infer a skill's behavior from its name or description. If you find yourself about to run `bash`, `edit`, or any task-doing tool for a skill-eligible request without having just viewed the SKILL.md, stop and load the skill first.\\n\\nBuiltin skills (type=builtin) use virtual `crush://skills/...` location identifiers. The \\\"crush://\\\" prefix is NOT a URL, network address, or MCP resource — it is a special internal identifier the View tool understands natively. Pass the `<location>` verbatim to View.\\n\\nDo not use MCP tools (including read_mcp_resource) to load skills.\\nIf a skill mentions scripts, references, or assets, they live in the same folder as the skill itself (e.g., scripts/, references/, assets/ subdirectories within the skill's folder).\\n</skills_usage>\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"<system_reminder>This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.</system_reminder>\",\"role\":\"user\"},{\"content\":\"use ls to list the files in the current directory\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_9f47b2a8049648eba6e14139\",\"function\":{\"arguments\":\"{}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/glm-5.1/ls_tool/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_9f47b2a8049648eba6e14139\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
244 headers:
224 headers:
245 Accept:
225 Accept:
246 - application/json
226 - application/json
@@ -257,27 +237,27 @@ interactions:
257 content_length: -1
237 content_length: -1
258 uncompressed: true
238 uncompressed: true
259 body: |+
239 body: |+
260− data: {"id":"chatcmpl-f2baa404e30bd65bbb71763f","object":"chat.completion.chunk","created":1778601744,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
240+ data: {"id":"chatcmpl-04c02126e54c5eeac9e5e262","object":"chat.completion.chunk","created":1778602951,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
261
241
262− data: {"id":"chatcmpl-f2baa404e30bd65bbb71763f","object":"chat.completion.chunk","created":1778601744,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Files"},"finish_reason":null}]}
242+ data: {"id":"chatcmpl-04c02126e54c5eeac9e5e262","object":"chat.completion.chunk","created":1778602951,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Files"},"finish_reason":null}]}
263
243
264− data: {"id":"chatcmpl-f2baa404e30bd65bbb71763f","object":"chat.completion.chunk","created":1778601744,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" in"},"finish_reason":null}]}
244+ data: {"id":"chatcmpl-04c02126e54c5eeac9e5e262","object":"chat.completion.chunk","created":1778602951,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" in"},"finish_reason":null}]}
265
245
266− data: {"id":"chatcmpl-f2baa404e30bd65bbb71763f","object":"chat.completion.chunk","created":1778601744,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" the current directory"},"finish_reason":null}]}
246+ data: {"id":"chatcmpl-04c02126e54c5eeac9e5e262","object":"chat.completion.chunk","created":1778602951,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" the current directory"},"finish_reason":null}]}
267
247
268− data: {"id":"chatcmpl-f2baa404e30bd65bbb71763f","object":"chat.completion.chunk","created":1778601744,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":":\n- `"},"finish_reason":null}]}
248+ data: {"id":"chatcmpl-04c02126e54c5eeac9e5e262","object":"chat.completion.chunk","created":1778602951,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":":\n- `"},"finish_reason":null}]}
269
249
270− data: {"id":"chatcmpl-f2baa404e30bd65bbb71763f","object":"chat.completion.chunk","created":1778601744,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"go.mod`\n"},"finish_reason":null}]}
250+ data: {"id":"chatcmpl-04c02126e54c5eeac9e5e262","object":"chat.completion.chunk","created":1778602951,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"go.mod"},"finish_reason":null}]}
271
251
272− data: {"id":"chatcmpl-f2baa404e30bd65bbb71763f","object":"chat.completion.chunk","created":1778601744,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"- `"},"finish_reason":null}]}
252+ data: {"id":"chatcmpl-04c02126e54c5eeac9e5e262","object":"chat.completion.chunk","created":1778602951,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`\n-"},"finish_reason":null}]}
273
253
274− data: {"id":"chatcmpl-f2baa404e30bd65bbb71763f","object":"chat.completion.chunk","created":1778601744,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"main.go"},"finish_reason":null}]}
254+ data: {"id":"chatcmpl-04c02126e54c5eeac9e5e262","object":"chat.completion.chunk","created":1778602951,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `main"},"finish_reason":null}]}
275
255
276− data: {"id":"chatcmpl-f2baa404e30bd65bbb71763f","object":"chat.completion.chunk","created":1778601744,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`"},"finish_reason":null}]}
256+ data: {"id":"chatcmpl-04c02126e54c5eeac9e5e262","object":"chat.completion.chunk","created":1778602951,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":".go`"},"finish_reason":null}]}
277
257
278− data: {"id":"chatcmpl-f2baa404e30bd65bbb71763f","object":"chat.completion.chunk","created":1778601744,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
258+ data: {"id":"chatcmpl-04c02126e54c5eeac9e5e262","object":"chat.completion.chunk","created":1778602951,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
279
259
280− data: {"id":"chatcmpl-f2baa404e30bd65bbb71763f","object":"chat.completion.chunk","created":1778601744,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7827,"completion_tokens":18,"total_tokens":7845,"completion_tokens_details":{"reasoning_tokens":17}}}
260+ data: {"id":"chatcmpl-04c02126e54c5eeac9e5e262","object":"chat.completion.chunk","created":1778602951,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7806,"completion_tokens":18,"total_tokens":7824,"completion_tokens_details":{"reasoning_tokens":17}}}
281
261
282 data: [DONE]
262 data: [DONE]
283
263
@@ -286,4 +266,4 @@ interactions:
286 - text/event-stream
266 - text/event-stream
287 status: 200 OK
267 status: 200 OK
288 code: 200
268 code: 200
289− duration: 2.545317042s
269+ duration: 4.81730275s
internal/agent/testdata/TestCoderAgent/glm-5.1/multiedit_tool.yaml+296−752
@@ -25,657 +25,391 @@ interactions:
25 content_length: -1
25 content_length: -1
26 uncompressed: true
26 uncompressed: true
27 body: |+
27 body: |+
28− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
28+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
29
29
30− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"User"},"finish_reason":null}]}
30+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
31
31
32− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" wants"},"finish_reason":null}]}
32+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
33
33
34− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
34+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" wants"},"finish_reason":null}]}
35
35
36− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
36+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
37
37
38− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
38+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
39
39
40− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
40+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
41
41
42− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" same"},"finish_reason":null}]}
42+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
43
43
44− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" language"},"finish_reason":null}]}
44+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
45
45
46− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
46+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
47
47
48− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"English"},"finish_reason":null}]}
48+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
49
49
50− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")."},"finish_reason":null}]}
50+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Must"},"finish_reason":null}]}
51
51
52− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Summ"},"finish_reason":null}]}
52+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
53
53
54− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ar"},"finish_reason":null}]}
54+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" short"},"finish_reason":null}]}
55
55
56− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ize"},"finish_reason":null}]}
56+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \u003c="},"finish_reason":null}]}
57
57
58− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
58+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
59
59
60− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" using"},"finish_reason":null}]}
60+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
61
61
62− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" mult"},"finish_reason":null}]}
62+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
63
63
64− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ied"},"finish_reason":null}]}
64+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
65
65
66− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"it"},"finish_reason":null}]}
66+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" same"},"finish_reason":null}]}
67
67
68− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
68+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" language"},"finish_reason":null}]}
69
69
70− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" modify"},"finish_reason":null}]}
70+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
71
71
72− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" string"},"finish_reason":null}]}
72+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"English"},"finish_reason":null}]}
73
73
74− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
74+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"),"},"finish_reason":null}]}
75
75
76− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" add"},"finish_reason":null}]}
76+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" no"},"finish_reason":null}]}
77
77
78− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
78+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
79
79
80− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
80+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" or"},"finish_reason":null}]}
81
81
82− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Title"},"finish_reason":null}]}
82+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" col"},"finish_reason":null}]}
83
83
84− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
84+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ons"},"finish_reason":null}]}
85
85
86− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Use"},"finish_reason":null}]}
86+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
87
87
88− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" mult"},"finish_reason":null}]}
88+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Summ"},"finish_reason":null}]}
89
89
90− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ied"},"finish_reason":null}]}
90+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ar"},"finish_reason":null}]}
91
91
92− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"it"},"finish_reason":null}]}
92+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ize"},"finish_reason":null}]}
93
93
94− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
94+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
95
95
96− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" update"},"finish_reason":null}]}
96+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
97
97
98− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" greeting"},"finish_reason":null}]}
98+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Use"},"finish_reason":null}]}
99
99
100− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
100+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" mult"},"finish_reason":null}]}
101
101
102− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" add"},"finish_reason":null}]}
102+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ied"},"finish_reason":null}]}
103
103
104− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
104+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"it"},"finish_reason":null}]}
105
105
106− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
106+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
107
107
108− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
108+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" replace"},"finish_reason":null}]}
109
109
110− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".go"},"finish_reason":null}]}
110+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Hello"},"finish_reason":null}]}
111
111
112− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
112+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" World"},"finish_reason":null}]}
113
113
114− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Need"},"finish_reason":null}]}
114+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
115
115
116− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \u003c="},"finish_reason":null}]}
116+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Hello"},"finish_reason":null}]}
117
117
118− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
118+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Crush"},"finish_reason":null}]}
119
119
120− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
120+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
121
121
122− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
122+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" add"},"finish_reason":null}]}
123
123
124− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
124+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
125
125
126− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
126+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
127
127
128− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
128+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Title"},"finish_reason":null}]}
129
129
130− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Use"},"finish_reason":null}]}
130+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" maybe"},"finish_reason":null}]}
131
131
132− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" mult"},"finish_reason":null}]}
132+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
133
133
134− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ied"},"finish_reason":null}]}
134+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
135
135
136− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"it"},"finish_reason":null}]}
136+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Mult"},"finish_reason":null}]}
137
137
138− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
138+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ied"},"finish_reason":null}]}
139
139
140− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" update"},"finish_reason":null}]}
140+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"it"},"finish_reason":null}]}
141
141
142− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" greeting"},"finish_reason":null}]}
142+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
143
143
144− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
144+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" replace"},"finish_reason":null}]}
145
145
146− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" add"},"finish_reason":null}]}
146+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" greeting"},"finish_reason":null}]}
147
147
148− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
148+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
149
149
150− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
150+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" add"},"finish_reason":null}]}
151
151
152− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
152+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
153
153
154− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".go"},"finish_reason":null}]}
154+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
155
155
156− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
156+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Must"},"finish_reason":null}]}
157
157
158− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Let's"},"finish_reason":null}]}
158+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
159
159
160− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
160+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" under"},"finish_reason":null}]}
161
161
162− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
162+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
163
163
164− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
164+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
165
165
166− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" U"},"finish_reason":null}]}
166+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
167
167
168− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
168+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
169
169
170− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
170+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
171
171
172− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")s"},"finish_reason":null}]}
172+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Replace"},"finish_reason":null}]}
173
173
174− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"..."},"finish_reason":null}]}
174+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" greeting"},"finish_reason":null}]}
175
175
176− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Let's"},"finish_reason":null}]}
176+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
177
177
178− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
178+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" add"},"finish_reason":null}]}
179
179
180− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
180+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
181
181
182− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
182+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
183
183
184− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Use"},"finish_reason":null}]}
184+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" mult"},"finish_reason":null}]}
185
185
186− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" mult"},"finish_reason":null}]}
186+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ied"},"finish_reason":null}]}
187
187
188− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ied"},"finish_reason":null}]}
188+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"it"},"finish_reason":null}]}
189
189
190− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"it"},"finish_reason":null}]}
190+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
191
191
192− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
192+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
193
193
194− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" update"},"finish_reason":null}]}
194+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
195
195
196− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" greeting"},"finish_reason":null}]}
196+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
197
197
198− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
198+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Replace"},"finish_reason":null}]}
199
199
200− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" add"},"finish_reason":null}]}
200+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" greeting"},"finish_reason":null}]}
201
201
202− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
202+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
203
203
204− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
204+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" add"},"finish_reason":null}]}
205
205
206− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
206+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
207
207
208− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".go"},"finish_reason":null}]}
208+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
209
209
210− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
210+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" mult"},"finish_reason":null}]}
211
211
212− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
212+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ied"},"finish_reason":null}]}
213
213
214− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" spaces"},"finish_reason":null}]}
214+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"it"},"finish_reason":null}]}
215
215
216− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
216+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
217
217
218− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" punctuation"},"finish_reason":null}]}
218+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ="},"finish_reason":null}]}
219
219
220− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
220+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" let's"},"finish_reason":null}]}
221
221
222− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" We'll"},"finish_reason":null}]}
222+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
223
223
224− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
224+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
225
225
226− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
226+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
227
227
228− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Use"},"finish_reason":null}]}
228+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Replace"},"finish_reason":null}]}
229
229
230− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
230+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
231
231
232− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
232+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
233
233
234− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
234+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
235
235
236− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" +"},"finish_reason":null}]}
236+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
237
237
238− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
238+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
239
239
240− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
240+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
241
241
242− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
242+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
243
243
244− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" =\u003e"},"finish_reason":null}]}
244+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"8"},"finish_reason":null}]}
245
245
246− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
246+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
247
247
248− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
248+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" greeting"},"finish_reason":null}]}
249
249
250− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" mult"},"finish_reason":null}]}
250+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
251
251
252− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ied"},"finish_reason":null}]}
252+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"8"},"finish_reason":null}]}
253
253
254− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"it"},"finish_reason":null}]}
254+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
255
255
256− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
256+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"16"},"finish_reason":null}]}
257
257
258− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"9"},"finish_reason":null}]}
258+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
259
259
260− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
260+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
261
261
262− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" =\u003e"},"finish_reason":null}]}
262+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
263
263
264− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"13"},"finish_reason":null}]}
264+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"17"},"finish_reason":null}]}
265
265
266− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
266+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
267
267
268− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
268+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
269
269
270− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
270+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
271
271
272− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
272+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
273
273
274− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" =\u003e"},"finish_reason":null}]}
274+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
275
275
276− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"14"},"finish_reason":null}]}
276+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"20"},"finish_reason":null}]}
277
277
278− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
278+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
279
279
280− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
280+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
281
281
282− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
282+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
283
283
284− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
284+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"21"},"finish_reason":null}]}
285
285
286− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")=\u003e"},"finish_reason":null}]}
286+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
287
287
288− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"16"},"finish_reason":null}]}
288+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" add"},"finish_reason":null}]}
289
289
290− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
290+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
291
291
292− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
292+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
293
293
294− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
294+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
295
295
296− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
296+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"24"},"finish_reason":null}]}
297
297
298− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"=\u003e"},"finish_reason":null}]}
298+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
299
299
300− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"17"},"finish_reason":null}]}
300+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
301
301
302− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
302+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
303
303
304− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" update"},"finish_reason":null}]}
304+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"25"},"finish_reason":null}]}
305
305
306− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
306+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
307
307
308− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
308+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
309
309
310− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")=\u003e"},"finish_reason":null}]}
310+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
311
311
312− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"23"},"finish_reason":null}]}
312+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
313
313
314− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
314+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
315
315
316− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
316+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"32"},"finish_reason":null}]}
317
317
318− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
318+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
319
319
320− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
320+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
321
321
322− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"=\u003e"},"finish_reason":null}]}
322+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
323
323
324− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"24"},"finish_reason":null}]}
324+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"33"},"finish_reason":null}]}
325
325
326− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
326+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
327
327
328− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" greeting"},"finish_reason":null}]}
328+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
329
329
330− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
330+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
331
331
332− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"8"},"finish_reason":null}]}
332+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
333
333
334− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")=\u003e"},"finish_reason":null}]}
334+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
335
335
336− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"32"},"finish_reason":null}]}
336+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"37"},"finish_reason":null}]}
337
337
338− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
338+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
339
339
340− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
340+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
341
341
342− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
342+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
343
343
344− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
344+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"38"},"finish_reason":null}]}
345
345
346− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"=\u003e"},"finish_reason":null}]}
346+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
347
347
348− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"33"},"finish_reason":null}]}
348+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" mult"},"finish_reason":null}]}
349
349
350− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
350+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ied"},"finish_reason":null}]}
351
351
352− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
352+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"it"},"finish_reason":null}]}
353
353
354− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
354+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
355
355
356− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
356+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"9"},"finish_reason":null}]}
357
357
358− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")=\u003e"},"finish_reason":null}]}
358+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
359
359
360− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"36"},"finish_reason":null}]}
360+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"47"},"finish_reason":null}]}
361
361
362− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
362+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
363
363
364− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
364+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
365
365
366− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
366+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
367
367
368− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
368+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"47"},"finish_reason":null}]}
369
369
370− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"=\u003e"},"finish_reason":null}]}
370+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
371
371
372− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"37"},"finish_reason":null}]}
372+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
373
373
374− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
374+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Okay"},"finish_reason":null}]}
375
375
376− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" add"},"finish_reason":null}]}
376+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".\n\n"},"finish_reason":null}]}
377
377
378− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
378+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"No"},"finish_reason":null}]}
379
379
380− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
380+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
381
381
382− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")=\u003e"},"finish_reason":null}]}
382+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
383
383
384− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"40"},"finish_reason":null}]}
384+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Return"},"finish_reason":null}]}
385
385
386− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
386+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that"},"finish_reason":null}]}
387
387
388− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
388+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" exactly"},"finish_reason":null}]}
389
389
390− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
390+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
391
391
392− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
392+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Replace"},"finish_reason":null}]}
393
393
394− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"=\u003e"},"finish_reason":null}]}
394+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" greeting"},"finish_reason":null}]}
395
395
396− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"41"},"finish_reason":null}]}
396+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" and"},"finish_reason":null}]}
397
397
398− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
398+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" add"},"finish_reason":null}]}
399
399
400− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
400+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" comment"},"finish_reason":null}]}
401
401
402− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
402+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" with"},"finish_reason":null}]}
403
403
404− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
404+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" mult"},"finish_reason":null}]}
405
405
406− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")=\u003e"},"finish_reason":null}]}
406+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"ied"},"finish_reason":null}]}
407
407
408− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"48"},"finish_reason":null}]}
408+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"it"},"finish_reason":null}]}
409
409
410− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
410+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
411
411
412− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
412+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":43,"completion_tokens":200,"total_tokens":435,"prompt_tokens_details":{"cached_tokens":192}}}
413−
414− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
415−
416− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
417−
418− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"=\u003e"},"finish_reason":null}]}
419−
420− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"49"},"finish_reason":null}]}
421−
422− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
423−
424− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
425−
426− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
427−
428− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
429−
430− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")=\u003e"},"finish_reason":null}]}
431−
432− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"51"},"finish_reason":null}]}
433−
434− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
435−
436− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
437−
438− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
439−
440− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
441−
442− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"=\u003e"},"finish_reason":null}]}
443−
444− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"52"},"finish_reason":null}]}
445−
446− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
447−
448− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
449−
450− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".go"},"finish_reason":null}]}
451−
452− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
453−
454− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
455−
456− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")=\u003e"},"finish_reason":null}]}
457−
458− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"59"},"finish_reason":null}]}
459−
460− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
461−
462− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Too"},"finish_reason":null}]}
463−
464− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" long"},"finish_reason":null}]}
465−
466− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".\n\n"},"finish_reason":null}]}
467−
468− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Need"},"finish_reason":null}]}
469−
470− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \u003c="},"finish_reason":null}]}
471−
472− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
473−
474− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
475−
476− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Maybe"},"finish_reason":null}]}
477−
478− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
479−
480− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
481−
482− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Mult"},"finish_reason":null}]}
483−
484− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ied"},"finish_reason":null}]}
485−
486− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"it"},"finish_reason":null}]}
487−
488− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
489−
490− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" change"},"finish_reason":null}]}
491−
492− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" greeting"},"finish_reason":null}]}
493−
494− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
495−
496− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" add"},"finish_reason":null}]}
497−
498− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
499−
500− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
501−
502− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
503−
504− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
505−
506− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Mult"},"finish_reason":null}]}
507−
508− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ied"},"finish_reason":null}]}
509−
510− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"it"},"finish_reason":null}]}
511−
512− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":("},"finish_reason":null}]}
513−
514− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"9"},"finish_reason":null}]}
515−
516− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
517−
518− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" +"},"finish_reason":null}]}
519−
520− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
521−
522− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
523−
524− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
525−
526− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"10"},"finish_reason":null}]}
527−
528− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
529−
530− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" change"},"finish_reason":null}]}
531−
532− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
533−
534− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
535−
536− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")=\u003e"},"finish_reason":null}]}
537−
538− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"16"},"finish_reason":null}]}
539−
540− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
541−
542− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
543−
544− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
545−
546− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
547−
548− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"=\u003e"},"finish_reason":null}]}
549−
550− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"17"},"finish_reason":null}]}
551−
552− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
553−
554− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" greeting"},"finish_reason":null}]}
555−
556− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
557−
558− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"8"},"finish_reason":null}]}
559−
560− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")=\u003e"},"finish_reason":null}]}
561−
562− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"25"},"finish_reason":null}]}
563−
564− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
565−
566− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
567−
568− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
569−
570− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
571−
572− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"=\u003e"},"finish_reason":null}]}
573−
574− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"26"},"finish_reason":null}]}
575−
576− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
577−
578− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
579−
580− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
581−
582− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
583−
584− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")=\u003e"},"finish_reason":null}]}
585−
586− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"29"},"finish_reason":null}]}
587−
588− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
589−
590− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
591−
592− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
593−
594− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
595−
596− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"=\u003e"},"finish_reason":null}]}
597−
598− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"30"},"finish_reason":null}]}
599−
600− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
601−
602− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" add"},"finish_reason":null}]}
603−
604− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
605−
606− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
607−
608− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")=\u003e"},"finish_reason":null}]}
609−
610− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"33"},"finish_reason":null}]}
611−
612− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
613−
614− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
615−
616− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
617−
618− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
619−
620− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"=\u003e"},"finish_reason":null}]}
621−
622− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"34"},"finish_reason":null}]}
623−
624− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
625−
626− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
627−
628− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
629−
630− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
631−
632− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")=\u003e"},"finish_reason":null}]}
633−
634− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"41"},"finish_reason":null}]}
635−
636− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
637−
638− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
639−
640− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
641−
642− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"41"},"finish_reason":null}]}
643−
644− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
645−
646− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" within"},"finish_reason":null}]}
647−
648− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" limit"},"finish_reason":null}]}
649−
650− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".\n\n"},"finish_reason":null}]}
651−
652− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Return"},"finish_reason":null}]}
653−
654− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that"},"finish_reason":null}]}
655−
656− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
657−
658− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Mult"},"finish_reason":null}]}
659−
660− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"ied"},"finish_reason":null}]}
661−
662− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"it"},"finish_reason":null}]}
663−
664− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}]}
665−
666− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" change"},"finish_reason":null}]}
667−
668− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" greeting"},"finish_reason":null}]}
669−
670− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" and"},"finish_reason":null}]}
671−
672− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" add"},"finish_reason":null}]}
673−
674− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" comment"},"finish_reason":null}]}
675−
676− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
677−
678− data: {"id":"chatcmpl-1681c841a760d422b6d9bbf0","object":"chat.completion.chunk","created":1778601745,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":55,"completion_tokens":333,"total_tokens":564,"prompt_tokens_details":{"cached_tokens":176}}}
679
413
680 data: [DONE]
414 data: [DONE]
681
415
@@ -684,7 +418,7 @@ interactions:
684 - text/event-stream
418 - text/event-stream
685 status: 200 OK
419 status: 200 OK
686 code: 200
420 code: 200
687− duration: 600.672042ms
421+ duration: 492.312166ms
688- id: 1
422- id: 1
689 request:
423 request:
690 proto: HTTP/1.1
424 proto: HTTP/1.1
@@ -709,59 +443,59 @@ interactions:
709 content_length: -1
443 content_length: -1
710 uncompressed: true
444 uncompressed: true
711 body: |+
445 body: |+
712− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
446+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
713
447
714− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"Let"},"finish_reason":null}]}
448+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"Let"},"finish_reason":null}]}
715
449
716− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" me"},"finish_reason":null}]}
450+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" me"},"finish_reason":null}]}
717
451
718− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" first read"},"finish_reason":null}]}
452+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" first read"},"finish_reason":null}]}
719
453
720− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" the main.go"},"finish_reason":null}]}
454+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" the file"},"finish_reason":null}]}
721
455
722− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" file to see"},"finish_reason":null}]}
456+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" to see"},"finish_reason":null}]}
723
457
724− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" its current"},"finish_reason":null}]}
458+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" its current"},"finish_reason":null}]}
725
459
726− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" contents."},"finish_reason":null}]}
460+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" contents"},"finish_reason":null}]}
727
461
728− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_813fe8edde9041c18e85fd3c","type":"function","index":0,"function":{"name":"view","arguments":""}}]},"finish_reason":null}]}
462+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
729
463
730− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
464+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_fc1d5e25b1c14cb68be5d476","type":"function","index":0,"function":{"name":"view","arguments":""}}]},"finish_reason":null}]}
731
465
732− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
466+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
733
467
734− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"file_path\": "}}]},"finish_reason":null}]}
468+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
735
469
736− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/tmp/c"}}]},"finish_reason":null}]}
470+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"file_path\": \"/tmp/c"}}]},"finish_reason":null}]}
737
471
738− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"rush-test"}}]},"finish_reason":null}]}
472+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"rush-test"}}]},"finish_reason":null}]}
739
473
740− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}]}
474+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}]}
741
475
742− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}]}
476+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}]}
743
477
744− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}]}
478+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}]}
745
479
746− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/glm"}}]},"finish_reason":null}]}
480+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/glm"}}]},"finish_reason":null}]}
747
481
748− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-5.1"}}]},"finish_reason":null}]}
482+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-5"}}]},"finish_reason":null}]}
749
483
750− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/mult"}}]},"finish_reason":null}]}
484+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".1"}}]},"finish_reason":null}]}
751
485
752− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ied"}}]},"finish_reason":null}]}
486+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/multied"}}]},"finish_reason":null}]}
753
487
754− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"it"}}]},"finish_reason":null}]}
488+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"it_tool"}}]},"finish_reason":null}]}
755
489
756− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool/main.go"}}]},"finish_reason":null}]}
490+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main.go"}}]},"finish_reason":null}]}
757
491
758− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\""}}]},"finish_reason":null}]}
492+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\""}}]},"finish_reason":null}]}
759
493
760− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
494+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
761
495
762− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
496+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
763
497
764− data: {"id":"chatcmpl-d7f66a4943ebca0c1fa332dd","object":"chat.completion.chunk","created":1778601748,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7792,"completion_tokens":45,"total_tokens":7837,"completion_tokens_details":{"reasoning_tokens":14}}}
498+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":752,"completion_tokens":43,"total_tokens":7835,"prompt_tokens_details":{"cached_tokens":7040},"completion_tokens_details":{"reasoning_tokens":12}}}
765
499
766 data: [DONE]
500 data: [DONE]
767
501
@@ -770,15 +504,15 @@ interactions:
770 - text/event-stream
504 - text/event-stream
771 status: 200 OK
505 status: 200 OK
772 code: 200
506 code: 200
773− duration: 3.563327417s
507+ duration: 3.0584735s
774- id: 2
508- id: 2
775 request:
509 request:
776 proto: HTTP/1.1
510 proto: HTTP/1.1
777 proto_major: 1
511 proto_major: 1
778 proto_minor: 1
512 proto_minor: 1
779− content_length: 34341
513+ content_length: 34342
780 host: ""
514 host: ""
781− 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/multiedit_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\",\"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 multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_813fe8edde9041c18e85fd3c\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"Let me first read the main.go file to see its current contents.\"},{\"content\":\"<file>\\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</file>\\n\",\"tool_call_id\":\"call_813fe8edde9041c18e85fd3c\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
515+ 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/multiedit_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\",\"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 multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_fc1d5e25b1c14cb68be5d476\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"Let me first read the file to see its current contents.\"},{\"content\":\"<file>\\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 8|\\n</file>\\n\",\"tool_call_id\":\"call_fc1d5e25b1c14cb68be5d476\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
782 headers:
516 headers:
783 Accept:
517 Accept:
784 - application/json
518 - application/json
@@ -795,99 +529,93 @@ interactions:
795 content_length: -1
529 content_length: -1
796 uncompressed: true
530 uncompressed: true
797 body: |+
531 body: |+
798− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
532+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
799−
800− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_c18af77e70014616b852dd7f","type":"function","index":0,"function":{"name":"multiedit","arguments":""}}]},"finish_reason":null}]}
801
533
802− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
534+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_9dfbb4b9cd7a4af3881b997b","type":"function","index":0,"function":{"name":"multiedit","arguments":""}}]},"finish_reason":null}]}
803
535
804− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
536+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
805
537
806− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"edits\": "}}]},"finish_reason":null}]}
538+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
807
539
808− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"[{\""}}]},"finish_reason":null}]}
540+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"edits\": "}}]},"finish_reason":null}]}
809
541
810− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"new"}}]},"finish_reason":null}]}
542+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"[{\""}}]},"finish_reason":null}]}
811
543
812− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string\": \""}}]},"finish_reason":null}]}
544+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"new"}}]},"finish_reason":null}]}
813
545
814− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello"}}]},"finish_reason":null}]}
546+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}]}
815
547
816− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":", Crush"}}]},"finish_reason":null}]}
548+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\": \"\\"}}]},"finish_reason":null}]}
817
549
818− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\", \""}}]},"finish_reason":null}]}
550+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"t//"}}]},"finish_reason":null}]}
819
551
820− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"old_string\":"}}]},"finish_reason":null}]}
552+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" G"}}]},"finish_reason":null}]}
821
553
822− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \"Hello"}}]},"finish_reason":null}]}
554+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"reeting"}}]},"finish_reason":null}]}
823
555
824− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":", World"}}]},"finish_reason":null}]}
556+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\n\\t"}}]},"finish_reason":null}]}
825
557
826− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\"}, {\""}}]},"finish_reason":null}]}
558+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"fmt"}}]},"finish_reason":null}]}
827
559
828− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"new_string\":"}}]},"finish_reason":null}]}
560+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}]}
829
561
830− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \"\\t"}}]},"finish_reason":null}]}
562+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\"Hello"}}]},"finish_reason":null}]}
831
563
832− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"// G"}}]},"finish_reason":null}]}
564+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":", Crush"}}]},"finish_reason":null}]}
833
565
834− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"reeting\\n\\t"}}]},"finish_reason":null}]}
566+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\\")"}}]},"finish_reason":null}]}
835
567
836− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"fmt.Println"}}]},"finish_reason":null}]}
568+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\", \"old"}}]},"finish_reason":null}]}
837
569
838− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}]}
570+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string\": \"\\"}}]},"finish_reason":null}]}
839
571
840− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello, Crush"}}]},"finish_reason":null}]}
572+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tf"}}]},"finish_reason":null}]}
841
573
842− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\\")"}}]},"finish_reason":null}]}
574+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"mt"}}]},"finish_reason":null}]}
843
575
844− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\", \""}}]},"finish_reason":null}]}
576+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println(\\\""}}]},"finish_reason":null}]}
845
577
846− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"old_string\":"}}]},"finish_reason":null}]}
578+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello, World"}}]},"finish_reason":null}]}
847
579
848− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \"\\t"}}]},"finish_reason":null}]}
580+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\\")"}}]},"finish_reason":null}]}
849
581
850− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"fmt.Println(\\\""}}]},"finish_reason":null}]}
582+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}]"}}]},"finish_reason":null}]}
851
583
852− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello, World"}}]},"finish_reason":null}]}
584+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":", "}}]},"finish_reason":null}]}
853
585
854− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\\")"}}]},"finish_reason":null}]}
586+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"file_path\": \"/tmp"}}]},"finish_reason":null}]}
855
587
856− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}]"}}]},"finish_reason":null}]}
588+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/c"}}]},"finish_reason":null}]}
857
589
858− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":", "}}]},"finish_reason":null}]}
590+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"rush"}}]},"finish_reason":null}]}
859
591
860− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"file_path\": "}}]},"finish_reason":null}]}
592+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}]}
861
593
862− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/tmp/c"}}]},"finish_reason":null}]}
594+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}]}
863
595
864− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"rush"}}]},"finish_reason":null}]}
596+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}]}
865
597
866− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test/Test"}}]},"finish_reason":null}]}
598+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent/g"}}]},"finish_reason":null}]}
867
599
868− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}]}
600+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"lm-"}}]},"finish_reason":null}]}
869
601
870− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}]}
602+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5."}}]},"finish_reason":null}]}
871
603
872− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/glm"}}]},"finish_reason":null}]}
604+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"1/m"}}]},"finish_reason":null}]}
873
605
874− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-5"}}]},"finish_reason":null}]}
606+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ultied"}}]},"finish_reason":null}]}
875
607
876− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".1"}}]},"finish_reason":null}]}
608+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"it"}}]},"finish_reason":null}]}
877
609
878− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/mult"}}]},"finish_reason":null}]}
610+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool/main"}}]},"finish_reason":null}]}
879
611
880− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"iedit"}}]},"finish_reason":null}]}
612+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go\""}}]},"finish_reason":null}]}
881
613
882− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool/main"}}]},"finish_reason":null}]}
614+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
883
615
884− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go\""}}]},"finish_reason":null}]}
616+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
885
617
886− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
618+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":843,"completion_tokens":76,"total_tokens":7959,"prompt_tokens_details":{"cached_tokens":7040},"completion_tokens_details":{"reasoning_tokens":75}}}
887−
888− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
889−
890− data: {"id":"chatcmpl-a69a664769bb94eb14ee9e5d","object":"chat.completion.chunk","created":1778601751,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7879,"completion_tokens":95,"total_tokens":7974,"completion_tokens_details":{"reasoning_tokens":94}}}
891
619
892 data: [DONE]
620 data: [DONE]
893
621
@@ -896,121 +624,15 @@ interactions:
896 - text/event-stream
624 - text/event-stream
897 status: 200 OK
625 status: 200 OK
898 code: 200
626 code: 200
899− duration: 2.000582291s
627+ duration: 3.67935125s
900- id: 3
628- id: 3
901 request:
629 request:
902 proto: HTTP/1.1
630 proto: HTTP/1.1
903 proto_major: 1
631 proto_major: 1
904 proto_minor: 1
632 proto_minor: 1
905− content_length: 35017
633+ content_length: 34922
906− host: ""
907− 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/multiedit_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\",\"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 multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_813fe8edde9041c18e85fd3c\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"Let me first read the main.go file to see its current contents.\"},{\"content\":\"<file>\\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</file>\\n\",\"tool_call_id\":\"call_813fe8edde9041c18e85fd3c\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_c18af77e70014616b852dd7f\",\"function\":{\"arguments\":\"{\\\"edits\\\": [{\\\"new_string\\\": \\\"Hello, Crush!\\\", \\\"old_string\\\": \\\"Hello, World!\\\"}, {\\\"new_string\\\": \\\"\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\", \\\"old_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\"}], \\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"multiedit\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"\"},{\"content\":\"<result>\\nApplied 1 of 2 edits to file: /tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go (1 edit(s) failed)\\n</result>\\n\",\"tool_call_id\":\"call_c18af77e70014616b852dd7f\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
908− headers:
909− Accept:
910− - application/json
911− Content-Type:
912− - application/json
913− User-Agent:
914− - Charm-Crush/devel (https://charm.land/crush)
915− url: https://hyper.charm.land/v1/chat/completions
916− method: POST
917− response:
918− proto: HTTP/2.0
919− proto_major: 2
920− proto_minor: 0
921− content_length: -1
922− uncompressed: true
923− body: |+
924− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
925−
926− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"The"},"finish_reason":null}]}
927−
928− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" first edit"},"finish_reason":null}]}
929−
930− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" changed"},"finish_reason":null}]}
931−
932− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" the"},"finish_reason":null}]}
933−
934− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" string, which"},"finish_reason":null}]}
935−
936− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" made"},"finish_reason":null}]}
937−
938− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" the second"},"finish_reason":null}]}
939−
940− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" edit"},"finish_reason":null}]}
941−
942− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"'s old"},"finish_reason":null}]}
943−
944− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"_string"},"finish_reason":null}]}
945−
946− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" not"},"finish_reason":null}]}
947−
948− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" match. Let"},"finish_reason":null}]}
949−
950− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" me re"},"finish_reason":null}]}
951−
952− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"-read and"},"finish_reason":null}]}
953−
954− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" fix"},"finish_reason":null}]}
955−
956− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"."},"finish_reason":null}]}
957−
958− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_72491b955eb045b08f557741","type":"function","index":0,"function":{"name":"view","arguments":""}}]},"finish_reason":null}]}
959−
960− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
961−
962− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
963−
964− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"file_path\": "}}]},"finish_reason":null}]}
965−
966− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/tmp/c"}}]},"finish_reason":null}]}
967−
968− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"rush-test"}}]},"finish_reason":null}]}
969−
970− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}]}
971−
972− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}]}
973−
974− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent/g"}}]},"finish_reason":null}]}
975−
976− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"lm-"}}]},"finish_reason":null}]}
977−
978− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5."}}]},"finish_reason":null}]}
979−
980− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"1/m"}}]},"finish_reason":null}]}
981−
982− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ult"}}]},"finish_reason":null}]}
983−
984− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ied"}}]},"finish_reason":null}]}
985−
986− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"it_tool"}}]},"finish_reason":null}]}
987−
988− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main.go"}}]},"finish_reason":null}]}
989−
990− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\""}}]},"finish_reason":null}]}
991−
992− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
993−
994− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
995−
996− data: {"id":"chatcmpl-2edb4a948db2acecbbcac1b7","object":"chat.completion.chunk","created":1778601756,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":8022,"completion_tokens":56,"total_tokens":8078,"completion_tokens_details":{"reasoning_tokens":55}}}
997−
998− data: [DONE]
999−
1000− headers:
1001− Content-Type:
1002− - text/event-stream
1003− status: 200 OK
1004− code: 200
1005− duration: 3.717709083s
1006−- id: 4
1007− request:
1008− proto: HTTP/1.1
1009− proto_major: 1
1010− proto_minor: 1
1011− content_length: 35607
1012 host: ""
634 host: ""
1013− 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/multiedit_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\",\"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 multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_813fe8edde9041c18e85fd3c\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"Let me first read the main.go file to see its current contents.\"},{\"content\":\"<file>\\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</file>\\n\",\"tool_call_id\":\"call_813fe8edde9041c18e85fd3c\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_c18af77e70014616b852dd7f\",\"function\":{\"arguments\":\"{\\\"edits\\\": [{\\\"new_string\\\": \\\"Hello, Crush!\\\", \\\"old_string\\\": \\\"Hello, World!\\\"}, {\\\"new_string\\\": \\\"\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\", \\\"old_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\"}], \\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"multiedit\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"\"},{\"content\":\"<result>\\nApplied 1 of 2 edits to file: /tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go (1 edit(s) failed)\\n</result>\\n\",\"tool_call_id\":\"call_c18af77e70014616b852dd7f\",\"role\":\"tool\"},{\"content\":\"The first edit changed the string, which made the second edit's old_string not match. Let me re-read and fix.\",\"tool_calls\":[{\"id\":\"call_72491b955eb045b08f557741\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, Crush!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"call_72491b955eb045b08f557741\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
635+ 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/multiedit_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\",\"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 multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_fc1d5e25b1c14cb68be5d476\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"Let me first read the file to see its current contents.\"},{\"content\":\"<file>\\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 8|\\n</file>\\n\",\"tool_call_id\":\"call_fc1d5e25b1c14cb68be5d476\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_9dfbb4b9cd7a4af3881b997b\",\"function\":{\"arguments\":\"{\\\"edits\\\": [{\\\"new_string\\\": \\\"\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\", \\\"old_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\"}], \\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"multiedit\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"\"},{\"content\":\"<result>\\nApplied 1 edits to file: /tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\n</result>\\n\",\"tool_call_id\":\"call_9dfbb4b9cd7a4af3881b997b\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
1014 headers:
636 headers:
1015 Accept:
637 Accept:
1016 - application/json
638 - application/json
@@ -1027,131 +649,53 @@ interactions:
1027 content_length: -1
649 content_length: -1
1028 uncompressed: true
650 uncompressed: true
1029 body: |+
651 body: |+
1030− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
652+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
1031−
1032− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_e5a1488c26a84022bb580a81","type":"function","index":0,"function":{"name":"edit","arguments":""}}]},"finish_reason":null}]}
1033−
1034− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
1035−
1036− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
1037−
1038− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"file_path\": \"/tmp"}}]},"finish_reason":null}]}
1039−
1040− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/c"}}]},"finish_reason":null}]}
1041−
1042− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"rush-test"}}]},"finish_reason":null}]}
1043−
1044− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}]}
1045−
1046− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}]}
1047−
1048− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent/g"}}]},"finish_reason":null}]}
1049−
1050− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"lm-"}}]},"finish_reason":null}]}
1051−
1052− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5.1/m"}}]},"finish_reason":null}]}
1053−
1054− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ultiedit_tool"}}]},"finish_reason":null}]}
1055−
1056− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main.go\""}}]},"finish_reason":null}]}
1057−
1058− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":", "}}]},"finish_reason":null}]}
1059−
1060− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"new_string\": "}}]},"finish_reason":null}]}
1061−
1062− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"\\t// G"}}]},"finish_reason":null}]}
1063−
1064− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"reeting\\n\\tfmt"}}]},"finish_reason":null}]}
1065−
1066− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println(\\\"Hello"}}]},"finish_reason":null}]}
1067−
1068− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":", Crush"}}]},"finish_reason":null}]}
1069−
1070− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\\")\", "}}]},"finish_reason":null}]}
1071
653
1072− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"old_string\": "}}]},"finish_reason":null}]}
654+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Both"},"finish_reason":null}]}
1073
655
1074− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"\\tfmt"}}]},"finish_reason":null}]}
656+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" changes applied"},"finish_reason":null}]}
1075
657
1076− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println(\\\"Hello,"}}]},"finish_reason":null}]}
658+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" in a"},"finish_reason":null}]}
1077
659
1078− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" Crush!\\\")"}}]},"finish_reason":null}]}
660+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" single mult"},"finish_reason":null}]}
1079
661
1080− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\""}}]},"finish_reason":null}]}
662+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"ied"},"finish_reason":null}]}
1081
663
1082− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
664+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"it"},"finish_reason":null}]}
1083−
1084− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
1085−
1086− data: {"id":"chatcmpl-d163029b902928d9f8c7e6da","object":"chat.completion.chunk","created":1778601763,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":8134,"completion_tokens":62,"total_tokens":8196,"completion_tokens_details":{"reasoning_tokens":61}}}
1087−
1088− data: [DONE]
1089−
1090− headers:
1091− Content-Type:
1092− - text/event-stream
1093− status: 200 OK
1094− code: 200
1095− duration: 4.809219875s
1096−- id: 5
1097− request:
1098− proto: HTTP/1.1
1099− proto_major: 1
1100− proto_minor: 1
1101− content_length: 36168
1102− host: ""
1103− 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/multiedit_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\",\"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 multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_813fe8edde9041c18e85fd3c\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"Let me first read the main.go file to see its current contents.\"},{\"content\":\"<file>\\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</file>\\n\",\"tool_call_id\":\"call_813fe8edde9041c18e85fd3c\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_c18af77e70014616b852dd7f\",\"function\":{\"arguments\":\"{\\\"edits\\\": [{\\\"new_string\\\": \\\"Hello, Crush!\\\", \\\"old_string\\\": \\\"Hello, World!\\\"}, {\\\"new_string\\\": \\\"\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\", \\\"old_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\"}], \\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"multiedit\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"\"},{\"content\":\"<result>\\nApplied 1 of 2 edits to file: /tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go (1 edit(s) failed)\\n</result>\\n\",\"tool_call_id\":\"call_c18af77e70014616b852dd7f\",\"role\":\"tool\"},{\"content\":\"The first edit changed the string, which made the second edit's old_string not match. Let me re-read and fix.\",\"tool_calls\":[{\"id\":\"call_72491b955eb045b08f557741\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, Crush!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"call_72491b955eb045b08f557741\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_e5a1488c26a84022bb580a81\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\", \\\"new_string\\\": \\\"\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\", \\\"old_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\"}\",\"name\":\"edit\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"\"},{\"content\":\"<result>\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\n</result>\\n\",\"tool_call_id\":\"call_e5a1488c26a84022bb580a81\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
1104− headers:
1105− Accept:
1106− - application/json
1107− Content-Type:
1108− - application/json
1109− User-Agent:
1110− - Charm-Crush/devel (https://charm.land/crush)
1111− url: https://hyper.charm.land/v1/chat/completions
1112− method: POST
1113− response:
1114− proto: HTTP/2.0
1115− proto_major: 2
1116− proto_minor: 0
1117− content_length: -1
1118− uncompressed: true
1119− body: |+
1120− data: {"id":"chatcmpl-2b5097e0950d1e7e3132f1fd","object":"chat.completion.chunk","created":1778601766,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
1121
665
1122− data: {"id":"chatcmpl-2b5097e0950d1e7e3132f1fd","object":"chat.completion.chunk","created":1778601766,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Done"},"finish_reason":null}]}
666+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":":\n\n"},"finish_reason":null}]}
1123
667
1124− data: {"id":"chatcmpl-2b5097e0950d1e7e3132f1fd","object":"chat.completion.chunk","created":1778601766,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" —"},"finish_reason":null}]}
668+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"- `\""},"finish_reason":null}]}
1125
669
1126− data: {"id":"chatcmpl-2b5097e0950d1e7e3132f1fd","object":"chat.completion.chunk","created":1778601766,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" both changes"},"finish_reason":null}]}
670+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}
1127
671
1128− data: {"id":"chatcmpl-2b5097e0950d1e7e3132f1fd","object":"chat.completion.chunk","created":1778601766,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" applied"},"finish_reason":null}]}
672+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":", World"},"finish_reason":null}]}
1129
673
1130− data: {"id":"chatcmpl-2b5097e0950d1e7e3132f1fd","object":"chat.completion.chunk","created":1778601766,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":": `\""},"finish_reason":null}]}
674+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"!\"`"},"finish_reason":null}]}
1131
675
1132− data: {"id":"chatcmpl-2b5097e0950d1e7e3132f1fd","object":"chat.completion.chunk","created":1778601766,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Hello, World"},"finish_reason":null}]}
676+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" → `\""},"finish_reason":null}]}
1133
677
1134− data: {"id":"chatcmpl-2b5097e0950d1e7e3132f1fd","object":"chat.completion.chunk","created":1778601766,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"!\"` →"},"finish_reason":null}]}
678+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Hello, Crush"},"finish_reason":null}]}
1135
679
1136− data: {"id":"chatcmpl-2b5097e0950d1e7e3132f1fd","object":"chat.completion.chunk","created":1778601766,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `\"Hello, Crush"},"finish_reason":null}]}
680+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"!\"`\n- Added"},"finish_reason":null}]}
1137
681
1138− data: {"id":"chatcmpl-2b5097e0950d1e7e3132f1fd","object":"chat.completion.chunk","created":1778601766,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"!\"` and `"},"finish_reason":null}]}
682+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `//"},"finish_reason":null}]}
1139
683
1140− data: {"id":"chatcmpl-2b5097e0950d1e7e3132f1fd","object":"chat.completion.chunk","created":1778601766,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"// G"},"finish_reason":null}]}
684+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" G"},"finish_reason":null}]}
1141
685
1142− data: {"id":"chatcmpl-2b5097e0950d1e7e3132f1fd","object":"chat.completion.chunk","created":1778601766,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"reeting` comment"},"finish_reason":null}]}
686+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"reeting"},"finish_reason":null}]}
1143
687
1144− data: {"id":"chatcmpl-2b5097e0950d1e7e3132f1fd","object":"chat.completion.chunk","created":1778601766,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" added"},"finish_reason":null}]}
688+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"` comment"},"finish_reason":null}]}
1145
689
1146− data: {"id":"chatcmpl-2b5097e0950d1e7e3132f1fd","object":"chat.completion.chunk","created":1778601766,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" above the `"},"finish_reason":null}]}
690+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" above `"},"finish_reason":null}]}
1147
691
1148− data: {"id":"chatcmpl-2b5097e0950d1e7e3132f1fd","object":"chat.completion.chunk","created":1778601766,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"fmt.Println` line"},"finish_reason":null}]}
692+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"fmt.Println"},"finish_reason":null}]}
1149
693
1150− data: {"id":"chatcmpl-2b5097e0950d1e7e3132f1fd","object":"chat.completion.chunk","created":1778601766,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"."},"finish_reason":null}]}
694+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`"},"finish_reason":null}]}
1151
695
1152− data: {"id":"chatcmpl-2b5097e0950d1e7e3132f1fd","object":"chat.completion.chunk","created":1778601766,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
696+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
1153
697
1154− data: {"id":"chatcmpl-2b5097e0950d1e7e3132f1fd","object":"chat.completion.chunk","created":1778601766,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":8233,"completion_tokens":37,"total_tokens":8270,"completion_tokens_details":{"reasoning_tokens":36}}}
698+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":126,"completion_tokens":39,"total_tokens":8037,"prompt_tokens_details":{"cached_tokens":7872},"completion_tokens_details":{"reasoning_tokens":38}}}
1155
699
1156 data: [DONE]
700 data: [DONE]
1157
701
@@ -1160,4 +704,4 @@ interactions:
1160 - text/event-stream
704 - text/event-stream
1161 status: 200 OK
705 status: 200 OK
1162 code: 200
706 code: 200
1163− duration: 2.961048333s
707+ duration: 2.673102083s
internal/agent/testdata/TestCoderAgent/glm-5.1/parallel_tool_calls.yaml+318−284
@@ -25,499 +25,471 @@ interactions:
25 content_length: -1
25 content_length: -1
26 uncompressed: true
26 uncompressed: true
27 body: |+
27 body: |+
28− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
28+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
29
29
30− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
30+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
31
31
32− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
32+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
33
33
34− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" says"},"finish_reason":null}]}
34+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" wants"},"finish_reason":null}]}
35
35
36− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
36+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
37
37
38− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
38+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
39
39
40− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Generate"},"finish_reason":null}]}
40+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
41
41
42− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
42+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" summar"},"finish_reason":null}]}
43
43
44− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
44+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"izing"},"finish_reason":null}]}
45
45
46− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
46+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
47
47
48− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
48+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
49
49
50− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
50+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
51
51
52− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" following"},"finish_reason":null}]}
52+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
53
53
54− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
54+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"use"},"finish_reason":null}]}
55
55
56− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":\n\n"},"finish_reason":null}]}
56+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" glob"},"finish_reason":null}]}
57
57
58− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"use"},"finish_reason":null}]}
58+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
59
59
60− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" glob"},"finish_reason":null}]}
60+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" find"},"finish_reason":null}]}
61
61
62− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
62+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" all"},"finish_reason":null}]}
63
63
64− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" find"},"finish_reason":null}]}
64+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ."},"finish_reason":null}]}
65
65
66− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" all"},"finish_reason":null}]}
66+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"go"},"finish_reason":null}]}
67
67
68− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ."},"finish_reason":null}]}
68+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
69
69
70− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"go"},"finish_reason":null}]}
70+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
71
71
72− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
72+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" use"},"finish_reason":null}]}
73
73
74− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
74+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ls"},"finish_reason":null}]}
75
75
76− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" use"},"finish_reason":null}]}
76+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
77
77
78− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ls"},"finish_reason":null}]}
78+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" list"},"finish_reason":null}]}
79
79
80− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
80+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
81
81
82− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" list"},"finish_reason":null}]}
82+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" current"},"finish_reason":null}]}
83
83
84− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
84+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" directory"},"finish_reason":null}]}
85
85
86− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" current"},"finish_reason":null}]}
86+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
87
87
88− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" directory"},"finish_reason":null}]}
88+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" it"},"finish_reason":null}]}
89
89
90− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
90+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" is"},"finish_reason":null}]}
91
91
92− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" it"},"finish_reason":null}]}
92+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" very"},"finish_reason":null}]}
93
93
94− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" is"},"finish_reason":null}]}
94+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" important"},"finish_reason":null}]}
95
95
96− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" very"},"finish_reason":null}]}
96+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that"},"finish_reason":null}]}
97
97
98− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" important"},"finish_reason":null}]}
98+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" you"},"finish_reason":null}]}
99
99
100− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that"},"finish_reason":null}]}
100+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" run"},"finish_reason":null}]}
101
101
102− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" you"},"finish_reason":null}]}
102+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" both"},"finish_reason":null}]}
103
103
104− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" run"},"finish_reason":null}]}
104+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" tool"},"finish_reason":null}]}
105
105
106− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" both"},"finish_reason":null}]}
106+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" calls"},"finish_reason":null}]}
107
107
108− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" tool"},"finish_reason":null}]}
108+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
109
109
110− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" calls"},"finish_reason":null}]}
110+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" parallel"},"finish_reason":null}]}
111
111
112− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
112+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
113
113
114− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" parallel"},"finish_reason":null}]}
114+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Must"},"finish_reason":null}]}
115
115
116− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
116+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
117
117
118− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" So"},"finish_reason":null}]}
118+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" up"},"finish_reason":null}]}
119
119
120− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" need"},"finish_reason":null}]}
120+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
121
121
122− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
122+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
123
123
124− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
124+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
125
125
126− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" summar"},"finish_reason":null}]}
126+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
127
127
128− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"izing"},"finish_reason":null}]}
128+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
129
129
130− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that"},"finish_reason":null}]}
130+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" one"},"finish_reason":null}]}
131
131
132− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
132+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
133
133
134− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Language"},"finish_reason":null}]}
134+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
135
135
136− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" English"},"finish_reason":null}]}
136+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" no"},"finish_reason":null}]}
137
137
138− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
138+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
139
139
140− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Title"},"finish_reason":null}]}
140+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
141
141
142− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \u003c="},"finish_reason":null}]}
142+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" no"},"finish_reason":null}]}
143
143
144− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
144+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" colon"},"finish_reason":null}]}
145
145
146− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
146+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
147
147
148− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
148+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Should"},"finish_reason":null}]}
149
149
150− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Something"},"finish_reason":null}]}
150+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
151
151
152− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" like"},"finish_reason":null}]}
152+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
153
153
154− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
154+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" English"},"finish_reason":null}]}
155
155
156− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Parallel"},"finish_reason":null}]}
156+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
157
157
158− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Glob"},"finish_reason":null}]}
158+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"the"},"finish_reason":null}]}
159
159
160− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ."},"finish_reason":null}]}
160+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
161
161
162− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"go"},"finish_reason":null}]}
162+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" wrote"},"finish_reason":null}]}
163
163
164− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Search"},"finish_reason":null}]}
164+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" English"},"finish_reason":null}]}
165
165
166− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
166+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")."},"finish_reason":null}]}
167
167
168− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Directory"},"finish_reason":null}]}
168+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Title"},"finish_reason":null}]}
169
169
170− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Listing"},"finish_reason":null}]}
170+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" could"},"finish_reason":null}]}
171
171
172− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
172+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
173
173
174− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
174+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
175
175
176− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
176+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
177
177
178− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
178+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Parallel"},"finish_reason":null}]}
179
179
180− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
180+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" glob"},"finish_reason":null}]}
181
181
182− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Parallel"},"finish_reason":null}]}
182+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
183
183
184− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Glob"},"finish_reason":null}]}
184+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ."},"finish_reason":null}]}
185
185
186− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ."},"finish_reason":null}]}
186+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"go"},"finish_reason":null}]}
187
187
188− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"go"},"finish_reason":null}]}
188+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
189
189
190− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Search"},"finish_reason":null}]}
190+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
191
191
192− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
192+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ls"},"finish_reason":null}]}
193
193
194− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Directory"},"finish_reason":null}]}
194+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" directory"},"finish_reason":null}]}
195
195
196− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Listing"},"finish_reason":null}]}
196+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
197
197
198− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
198+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
199
199
200− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ="},"finish_reason":null}]}
200+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
201
201
202− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" let's"},"finish_reason":null}]}
202+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
203
203
204− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
204+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Let's"},"finish_reason":null}]}
205
205
206− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
206+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
207
207
208− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Parallel"},"finish_reason":null}]}
208+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
209
209
210− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
210+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
211
211
212− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"8"},"finish_reason":null}]}
212+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Parallel"},"finish_reason":null}]}
213
213
214− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
214+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" glob"},"finish_reason":null}]}
215
215
216− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" +"},"finish_reason":null}]}
216+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
217
217
218− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
218+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ."},"finish_reason":null}]}
219
219
220− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
220+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"go"},"finish_reason":null}]}
221
221
222− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
222+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" files"},"finish_reason":null}]}
223
223
224− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"9"},"finish_reason":null}]}
224+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
225
225
226− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
226+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ls"},"finish_reason":null}]}
227
227
228− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Glob"},"finish_reason":null}]}
228+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" directory"},"finish_reason":null}]}
229
229
230− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
230+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
231
231
232− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
232+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
233
233
234− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
234+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
235
235
236− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"13"},"finish_reason":null}]}
236+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"44"},"finish_reason":null}]}
237
237
238− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
238+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
239
239
240− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
240+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"?"},"finish_reason":null}]}
241
241
242− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
242+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Let's"},"finish_reason":null}]}
243
243
244− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"14"},"finish_reason":null}]}
244+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
245
245
246− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
246+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" precisely"},"finish_reason":null}]}
247
247
248− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ."},"finish_reason":null}]}
248+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
249
249
250− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"go"},"finish_reason":null}]}
250+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" P"},"finish_reason":null}]}
251
251
252− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
252+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
253
253
254− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
254+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
255
255
256− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
256+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")a"},"finish_reason":null}]}
257
257
258− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"17"},"finish_reason":null}]}
258+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
259
259
260− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
260+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"r"},"finish_reason":null}]}
261
261
262− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
262+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
263
263
264− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
264+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"a"},"finish_reason":null}]}
265
265
266− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"18"},"finish_reason":null}]}
266+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
267
267
268− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
268+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"l"},"finish_reason":null}]}
269
269
270− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Search"},"finish_reason":null}]}
270+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
271
271
272− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
272+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"l"},"finish_reason":null}]}
273
273
274− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
274+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
275
275
276− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
276+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"e"},"finish_reason":null}]}
277
277
278− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"24"},"finish_reason":null}]}
278+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
279
279
280− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
280+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"l"},"finish_reason":null}]}
281
281
282− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
282+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"8"},"finish_reason":null}]}
283
283
284− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
284+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
285
285
286− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"25"},"finish_reason":null}]}
286+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"space"},"finish_reason":null}]}
287
287
288− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
288+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
289
289
290− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
290+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"9"},"finish_reason":null}]}
291
291
292− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
292+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
293
293
294− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
294+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" g"},"finish_reason":null}]}
295
295
296− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
296+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"10"},"finish_reason":null}]}
297
297
298− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"28"},"finish_reason":null}]}
298+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"l"},"finish_reason":null}]}
299
299
300− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
300+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"11"},"finish_reason":null}]}
301
301
302− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
302+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"o"},"finish_reason":null}]}
303
303
304− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
304+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"12"},"finish_reason":null}]}
305
305
306− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"29"},"finish_reason":null}]}
306+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"b"},"finish_reason":null}]}
307
307
308− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
308+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"13"},"finish_reason":null}]}
309
309
310− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Directory"},"finish_reason":null}]}
310+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
311
311
312− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
312+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"space"},"finish_reason":null}]}
313
313
314− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"9"},"finish_reason":null}]}
314+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"14"},"finish_reason":null}]}
315
315
316− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
316+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
317
317
318− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"38"},"finish_reason":null}]}
318+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" f"},"finish_reason":null}]}
319
319
320− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
320+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"15"},"finish_reason":null}]}
321
321
322− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
322+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"o"},"finish_reason":null}]}
323
323
324− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
324+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"16"},"finish_reason":null}]}
325
325
326− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"39"},"finish_reason":null}]}
326+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"r"},"finish_reason":null}]}
327
327
328− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
328+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"17"},"finish_reason":null}]}
329
329
330− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Listing"},"finish_reason":null}]}
330+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
331
331
332− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
332+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"space"},"finish_reason":null}]}
333
333
334− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
334+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"18"},"finish_reason":null}]}
335
335
336− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
336+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
337
337
338− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"46"},"finish_reason":null}]}
338+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ."},"finish_reason":null}]}
339
339
340− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
340+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"19"},"finish_reason":null}]}
341
341
342− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" So"},"finish_reason":null}]}
342+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"g"},"finish_reason":null}]}
343
343
344− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
344+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"20"},"finish_reason":null}]}
345
345
346− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"46"},"finish_reason":null}]}
346+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"o"},"finish_reason":null}]}
347
347
348− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
348+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"21"},"finish_reason":null}]}
349
349
350− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
350+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
351
351
352− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" okay"},"finish_reason":null}]}
352+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"space"},"finish_reason":null}]}
353
353
354− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".\n\n"},"finish_reason":null}]}
354+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"22"},"finish_reason":null}]}
355
355
356− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"No"},"finish_reason":null}]}
356+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
357
357
358− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
358+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" f"},"finish_reason":null}]}
359
359
360− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
360+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"23"},"finish_reason":null}]}
361
361
362− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" One"},"finish_reason":null}]}
362+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"i"},"finish_reason":null}]}
363
363
364− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
364+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"24"},"finish_reason":null}]}
365
365
366− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".\n\n"},"finish_reason":null}]}
366+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"l"},"finish_reason":null}]}
367
367
368− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Return"},"finish_reason":null}]}
368+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"25"},"finish_reason":null}]}
369
369
370− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that"},"finish_reason":null}]}
370+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"e"},"finish_reason":null}]}
371
371
372− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
372+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"26"},"finish_reason":null}]}
373
373
374− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Parallel"},"finish_reason":null}]}
374+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"s"},"finish_reason":null}]}
375
375
376− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Glob"},"finish_reason":null}]}
376+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"27"},"finish_reason":null}]}
377
377
378− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" ."},"finish_reason":null}]}
378+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
379
379
380− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"go"},"finish_reason":null}]}
380+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"space"},"finish_reason":null}]}
381
381
382− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Search"},"finish_reason":null}]}
382+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"28"},"finish_reason":null}]}
383
383
384− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" and"},"finish_reason":null}]}
384+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
385
385
386− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Directory"},"finish_reason":null}]}
386+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
387
387
388− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Listing"},"finish_reason":null}]}
388+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"29"},"finish_reason":null}]}
389
389
390− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
390+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"n"},"finish_reason":null}]}
391
391
392− data: {"id":"chatcmpl-cb928907f856822f9bb954b1","object":"chat.completion.chunk","created":1778601795,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":40,"completion_tokens":190,"total_tokens":422,"prompt_tokens_details":{"cached_tokens":192}}}
392+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"30"},"finish_reason":null}]}
393
393
394− data: [DONE]
394+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"d"},"finish_reason":null}]}
395
395
396− headers:
396+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"31"},"finish_reason":null}]}
397− Content-Type:
398− - text/event-stream
399− status: 200 OK
400− code: 200
401− duration: 477.99625ms
402−- id: 1
403− request:
404− proto: HTTP/1.1
405− proto_major: 1
406− proto_minor: 1
407− content_length: 33821
408− host: ""
409− 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/parallel_tool_calls\\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\",\"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 and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
410− headers:
411− Accept:
412− - application/json
413− Content-Type:
414− - application/json
415− User-Agent:
416− - Charm-Crush/devel (https://charm.land/crush)
417− url: https://hyper.charm.land/v1/chat/completions
418− method: POST
419− response:
420− proto: HTTP/2.0
421− proto_major: 2
422− proto_minor: 0
423− content_length: -1
424− uncompressed: true
425− body: |+
426− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
427
397
428− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
398+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
429
399
430− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
400+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"space"},"finish_reason":null}]}
431
401
432− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" wants me"},"finish_reason":null}]}
402+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"32"},"finish_reason":null}]}
433
403
434− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" to run"},"finish_reason":null}]}
404+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
435
405
436− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" two independent"},"finish_reason":null}]}
406+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" l"},"finish_reason":null}]}
437
407
438− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" tool"},"finish_reason":null}]}
408+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"33"},"finish_reason":null}]}
439
409
440− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" calls"},"finish_reason":null}]}
410+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"s"},"finish_reason":null}]}
441
411
442− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" in parallel"},"finish_reason":null}]}
412+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"34 (space35) d36i37"},"finish_reason":null}]}
443
413
444− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":": glob"},"finish_reason":null}]}
414+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"r"},"finish_reason":null}]}
445
415
446− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
416+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"38"},"finish_reason":null}]}
447
417
448− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" find ."},"finish_reason":null}]}
418+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"e"},"finish_reason":null}]}
449
419
450− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"go files"},"finish_reason":null}]}
420+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"39"},"finish_reason":null}]}
451
421
452− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" and ls"},"finish_reason":null}]}
422+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"c"},"finish_reason":null}]}
453
423
454− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" to list"},"finish_reason":null}]}
424+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"40"},"finish_reason":null}]}
455
425
456− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" the current directory"},"finish_reason":null}]}
426+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"t"},"finish_reason":null}]}
457
427
458− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
428+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"41"},"finish_reason":null}]}
459
429
460− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_0f6894f9f61447448d4c4684","type":"function","index":0,"function":{"name":"glob","arguments":""}}]},"finish_reason":null}]}
430+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"o"},"finish_reason":null}]}
461
431
462− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
432+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"42"},"finish_reason":null}]}
463
433
464− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
434+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"r"},"finish_reason":null}]}
465
435
466− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"pattern\": "}}]},"finish_reason":null}]}
436+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"43"},"finish_reason":null}]}
467
437
468− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"**/*.go"}}]},"finish_reason":null}]}
438+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"y"},"finish_reason":null}]}
469
439
470− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\", "}}]},"finish_reason":null}]}
440+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"44"},"finish_reason":null}]}
471
441
472− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"path\": \"/tmp"}}]},"finish_reason":null}]}
442+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
473
443
474− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/c"}}]},"finish_reason":null}]}
444+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" So"},"finish_reason":null}]}
475
445
476− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"rush"}}]},"finish_reason":null}]}
446+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
477
447
478− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}]}
448+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"44"},"finish_reason":null}]}
479
449
480− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}]}
450+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
481
451
482− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}]}
452+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
483
453
484− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}]}
454+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" okay"},"finish_reason":null}]}
485
455
486− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/glm"}}]},"finish_reason":null}]}
456+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
487
457
488− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-5"}}]},"finish_reason":null}]}
458+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" No"},"finish_reason":null}]}
489
459
490− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".1/"}}]},"finish_reason":null}]}
460+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" colon"},"finish_reason":null}]}
491
461
492− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"parallel_tool"}}]},"finish_reason":null}]}
462+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".\n\n"},"finish_reason":null}]}
493
463
494− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_calls"}}]},"finish_reason":null}]}
464+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Return"},"finish_reason":null}]}
495
465
496− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\""}}]},"finish_reason":null}]}
466+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" just"},"finish_reason":null}]}
497
467
498− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
468+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that"},"finish_reason":null}]}
499
469
500− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_8f3552dac9144331b36f56d6","type":"function","index":1,"function":{"name":"ls","arguments":""}}]},"finish_reason":null}]}
470+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
501
471
502− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":""}}]},"finish_reason":null}]}
472+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Parallel"},"finish_reason":null}]}
503
473
504− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"{\"path\": "}}]},"finish_reason":null}]}
474+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" glob"},"finish_reason":null}]}
505
475
506− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"\"/tmp/crush-test"}}]},"finish_reason":null}]}
476+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" for"},"finish_reason":null}]}
507
477
508− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"/TestCoderAgent/g"}}]},"finish_reason":null}]}
478+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" ."},"finish_reason":null}]}
509
479
510− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"lm-5."}}]},"finish_reason":null}]}
480+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"go"},"finish_reason":null}]}
511
481
512− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"1/parallel_tool"}}]},"finish_reason":null}]}
482+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" files"},"finish_reason":null}]}
513
483
514− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"_calls\""}}]},"finish_reason":null}]}
484+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" and"},"finish_reason":null}]}
515
485
516− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"}"}}]},"finish_reason":null}]}
486+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" ls"},"finish_reason":null}]}
517
487
518− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
488+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" directory"},"finish_reason":null}]}
519
489
520− data: {"id":"chatcmpl-48fbb55262ca288daf4e9c41","object":"chat.completion.chunk","created":1778601801,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7787,"completion_tokens":87,"total_tokens":7874,"completion_tokens_details":{"reasoning_tokens":27}}}
490+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
491+
492+ data: {"id":"chatcmpl-d2af82d91579ef57f1558193","object":"chat.completion.chunk","created":1778603002,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":52,"completion_tokens":248,"total_tokens":476,"prompt_tokens_details":{"cached_tokens":176}}}
521
493
522 data: [DONE]
494 data: [DONE]
523
495
@@ -526,15 +498,15 @@ interactions:
526 - text/event-stream
498 - text/event-stream
527 status: 200 OK
499 status: 200 OK
528 code: 200
500 code: 200
529− duration: 6.487687083s
501+ duration: 452.108583ms
530−- id: 2
502+- id: 1
531 request:
503 request:
532 proto: HTTP/1.1
504 proto: HTTP/1.1
533 proto_major: 1
505 proto_major: 1
534 proto_minor: 1
506 proto_minor: 1
535− content_length: 34683
507+ content_length: 33821
536 host: ""
508 host: ""
537− 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/parallel_tool_calls\\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\",\"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 and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_0f6894f9f61447448d4c4684\",\"function\":{\"arguments\":\"{\\\"pattern\\\": \\\"**/*.go\\\", \\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/parallel_tool_calls\\\"}\",\"name\":\"glob\"},\"type\":\"function\"},{\"id\":\"call_8f3552dac9144331b36f56d6\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/parallel_tool_calls\\\"}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"The user wants me to run two independent tool calls in parallel: glob to find .go files and ls to list the current directory.\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/glm-5.1/parallel_tool_calls/main.go\",\"tool_call_id\":\"call_0f6894f9f61447448d4c4684\",\"role\":\"tool\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/glm-5.1/parallel_tool_calls/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_8f3552dac9144331b36f56d6\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
509+ 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/parallel_tool_calls\\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\",\"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 and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
538 headers:
510 headers:
539 Accept:
511 Accept:
540 - application/json
512 - application/json
@@ -551,39 +523,101 @@ interactions:
551 content_length: -1
523 content_length: -1
552 uncompressed: true
524 uncompressed: true
553 body: |+
525 body: |+
554− data: {"id":"chatcmpl-25fded183d7a9936dd525fb3","object":"chat.completion.chunk","created":1778601816,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
526+ data: {"id":"chatcmpl-bc3822d8f82041eddd5dd9fc","object":"chat.completion.chunk","created":1778603004,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
527+
528+ data: {"id":"chatcmpl-bc3822d8f82041eddd5dd9fc","object":"chat.completion.chunk","created":1778603004,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
529+
530+ data: {"id":"chatcmpl-bc3822d8f82041eddd5dd9fc","object":"chat.completion.chunk","created":1778603004,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" user wants"},"finish_reason":null}]}
531+
532+ data: {"id":"chatcmpl-bc3822d8f82041eddd5dd9fc","object":"chat.completion.chunk","created":1778603004,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" me"},"finish_reason":null}]}
533+
534+ data: {"id":"chatcmpl-bc3822d8f82041eddd5dd9fc","object":"chat.completion.chunk","created":1778603004,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" to run"},"finish_reason":null}]}
535+
536+ data: {"id":"chatcmpl-bc3822d8f82041eddd5dd9fc","object":"chat.completion.chunk","created":1778603004,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" both glob"},"finish_reason":null}]}
555
537
556− data: {"id":"chatcmpl-25fded183d7a9936dd525fb3","object":"chat.completion.chunk","created":1778601816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}]}
538+ data: {"id":"chatcmpl-bc3822d8f82041eddd5dd9fc","object":"chat.completion.chunk","created":1778603004,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" and ls"},"finish_reason":null}]}
557
539
558− data: {"id":"chatcmpl-25fded183d7a9936dd525fb3","object":"chat.completion.chunk","created":1778601816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" **G"},"finish_reason":null}]}
540+ data: {"id":"chatcmpl-bc3822d8f82041eddd5dd9fc","object":"chat.completion.chunk","created":1778603004,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" in parallel"},"finish_reason":null}]}
559
541
560− data: {"id":"chatcmpl-25fded183d7a9936dd525fb3","object":"chat.completion.chunk","created":1778601816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"lob**:"},"finish_reason":null}]}
542+ data: {"id":"chatcmpl-bc3822d8f82041eddd5dd9fc","object":"chat.completion.chunk","created":1778603004,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
543+
544+ data: {"id":"chatcmpl-bc3822d8f82041eddd5dd9fc","object":"chat.completion.chunk","created":1778603004,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"tool-b12997836ec947bc8b6de0071cc64ba1","type":"function","index":0,"function":{"name":"glob","arguments":""}}]},"finish_reason":null}]}
545+
546+ data: {"id":"chatcmpl-bc3822d8f82041eddd5dd9fc","object":"chat.completion.chunk","created":1778603004,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
547+
548+ data: {"id":"chatcmpl-bc3822d8f82041eddd5dd9fc","object":"chat.completion.chunk","created":1778603004,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"pattern\": \""}}]},"finish_reason":null}]}
549+
550+ data: {"id":"chatcmpl-bc3822d8f82041eddd5dd9fc","object":"chat.completion.chunk","created":1778603004,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"**/*.go\""}}]},"finish_reason":null}]}
551+
552+ data: {"id":"chatcmpl-bc3822d8f82041eddd5dd9fc","object":"chat.completion.chunk","created":1778603004,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
553+
554+ data: {"id":"chatcmpl-bc3822d8f82041eddd5dd9fc","object":"chat.completion.chunk","created":1778603004,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"tool-b58136b989994c80a12671914bc5955a","type":"function","index":1,"function":{"name":"ls","arguments":""}}]},"finish_reason":null}]}
555+
556+ data: {"id":"chatcmpl-bc3822d8f82041eddd5dd9fc","object":"chat.completion.chunk","created":1778603004,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"{}"}}]},"finish_reason":null}]}
557+
558+ data: {"id":"chatcmpl-bc3822d8f82041eddd5dd9fc","object":"chat.completion.chunk","created":1778603004,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
559+
560+ data: {"id":"chatcmpl-bc3822d8f82041eddd5dd9fc","object":"chat.completion.chunk","created":1778603004,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7787,"completion_tokens":29,"total_tokens":7816,"completion_tokens_details":{"reasoning_tokens":13}}}
561+
562+ data: [DONE]
563+
564+ headers:
565+ Content-Type:
566+ - text/event-stream
567+ status: 200 OK
568+ code: 200
569+ duration: 3.282010458s
570+- id: 2
571+ request:
572+ proto: HTTP/1.1
573+ proto_major: 1
574+ proto_minor: 1
575+ content_length: 34498
576+ host: ""
577+ 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/parallel_tool_calls\\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\",\"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 and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"tool-b12997836ec947bc8b6de0071cc64ba1\",\"function\":{\"arguments\":\"{\\\"pattern\\\": \\\"**/*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"},{\"id\":\"tool-b58136b989994c80a12671914bc5955a\",\"function\":{\"arguments\":\"{}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"The user wants me to run both glob and ls in parallel.\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/glm-5.1/parallel_tool_calls/main.go\",\"tool_call_id\":\"tool-b12997836ec947bc8b6de0071cc64ba1\",\"role\":\"tool\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/glm-5.1/parallel_tool_calls/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"tool-b58136b989994c80a12671914bc5955a\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
578+ headers:
579+ Accept:
580+ - application/json
581+ Content-Type:
582+ - application/json
583+ User-Agent:
584+ - Charm-Crush/devel (https://charm.land/crush)
585+ url: https://hyper.charm.land/v1/chat/completions
586+ method: POST
587+ response:
588+ proto: HTTP/2.0
589+ proto_major: 2
590+ proto_minor: 0
591+ content_length: -1
592+ uncompressed: true
593+ body: |+
594+ data: {"id":"chatcmpl-64d4e9ac2b579005483df8b6","object":"chat.completion.chunk","created":1778603013,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
561
595
562− data: {"id":"chatcmpl-25fded183d7a9936dd525fb3","object":"chat.completion.chunk","created":1778601816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" One"},"finish_reason":null}]}
596+ data: {"id":"chatcmpl-64d4e9ac2b579005483df8b6","object":"chat.completion.chunk","created":1778603013,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Fou"},"finish_reason":null}]}
563
597
564− data: {"id":"chatcmpl-25fded183d7a9936dd525fb3","object":"chat.completion.chunk","created":1778601816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `."},"finish_reason":null}]}
598+ data: {"id":"chatcmpl-64d4e9ac2b579005483df8b6","object":"chat.completion.chunk","created":1778603013,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"nd 1 `"},"finish_reason":null}]}
565
599
566− data: {"id":"chatcmpl-25fded183d7a9936dd525fb3","object":"chat.completion.chunk","created":1778601816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"go`"},"finish_reason":null}]}
600+ data: {"id":"chatcmpl-64d4e9ac2b579005483df8b6","object":"chat.completion.chunk","created":1778603013,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":".g"},"finish_reason":null}]}
567
601
568− data: {"id":"chatcmpl-25fded183d7a9936dd525fb3","object":"chat.completion.chunk","created":1778601816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" file found: `"},"finish_reason":null}]}
602+ data: {"id":"chatcmpl-64d4e9ac2b579005483df8b6","object":"chat.completion.chunk","created":1778603013,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"o` file"},"finish_reason":null}]}
569
603
570− data: {"id":"chatcmpl-25fded183d7a9936dd525fb3","object":"chat.completion.chunk","created":1778601816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"main.go`\n"},"finish_reason":null}]}
604+ data: {"id":"chatcmpl-64d4e9ac2b579005483df8b6","object":"chat.completion.chunk","created":1778603013,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":": `main.go`."},"finish_reason":null}]}
571
605
572− data: {"id":"chatcmpl-25fded183d7a9936dd525fb3","object":"chat.completion.chunk","created":1778601816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"- **LS"},"finish_reason":null}]}
606+ data: {"id":"chatcmpl-64d4e9ac2b579005483df8b6","object":"chat.completion.chunk","created":1778603013,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" Directory "},"finish_reason":null}]}
573
607
574− data: {"id":"chatcmpl-25fded183d7a9936dd525fb3","object":"chat.completion.chunk","created":1778601816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"**:"},"finish_reason":null}]}
608+ data: {"id":"chatcmpl-64d4e9ac2b579005483df8b6","object":"chat.completion.chunk","created":1778603013,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"contai"},"finish_reason":null}]}
575
609
576− data: {"id":"chatcmpl-25fded183d7a9936dd525fb3","object":"chat.completion.chunk","created":1778601816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" Directory contains `"},"finish_reason":null}]}
610+ data: {"id":"chatcmpl-64d4e9ac2b579005483df8b6","object":"chat.completion.chunk","created":1778603013,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"ns `g"},"finish_reason":null}]}
577
611
578− data: {"id":"chatcmpl-25fded183d7a9936dd525fb3","object":"chat.completion.chunk","created":1778601816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"go.mod`"},"finish_reason":null}]}
612+ data: {"id":"chatcmpl-64d4e9ac2b579005483df8b6","object":"chat.completion.chunk","created":1778603013,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"o.mod`"},"finish_reason":null}]}
579
613
580− data: {"id":"chatcmpl-25fded183d7a9936dd525fb3","object":"chat.completion.chunk","created":1778601816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" and `main"},"finish_reason":null}]}
614+ data: {"id":"chatcmpl-64d4e9ac2b579005483df8b6","object":"chat.completion.chunk","created":1778603013,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" and "},"finish_reason":null}]}
581
615
582− data: {"id":"chatcmpl-25fded183d7a9936dd525fb3","object":"chat.completion.chunk","created":1778601816,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":".go`"},"finish_reason":null}]}
616+ data: {"id":"chatcmpl-64d4e9ac2b579005483df8b6","object":"chat.completion.chunk","created":1778603013,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`main.go`."},"finish_reason":null}]}
583
617
584− data: {"id":"chatcmpl-25fded183d7a9936dd525fb3","object":"chat.completion.chunk","created":1778601816,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
618+ data: {"id":"chatcmpl-64d4e9ac2b579005483df8b6","object":"chat.completion.chunk","created":1778603013,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
585
619
586− data: {"id":"chatcmpl-25fded183d7a9936dd525fb3","object":"chat.completion.chunk","created":1778601816,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":863,"completion_tokens":33,"total_tokens":7936,"prompt_tokens_details":{"cached_tokens":7040},"completion_tokens_details":{"reasoning_tokens":32}}}
620+ data: {"id":"chatcmpl-64d4e9ac2b579005483df8b6","object":"chat.completion.chunk","created":1778603013,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":179,"completion_tokens":25,"total_tokens":7884,"prompt_tokens_details":{"cached_tokens":7680}}}
587
621
588 data: [DONE]
622 data: [DONE]
589
623
@@ -592,4 +626,4 @@ interactions:
592 - text/event-stream
626 - text/event-stream
593 status: 200 OK
627 status: 200 OK
594 code: 200
628 code: 200
595− duration: 13.518372625s
629+ duration: 7.649120625s
internal/agent/testdata/TestCoderAgent/glm-5.1/read_a_file.yaml+152−124
@@ -25,111 +25,147 @@ interactions:
25 content_length: -1
25 content_length: -1
26 uncompressed: true
26 uncompressed: true
27 body: |+
27 body: |+
28− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
28+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
29
29
30− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"User"},"finish_reason":null}]}
30+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
31
31
32− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" wants"},"finish_reason":null}]}
32+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
33
33
34− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
34+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
35
35
36− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
36+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
37
37
38− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
38+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Generate"},"finish_reason":null}]}
39
39
40− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
40+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
41
41
42− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
42+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
43
43
44− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Read"},"finish_reason":null}]}
44+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
45
45
46− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
46+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
47
47
48− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" go"},"finish_reason":null}]}
48+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
49
49
50− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" mod"},"finish_reason":null}]}
50+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" following"},"finish_reason":null}]}
51
51
52− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
52+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
53
53
54− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Title"},"finish_reason":null}]}
54+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":\n\n"},"finish_reason":null}]}
55
55
56− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" should"},"finish_reason":null}]}
56+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Read"},"finish_reason":null}]}
57
57
58− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
58+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
59
59
60− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" summary"},"finish_reason":null}]}
60+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" go"},"finish_reason":null}]}
61
61
62− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
62+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" mod"},"finish_reason":null}]}
63
63
64− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \u003c="},"finish_reason":null}]}
64+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\n"},"finish_reason":null}]}
65
65
66− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
66+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \u003c"},"finish_reason":null}]}
67
67
68− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
68+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"think"},"finish_reason":null}]}
69
69
70− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
70+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\u003e\n\n"},"finish_reason":null}]}
71
71
72− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" one"},"finish_reason":null}]}
72+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\u003c/"},"finish_reason":null}]}
73
73
74− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
74+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"think"},"finish_reason":null}]}
75
75
76− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
76+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\u003e"},"finish_reason":null}]}
77
77
78− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Lik"},"finish_reason":null}]}
78+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"\n\n"},"finish_reason":null}]}
79
79
80− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ely"},"finish_reason":null}]}
80+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"They"},"finish_reason":null}]}
81
81
82− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
82+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" want"},"finish_reason":null}]}
83
83
84− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Reading"},"finish_reason":null}]}
84+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
85
85
86− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
86+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" short"},"finish_reason":null}]}
87
87
88− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Go"},"finish_reason":null}]}
88+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
89
89
90− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" module"},"finish_reason":null}]}
90+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" summar"},"finish_reason":null}]}
91
91
92− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" file"},"finish_reason":null}]}
92+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"izing"},"finish_reason":null}]}
93
93
94− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
94+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
95
95
96− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
96+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Read"},"finish_reason":null}]}
97
97
98− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
98+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
99
99
100− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"29"},"finish_reason":null}]}
100+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" go"},"finish_reason":null}]}
101
101
102− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
102+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" mod"},"finish_reason":null}]}
103
103
104− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
104+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
105
105
106− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" No"},"finish_reason":null}]}
106+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" So"},"finish_reason":null}]}
107
107
108− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
108+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
109
109
110− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
110+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
111
111
112− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Return"},"finish_reason":null}]}
112+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
113
113
114− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" just"},"finish_reason":null}]}
114+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Reading"},"finish_reason":null}]}
115
115
116− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that"},"finish_reason":null}]}
116+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
117
117
118− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
118+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Go"},"finish_reason":null}]}
119
119
120− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Reading"},"finish_reason":null}]}
120+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Mod"},"finish_reason":null}]}
121
121
122− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" the"},"finish_reason":null}]}
122+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" File"},"finish_reason":null}]}
123
123
124− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Go"},"finish_reason":null}]}
124+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
125
125
126− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" module"},"finish_reason":null}]}
126+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Must"},"finish_reason":null}]}
127
127
128− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" file"},"finish_reason":null}]}
128+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
129
129
130− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
130+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \u003c="},"finish_reason":null}]}
131
131
132− data: {"id":"chatcmpl-34f12044a0a3d5db41d65ef0","object":"chat.completion.chunk","created":1778601665,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":15,"completion_tokens":60,"total_tokens":267,"prompt_tokens_details":{"cached_tokens":192}}}
132+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
133+
134+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
135+
136+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
137+
138+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
139+
140+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" fine"},"finish_reason":null}]}
141+
142+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
143+
144+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" One"},"finish_reason":null}]}
145+
146+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
147+
148+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
149+
150+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" no"},"finish_reason":null}]}
151+
152+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
153+
154+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
155+
156+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Reading"},"finish_reason":null}]}
157+
158+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" the"},"finish_reason":null}]}
159+
160+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Go"},"finish_reason":null}]}
161+
162+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Mod"},"finish_reason":null}]}
163+
164+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" File"},"finish_reason":null}]}
165+
166+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
167+
168+ data: {"id":"chatcmpl-327d86336eb201b69704e0df","object":"chat.completion.chunk","created":1778602866,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":15,"completion_tokens":78,"total_tokens":285,"prompt_tokens_details":{"cached_tokens":192}}}
133
169
134 data: [DONE]
170 data: [DONE]
135
171
@@ -138,7 +174,7 @@ interactions:
138 - text/event-stream
174 - text/event-stream
139 status: 200 OK
175 status: 200 OK
140 code: 200
176 code: 200
141− duration: 882.88625ms
177+ duration: 513.244875ms
142- id: 1
178- id: 1
143 request:
179 request:
144 proto: HTTP/1.1
180 proto: HTTP/1.1
@@ -163,45 +199,35 @@ interactions:
163 content_length: -1
199 content_length: -1
164 uncompressed: true
200 uncompressed: true
165 body: |+
201 body: |+
166− data: {"id":"chatcmpl-9629fffcdf5950b0d962b784","object":"chat.completion.chunk","created":1778601667,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
202+ data: {"id":"chatcmpl-ce993d2807b33f3eb38f6a97","object":"chat.completion.chunk","created":1778602870,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
167
203
168− data: {"id":"chatcmpl-9629fffcdf5950b0d962b784","object":"chat.completion.chunk","created":1778601667,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
204+ data: {"id":"chatcmpl-ce993d2807b33f3eb38f6a97","object":"chat.completion.chunk","created":1778602870,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
169
205
170− data: {"id":"chatcmpl-9629fffcdf5950b0d962b784","object":"chat.completion.chunk","created":1778601667,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
206+ data: {"id":"chatcmpl-ce993d2807b33f3eb38f6a97","object":"chat.completion.chunk","created":1778602870,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
171
207
172− data: {"id":"chatcmpl-9629fffcdf5950b0d962b784","object":"chat.completion.chunk","created":1778601667,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" wants me"},"finish_reason":null}]}
208+ data: {"id":"chatcmpl-ce993d2807b33f3eb38f6a97","object":"chat.completion.chunk","created":1778602870,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" wants me to read"},"finish_reason":null}]}
173
209
174− data: {"id":"chatcmpl-9629fffcdf5950b0d962b784","object":"chat.completion.chunk","created":1778601667,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" to read a"},"finish_reason":null}]}
210+ data: {"id":"chatcmpl-ce993d2807b33f3eb38f6a97","object":"chat.completion.chunk","created":1778602870,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
175
211
176− data: {"id":"chatcmpl-9629fffcdf5950b0d962b784","object":"chat.completion.chunk","created":1778601667,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" go.mod"},"finish_reason":null}]}
212+ data: {"id":"chatcmpl-ce993d2807b33f3eb38f6a97","object":"chat.completion.chunk","created":1778602870,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" go.mod file"},"finish_reason":null}]}
177
213
178− data: {"id":"chatcmpl-9629fffcdf5950b0d962b784","object":"chat.completion.chunk","created":1778601667,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" file. Let"},"finish_reason":null}]}
214+ data: {"id":"chatcmpl-ce993d2807b33f3eb38f6a97","object":"chat.completion.chunk","created":1778602870,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
179
215
180− data: {"id":"chatcmpl-9629fffcdf5950b0d962b784","object":"chat.completion.chunk","created":1778601667,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" me find"},"finish_reason":null}]}
216+ data: {"id":"chatcmpl-ce993d2807b33f3eb38f6a97","object":"chat.completion.chunk","created":1778602870,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_12f34ed5a6f341f4b20ca8b7","type":"function","index":0,"function":{"name":"glob","arguments":""}}]},"finish_reason":null}]}
181
217
182− data: {"id":"chatcmpl-9629fffcdf5950b0d962b784","object":"chat.completion.chunk","created":1778601667,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
218+ data: {"id":"chatcmpl-ce993d2807b33f3eb38f6a97","object":"chat.completion.chunk","created":1778602870,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
183
219
184− data: {"id":"chatcmpl-9629fffcdf5950b0d962b784","object":"chat.completion.chunk","created":1778601667,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" read it"},"finish_reason":null}]}
220+ data: {"id":"chatcmpl-ce993d2807b33f3eb38f6a97","object":"chat.completion.chunk","created":1778602870,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
185
221
186− data: {"id":"chatcmpl-9629fffcdf5950b0d962b784","object":"chat.completion.chunk","created":1778601667,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
222+ data: {"id":"chatcmpl-ce993d2807b33f3eb38f6a97","object":"chat.completion.chunk","created":1778602870,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"pattern\": \"**"}}]},"finish_reason":null}]}
187
223
188− data: {"id":"chatcmpl-9629fffcdf5950b0d962b784","object":"chat.completion.chunk","created":1778601667,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_d7e2b939d2a44b4a8dc06b32","type":"function","index":0,"function":{"name":"glob","arguments":""}}]},"finish_reason":null}]}
224+ data: {"id":"chatcmpl-ce993d2807b33f3eb38f6a97","object":"chat.completion.chunk","created":1778602870,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/go.mod\""}}]},"finish_reason":null}]}
189
225
190− data: {"id":"chatcmpl-9629fffcdf5950b0d962b784","object":"chat.completion.chunk","created":1778601667,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
226+ data: {"id":"chatcmpl-ce993d2807b33f3eb38f6a97","object":"chat.completion.chunk","created":1778602870,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
191
227
192− data: {"id":"chatcmpl-9629fffcdf5950b0d962b784","object":"chat.completion.chunk","created":1778601667,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
228+ data: {"id":"chatcmpl-ce993d2807b33f3eb38f6a97","object":"chat.completion.chunk","created":1778602870,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
193
229
194− data: {"id":"chatcmpl-9629fffcdf5950b0d962b784","object":"chat.completion.chunk","created":1778601667,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"pattern\": "}}]},"finish_reason":null}]}
230+ data: {"id":"chatcmpl-ce993d2807b33f3eb38f6a97","object":"chat.completion.chunk","created":1778602870,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7761,"completion_tokens":25,"total_tokens":7786,"completion_tokens_details":{"reasoning_tokens":11}}}
195−
196− data: {"id":"chatcmpl-9629fffcdf5950b0d962b784","object":"chat.completion.chunk","created":1778601667,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"**/"}}]},"finish_reason":null}]}
197−
198− data: {"id":"chatcmpl-9629fffcdf5950b0d962b784","object":"chat.completion.chunk","created":1778601667,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go.mod\""}}]},"finish_reason":null}]}
199−
200− data: {"id":"chatcmpl-9629fffcdf5950b0d962b784","object":"chat.completion.chunk","created":1778601667,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
201−
202− data: {"id":"chatcmpl-9629fffcdf5950b0d962b784","object":"chat.completion.chunk","created":1778601667,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
203−
204− data: {"id":"chatcmpl-9629fffcdf5950b0d962b784","object":"chat.completion.chunk","created":1778601667,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":721,"completion_tokens":32,"total_tokens":7793,"prompt_tokens_details":{"cached_tokens":7040},"completion_tokens_details":{"reasoning_tokens":18}}}
205
231
206 data: [DONE]
232 data: [DONE]
207
233
@@ -210,15 +236,15 @@ interactions:
210 - text/event-stream
236 - text/event-stream
211 status: 200 OK
237 status: 200 OK
212 code: 200
238 code: 200
213− duration: 3.481540708s
239+ duration: 3.905015s
214- id: 2
240- id: 2
215 request:
241 request:
216 proto: HTTP/1.1
242 proto: HTTP/1.1
217 proto_major: 1
243 proto_major: 1
218 proto_minor: 1
244 proto_minor: 1
219− content_length: 34078
245+ content_length: 34053
220 host: ""
246 host: ""
221− 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/read_a_file\\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\",\"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\":\"Read the go mod\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_d7e2b939d2a44b4a8dc06b32\",\"function\":{\"arguments\":\"{\\\"pattern\\\": \\\"**/go.mod\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"The user wants me to read a go.mod file. Let me find and read it.\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/glm-5.1/read_a_file/go.mod\",\"tool_call_id\":\"call_d7e2b939d2a44b4a8dc06b32\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
247+ 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/read_a_file\\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\",\"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\":\"Read the go mod\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_12f34ed5a6f341f4b20ca8b7\",\"function\":{\"arguments\":\"{\\\"pattern\\\": \\\"**/go.mod\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"The user wants me to read a go.mod file.\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/glm-5.1/read_a_file/go.mod\",\"tool_call_id\":\"call_12f34ed5a6f341f4b20ca8b7\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
222 headers:
248 headers:
223 Accept:
249 Accept:
224 - application/json
250 - application/json
@@ -235,43 +261,43 @@ interactions:
235 content_length: -1
261 content_length: -1
236 uncompressed: true
262 uncompressed: true
237 body: |+
263 body: |+
238− data: {"id":"chatcmpl-b0780eb38d68c8307b683bae","object":"chat.completion.chunk","created":1778601670,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
264+ data: {"id":"chatcmpl-5ae0cdaa4c07bbc11cf02c8c","object":"chat.completion.chunk","created":1778602873,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
239
265
240− data: {"id":"chatcmpl-b0780eb38d68c8307b683bae","object":"chat.completion.chunk","created":1778601670,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_c11e4a0a1d9b46e4b049a005","type":"function","index":0,"function":{"name":"view","arguments":""}}]},"finish_reason":null}]}
266+ data: {"id":"chatcmpl-5ae0cdaa4c07bbc11cf02c8c","object":"chat.completion.chunk","created":1778602873,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_6b8b8e28c9444f4bb161b549","type":"function","index":0,"function":{"name":"view","arguments":""}}]},"finish_reason":null}]}
241
267
242− data: {"id":"chatcmpl-b0780eb38d68c8307b683bae","object":"chat.completion.chunk","created":1778601670,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
268+ data: {"id":"chatcmpl-5ae0cdaa4c07bbc11cf02c8c","object":"chat.completion.chunk","created":1778602873,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
243
269
244− data: {"id":"chatcmpl-b0780eb38d68c8307b683bae","object":"chat.completion.chunk","created":1778601670,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
270+ data: {"id":"chatcmpl-5ae0cdaa4c07bbc11cf02c8c","object":"chat.completion.chunk","created":1778602873,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
245
271
246− data: {"id":"chatcmpl-b0780eb38d68c8307b683bae","object":"chat.completion.chunk","created":1778601670,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"file_path\": "}}]},"finish_reason":null}]}
272+ data: {"id":"chatcmpl-5ae0cdaa4c07bbc11cf02c8c","object":"chat.completion.chunk","created":1778602873,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"file_path\": \"/tmp"}}]},"finish_reason":null}]}
247
273
248− data: {"id":"chatcmpl-b0780eb38d68c8307b683bae","object":"chat.completion.chunk","created":1778601670,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/tmp/c"}}]},"finish_reason":null}]}
274+ data: {"id":"chatcmpl-5ae0cdaa4c07bbc11cf02c8c","object":"chat.completion.chunk","created":1778602873,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/c"}}]},"finish_reason":null}]}
249
275
250− data: {"id":"chatcmpl-b0780eb38d68c8307b683bae","object":"chat.completion.chunk","created":1778601670,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"rush"}}]},"finish_reason":null}]}
276+ data: {"id":"chatcmpl-5ae0cdaa4c07bbc11cf02c8c","object":"chat.completion.chunk","created":1778602873,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"rush-test"}}]},"finish_reason":null}]}
251
277
252− data: {"id":"chatcmpl-b0780eb38d68c8307b683bae","object":"chat.completion.chunk","created":1778601670,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}]}
278+ data: {"id":"chatcmpl-5ae0cdaa4c07bbc11cf02c8c","object":"chat.completion.chunk","created":1778602873,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}]}
253
279
254− data: {"id":"chatcmpl-b0780eb38d68c8307b683bae","object":"chat.completion.chunk","created":1778601670,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}]}
280+ data: {"id":"chatcmpl-5ae0cdaa4c07bbc11cf02c8c","object":"chat.completion.chunk","created":1778602873,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}]}
255
281
256− data: {"id":"chatcmpl-b0780eb38d68c8307b683bae","object":"chat.completion.chunk","created":1778601670,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}]}
282+ data: {"id":"chatcmpl-5ae0cdaa4c07bbc11cf02c8c","object":"chat.completion.chunk","created":1778602873,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent/g"}}]},"finish_reason":null}]}
257
283
258− data: {"id":"chatcmpl-b0780eb38d68c8307b683bae","object":"chat.completion.chunk","created":1778601670,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent/g"}}]},"finish_reason":null}]}
284+ data: {"id":"chatcmpl-5ae0cdaa4c07bbc11cf02c8c","object":"chat.completion.chunk","created":1778602873,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"lm-"}}]},"finish_reason":null}]}
259
285
260− data: {"id":"chatcmpl-b0780eb38d68c8307b683bae","object":"chat.completion.chunk","created":1778601670,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"lm-"}}]},"finish_reason":null}]}
286+ data: {"id":"chatcmpl-5ae0cdaa4c07bbc11cf02c8c","object":"chat.completion.chunk","created":1778602873,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5.1"}}]},"finish_reason":null}]}
261
287
262− data: {"id":"chatcmpl-b0780eb38d68c8307b683bae","object":"chat.completion.chunk","created":1778601670,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5.1"}}]},"finish_reason":null}]}
288+ data: {"id":"chatcmpl-5ae0cdaa4c07bbc11cf02c8c","object":"chat.completion.chunk","created":1778602873,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/read_a"}}]},"finish_reason":null}]}
263
289
264− data: {"id":"chatcmpl-b0780eb38d68c8307b683bae","object":"chat.completion.chunk","created":1778601670,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/read_a"}}]},"finish_reason":null}]}
290+ data: {"id":"chatcmpl-5ae0cdaa4c07bbc11cf02c8c","object":"chat.completion.chunk","created":1778602873,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}]}
265
291
266− data: {"id":"chatcmpl-b0780eb38d68c8307b683bae","object":"chat.completion.chunk","created":1778601670,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}]}
292+ data: {"id":"chatcmpl-5ae0cdaa4c07bbc11cf02c8c","object":"chat.completion.chunk","created":1778602873,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/go.mod"}}]},"finish_reason":null}]}
267
293
268− data: {"id":"chatcmpl-b0780eb38d68c8307b683bae","object":"chat.completion.chunk","created":1778601670,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/go.mod\""}}]},"finish_reason":null}]}
294+ data: {"id":"chatcmpl-5ae0cdaa4c07bbc11cf02c8c","object":"chat.completion.chunk","created":1778602873,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\""}}]},"finish_reason":null}]}
269
295
270− data: {"id":"chatcmpl-b0780eb38d68c8307b683bae","object":"chat.completion.chunk","created":1778601670,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
296+ data: {"id":"chatcmpl-5ae0cdaa4c07bbc11cf02c8c","object":"chat.completion.chunk","created":1778602873,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
271
297
272− data: {"id":"chatcmpl-b0780eb38d68c8307b683bae","object":"chat.completion.chunk","created":1778601670,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
298+ data: {"id":"chatcmpl-5ae0cdaa4c07bbc11cf02c8c","object":"chat.completion.chunk","created":1778602873,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
273
299
274− data: {"id":"chatcmpl-b0780eb38d68c8307b683bae","object":"chat.completion.chunk","created":1778601670,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":53,"completion_tokens":29,"total_tokens":7826,"prompt_tokens_details":{"cached_tokens":7744},"completion_tokens_details":{"reasoning_tokens":28}}}
300+ data: {"id":"chatcmpl-5ae0cdaa4c07bbc11cf02c8c","object":"chat.completion.chunk","created":1778602873,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":53,"completion_tokens":29,"total_tokens":7826,"prompt_tokens_details":{"cached_tokens":7744},"completion_tokens_details":{"reasoning_tokens":28}}}
275
301
276 data: [DONE]
302 data: [DONE]
277
303
@@ -280,15 +306,15 @@ interactions:
280 - text/event-stream
306 - text/event-stream
281 status: 200 OK
307 status: 200 OK
282 code: 200
308 code: 200
283− duration: 1.901558459s
309+ duration: 3.545196959s
284- id: 3
310- id: 3
285 request:
311 request:
286 proto: HTTP/1.1
312 proto: HTTP/1.1
287 proto_major: 1
313 proto_major: 1
288 proto_minor: 1
314 proto_minor: 1
289− content_length: 34471
315+ content_length: 34455
290 host: ""
316 host: ""
291− 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/read_a_file\\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\",\"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\":\"Read the go mod\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_d7e2b939d2a44b4a8dc06b32\",\"function\":{\"arguments\":\"{\\\"pattern\\\": \\\"**/go.mod\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"The user wants me to read a go.mod file. Let me find and read it.\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/glm-5.1/read_a_file/go.mod\",\"tool_call_id\":\"call_d7e2b939d2a44b4a8dc06b32\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_c11e4a0a1d9b46e4b049a005\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/read_a_file/go.mod\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"\"},{\"content\":\"<file>\\n 1|module example.com/testproject\\n 2|\\n 3|go 1.23\\n</file>\\n\",\"tool_call_id\":\"call_c11e4a0a1d9b46e4b049a005\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
317+ 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/read_a_file\\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\",\"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\":\"Read the go mod\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_12f34ed5a6f341f4b20ca8b7\",\"function\":{\"arguments\":\"{\\\"pattern\\\": \\\"**/go.mod\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"The user wants me to read a go.mod file.\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/glm-5.1/read_a_file/go.mod\",\"tool_call_id\":\"call_12f34ed5a6f341f4b20ca8b7\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_6b8b8e28c9444f4bb161b549\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/read_a_file/go.mod\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"\"},{\"content\":\"<file>\\n 1|module example.com/testproject\\n 2|\\n 3|go 1.23\\n 4|\\n</file>\\n\",\"tool_call_id\":\"call_6b8b8e28c9444f4bb161b549\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
292 headers:
318 headers:
293 Accept:
319 Accept:
294 - application/json
320 - application/json
@@ -305,43 +331,45 @@ interactions:
305 content_length: -1
331 content_length: -1
306 uncompressed: true
332 uncompressed: true
307 body: |+
333 body: |+
308− data: {"id":"chatcmpl-d10ef5026cbac5e65b68913f","object":"chat.completion.chunk","created":1778601674,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
334+ data: {"id":"chatcmpl-84e0c2126d0fccec09842bac","object":"chat.completion.chunk","created":1778602877,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
335+
336+ data: {"id":"chatcmpl-84e0c2126d0fccec09842bac","object":"chat.completion.chunk","created":1778602877,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"The"},"finish_reason":null}]}
309
337
310− data: {"id":"chatcmpl-d10ef5026cbac5e65b68913f","object":"chat.completion.chunk","created":1778601674,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"The"},"finish_reason":null}]}
338+ data: {"id":"chatcmpl-84e0c2126d0fccec09842bac","object":"chat.completion.chunk","created":1778602877,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `"},"finish_reason":null}]}
311
339
312− data: {"id":"chatcmpl-d10ef5026cbac5e65b68913f","object":"chat.completion.chunk","created":1778601674,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `"},"finish_reason":null}]}
340+ data: {"id":"chatcmpl-84e0c2126d0fccec09842bac","object":"chat.completion.chunk","created":1778602877,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"go"},"finish_reason":null}]}
313
341
314− data: {"id":"chatcmpl-d10ef5026cbac5e65b68913f","object":"chat.completion.chunk","created":1778601674,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"go"},"finish_reason":null}]}
342+ data: {"id":"chatcmpl-84e0c2126d0fccec09842bac","object":"chat.completion.chunk","created":1778602877,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":".mod` defines"},"finish_reason":null}]}
315
343
316− data: {"id":"chatcmpl-d10ef5026cbac5e65b68913f","object":"chat.completion.chunk","created":1778601674,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":".mod"},"finish_reason":null}]}
344+ data: {"id":"chatcmpl-84e0c2126d0fccec09842bac","object":"chat.completion.chunk","created":1778602877,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":":\n\n-"},"finish_reason":null}]}
317
345
318− data: {"id":"chatcmpl-d10ef5026cbac5e65b68913f","object":"chat.completion.chunk","created":1778601674,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"` defines"},"finish_reason":null}]}
346+ data: {"id":"chatcmpl-84e0c2126d0fccec09842bac","object":"chat.completion.chunk","created":1778602877,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" **Module"},"finish_reason":null}]}
319
347
320− data: {"id":"chatcmpl-d10ef5026cbac5e65b68913f","object":"chat.completion.chunk","created":1778601674,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":":\n\n-"},"finish_reason":null}]}
348+ data: {"id":"chatcmpl-84e0c2126d0fccec09842bac","object":"chat.completion.chunk","created":1778602877,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"**: `"},"finish_reason":null}]}
321
349
322− data: {"id":"chatcmpl-d10ef5026cbac5e65b68913f","object":"chat.completion.chunk","created":1778601674,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" **Module**:"},"finish_reason":null}]}
350+ data: {"id":"chatcmpl-84e0c2126d0fccec09842bac","object":"chat.completion.chunk","created":1778602877,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"example.com"},"finish_reason":null}]}
323
351
324− data: {"id":"chatcmpl-d10ef5026cbac5e65b68913f","object":"chat.completion.chunk","created":1778601674,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `example"},"finish_reason":null}]}
352+ data: {"id":"chatcmpl-84e0c2126d0fccec09842bac","object":"chat.completion.chunk","created":1778602877,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"/testproject"},"finish_reason":null}]}
325
353
326− data: {"id":"chatcmpl-d10ef5026cbac5e65b68913f","object":"chat.completion.chunk","created":1778601674,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":".com/test"},"finish_reason":null}]}
354+ data: {"id":"chatcmpl-84e0c2126d0fccec09842bac","object":"chat.completion.chunk","created":1778602877,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`\n-"},"finish_reason":null}]}
327
355
328− data: {"id":"chatcmpl-d10ef5026cbac5e65b68913f","object":"chat.completion.chunk","created":1778601674,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"project"},"finish_reason":null}]}
356+ data: {"id":"chatcmpl-84e0c2126d0fccec09842bac","object":"chat.completion.chunk","created":1778602877,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" **Go"},"finish_reason":null}]}
329
357
330− data: {"id":"chatcmpl-d10ef5026cbac5e65b68913f","object":"chat.completion.chunk","created":1778601674,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`\n- **"},"finish_reason":null}]}
358+ data: {"id":"chatcmpl-84e0c2126d0fccec09842bac","object":"chat.completion.chunk","created":1778602877,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" version"},"finish_reason":null}]}
331
359
332− data: {"id":"chatcmpl-d10ef5026cbac5e65b68913f","object":"chat.completion.chunk","created":1778601674,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Go version"},"finish_reason":null}]}
360+ data: {"id":"chatcmpl-84e0c2126d0fccec09842bac","object":"chat.completion.chunk","created":1778602877,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"**: "},"finish_reason":null}]}
333
361
334− data: {"id":"chatcmpl-d10ef5026cbac5e65b68913f","object":"chat.completion.chunk","created":1778601674,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"**: "},"finish_reason":null}]}
362+ data: {"id":"chatcmpl-84e0c2126d0fccec09842bac","object":"chat.completion.chunk","created":1778602877,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"1."},"finish_reason":null}]}
335
363
336− data: {"id":"chatcmpl-d10ef5026cbac5e65b68913f","object":"chat.completion.chunk","created":1778601674,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"1.23"},"finish_reason":null}]}
364+ data: {"id":"chatcmpl-84e0c2126d0fccec09842bac","object":"chat.completion.chunk","created":1778602877,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"23\n-"},"finish_reason":null}]}
337
365
338− data: {"id":"chatcmpl-d10ef5026cbac5e65b68913f","object":"chat.completion.chunk","created":1778601674,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"\n"},"finish_reason":null}]}
366+ data: {"id":"chatcmpl-84e0c2126d0fccec09842bac","object":"chat.completion.chunk","created":1778602877,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" **No"},"finish_reason":null}]}
339
367
340− data: {"id":"chatcmpl-d10ef5026cbac5e65b68913f","object":"chat.completion.chunk","created":1778601674,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"- No dependencies"},"finish_reason":null}]}
368+ data: {"id":"chatcmpl-84e0c2126d0fccec09842bac","object":"chat.completion.chunk","created":1778602877,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" dependencies**"},"finish_reason":null}]}
341
369
342− data: {"id":"chatcmpl-d10ef5026cbac5e65b68913f","object":"chat.completion.chunk","created":1778601674,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
370+ data: {"id":"chatcmpl-84e0c2126d0fccec09842bac","object":"chat.completion.chunk","created":1778602877,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
343
371
344− data: {"id":"chatcmpl-d10ef5026cbac5e65b68913f","object":"chat.completion.chunk","created":1778601674,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7860,"completion_tokens":32,"total_tokens":7892,"completion_tokens_details":{"reasoning_tokens":31}}}
372+ data: {"id":"chatcmpl-84e0c2126d0fccec09842bac","object":"chat.completion.chunk","created":1778602877,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7864,"completion_tokens":34,"total_tokens":7898,"completion_tokens_details":{"reasoning_tokens":33}}}
345
373
346 data: [DONE]
374 data: [DONE]
347
375
@@ -350,4 +378,4 @@ interactions:
350 - text/event-stream
378 - text/event-stream
351 status: 200 OK
379 status: 200 OK
352 code: 200
380 code: 200
353− duration: 3.047584625s
381+ duration: 2.636356583s
internal/agent/testdata/TestCoderAgent/glm-5.1/simple_test.yaml+45−119
@@ -25,137 +25,81 @@ interactions:
25 content_length: -1
25 content_length: -1
26 uncompressed: true
26 uncompressed: true
27 body: |+
27 body: |+
28− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
28+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
29
29
30− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"User"},"finish_reason":null}]}
30+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"User"},"finish_reason":null}]}
31
31
32− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" asks"},"finish_reason":null}]}
32+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" wants"},"finish_reason":null}]}
33
33
34− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
34+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
35
35
36− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
36+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
37
37
38− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Generate"},"finish_reason":null}]}
38+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
39
39
40− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
40+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
41
41
42− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
42+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
43
43
44− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
44+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
45
45
46− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
46+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
47
47
48− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
48+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Hello"},"finish_reason":null}]}
49
49
50− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" following"},"finish_reason":null}]}
50+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
51
51
52− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
52+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Title"},"finish_reason":null}]}
53
53
54− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":\n\n"},"finish_reason":null}]}
54+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" should"},"finish_reason":null}]}
55
55
56− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Hello"},"finish_reason":null}]}
56+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
57
57
58− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\n"},"finish_reason":null}]}
58+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" short"},"finish_reason":null}]}
59
59
60− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \u003c"},"finish_reason":null}]}
60+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
61
61
62− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"think"},"finish_reason":null}]}
62+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
63
63
64− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\u003e\n\n"},"finish_reason":null}]}
64+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" same"},"finish_reason":null}]}
65
65
66− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\u003c/"},"finish_reason":null}]}
66+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" language"},"finish_reason":null}]}
67
67
68− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"think"},"finish_reason":null}]}
68+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
69
69
70− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\u003e\""},"finish_reason":null}]}
70+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"English"},"finish_reason":null}]}
71
71
72− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" So"},"finish_reason":null}]}
72+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")."},"finish_reason":null}]}
73
73
74− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
74+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Probably"},"finish_reason":null}]}
75
75
76− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" is"},"finish_reason":null}]}
76+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
77
77
78− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" just"},"finish_reason":null}]}
78+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Greeting"},"finish_reason":null}]}
79
79
80− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
80+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
81
81
82− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Hello"},"finish_reason":null}]}
82+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Under"},"finish_reason":null}]}
83
83
84− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
84+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
85
85
86− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Title"},"finish_reason":null}]}
86+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
87
87
88− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" should"},"finish_reason":null}]}
88+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
89
89
90− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
90+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
91
91
92− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
92+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" One"},"finish_reason":null}]}
93
93
94− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
94+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
95
95
96− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" summary"},"finish_reason":null}]}
96+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
97
97
98− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
98+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Greeting"},"finish_reason":null}]}
99
99
100− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" under"},"finish_reason":null}]}
100+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
101
101
102− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
102+ data: {"id":"chatcmpl-d2fa877a0dd7d5a06a3221af","object":"chat.completion.chunk","created":1778602865,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":12,"completion_tokens":45,"total_tokens":249,"prompt_tokens_details":{"cached_tokens":192}}}
103−
104− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
105−
106− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
107−
108− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
109−
110− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" one"},"finish_reason":null}]}
111−
112− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
113−
114− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
115−
116− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" no"},"finish_reason":null}]}
117−
118− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
119−
120− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" or"},"finish_reason":null}]}
121−
122− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" col"},"finish_reason":null}]}
123−
124− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ons"},"finish_reason":null}]}
125−
126− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
127−
128− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" So"},"finish_reason":null}]}
129−
130− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" maybe"},"finish_reason":null}]}
131−
132− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
133−
134− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Greeting"},"finish_reason":null}]}
135−
136− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
137−
138− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That"},"finish_reason":null}]}
139−
140− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" is"},"finish_reason":null}]}
141−
142− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
143−
144− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
145−
146− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Return"},"finish_reason":null}]}
147−
148− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" just"},"finish_reason":null}]}
149−
150− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that"},"finish_reason":null}]}
151−
152− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
153−
154− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Greeting"},"finish_reason":null}]}
155−
156− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
157−
158− data: {"id":"chatcmpl-9454579d686f7cec9572bb47","object":"chat.completion.chunk","created":1778601659,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":12,"completion_tokens":73,"total_tokens":277,"prompt_tokens_details":{"cached_tokens":192}}}
159
103
160 data: [DONE]
104 data: [DONE]
161
105
@@ -164,7 +108,7 @@ interactions:
164 - text/event-stream
108 - text/event-stream
165 status: 200 OK
109 status: 200 OK
166 code: 200
110 code: 200
167− duration: 793.427542ms
111+ duration: 724.351834ms
168- id: 1
112- id: 1
169 request:
113 request:
170 proto: HTTP/1.1
114 proto: HTTP/1.1
@@ -189,33 +133,15 @@ interactions:
189 content_length: -1
133 content_length: -1
190 uncompressed: true
134 uncompressed: true
191 body: |+
135 body: |+
192− data: {"id":"chatcmpl-54478dac3fa904184b20ee66","object":"chat.completion.chunk","created":1778601664,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
136+ data: {"id":"chatcmpl-3fc9afc7ce7eaa1ee5f8a0dd","object":"chat.completion.chunk","created":1778602866,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
193−
194− data: {"id":"chatcmpl-54478dac3fa904184b20ee66","object":"chat.completion.chunk","created":1778601664,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
195−
196− data: {"id":"chatcmpl-54478dac3fa904184b20ee66","object":"chat.completion.chunk","created":1778601664,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
197−
198− data: {"id":"chatcmpl-54478dac3fa904184b20ee66","object":"chat.completion.chunk","created":1778601664,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" simply"},"finish_reason":null}]}
199−
200− data: {"id":"chatcmpl-54478dac3fa904184b20ee66","object":"chat.completion.chunk","created":1778601664,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" said \""},"finish_reason":null}]}
201−
202− data: {"id":"chatcmpl-54478dac3fa904184b20ee66","object":"chat.completion.chunk","created":1778601664,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"Hello"},"finish_reason":null}]}
203−
204− data: {"id":"chatcmpl-54478dac3fa904184b20ee66","object":"chat.completion.chunk","created":1778601664,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"\". I"},"finish_reason":null}]}
205−
206− data: {"id":"chatcmpl-54478dac3fa904184b20ee66","object":"chat.completion.chunk","created":1778601664,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"'ll"},"finish_reason":null}]}
207−
208− data: {"id":"chatcmpl-54478dac3fa904184b20ee66","object":"chat.completion.chunk","created":1778601664,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" respond briefly"},"finish_reason":null}]}
209−
210− data: {"id":"chatcmpl-54478dac3fa904184b20ee66","object":"chat.completion.chunk","created":1778601664,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
211
137
212− data: {"id":"chatcmpl-54478dac3fa904184b20ee66","object":"chat.completion.chunk","created":1778601664,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Hi"},"finish_reason":null}]}
138+ data: {"id":"chatcmpl-3fc9afc7ce7eaa1ee5f8a0dd","object":"chat.completion.chunk","created":1778602866,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Hi"},"finish_reason":null}]}
213
139
214− data: {"id":"chatcmpl-54478dac3fa904184b20ee66","object":"chat.completion.chunk","created":1778601664,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"!"},"finish_reason":null}]}
140+ data: {"id":"chatcmpl-3fc9afc7ce7eaa1ee5f8a0dd","object":"chat.completion.chunk","created":1778602866,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"!"},"finish_reason":null}]}
215
141
216− data: {"id":"chatcmpl-54478dac3fa904184b20ee66","object":"chat.completion.chunk","created":1778601664,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
142+ data: {"id":"chatcmpl-3fc9afc7ce7eaa1ee5f8a0dd","object":"chat.completion.chunk","created":1778602866,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
217
143
218− data: {"id":"chatcmpl-54478dac3fa904184b20ee66","object":"chat.completion.chunk","created":1778601664,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7757,"completion_tokens":16,"total_tokens":7773,"completion_tokens_details":{"reasoning_tokens":12}}}
144+ data: {"id":"chatcmpl-3fc9afc7ce7eaa1ee5f8a0dd","object":"chat.completion.chunk","created":1778602866,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":717,"completion_tokens":4,"total_tokens":7761,"prompt_tokens_details":{"cached_tokens":7040},"completion_tokens_details":{"reasoning_tokens":3}}}
219
145
220 data: [DONE]
146 data: [DONE]
221
147
@@ -224,4 +150,4 @@ interactions:
224 - text/event-stream
150 - text/event-stream
225 status: 200 OK
151 status: 200 OK
226 code: 200
152 code: 200
227− duration: 5.192642417s
153+ duration: 1.657962917s
internal/agent/testdata/TestCoderAgent/glm-5.1/sourcegraph_tool.yaml+496−548
@@ -2,6 +2,92 @@
2version: 2
2version: 2
3interactions:
3interactions:
4- id: 0
4- id: 0
5+ request:
6+ proto: HTTP/1.1
7+ proto_major: 1
8+ proto_minor: 1
9+ content_length: 33744
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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/sourcegraph_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\",\"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 sourcegraph to search for 'func main' in Go repositories\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
29+
30+ data: {"id":"chatcmpl-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
31+
32+ data: {"id":"chatcmpl-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
33+
34+ data: {"id":"chatcmpl-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" wants me"},"finish_reason":null}]}
35+
36+ data: {"id":"chatcmpl-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
37+
38+ data: {"id":"chatcmpl-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" use"},"finish_reason":null}]}
39+
40+ data: {"id":"chatcmpl-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
41+
42+ data: {"id":"chatcmpl-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" Sourcegraph"},"finish_reason":null}]}
43+
44+ data: {"id":"chatcmpl-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" tool to search"},"finish_reason":null}]}
45+
46+ data: {"id":"chatcmpl-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" for '"},"finish_reason":null}]}
47+
48+ data: {"id":"chatcmpl-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"func"},"finish_reason":null}]}
49+
50+ data: {"id":"chatcmpl-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" main'"},"finish_reason":null}]}
51+
52+ data: {"id":"chatcmpl-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" in Go repositories"},"finish_reason":null}]}
53+
54+ data: {"id":"chatcmpl-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
55+
56+ data: {"id":"chatcmpl-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_ef7de30a947e4c41a99ddb3f","type":"function","index":0,"function":{"name":"sourcegraph","arguments":""}}]},"finish_reason":null}]}
57+
58+ data: {"id":"chatcmpl-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
59+
60+ data: {"id":"chatcmpl-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
61+
62+ data: {"id":"chatcmpl-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"count\": 10"}}]},"finish_reason":null}]}
63+
64+ data: {"id":"chatcmpl-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":", "}}]},"finish_reason":null}]}
65+
66+ data: {"id":"chatcmpl-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"query\": "}}]},"finish_reason":null}]}
67+
68+ data: {"id":"chatcmpl-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"func main"}}]},"finish_reason":null}]}
69+
70+ data: {"id":"chatcmpl-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" lang"}}]},"finish_reason":null}]}
71+
72+ data: {"id":"chatcmpl-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":":go"}}]},"finish_reason":null}]}
73+
74+ data: {"id":"chatcmpl-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\""}}]},"finish_reason":null}]}
75+
76+ data: {"id":"chatcmpl-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
77+
78+ data: {"id":"chatcmpl-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
79+
80+ data: {"id":"chatcmpl-2cbc28c12468a3d0a2a914cf","object":"chat.completion.chunk","created":1778602967,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7770,"completion_tokens":43,"total_tokens":7813,"completion_tokens_details":{"reasoning_tokens":21}}}
81+
82+ data: [DONE]
83+
84+ headers:
85+ Content-Type:
86+ - text/event-stream
87+ status: 200 OK
88+ code: 200
89+ duration: 3.017366125s
90+- id: 1
5 request:
91 request:
6 proto: HTTP/1.1
92 proto: HTTP/1.1
7 proto_major: 1
93 proto_major: 1
@@ -25,535 +111,557 @@ interactions:
25 content_length: -1
111 content_length: -1
26 uncompressed: true
112 uncompressed: true
27 body: |+
113 body: |+
28− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
114+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
29
115
30− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
116+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
31
117
32− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
118+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
33
119
34− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
120+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" wants"},"finish_reason":null}]}
35
121
36− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
122+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
37
123
38− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Generate"},"finish_reason":null}]}
124+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
39
125
40− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
126+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
41
127
42− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
128+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
43
129
44− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
130+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that"},"finish_reason":null}]}
45
131
46− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
132+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
47
133
48− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
134+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
49
135
50− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" following"},"finish_reason":null}]}
136+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Should"},"finish_reason":null}]}
51
137
52− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
138+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
53
139
54− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":\n\n"},"finish_reason":null}]}
140+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
55
141
56− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"use"},"finish_reason":null}]}
142+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" same"},"finish_reason":null}]}
57
143
58− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" source"},"finish_reason":null}]}
144+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" language"},"finish_reason":null}]}
59
145
60− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"graph"},"finish_reason":null}]}
146+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
61
147
62− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
148+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"English"},"finish_reason":null}]}
63
149
64− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" search"},"finish_reason":null}]}
150+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")."},"finish_reason":null}]}
65
151
66− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
152+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Not"},"finish_reason":null}]}
67
153
68− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
154+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" more"},"finish_reason":null}]}
69
155
70− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"func"},"finish_reason":null}]}
156+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" than"},"finish_reason":null}]}
71
157
72− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
158+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
73
159
74− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'"},"finish_reason":null}]}
160+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
75
161
76− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
162+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
77
163
78− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Go"},"finish_reason":null}]}
164+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
79
165
80− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" repositories"},"finish_reason":null}]}
166+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" One"},"finish_reason":null}]}
81
167
82− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\n"},"finish_reason":null}]}
168+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
83
169
84− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \u003c"},"finish_reason":null}]}
170+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
85
171
86− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"think"},"finish_reason":null}]}
172+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" no"},"finish_reason":null}]}
87
173
88− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\u003e\""},"finish_reason":null}]}
174+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
89
175
90− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" The"},"finish_reason":null}]}
176+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" or"},"finish_reason":null}]}
91
177
92− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
178+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" col"},"finish_reason":null}]}
93
179
94− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" wants"},"finish_reason":null}]}
180+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ons"},"finish_reason":null}]}
95
181
96− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
182+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
97
183
98− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
184+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Something"},"finish_reason":null}]}
99
185
100− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
186+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" like"},"finish_reason":null}]}
101
187
102− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" summary"},"finish_reason":null}]}
188+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
103
189
104− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
190+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Searching"},"finish_reason":null}]}
105
191
106− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Must"},"finish_reason":null}]}
192+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
107
193
108− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
194+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" func"},"finish_reason":null}]}
109
195
110− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" under"},"finish_reason":null}]}
196+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
111
197
112− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
198+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
113
199
114− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
200+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Go"},"finish_reason":null}]}
115
201
116− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
202+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" repos"},"finish_reason":null}]}
117
203
118− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
204+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
119
205
120− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" one"},"finish_reason":null}]}
206+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Source"},"finish_reason":null}]}
121
207
122− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
208+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"graph"},"finish_reason":null}]}
123
209
124− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
210+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
125
211
126− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Language"},"finish_reason":null}]}
212+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
127
213
128− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" is"},"finish_reason":null}]}
214+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
129
215
130− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" English"},"finish_reason":null}]}
216+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
131
217
132− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
218+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
133
219
134− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Title"},"finish_reason":null}]}
220+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Searching"},"finish_reason":null}]}
135
221
136− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
222+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
137
223
138− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
224+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" func"},"finish_reason":null}]}
139
225
140− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Using"},"finish_reason":null}]}
226+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
141
227
142− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Source"},"finish_reason":null}]}
228+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
143
229
144− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"graph"},"finish_reason":null}]}
230+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Go"},"finish_reason":null}]}
145
231
146− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
232+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" repos"},"finish_reason":null}]}
147
233
148− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Find"},"finish_reason":null}]}
234+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
149
235
150− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" func"},"finish_reason":null}]}
236+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Source"},"finish_reason":null}]}
151
237
152− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
238+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"graph"},"finish_reason":null}]}
153
239
154− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
240+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
155
241
156− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Go"},"finish_reason":null}]}
242+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" length"},"finish_reason":null}]}
157
243
158− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Re"},"finish_reason":null}]}
244+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"?"},"finish_reason":null}]}
159
245
160− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"pos"},"finish_reason":null}]}
246+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Let's"},"finish_reason":null}]}
161
247
162− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
248+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
163
249
164− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
250+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
165
251
166− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
252+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Searching"},"finish_reason":null}]}
167
253
168− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
254+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
169
255
170− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
256+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"9"},"finish_reason":null}]}
171
257
172− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Using"},"finish_reason":null}]}
258+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
173
259
174− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Source"},"finish_reason":null}]}
260+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" +"},"finish_reason":null}]}
175
261
176− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"graph"},"finish_reason":null}]}
262+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
177
263
178− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
264+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
179
265
180− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Find"},"finish_reason":null}]}
266+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
181
267
182− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" func"},"finish_reason":null}]}
268+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
183
269
184− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
270+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"10"},"finish_reason":null}]}
185
271
186− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
272+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
187
273
188− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Go"},"finish_reason":null}]}
274+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
189
275
190− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Re"},"finish_reason":null}]}
276+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
191
277
192− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"pos"},"finish_reason":null}]}
278+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
193
279
194− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
280+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
195
281
196− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
282+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"13"},"finish_reason":null}]}
197
283
198− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
284+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
199
285
200− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" let's"},"finish_reason":null}]}
286+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
201
287
202− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
288+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
203
289
204− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
290+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"14"},"finish_reason":null}]}
205
291
206− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Using"},"finish_reason":null}]}
292+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
207
293
208− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
294+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" func"},"finish_reason":null}]}
209
295
210− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
296+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
211
297
212− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
298+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
213
299
214− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" +"},"finish_reason":null}]}
300+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
215
301
216− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
302+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"18"},"finish_reason":null}]}
217
303
218− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
304+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
219
305
220− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
306+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
221
307
222− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" =\u003e"},"finish_reason":null}]}
308+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
223
309
224− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
310+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"19"},"finish_reason":null}]}
225
311
226− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
312+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
227
313
228− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Source"},"finish_reason":null}]}
314+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
229
315
230− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"graph"},"finish_reason":null}]}
316+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
231
317
232− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
318+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
233
319
234− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"11"},"finish_reason":null}]}
320+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
235
321
236− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
322+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"23"},"finish_reason":null}]}
237
323
238− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" =\u003e"},"finish_reason":null}]}
324+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
239
325
240− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"17"},"finish_reason":null}]}
326+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
241
327
242− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
328+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
243
329
244− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
330+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"24"},"finish_reason":null}]}
245
331
246− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
332+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
247
333
248− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
334+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
249
335
250− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" =\u003e"},"finish_reason":null}]}
336+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
251
337
252− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"18"},"finish_reason":null}]}
338+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
253
339
254− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
340+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
255
341
256− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
342+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"26"},"finish_reason":null}]}
257
343
258− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
344+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
259
345
260− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
346+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
261
347
262− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")=\u003e"},"finish_reason":null}]}
348+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
263
349
264− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"20"},"finish_reason":null}]}
350+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"27"},"finish_reason":null}]}
265
351
266− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
352+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
267
353
268− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
354+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Go"},"finish_reason":null}]}
269
355
270− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
356+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
271
357
272− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
358+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
273
359
274− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"=\u003e"},"finish_reason":null}]}
360+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
275
361
276− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"21"},"finish_reason":null}]}
362+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"29"},"finish_reason":null}]}
277
363
278− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
364+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
279
365
280− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Find"},"finish_reason":null}]}
366+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
281
367
282− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
368+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
283
369
284− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
370+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"30"},"finish_reason":null}]}
285
371
286− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")=\u003e"},"finish_reason":null}]}
372+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
287
373
288− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"25"},"finish_reason":null}]}
374+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" repos"},"finish_reason":null}]}
289
375
290− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
376+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
291
377
292− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
378+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
293
379
294− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
380+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
295
381
296− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
382+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"35"},"finish_reason":null}]}
297
383
298− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"=\u003e"},"finish_reason":null}]}
384+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
299
385
300− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"26"},"finish_reason":null}]}
386+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
301
387
302− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
388+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
303
389
304− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" func"},"finish_reason":null}]}
390+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"36"},"finish_reason":null}]}
305
391
306− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
392+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
307
393
308− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
394+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
309
395
310− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")=\u003e"},"finish_reason":null}]}
396+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
311
397
312− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"30"},"finish_reason":null}]}
398+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
313
399
314− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
400+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
315
401
316− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
402+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"40"},"finish_reason":null}]}
317
403
318− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
404+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
319
405
320− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
406+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
321
407
322− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"=\u003e"},"finish_reason":null}]}
408+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
323
409
324− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"31"},"finish_reason":null}]}
410+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"41"},"finish_reason":null}]}
325
411
326− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
412+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
327
413
328− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
414+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Source"},"finish_reason":null}]}
329
415
330− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
416+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"graph"},"finish_reason":null}]}
331
417
332− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
418+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
333
419
334− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")=\u003e"},"finish_reason":null}]}
420+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"11"},"finish_reason":null}]}
335
421
336− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"35"},"finish_reason":null}]}
422+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
337
423
338− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
424+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"52"},"finish_reason":null}]}
339
425
340− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
426+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
341
427
342− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
428+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
343
429
344− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
430+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
345
431
346− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"=\u003e"},"finish_reason":null}]}
432+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"52"},"finish_reason":null}]}
347
433
348− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"36"},"finish_reason":null}]}
434+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \u003e"},"finish_reason":null}]}
349
435
350− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
436+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
351
437
352− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
438+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
353
439
354− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
440+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Need"},"finish_reason":null}]}
355
441
356− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
442+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" shorter"},"finish_reason":null}]}
357
443
358− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")=\u003e"},"finish_reason":null}]}
444+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".\n\n"},"finish_reason":null}]}
359
445
360− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"38"},"finish_reason":null}]}
446+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Maybe"},"finish_reason":null}]}
361
447
362− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
448+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
363
449
364− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
450+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Source"},"finish_reason":null}]}
365
451
366− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
452+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"graph"},"finish_reason":null}]}
367
453
368− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
454+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" search"},"finish_reason":null}]}
369
455
370− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"=\u003e"},"finish_reason":null}]}
456+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
371
457
372− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"39"},"finish_reason":null}]}
458+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" func"},"finish_reason":null}]}
373
459
374− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
460+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
375
461
376− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Go"},"finish_reason":null}]}
462+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
377
463
378− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
464+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Go"},"finish_reason":null}]}
379
465
380− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
466+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" repos"},"finish_reason":null}]}
381
467
382− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")=\u003e"},"finish_reason":null}]}
468+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
383
469
384− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"41"},"finish_reason":null}]}
470+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
385
471
386− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
472+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
387
473
388− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
474+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Source"},"finish_reason":null}]}
389
475
390− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
476+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"graph"},"finish_reason":null}]}
391
477
392− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
478+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
393
479
394− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"=\u003e"},"finish_reason":null}]}
480+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"11"},"finish_reason":null}]}
395
481
396− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"42"},"finish_reason":null}]}
482+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")+"},"finish_reason":null}]}
397
483
398− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
484+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"space"},"finish_reason":null}]}
399
485
400− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Re"},"finish_reason":null}]}
486+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
401
487
402− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"pos"},"finish_reason":null}]}
488+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"12"},"finish_reason":null}]}
403
489
404− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
490+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
405
491
406− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
492+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"search"},"finish_reason":null}]}
407
493
408− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")=\u003e"},"finish_reason":null}]}
494+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
409
495
410− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"47"},"finish_reason":null}]}
496+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
411
497
412− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
498+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
413
499
414− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Under"},"finish_reason":null}]}
500+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"18"},"finish_reason":null}]}
415
501
416− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
502+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
417
503
418− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
504+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"space"},"finish_reason":null}]}
419
505
420− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
506+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
421
507
422− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" okay"},"finish_reason":null}]}
508+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"19"},"finish_reason":null}]}
423
509
424− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
510+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
425
511
426− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" No"},"finish_reason":null}]}
512+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"for"},"finish_reason":null}]}
427
513
428− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
514+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
429
515
430− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" or"},"finish_reason":null}]}
516+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
431
517
432− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" col"},"finish_reason":null}]}
518+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
433
519
434− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ons"},"finish_reason":null}]}
520+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"22"},"finish_reason":null}]}
435
521
436− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
522+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
437
523
438− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" One"},"finish_reason":null}]}
524+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"space"},"finish_reason":null}]}
439
525
440− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
526+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
441
527
442− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
528+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"23"},"finish_reason":null}]}
443
529
444− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Return"},"finish_reason":null}]}
530+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
445
531
446− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that"},"finish_reason":null}]}
532+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"func"},"finish_reason":null}]}
447
533
448− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
534+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
449
535
450− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Using"},"finish_reason":null}]}
536+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
451
537
452− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Source"},"finish_reason":null}]}
538+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
453
539
454− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"graph"},"finish_reason":null}]}
540+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"27"},"finish_reason":null}]}
455
541
456− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" to"},"finish_reason":null}]}
542+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
457
543
458− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Find"},"finish_reason":null}]}
544+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"space"},"finish_reason":null}]}
459
545
460− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" func"},"finish_reason":null}]}
546+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
461
547
462− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" main"},"finish_reason":null}]}
548+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"28"},"finish_reason":null}]}
463
549
464− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" in"},"finish_reason":null}]}
550+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
465
551
466− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Go"},"finish_reason":null}]}
552+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"main"},"finish_reason":null}]}
467
553
468− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Re"},"finish_reason":null}]}
554+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
469
555
470− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"pos"},"finish_reason":null}]}
556+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
471
557
472− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
558+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
473
559
474− data: {"id":"chatcmpl-b7b08c82ee26f8d6d7cb91fc","object":"chat.completion.chunk","created":1778601767,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":24,"completion_tokens":231,"total_tokens":447,"prompt_tokens_details":{"cached_tokens":192}}}
560+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"32"},"finish_reason":null}]}
475
561
476− data: [DONE]
562+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
477
563
478− headers:
564+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"space"},"finish_reason":null}]}
479− Content-Type:
565+
480− - text/event-stream
566+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
481− status: 200 OK
567+
482− code: 200
568+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"33"},"finish_reason":null}]}
483− duration: 432.945167ms
569+
484−- id: 1
570+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
485− request:
571+
486− proto: HTTP/1.1
572+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"in"},"finish_reason":null}]}
487− proto_major: 1
573+
488− proto_minor: 1
574+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
489− content_length: 33744
575+
490− host: ""
576+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
491− 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/sourcegraph_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\",\"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 sourcegraph to search for 'func main' in Go repositories\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
577+
492− headers:
578+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
493− Accept:
579+
494− - application/json
580+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"35"},"finish_reason":null}]}
495− Content-Type:
581+
496− - application/json
582+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
497− User-Agent:
498− - Charm-Crush/devel (https://charm.land/crush)
499− url: https://hyper.charm.land/v1/chat/completions
500− method: POST
501− response:
502− proto: HTTP/2.0
503− proto_major: 2
504− proto_minor: 0
505− content_length: -1
506− uncompressed: true
507− body: |+
508− data: {"id":"chatcmpl-1507a9a06fbf24ffeba5605d","object":"chat.completion.chunk","created":1778601770,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
509
583
510− data: {"id":"chatcmpl-1507a9a06fbf24ffeba5605d","object":"chat.completion.chunk","created":1778601770,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
584+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"space"},"finish_reason":null}]}
511
585
512− data: {"id":"chatcmpl-1507a9a06fbf24ffeba5605d","object":"chat.completion.chunk","created":1778601770,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
586+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
513
587
514− data: {"id":"chatcmpl-1507a9a06fbf24ffeba5605d","object":"chat.completion.chunk","created":1778601770,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" wants me to"},"finish_reason":null}]}
588+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"36"},"finish_reason":null}]}
515
589
516− data: {"id":"chatcmpl-1507a9a06fbf24ffeba5605d","object":"chat.completion.chunk","created":1778601770,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" search"},"finish_reason":null}]}
590+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
517
591
518− data: {"id":"chatcmpl-1507a9a06fbf24ffeba5605d","object":"chat.completion.chunk","created":1778601770,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" for '"},"finish_reason":null}]}
592+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Go"},"finish_reason":null}]}
519
593
520− data: {"id":"chatcmpl-1507a9a06fbf24ffeba5605d","object":"chat.completion.chunk","created":1778601770,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"func"},"finish_reason":null}]}
594+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
521
595
522− data: {"id":"chatcmpl-1507a9a06fbf24ffeba5605d","object":"chat.completion.chunk","created":1778601770,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" main' in"},"finish_reason":null}]}
596+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
523
597
524− data: {"id":"chatcmpl-1507a9a06fbf24ffeba5605d","object":"chat.completion.chunk","created":1778601770,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" Go repositories"},"finish_reason":null}]}
598+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
525
599
526− data: {"id":"chatcmpl-1507a9a06fbf24ffeba5605d","object":"chat.completion.chunk","created":1778601770,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" using the"},"finish_reason":null}]}
600+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"38"},"finish_reason":null}]}
527
601
528− data: {"id":"chatcmpl-1507a9a06fbf24ffeba5605d","object":"chat.completion.chunk","created":1778601770,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" Sourcegraph"},"finish_reason":null}]}
602+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
529
603
530− data: {"id":"chatcmpl-1507a9a06fbf24ffeba5605d","object":"chat.completion.chunk","created":1778601770,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" tool."},"finish_reason":null}]}
604+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"space"},"finish_reason":null}]}
531
605
532− data: {"id":"chatcmpl-1507a9a06fbf24ffeba5605d","object":"chat.completion.chunk","created":1778601770,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_2119903f18294120853e87c3","type":"function","index":0,"function":{"name":"sourcegraph","arguments":""}}]},"finish_reason":null}]}
606+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
533
607
534− data: {"id":"chatcmpl-1507a9a06fbf24ffeba5605d","object":"chat.completion.chunk","created":1778601770,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
608+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"39"},"finish_reason":null}]}
535
609
536− data: {"id":"chatcmpl-1507a9a06fbf24ffeba5605d","object":"chat.completion.chunk","created":1778601770,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
610+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
537
611
538− data: {"id":"chatcmpl-1507a9a06fbf24ffeba5605d","object":"chat.completion.chunk","created":1778601770,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"count\": "}}]},"finish_reason":null}]}
612+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"repos"},"finish_reason":null}]}
539
613
540− data: {"id":"chatcmpl-1507a9a06fbf24ffeba5605d","object":"chat.completion.chunk","created":1778601770,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"20"}}]},"finish_reason":null}]}
614+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
541
615
542− data: {"id":"chatcmpl-1507a9a06fbf24ffeba5605d","object":"chat.completion.chunk","created":1778601770,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":", "}}]},"finish_reason":null}]}
616+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
543
617
544− data: {"id":"chatcmpl-1507a9a06fbf24ffeba5605d","object":"chat.completion.chunk","created":1778601770,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"query\": "}}]},"finish_reason":null}]}
618+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
545
619
546− data: {"id":"chatcmpl-1507a9a06fbf24ffeba5605d","object":"chat.completion.chunk","created":1778601770,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"func main"}}]},"finish_reason":null}]}
620+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"44"},"finish_reason":null}]}
547
621
548− data: {"id":"chatcmpl-1507a9a06fbf24ffeba5605d","object":"chat.completion.chunk","created":1778601770,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" lang:"}}]},"finish_reason":null}]}
622+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
549
623
550− data: {"id":"chatcmpl-1507a9a06fbf24ffeba5605d","object":"chat.completion.chunk","created":1778601770,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go\""}}]},"finish_reason":null}]}
624+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
551
625
552− data: {"id":"chatcmpl-1507a9a06fbf24ffeba5605d","object":"chat.completion.chunk","created":1778601770,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
626+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
553
627
554− data: {"id":"chatcmpl-1507a9a06fbf24ffeba5605d","object":"chat.completion.chunk","created":1778601770,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
628+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"44"},"finish_reason":null}]}
555
629
556− data: {"id":"chatcmpl-1507a9a06fbf24ffeba5605d","object":"chat.completion.chunk","created":1778601770,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":730,"completion_tokens":42,"total_tokens":7812,"prompt_tokens_details":{"cached_tokens":7040},"completion_tokens_details":{"reasoning_tokens":20}}}
630+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
631+
632+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Good"},"finish_reason":null}]}
633+
634+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".\n\n"},"finish_reason":null}]}
635+
636+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Return"},"finish_reason":null}]}
637+
638+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that"},"finish_reason":null}]}
639+
640+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
641+
642+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
643+
644+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Source"},"finish_reason":null}]}
645+
646+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"graph"},"finish_reason":null}]}
647+
648+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" search"},"finish_reason":null}]}
649+
650+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" for"},"finish_reason":null}]}
651+
652+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" func"},"finish_reason":null}]}
653+
654+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" main"},"finish_reason":null}]}
655+
656+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" in"},"finish_reason":null}]}
657+
658+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Go"},"finish_reason":null}]}
659+
660+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" repos"},"finish_reason":null}]}
661+
662+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
663+
664+ data: {"id":"chatcmpl-204c63286d943aa63cde05c2","object":"chat.completion.chunk","created":1778602965,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":24,"completion_tokens":283,"total_tokens":499,"prompt_tokens_details":{"cached_tokens":192}}}
557
665
558 data: [DONE]
666 data: [DONE]
559
667
@@ -562,7 +670,7 @@ interactions:
562 - text/event-stream
670 - text/event-stream
563 status: 200 OK
671 status: 200 OK
564 code: 200
672 code: 200
565− duration: 3.269446209s
673+ duration: 591.566875ms
566- id: 2
674- id: 2
567 request:
675 request:
568 proto: HTTP/1.1
676 proto: HTTP/1.1
@@ -584,21 +692,21 @@ interactions:
584 proto_minor: 0
692 proto_minor: 0
585 content_length: -1
693 content_length: -1
586 uncompressed: true
694 uncompressed: true
587− body: '{"data":{"search":{"results":{"matchCount":30,"limitHit":true,"resultCount":30,"approximateResultCount":"30+","missing":[],"timedout":[],"indexUnavailable":false,"results":[{"__typename":"FileMatch","repository":{"name":"github.com/GoesToEleven/GolangTraining"},"file":{"path":"14_functions/10_func-expression/01_before-func-expression/main.go","url":"/r/github.com/GoesToEleven/GolangTraining/-/blob/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"},"lineMatches":[{"preview":"func main() {","lineNumber":8,"offsetAndLengths":[[0,9]]},{"preview":"package main","lineNumber":0,"offsetAndLengths":[[8,4]]},{"preview":"func greeting() {","lineNumber":4,"offsetAndLengths":[[0,4]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/GoesToEleven/GolangTraining"},"file":{"path":"14_functions/10_func-expression/02_func-expression/main.go","url":"/r/github.com/GoesToEleven/GolangTraining/-/blob/14_functions/10_func-expression/02_func-expression/main.go","content":"package main\n\nimport \"fmt\"\n\nfunc main() {\n\n\tgreeting := func() {\n\t\tfmt.Println(\"Hello world!\")\n\t}\n\n\tgreeting()\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":4,"offsetAndLengths":[[0,9]]},{"preview":"\tgreeting := func() {","lineNumber":6,"offsetAndLengths":[[13,4]]},{"preview":"package main","lineNumber":0,"offsetAndLengths":[[8,4]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/GoesToEleven/GolangTraining"},"file":{"path":"14_functions/10_func-expression/03_func-expression_shows-type/main.go","url":"/r/github.com/GoesToEleven/GolangTraining/-/blob/14_functions/10_func-expression/03_func-expression_shows-type/main.go","content":"package main\n\nimport \"fmt\"\n\nfunc main() {\n\n\tgreeting := func() {\n\t\tfmt.Println(\"Hello world!\")\n\t}\n\n\tgreeting()\n\tfmt.Printf(\"%T\\n\", greeting)\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":4,"offsetAndLengths":[[0,9]]},{"preview":"\tgreeting := func() {","lineNumber":6,"offsetAndLengths":[[13,4]]},{"preview":"package main","lineNumber":0,"offsetAndLengths":[[8,4]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/GoesToEleven/GolangTraining"},"file":{"path":"14_functions/10_func-expression/04_another-way_func-expression/main.go","url":"/r/github.com/GoesToEleven/GolangTraining/-/blob/14_functions/10_func-expression/04_another-way_func-expression/main.go","content":"package main\n\nimport \"fmt\"\n\nfunc makeGreeter() func() string {\n\treturn func() string {\n\t\treturn \"Hello world!\"\n\t}\n}\n\nfunc main() {\n\tgreet := makeGreeter()\n\tfmt.Println(greet())\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":10,"offsetAndLengths":[[0,9]]},{"preview":"package main","lineNumber":0,"offsetAndLengths":[[8,4]]},{"preview":"func makeGreeter() func() string {","lineNumber":4,"offsetAndLengths":[[0,4],[19,4]]},{"preview":"\treturn func() string {","lineNumber":5,"offsetAndLengths":[[8,4]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/GoesToEleven/GolangTraining"},"file":{"path":"14_functions/10_func-expression/05_another-way_func-expression_shows-type/main.go","url":"/r/github.com/GoesToEleven/GolangTraining/-/blob/14_functions/10_func-expression/05_another-way_func-expression_shows-type/main.go","content":"package main\n\nimport \"fmt\"\n\nfunc makeGreeter() func() string {\n\treturn func() string {\n\t\treturn \"Hello world!\"\n\t}\n}\n\nfunc main() {\n\tgreet := makeGreeter()\n\tfmt.Println(greet())\n\tfmt.Printf(\"%T\\n\", greet)\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":10,"offsetAndLengths":[[0,9]]},{"preview":"package main","lineNumber":0,"offsetAndLengths":[[8,4]]},{"preview":"func makeGreeter() func() string {","lineNumber":4,"offsetAndLengths":[[0,4],[19,4]]},{"preview":"\treturn func() string {","lineNumber":5,"offsetAndLengths":[[8,4]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/mauricioabreu/golings"},"file":{"path":"exercises/functions/functions1/main.go","url":"/r/github.com/mauricioabreu/golings/-/blob/exercises/functions/functions1/main.go","content":"// functions1\n// Make me compile!\n\n// I AM NOT DONE\npackage main\n\nfunc main() {\n\tcall_me()\n}\n"},"lineMatches":[{"preview":"package main","lineNumber":4,"offsetAndLengths":[[8,4]]},{"preview":"func main() {","lineNumber":6,"offsetAndLengths":[[0,9]]},{"preview":"// functions1","lineNumber":0,"offsetAndLengths":[[3,4]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/mauricioabreu/golings"},"file":{"path":"exercises/anonymous_functions/anonymous_functions2/main.go","url":"/r/github.com/mauricioabreu/golings/-/blob/exercises/anonymous_functions/anonymous_functions2/main.go","content":"// anonymous functions2\n// Make me compile!\n\n// I AM NOT DONE\npackage main\n\nimport \"fmt\"\n\nfunc main() {\n\tvar sayBye func(name string)\n\n\tsayBye = func() {\n\t\tfmt.Printf(\"Bye %s\", n)\n\t}\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":8,"offsetAndLengths":[[0,9]]},{"preview":"\tvar sayBye func(name string)","lineNumber":9,"offsetAndLengths":[[12,4]]},{"preview":"\tsayBye = func() {","lineNumber":11,"offsetAndLengths":[[10,4]]},{"preview":"package main","lineNumber":4,"offsetAndLengths":[[8,4]]},{"preview":"// anonymous functions2","lineNumber":0,"offsetAndLengths":[[13,4]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/mauricioabreu/golings"},"file":{"path":"exercises/anonymous_functions/anonymous_functions1/main.go","url":"/r/github.com/mauricioabreu/golings/-/blob/exercises/anonymous_functions/anonymous_functions1/main.go","content":"// anonymous functions1\n// Make me compile!\n\n// I AM NOT DONE\npackage main\n\nimport \"fmt\"\n\nfunc main() {\n\n\tfunc(name string) {\n\t\tfmt.Printf(\"Hello %s\", name)\n\t}()\n\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":8,"offsetAndLengths":[[0,9]]},{"preview":"\tfunc(name string) {","lineNumber":10,"offsetAndLengths":[[1,4]]},{"preview":"package main","lineNumber":4,"offsetAndLengths":[[8,4]]}]}]}}}}'
695+ body: '{"data":{"search":{"results":{"matchCount":30,"limitHit":true,"resultCount":30,"approximateResultCount":"30+","missing":[],"timedout":[],"indexUnavailable":false,"results":[{"__typename":"FileMatch","repository":{"name":"github.com/astaxie/build-web-application-with-golang"},"file":{"path":"fa/code/src/apps/ch.2.3/hidden_print_methods/main.go","url":"/r/github.com/astaxie/build-web-application-with-golang/-/blob/fa/code/src/apps/ch.2.3/hidden_print_methods/main.go","content":"// As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.\n// However it''s encouraged to use the print functions from the `fmt` package.\npackage main\n\nimport \"fmt\"\n\nfunc f() {\n\tfmt.Println(\"First\")\n\tprint(\"Second \")\n\tprintln(\" Third\")\n}\nfunc main() {\n\tf()\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":11,"offsetAndLengths":[[0,9]]},{"preview":"func f() {","lineNumber":6,"offsetAndLengths":[[0,4]]},{"preview":"// As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.","lineNumber":0,"offsetAndLengths":[[63,4]]},{"preview":"// However it''s encouraged to use the print functions from the `fmt` package.","lineNumber":1,"offsetAndLengths":[[44,4]]},{"preview":"package main","lineNumber":2,"offsetAndLengths":[[8,4]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/astaxie/build-web-application-with-golang"},"file":{"path":"en/code/src/apps/ch.2.3/hidden_print_methods/main.go","url":"/r/github.com/astaxie/build-web-application-with-golang/-/blob/en/code/src/apps/ch.2.3/hidden_print_methods/main.go","content":"// As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.\n// However it''s encouraged to use the print functions from the `fmt` package.\npackage main\n\nimport \"fmt\"\n\nfunc f() {\n\tfmt.Println(\"First\")\n\tprint(\"Second \")\n\tprintln(\" Third\")\n}\nfunc main() {\n\tf()\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":11,"offsetAndLengths":[[0,9]]},{"preview":"func f() {","lineNumber":6,"offsetAndLengths":[[0,4]]},{"preview":"// As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.","lineNumber":0,"offsetAndLengths":[[63,4]]},{"preview":"// However it''s encouraged to use the print functions from the `fmt` package.","lineNumber":1,"offsetAndLengths":[[44,4]]},{"preview":"package main","lineNumber":2,"offsetAndLengths":[[8,4]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/astaxie/build-web-application-with-golang"},"file":{"path":"de/code/src/apps/ch.2.3/hidden_print_methods/main.go","url":"/r/github.com/astaxie/build-web-application-with-golang/-/blob/de/code/src/apps/ch.2.3/hidden_print_methods/main.go","content":"// As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.\n// However it''s encouraged to use the print functions from the `fmt` package.\npackage main\n\nimport \"fmt\"\n\nfunc f() {\n\tfmt.Println(\"First\")\n\tprint(\"Second \")\n\tprintln(\" Third\")\n}\nfunc main() {\n\tf()\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":11,"offsetAndLengths":[[0,9]]},{"preview":"func f() {","lineNumber":6,"offsetAndLengths":[[0,4]]},{"preview":"// As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.","lineNumber":0,"offsetAndLengths":[[63,4]]},{"preview":"// However it''s encouraged to use the print functions from the `fmt` package.","lineNumber":1,"offsetAndLengths":[[44,4]]},{"preview":"package main","lineNumber":2,"offsetAndLengths":[[8,4]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/astaxie/build-web-application-with-golang"},"file":{"path":"th/code/src/apps/ch.2.3/hidden_print_methods/main.go","url":"/r/github.com/astaxie/build-web-application-with-golang/-/blob/th/code/src/apps/ch.2.3/hidden_print_methods/main.go","content":"// As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.\n// However it''s encouraged to use the print functions from the `fmt` package.\npackage main\n\nimport \"fmt\"\n\nfunc f() {\n\tfmt.Println(\"First\")\n\tprint(\"Second \")\n\tprintln(\" Third\")\n}\nfunc main() {\n\tf()\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":11,"offsetAndLengths":[[0,9]]},{"preview":"func f() {","lineNumber":6,"offsetAndLengths":[[0,4]]},{"preview":"// As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.","lineNumber":0,"offsetAndLengths":[[63,4]]},{"preview":"// However it''s encouraged to use the print functions from the `fmt` package.","lineNumber":1,"offsetAndLengths":[[44,4]]},{"preview":"package main","lineNumber":2,"offsetAndLengths":[[8,4]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/astaxie/build-web-application-with-golang"},"file":{"path":"de/code/src/apps/ch.2.3/basic_functions/main.go","url":"/r/github.com/astaxie/build-web-application-with-golang/-/blob/de/code/src/apps/ch.2.3/basic_functions/main.go","content":"// Example code for Chapter 2.3 from \"Build Web Application with Golang\"\n// Purpose: Creating a basic function\npackage main\n\nimport \"fmt\"\n\n// return greater value between a and b\nfunc max(a, b int) int {\n\tif a \u003e b {\n\t\treturn a\n\t}\n\treturn b\n}\n\nfunc main() {\n\tx := 3\n\ty := 4\n\tz := 5\n\n\tmax_xy := max(x, y) // call function max(x, y)\n\tmax_xz := max(x, z) // call function max(x, z)\n\n\tfmt.Printf(\"max(%d, %d) = %d\\n\", x, y, max_xy)\n\tfmt.Printf(\"max(%d, %d) = %d\\n\", x, z, max_xz)\n\tfmt.Printf(\"max(%d, %d) = %d\\n\", y, z, max(y, z)) // call function here\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":14,"offsetAndLengths":[[0,9]]},{"preview":"// Purpose: Creating a basic function","lineNumber":1,"offsetAndLengths":[[29,4]]},{"preview":"package main","lineNumber":2,"offsetAndLengths":[[8,4]]},{"preview":"func max(a, b int) int {","lineNumber":7,"offsetAndLengths":[[0,4]]},{"preview":"\tmax_xy := max(x, y) // call function max(x, y)","lineNumber":19,"offsetAndLengths":[[29,4]]},{"preview":"\tmax_xz := max(x, z) // call function max(x, z)","lineNumber":20,"offsetAndLengths":[[29,4]]},{"preview":"\tfmt.Printf(\"max(%d, %d) = %d\\n\", y, z, max(y, z)) // call function here","lineNumber":24,"offsetAndLengths":[[59,4]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/astaxie/build-web-application-with-golang"},"file":{"path":"en/code/src/apps/ch.2.3/basic_functions/main.go","url":"/r/github.com/astaxie/build-web-application-with-golang/-/blob/en/code/src/apps/ch.2.3/basic_functions/main.go","content":"// Example code for Chapter 2.3 from \"Build Web Application with Golang\"\n// Purpose: Creating a basic function\npackage main\n\nimport \"fmt\"\n\n// return greater value between a and b\nfunc max(a, b int) int {\n\tif a \u003e b {\n\t\treturn a\n\t}\n\treturn b\n}\n\nfunc main() {\n\tx := 3\n\ty := 4\n\tz := 5\n\n\tmax_xy := max(x, y) // call function max(x, y)\n\tmax_xz := max(x, z) // call function max(x, z)\n\n\tfmt.Printf(\"max(%d, %d) = %d\\n\", x, y, max_xy)\n\tfmt.Printf(\"max(%d, %d) = %d\\n\", x, z, max_xz)\n\tfmt.Printf(\"max(%d, %d) = %d\\n\", y, z, max(y, z)) // call function here\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":14,"offsetAndLengths":[[0,9]]},{"preview":"// Purpose: Creating a basic function","lineNumber":1,"offsetAndLengths":[[29,4]]},{"preview":"package main","lineNumber":2,"offsetAndLengths":[[8,4]]}]}]}}}}'
588 headers:
696 headers:
589 Content-Type:
697 Content-Type:
590 - application/json
698 - application/json
591 status: 200 OK
699 status: 200 OK
592 code: 200
700 code: 200
593− duration: 1.383383209s
701+ duration: 2.249265625s
594- id: 3
702- id: 3
595 request:
703 request:
596 proto: HTTP/1.1
704 proto: HTTP/1.1
597 proto_major: 1
705 proto_major: 1
598 proto_minor: 1
706 proto_minor: 1
599− content_length: 42747
707+ content_length: 47233
600 host: ""
708 host: ""
601− 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/sourcegraph_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\",\"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 sourcegraph to search for 'func main' in Go repositories\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_2119903f18294120853e87c3\",\"function\":{\"arguments\":\"{\\\"count\\\": 20, \\\"query\\\": \\\"func main lang:go\\\"}\",\"name\":\"sourcegraph\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"The user wants me to search for 'func main' in Go repositories using the Sourcegraph tool.\"},{\"content\":\"# 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/GoesToEleven/GolangTraining/14_functions/10_func-expression/01_before-func-expression/main.go\\n\\nURL: /r/github.com/GoesToEleven/GolangTraining/-/blob/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| \\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```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| func greeting() {\\n5| func greeting() {\\n6| \\tfmt.Println(\\\"Hello world!\\\")\\n7| }\\n8| \\n9| func main() {\\n10| \\tgreeting()\\n11| }\\n12| \\n```\\n\\n## Result 2: github.com/GoesToEleven/GolangTraining/14_functions/10_func-expression/02_func-expression/main.go\\n\\nURL: /r/github.com/GoesToEleven/GolangTraining/-/blob/14_functions/10_func-expression/02_func-expression/main.go\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| func main() {\\n5| func main() {\\n6| \\n7| \\tgreeting := func() {\\n8| \\t\\tfmt.Println(\\\"Hello world!\\\")\\n9| \\t}\\n10| \\n11| \\tgreeting()\\n12| }\\n13| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func main() {\\n6| \\tgreeting := func() {\\n7| \\tgreeting := func() {\\n8| \\t\\tfmt.Println(\\\"Hello world!\\\")\\n9| \\t}\\n10| \\n11| \\tgreeting()\\n12| }\\n13| \\n```\\n\\n```\\n0| package main\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func main() {\\n6| \\n7| \\tgreeting := func() {\\n8| \\t\\tfmt.Println(\\\"Hello world!\\\")\\n9| \\t}\\n10| \\n```\\n\\n## Result 3: github.com/GoesToEleven/GolangTraining/14_functions/10_func-expression/03_func-expression_shows-type/main.go\\n\\nURL: /r/github.com/GoesToEleven/GolangTraining/-/blob/14_functions/10_func-expression/03_func-expression_shows-type/main.go\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| func main() {\\n5| func main() {\\n6| \\n7| \\tgreeting := func() {\\n8| \\t\\tfmt.Println(\\\"Hello world!\\\")\\n9| \\t}\\n10| \\n11| \\tgreeting()\\n12| \\tfmt.Printf(\\\"%T\\\\n\\\", greeting)\\n13| }\\n14| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func main() {\\n6| \\tgreeting := func() {\\n7| \\tgreeting := func() {\\n8| \\t\\tfmt.Println(\\\"Hello world!\\\")\\n9| \\t}\\n10| \\n11| \\tgreeting()\\n12| \\tfmt.Printf(\\\"%T\\\\n\\\", greeting)\\n13| }\\n14| \\n```\\n\\n```\\n0| package main\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func main() {\\n6| \\n7| \\tgreeting := func() {\\n8| \\t\\tfmt.Println(\\\"Hello world!\\\")\\n9| \\t}\\n10| \\n```\\n\\n## Result 4: github.com/GoesToEleven/GolangTraining/14_functions/10_func-expression/04_another-way_func-expression/main.go\\n\\nURL: /r/github.com/GoesToEleven/GolangTraining/-/blob/14_functions/10_func-expression/04_another-way_func-expression/main.go\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func makeGreeter() func() string {\\n6| \\treturn func() string {\\n7| \\t\\treturn \\\"Hello world!\\\"\\n8| \\t}\\n9| }\\n10| func main() {\\n11| func main() {\\n12| \\tgreet := makeGreeter()\\n13| \\tfmt.Println(greet())\\n14| }\\n15| \\n```\\n\\n```\\n0| package main\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func makeGreeter() func() string {\\n6| \\treturn func() string {\\n7| \\t\\treturn \\\"Hello world!\\\"\\n8| \\t}\\n9| }\\n10| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| func makeGreeter() func() string {\\n5| func makeGreeter() func() string {\\n6| \\treturn func() string {\\n7| \\t\\treturn \\\"Hello world!\\\"\\n8| \\t}\\n9| }\\n10| \\n11| func main() {\\n12| \\tgreet := makeGreeter()\\n13| \\tfmt.Println(greet())\\n14| }\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| \\treturn func() string {\\n6| \\treturn func() string {\\n7| \\t\\treturn \\\"Hello world!\\\"\\n8| \\t}\\n9| }\\n10| \\n11| func main() {\\n12| \\tgreet := makeGreeter()\\n13| \\tfmt.Println(greet())\\n14| }\\n15| \\n```\\n\\n## Result 5: github.com/GoesToEleven/GolangTraining/14_functions/10_func-expression/05_another-way_func-expression_shows-type/main.go\\n\\nURL: /r/github.com/GoesToEleven/GolangTraining/-/blob/14_functions/10_func-expression/05_another-way_func-expression_shows-type/main.go\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func makeGreeter() func() string {\\n6| \\treturn func() string {\\n7| \\t\\treturn \\\"Hello world!\\\"\\n8| \\t}\\n9| }\\n10| func main() {\\n11| func main() {\\n12| \\tgreet := makeGreeter()\\n13| \\tfmt.Println(greet())\\n14| \\tfmt.Printf(\\\"%T\\\\n\\\", greet)\\n15| }\\n16| \\n```\\n\\n```\\n0| package main\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func makeGreeter() func() string {\\n6| \\treturn func() string {\\n7| \\t\\treturn \\\"Hello world!\\\"\\n8| \\t}\\n9| }\\n10| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| func makeGreeter() func() string {\\n5| func makeGreeter() func() string {\\n6| \\treturn func() string {\\n7| \\t\\treturn \\\"Hello world!\\\"\\n8| \\t}\\n9| }\\n10| \\n11| func main() {\\n12| \\tgreet := makeGreeter()\\n13| \\tfmt.Println(greet())\\n14| \\tfmt.Printf(\\\"%T\\\\n\\\", greet)\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| \\treturn func() string {\\n6| \\treturn func() string {\\n7| \\t\\treturn \\\"Hello world!\\\"\\n8| \\t}\\n9| }\\n10| \\n11| func main() {\\n12| \\tgreet := makeGreeter()\\n13| \\tfmt.Println(greet())\\n14| \\tfmt.Printf(\\\"%T\\\\n\\\", greet)\\n15| }\\n```\\n\\n## Result 6: github.com/mauricioabreu/golings/exercises/functions/functions1/main.go\\n\\nURL: /r/github.com/mauricioabreu/golings/-/blob/exercises/functions/functions1/main.go\\n\\n```\\n1| // functions1\\n2| // Make me compile!\\n3| \\n4| package main\\n5| package main\\n6| \\n7| func main() {\\n8| \\tcall_me()\\n9| }\\n10| \\n```\\n\\n```\\n1| // functions1\\n2| // Make me compile!\\n3| \\n4| // I AM NOT DONE\\n5| package main\\n6| func main() {\\n7| func main() {\\n8| \\tcall_me()\\n9| }\\n10| \\n```\\n\\n```\\n0| // functions1\\n1| // functions1\\n2| // Make me compile!\\n3| \\n4| // I AM NOT DONE\\n5| package main\\n6| \\n7| func main() {\\n8| \\tcall_me()\\n9| }\\n10| \\n```\\n\\n## Result 7: github.com/mauricioabreu/golings/exercises/anonymous_functions/anonymous_functions2/main.go\\n\\nURL: /r/github.com/mauricioabreu/golings/-/blob/exercises/anonymous_functions/anonymous_functions2/main.go\\n\\n```\\n1| // anonymous functions2\\n2| // Make me compile!\\n3| \\n4| // I AM NOT DONE\\n5| package main\\n6| \\n7| import \\\"fmt\\\"\\n8| func main() {\\n9| func main() {\\n10| \\tvar sayBye func(name string)\\n11| \\n12| \\tsayBye = func() {\\n13| \\t\\tfmt.Printf(\\\"Bye %s\\\", n)\\n14| \\t}\\n15| }\\n16| \\n```\\n\\n```\\n1| // anonymous functions2\\n2| // Make me compile!\\n3| \\n4| // I AM NOT DONE\\n5| package main\\n6| \\n7| import \\\"fmt\\\"\\n8| \\n9| \\tvar sayBye func(name string)\\n10| \\tvar sayBye func(name string)\\n11| \\n12| \\tsayBye = func() {\\n13| \\t\\tfmt.Printf(\\\"Bye %s\\\", n)\\n14| \\t}\\n15| }\\n16| \\n```\\n\\n```\\n1| // anonymous functions2\\n2| // Make me compile!\\n3| \\n4| // I AM NOT DONE\\n5| package main\\n6| \\n7| import \\\"fmt\\\"\\n8| \\n9| func main() {\\n10| \\tvar sayBye func(name string)\\n11| \\tsayBye = func() {\\n12| \\tsayBye = func() {\\n13| \\t\\tfmt.Printf(\\\"Bye %s\\\", n)\\n14| \\t}\\n15| }\\n16| \\n```\\n\\n```\\n1| // anonymous functions2\\n2| // Make me compile!\\n3| \\n4| package main\\n5| package main\\n6| \\n7| import \\\"fmt\\\"\\n8| \\n9| func main() {\\n10| \\tvar sayBye func(name string)\\n11| \\n12| \\tsayBye = func() {\\n13| \\t\\tfmt.Printf(\\\"Bye %s\\\", n)\\n14| \\t}\\n```\\n\\n```\\n0| // anonymous functions2\\n1| // anonymous functions2\\n2| // Make me compile!\\n3| \\n4| // I AM NOT DONE\\n5| package main\\n6| \\n7| import \\\"fmt\\\"\\n8| \\n9| func main() {\\n10| \\tvar sayBye func(name string)\\n```\\n\\n## Result 8: github.com/mauricioabreu/golings/exercises/anonymous_functions/anonymous_functions1/main.go\\n\\nURL: /r/github.com/mauricioabreu/golings/-/blob/exercises/anonymous_functions/anonymous_functions1/main.go\\n\\n```\\n1| // anonymous functions1\\n2| // Make me compile!\\n3| \\n4| // I AM NOT DONE\\n5| package main\\n6| \\n7| import \\\"fmt\\\"\\n8| func main() {\\n9| func main() {\\n10| \\n11| \\tfunc(name string) {\\n12| \\t\\tfmt.Printf(\\\"Hello %s\\\", name)\\n13| \\t}()\\n14| \\n15| }\\n16| \\n```\\n\\n```\\n1| // anonymous functions1\\n2| // Make me compile!\\n3| \\n4| // I AM NOT DONE\\n5| package main\\n6| \\n7| import \\\"fmt\\\"\\n8| \\n9| func main() {\\n10| \\tfunc(name string) {\\n11| \\tfunc(name string) {\\n12| \\t\\tfmt.Printf(\\\"Hello %s\\\", name)\\n13| \\t}()\\n14| \\n15| }\\n16| \\n```\\n\\n```\\n1| // anonymous functions1\\n2| // Make me compile!\\n3| \\n4| package main\\n5| package main\\n6| \\n7| import \\\"fmt\\\"\\n8| \\n9| func main() {\\n10| \\n11| \\tfunc(name string) {\\n12| \\t\\tfmt.Printf(\\\"Hello %s\\\", name)\\n13| \\t}()\\n14| \\n```\\n\\n\",\"tool_call_id\":\"call_2119903f18294120853e87c3\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
709+ 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/sourcegraph_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\",\"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 sourcegraph to search for 'func main' in Go repositories\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_ef7de30a947e4c41a99ddb3f\",\"function\":{\"arguments\":\"{\\\"count\\\": 10, \\\"query\\\": \\\"func main lang:go\\\"}\",\"name\":\"sourcegraph\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"The user wants me to use the Sourcegraph tool to search for 'func main' in Go repositories.\"},{\"content\":\"# 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/astaxie/build-web-application-with-golang/fa/code/src/apps/ch.2.3/hidden_print_methods/main.go\\n\\nURL: /r/github.com/astaxie/build-web-application-with-golang/-/blob/fa/code/src/apps/ch.2.3/hidden_print_methods/main.go\\n\\n```\\n1| // As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.\\n2| // However it's encouraged to use the print functions from the `fmt` package.\\n3| package main\\n4| \\n5| import \\\"fmt\\\"\\n6| \\n7| func f() {\\n8| \\tfmt.Println(\\\"First\\\")\\n9| \\tprint(\\\"Second \\\")\\n10| \\tprintln(\\\" Third\\\")\\n11| func main() {\\n12| func main() {\\n13| \\tf()\\n14| }\\n15| \\n```\\n\\n```\\n1| // As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.\\n2| // However it's encouraged to use the print functions from the `fmt` package.\\n3| package main\\n4| \\n5| import \\\"fmt\\\"\\n6| func f() {\\n7| func f() {\\n8| \\tfmt.Println(\\\"First\\\")\\n9| \\tprint(\\\"Second \\\")\\n10| \\tprintln(\\\" Third\\\")\\n11| }\\n12| func main() {\\n13| \\tf()\\n14| }\\n15| \\n```\\n\\n```\\n0| // As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.\\n1| // As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.\\n2| // However it's encouraged to use the print functions from the `fmt` package.\\n3| package main\\n4| \\n5| import \\\"fmt\\\"\\n6| \\n7| func f() {\\n8| \\tfmt.Println(\\\"First\\\")\\n9| \\tprint(\\\"Second \\\")\\n10| \\tprintln(\\\" Third\\\")\\n```\\n\\n```\\n1| // However it's encouraged to use the print functions from the `fmt` package.\\n2| // However it's encouraged to use the print functions from the `fmt` package.\\n3| package main\\n4| \\n5| import \\\"fmt\\\"\\n6| \\n7| func f() {\\n8| \\tfmt.Println(\\\"First\\\")\\n9| \\tprint(\\\"Second \\\")\\n10| \\tprintln(\\\" Third\\\")\\n11| }\\n```\\n\\n```\\n1| // As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.\\n2| package main\\n3| package main\\n4| \\n5| import \\\"fmt\\\"\\n6| \\n7| func f() {\\n8| \\tfmt.Println(\\\"First\\\")\\n9| \\tprint(\\\"Second \\\")\\n10| \\tprintln(\\\" Third\\\")\\n11| }\\n12| func main() {\\n```\\n\\n## Result 2: github.com/astaxie/build-web-application-with-golang/en/code/src/apps/ch.2.3/hidden_print_methods/main.go\\n\\nURL: /r/github.com/astaxie/build-web-application-with-golang/-/blob/en/code/src/apps/ch.2.3/hidden_print_methods/main.go\\n\\n```\\n1| // As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.\\n2| // However it's encouraged to use the print functions from the `fmt` package.\\n3| package main\\n4| \\n5| import \\\"fmt\\\"\\n6| \\n7| func f() {\\n8| \\tfmt.Println(\\\"First\\\")\\n9| \\tprint(\\\"Second \\\")\\n10| \\tprintln(\\\" Third\\\")\\n11| func main() {\\n12| func main() {\\n13| \\tf()\\n14| }\\n15| \\n```\\n\\n```\\n1| // As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.\\n2| // However it's encouraged to use the print functions from the `fmt` package.\\n3| package main\\n4| \\n5| import \\\"fmt\\\"\\n6| func f() {\\n7| func f() {\\n8| \\tfmt.Println(\\\"First\\\")\\n9| \\tprint(\\\"Second \\\")\\n10| \\tprintln(\\\" Third\\\")\\n11| }\\n12| func main() {\\n13| \\tf()\\n14| }\\n15| \\n```\\n\\n```\\n0| // As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.\\n1| // As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.\\n2| // However it's encouraged to use the print functions from the `fmt` package.\\n3| package main\\n4| \\n5| import \\\"fmt\\\"\\n6| \\n7| func f() {\\n8| \\tfmt.Println(\\\"First\\\")\\n9| \\tprint(\\\"Second \\\")\\n10| \\tprintln(\\\" Third\\\")\\n```\\n\\n```\\n1| // However it's encouraged to use the print functions from the `fmt` package.\\n2| // However it's encouraged to use the print functions from the `fmt` package.\\n3| package main\\n4| \\n5| import \\\"fmt\\\"\\n6| \\n7| func f() {\\n8| \\tfmt.Println(\\\"First\\\")\\n9| \\tprint(\\\"Second \\\")\\n10| \\tprintln(\\\" Third\\\")\\n11| }\\n```\\n\\n```\\n1| // As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.\\n2| package main\\n3| package main\\n4| \\n5| import \\\"fmt\\\"\\n6| \\n7| func f() {\\n8| \\tfmt.Println(\\\"First\\\")\\n9| \\tprint(\\\"Second \\\")\\n10| \\tprintln(\\\" Third\\\")\\n11| }\\n12| func main() {\\n```\\n\\n## Result 3: github.com/astaxie/build-web-application-with-golang/de/code/src/apps/ch.2.3/hidden_print_methods/main.go\\n\\nURL: /r/github.com/astaxie/build-web-application-with-golang/-/blob/de/code/src/apps/ch.2.3/hidden_print_methods/main.go\\n\\n```\\n1| // As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.\\n2| // However it's encouraged to use the print functions from the `fmt` package.\\n3| package main\\n4| \\n5| import \\\"fmt\\\"\\n6| \\n7| func f() {\\n8| \\tfmt.Println(\\\"First\\\")\\n9| \\tprint(\\\"Second \\\")\\n10| \\tprintln(\\\" Third\\\")\\n11| func main() {\\n12| func main() {\\n13| \\tf()\\n14| }\\n15| \\n```\\n\\n```\\n1| // As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.\\n2| // However it's encouraged to use the print functions from the `fmt` package.\\n3| package main\\n4| \\n5| import \\\"fmt\\\"\\n6| func f() {\\n7| func f() {\\n8| \\tfmt.Println(\\\"First\\\")\\n9| \\tprint(\\\"Second \\\")\\n10| \\tprintln(\\\" Third\\\")\\n11| }\\n12| func main() {\\n13| \\tf()\\n14| }\\n15| \\n```\\n\\n```\\n0| // As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.\\n1| // As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.\\n2| // However it's encouraged to use the print functions from the `fmt` package.\\n3| package main\\n4| \\n5| import \\\"fmt\\\"\\n6| \\n7| func f() {\\n8| \\tfmt.Println(\\\"First\\\")\\n9| \\tprint(\\\"Second \\\")\\n10| \\tprintln(\\\" Third\\\")\\n```\\n\\n```\\n1| // However it's encouraged to use the print functions from the `fmt` package.\\n2| // However it's encouraged to use the print functions from the `fmt` package.\\n3| package main\\n4| \\n5| import \\\"fmt\\\"\\n6| \\n7| func f() {\\n8| \\tfmt.Println(\\\"First\\\")\\n9| \\tprint(\\\"Second \\\")\\n10| \\tprintln(\\\" Third\\\")\\n11| }\\n```\\n\\n```\\n1| // As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.\\n2| package main\\n3| package main\\n4| \\n5| import \\\"fmt\\\"\\n6| \\n7| func f() {\\n8| \\tfmt.Println(\\\"First\\\")\\n9| \\tprint(\\\"Second \\\")\\n10| \\tprintln(\\\" Third\\\")\\n11| }\\n12| func main() {\\n```\\n\\n## Result 4: github.com/astaxie/build-web-application-with-golang/th/code/src/apps/ch.2.3/hidden_print_methods/main.go\\n\\nURL: /r/github.com/astaxie/build-web-application-with-golang/-/blob/th/code/src/apps/ch.2.3/hidden_print_methods/main.go\\n\\n```\\n1| // As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.\\n2| // However it's encouraged to use the print functions from the `fmt` package.\\n3| package main\\n4| \\n5| import \\\"fmt\\\"\\n6| \\n7| func f() {\\n8| \\tfmt.Println(\\\"First\\\")\\n9| \\tprint(\\\"Second \\\")\\n10| \\tprintln(\\\" Third\\\")\\n11| func main() {\\n12| func main() {\\n13| \\tf()\\n14| }\\n15| \\n```\\n\\n```\\n1| // As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.\\n2| // However it's encouraged to use the print functions from the `fmt` package.\\n3| package main\\n4| \\n5| import \\\"fmt\\\"\\n6| func f() {\\n7| func f() {\\n8| \\tfmt.Println(\\\"First\\\")\\n9| \\tprint(\\\"Second \\\")\\n10| \\tprintln(\\\" Third\\\")\\n11| }\\n12| func main() {\\n13| \\tf()\\n14| }\\n15| \\n```\\n\\n```\\n0| // As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.\\n1| // As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.\\n2| // However it's encouraged to use the print functions from the `fmt` package.\\n3| package main\\n4| \\n5| import \\\"fmt\\\"\\n6| \\n7| func f() {\\n8| \\tfmt.Println(\\\"First\\\")\\n9| \\tprint(\\\"Second \\\")\\n10| \\tprintln(\\\" Third\\\")\\n```\\n\\n```\\n1| // However it's encouraged to use the print functions from the `fmt` package.\\n2| // However it's encouraged to use the print functions from the `fmt` package.\\n3| package main\\n4| \\n5| import \\\"fmt\\\"\\n6| \\n7| func f() {\\n8| \\tfmt.Println(\\\"First\\\")\\n9| \\tprint(\\\"Second \\\")\\n10| \\tprintln(\\\" Third\\\")\\n11| }\\n```\\n\\n```\\n1| // As of Google go 1.1.2, `println()` and `print()` are hidden functions included from the runtime package.\\n2| package main\\n3| package main\\n4| \\n5| import \\\"fmt\\\"\\n6| \\n7| func f() {\\n8| \\tfmt.Println(\\\"First\\\")\\n9| \\tprint(\\\"Second \\\")\\n10| \\tprintln(\\\" Third\\\")\\n11| }\\n12| func main() {\\n```\\n\\n## Result 5: github.com/astaxie/build-web-application-with-golang/de/code/src/apps/ch.2.3/basic_functions/main.go\\n\\nURL: /r/github.com/astaxie/build-web-application-with-golang/-/blob/de/code/src/apps/ch.2.3/basic_functions/main.go\\n\\n```\\n4| \\n5| import \\\"fmt\\\"\\n6| \\n7| // return greater value between a and b\\n8| func max(a, b int) int {\\n9| \\tif a > b {\\n10| \\t\\treturn a\\n11| \\t}\\n12| \\treturn b\\n13| }\\n14| func main() {\\n15| func main() {\\n16| \\tx := 3\\n17| \\ty := 4\\n18| \\tz := 5\\n19| \\n20| \\tmax_xy := max(x, y) // call function max(x, y)\\n21| \\tmax_xz := max(x, z) // call function max(x, z)\\n22| \\n23| \\tfmt.Printf(\\\"max(%d, %d) = %d\\\\n\\\", x, y, max_xy)\\n24| \\tfmt.Printf(\\\"max(%d, %d) = %d\\\\n\\\", x, z, max_xz)\\n```\\n\\n```\\n1| // Purpose: Creating a basic function\\n2| // Purpose: Creating a basic function\\n3| package main\\n4| \\n5| import \\\"fmt\\\"\\n6| \\n7| // return greater value between a and b\\n8| func max(a, b int) int {\\n9| \\tif a > b {\\n10| \\t\\treturn a\\n11| \\t}\\n```\\n\\n```\\n1| // Example code for Chapter 2.3 from \\\"Build Web Application with Golang\\\"\\n2| package main\\n3| package main\\n4| \\n5| import \\\"fmt\\\"\\n6| \\n7| // return greater value between a and b\\n8| func max(a, b int) int {\\n9| \\tif a > b {\\n10| \\t\\treturn a\\n11| \\t}\\n12| \\treturn b\\n```\\n\\n```\\n1| // Example code for Chapter 2.3 from \\\"Build Web Application with Golang\\\"\\n2| // Purpose: Creating a basic function\\n3| package main\\n4| \\n5| import \\\"fmt\\\"\\n6| \\n7| func max(a, b int) int {\\n8| func max(a, b int) int {\\n9| \\tif a > b {\\n10| \\t\\treturn a\\n11| \\t}\\n12| \\treturn b\\n13| }\\n14| \\n15| func main() {\\n16| \\tx := 3\\n17| \\ty := 4\\n```\\n\\n```\\n9| \\tif a > b {\\n10| \\t\\treturn a\\n11| \\t}\\n12| \\treturn b\\n13| }\\n14| \\n15| func main() {\\n16| \\tx := 3\\n17| \\ty := 4\\n18| \\tz := 5\\n19| \\tmax_xy := max(x, y) // call function max(x, y)\\n20| \\tmax_xy := max(x, y) // call function max(x, y)\\n21| \\tmax_xz := max(x, z) // call function max(x, z)\\n22| \\n23| \\tfmt.Printf(\\\"max(%d, %d) = %d\\\\n\\\", x, y, max_xy)\\n24| \\tfmt.Printf(\\\"max(%d, %d) = %d\\\\n\\\", x, z, max_xz)\\n25| \\tfmt.Printf(\\\"max(%d, %d) = %d\\\\n\\\", y, z, max(y, z)) // call function here\\n26| }\\n27| \\n```\\n\\n```\\n10| \\t\\treturn a\\n11| \\t}\\n12| \\treturn b\\n13| }\\n14| \\n15| func main() {\\n16| \\tx := 3\\n17| \\ty := 4\\n18| \\tz := 5\\n19| \\n20| \\tmax_xz := max(x, z) // call function max(x, z)\\n21| \\tmax_xz := max(x, z) // call function max(x, z)\\n22| \\n23| \\tfmt.Printf(\\\"max(%d, %d) = %d\\\\n\\\", x, y, max_xy)\\n24| \\tfmt.Printf(\\\"max(%d, %d) = %d\\\\n\\\", x, z, max_xz)\\n25| \\tfmt.Printf(\\\"max(%d, %d) = %d\\\\n\\\", y, z, max(y, z)) // call function here\\n26| }\\n27| \\n```\\n\\n```\\n14| \\n15| func main() {\\n16| \\tx := 3\\n17| \\ty := 4\\n18| \\tz := 5\\n19| \\n20| \\tmax_xy := max(x, y) // call function max(x, y)\\n21| \\tmax_xz := max(x, z) // call function max(x, z)\\n22| \\n23| \\tfmt.Printf(\\\"max(%d, %d) = %d\\\\n\\\", x, y, max_xy)\\n24| \\tfmt.Printf(\\\"max(%d, %d) = %d\\\\n\\\", y, z, max(y, z)) // call function here\\n25| \\tfmt.Printf(\\\"max(%d, %d) = %d\\\\n\\\", y, z, max(y, z)) // call function here\\n26| }\\n27| \\n```\\n\\n## Result 6: github.com/astaxie/build-web-application-with-golang/en/code/src/apps/ch.2.3/basic_functions/main.go\\n\\nURL: /r/github.com/astaxie/build-web-application-with-golang/-/blob/en/code/src/apps/ch.2.3/basic_functions/main.go\\n\\n```\\n4| \\n5| import \\\"fmt\\\"\\n6| \\n7| // return greater value between a and b\\n8| func max(a, b int) int {\\n9| \\tif a > b {\\n10| \\t\\treturn a\\n11| \\t}\\n12| \\treturn b\\n13| }\\n14| func main() {\\n15| func main() {\\n16| \\tx := 3\\n17| \\ty := 4\\n18| \\tz := 5\\n19| \\n20| \\tmax_xy := max(x, y) // call function max(x, y)\\n21| \\tmax_xz := max(x, z) // call function max(x, z)\\n22| \\n23| \\tfmt.Printf(\\\"max(%d, %d) = %d\\\\n\\\", x, y, max_xy)\\n24| \\tfmt.Printf(\\\"max(%d, %d) = %d\\\\n\\\", x, z, max_xz)\\n```\\n\\n```\\n1| // Purpose: Creating a basic function\\n2| // Purpose: Creating a basic function\\n3| package main\\n4| \\n5| import \\\"fmt\\\"\\n6| \\n7| // return greater value between a and b\\n8| func max(a, b int) int {\\n9| \\tif a > b {\\n10| \\t\\treturn a\\n11| \\t}\\n```\\n\\n```\\n1| // Example code for Chapter 2.3 from \\\"Build Web Application with Golang\\\"\\n2| package main\\n3| package main\\n4| \\n5| import \\\"fmt\\\"\\n6| \\n7| // return greater value between a and b\\n8| func max(a, b int) int {\\n9| \\tif a > b {\\n10| \\t\\treturn a\\n11| \\t}\\n12| \\treturn b\\n```\\n\\n\",\"tool_call_id\":\"call_ef7de30a947e4c41a99ddb3f\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
602 headers:
710 headers:
603 Accept:
711 Accept:
604 - application/json
712 - application/json
@@ -615,369 +723,209 @@ interactions:
615 content_length: -1
723 content_length: -1
616 uncompressed: true
724 uncompressed: true
617 body: |+
725 body: |+
618− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
726+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
619−
620− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Found"},"finish_reason":null}]}
621−
622− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" 30"},"finish_reason":null}]}
623−
624− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"+ matches"},"finish_reason":null}]}
625−
626− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" across Go"},"finish_reason":null}]}
627−
628− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" repositories"},"finish_reason":null}]}
629−
630− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":". Here"},"finish_reason":null}]}
631−
632− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"'s a summary"},"finish_reason":null}]}
633−
634− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" of the"},"finish_reason":null}]}
635−
636− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" top results"},"finish_reason":null}]}
637−
638− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":":\n\n|"},"finish_reason":null}]}
639−
640− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" #"},"finish_reason":null}]}
641−
642− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" | Repository"},"finish_reason":null}]}
643−
644− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" | File"},"finish_reason":null}]}
645−
646− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" | Context"},"finish_reason":null}]}
647−
648− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" |\n|"},"finish_reason":null}]}
649−
650− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"---|-----------"},"finish_reason":null}]}
651−
652− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"|------"},"finish_reason":null}]}
653−
654− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"|---------"},"finish_reason":null}]}
655−
656− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"|\n|"},"finish_reason":null}]}
657−
658− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" 1 | `"},"finish_reason":null}]}
659−
660− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Goes"},"finish_reason":null}]}
661−
662− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"To"},"finish_reason":null}]}
663−
664− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Ele"},"finish_reason":null}]}
665−
666− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"ven"},"finish_reason":null}]}
667−
668− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"/Golang"},"finish_reason":null}]}
669−
670− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Training"},"finish_reason":null}]}
671−
672− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"` | `..."},"finish_reason":null}]}
673−
674− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"/01"},"finish_reason":null}]}
675−
676− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"_before"},"finish_reason":null}]}
677−
678− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"-f"},"finish_reason":null}]}
679−
680− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"unc-expression"},"finish_reason":null}]}
681−
682− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"/main.go"},"finish_reason":null}]}
683−
684− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"` | Simple"},"finish_reason":null}]}
685−
686− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `"},"finish_reason":null}]}
687−
688− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"func"},"finish_reason":null}]}
689−
690− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" main()`"},"finish_reason":null}]}
691−
692− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" calling `g"},"finish_reason":null}]}
693−
694− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"reeting()`"},"finish_reason":null}]}
695−
696− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" |\n|"},"finish_reason":null}]}
697−
698− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" 2"},"finish_reason":null}]}
699−
700− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" | `G"},"finish_reason":null}]}
701−
702− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"oesToEle"},"finish_reason":null}]}
703−
704− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"ven/Golang"},"finish_reason":null}]}
705−
706− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Training` |"},"finish_reason":null}]}
707−
708− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `.../02"},"finish_reason":null}]}
709−
710− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"_func"},"finish_reason":null}]}
711−
712− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"-expression"},"finish_reason":null}]}
713−
714− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"/main.go"},"finish_reason":null}]}
715−
716− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"` | `func"},"finish_reason":null}]}
717−
718− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" main()`"},"finish_reason":null}]}
719−
720− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" with a"},"finish_reason":null}]}
721−
722− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" function expression"},"finish_reason":null}]}
723−
724− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" assigned to a"},"finish_reason":null}]}
725−
726− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" variable |\n"},"finish_reason":null}]}
727−
728− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"| "},"finish_reason":null}]}
729−
730− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"3 | `G"},"finish_reason":null}]}
731−
732− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"oesToEle"},"finish_reason":null}]}
733−
734− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"ven/Golang"},"finish_reason":null}]}
735−
736− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Training` |"},"finish_reason":null}]}
737−
738− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `.../"},"finish_reason":null}]}
739−
740− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"03_func"},"finish_reason":null}]}
741−
742− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"-expression_sh"},"finish_reason":null}]}
743−
744− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"ows-type"},"finish_reason":null}]}
745−
746− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"/main.go"},"finish_reason":null}]}
747−
748− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"` | Same"},"finish_reason":null}]}
749−
750− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":","},"finish_reason":null}]}
751−
752− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" plus"},"finish_reason":null}]}
753−
754− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" printing the"},"finish_reason":null}]}
755−
756− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" type |\n"},"finish_reason":null}]}
757−
758− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"| "},"finish_reason":null}]}
759−
760− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"4 | `G"},"finish_reason":null}]}
761−
762− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"oesToEle"},"finish_reason":null}]}
763−
764− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"ven/GolangTraining"},"finish_reason":null}]}
765−
766− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"` |"},"finish_reason":null}]}
767−
768− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `.../04"},"finish_reason":null}]}
769−
770− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"_another-way"},"finish_reason":null}]}
771−
772− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"_func"},"finish_reason":null}]}
773−
774− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"-expression/main.go`"},"finish_reason":null}]}
775−
776− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" | `func"},"finish_reason":null}]}
777−
778− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" main()` using"},"finish_reason":null}]}
779
727
780− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" a closure"},"finish_reason":null}]}
728+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Found"},"finish_reason":null}]}
781
729
782− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" returned from `make"},"finish_reason":null}]}
730+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" "},"finish_reason":null}]}
783
731
784− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Gre"},"finish_reason":null}]}
732+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"30+"},"finish_reason":null}]}
785
733
786− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"eter"},"finish_reason":null}]}
734+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" matches across"},"finish_reason":null}]}
787
735
788− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"()` |\n|"},"finish_reason":null}]}
736+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" Go"},"finish_reason":null}]}
789
737
790− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" 5 |"},"finish_reason":null}]}
738+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" repositories"},"finish_reason":null}]}
791
739
792− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `G"},"finish_reason":null}]}
740+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":". Key"},"finish_reason":null}]}
793
741
794− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"oesToEle"},"finish_reason":null}]}
742+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" results include"},"finish_reason":null}]}
795
743
796− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"ven/G"},"finish_reason":null}]}
744+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":":\n\n-"},"finish_reason":null}]}
797
745
798− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"olangTraining"},"finish_reason":null}]}
746+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `"},"finish_reason":null}]}
799
747
800− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"` |"},"finish_reason":null}]}
748+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"github.com/"},"finish_reason":null}]}
801
749
802− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `..."},"finish_reason":null}]}
750+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"astax"},"finish_reason":null}]}
803
751
804− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"/05_an"},"finish_reason":null}]}
752+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"ie/build"},"finish_reason":null}]}
805
753
806− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"other-way"},"finish_reason":null}]}
754+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"-web"},"finish_reason":null}]}
807
755
808− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"_func-expression"},"finish_reason":null}]}
756+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"-application"},"finish_reason":null}]}
809
757
810− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"_shows-type"},"finish_reason":null}]}
758+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"-with"},"finish_reason":null}]}
811
759
812− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"/main.go"},"finish_reason":null}]}
760+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"-g"},"finish_reason":null}]}
813
761
814− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"` |"},"finish_reason":null}]}
762+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"olang"},"finish_reason":null}]}
815
763
816− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" Same with"},"finish_reason":null}]}
764+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"` — multiple"},"finish_reason":null}]}
817
765
818− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" type"},"finish_reason":null}]}
766+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" language"},"finish_reason":null}]}
819
767
820− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" inspection"},"finish_reason":null}]}
768+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" translations"},"finish_reason":null}]}
821
769
822− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" |\n|"},"finish_reason":null}]}
770+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" (en"},"finish_reason":null}]}
823
771
824− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" 6 |"},"finish_reason":null}]}
772+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":", de"},"finish_reason":null}]}
825
773
826− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `maur"},"finish_reason":null}]}
774+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":", fa"},"finish_reason":null}]}
827
775
828− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"icioab"},"finish_reason":null}]}
776+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":", th"},"finish_reason":null}]}
829
777
830− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"reu"},"finish_reason":null}]}
778+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":") with"},"finish_reason":null}]}
831
779
832− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"/g"},"finish_reason":null}]}
780+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `func"},"finish_reason":null}]}
833
781
834− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"olings"},"finish_reason":null}]}
782+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" main()` in"},"finish_reason":null}]}
835
783
836− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"` | `"},"finish_reason":null}]}
784+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" chapter"},"finish_reason":null}]}
837
785
838− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"ex"},"finish_reason":null}]}
786+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" examples"},"finish_reason":null}]}
839
787
840− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"ercises/functions"},"finish_reason":null}]}
788+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" like `"},"finish_reason":null}]}
841
789
842− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"/functions"},"finish_reason":null}]}
790+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"hidden"},"finish_reason":null}]}
843
791
844− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"1"},"finish_reason":null}]}
792+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"_print"},"finish_reason":null}]}
845
793
846− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"/main.go` |"},"finish_reason":null}]}
794+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"_methods"},"finish_reason":null}]}
847
795
848− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" Exercise"},"finish_reason":null}]}
796+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"/main"},"finish_reason":null}]}
849
797
850− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}]}
798+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}]}
851
799
852− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" calling"},"finish_reason":null}]}
800+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"` and `"},"finish_reason":null}]}
853
801
854− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `call"},"finish_reason":null}]}
802+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"basic_functions"},"finish_reason":null}]}
855
803
856− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"_me()`"},"finish_reason":null}]}
804+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"/main.go`\n"},"finish_reason":null}]}
857
805
858− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" from"},"finish_reason":null}]}
806+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"- Common"},"finish_reason":null}]}
859
807
860− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" main |\n|"},"finish_reason":null}]}
808+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" pattern"},"finish_reason":null}]}
861
809
862− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" 7 |"},"finish_reason":null}]}
810+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":": `func"},"finish_reason":null}]}
863
811
864− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `mauricio"},"finish_reason":null}]}
812+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" main()` calling"},"finish_reason":null}]}
865
813
866− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"abreu"},"finish_reason":null}]}
814+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" helper"},"finish_reason":null}]}
867
815
868− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"/golings`"},"finish_reason":null}]}
816+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" functions ("},"finish_reason":null}]}
869
817
870− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" | `ex"},"finish_reason":null}]}
818+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"e.g"},"finish_reason":null}]}
871
819
872− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"ercises/anonymous_functions"},"finish_reason":null}]}
820+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"., `f"},"finish_reason":null}]}
873
821
874− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"/anonymous"},"finish_reason":null}]}
822+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"()`, `max"},"finish_reason":null}]}
875
823
876− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"_functions2"},"finish_reason":null}]}
824+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"()"},"finish_reason":null}]}
877
825
878− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"/main.go` |"},"finish_reason":null}]}
826+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`) with"},"finish_reason":null}]}
879
827
880− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" Exercise: anonymous"},"finish_reason":null}]}
828+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `fmt`"},"finish_reason":null}]}
881
829
882− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" function assignment |\n"},"finish_reason":null}]}
830+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" package"},"finish_reason":null}]}
883
831
884− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"| "},"finish_reason":null}]}
832+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" imports"},"finish_reason":null}]}
885
833
886− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"8 |"},"finish_reason":null}]}
834+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"\n\nThe"},"finish_reason":null}]}
887
835
888− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `mauricio"},"finish_reason":null}]}
836+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" query `"},"finish_reason":null}]}
889
837
890− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"abreu"},"finish_reason":null}]}
838+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"func"},"finish_reason":null}]}
891
839
892− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"/golings`"},"finish_reason":null}]}
840+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" main lang"},"finish_reason":null}]}
893
841
894− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" | `ex"},"finish_reason":null}]}
842+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}]}
895
843
896− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"ercises/anonymous"},"finish_reason":null}]}
844+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"go` is"},"finish_reason":null}]}
897
845
898− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"_functions/anonymous"},"finish_reason":null}]}
846+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" very broad"},"finish_reason":null}]}
899
847
900− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"_functions1"},"finish_reason":null}]}
848+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" — Source"},"finish_reason":null}]}
901
849
902− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"/main.go` |"},"finish_reason":null}]}
850+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"graph"},"finish_reason":null}]}
903
851
904− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" Exercise: immediately"},"finish_reason":null}]}
852+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" found "},"finish_reason":null}]}
905
853
906− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"-inv"},"finish_reason":null}]}
854+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"30 matches"},"finish_reason":null}]}
907
855
908− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"oked anonymous"},"finish_reason":null}]}
856+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" ("},"finish_reason":null}]}
909
857
910− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" function |\n\nThe"},"finish_reason":null}]}
858+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"result"},"finish_reason":null}]}
911
859
912− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" results"},"finish_reason":null}]}
860+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" limit reached"},"finish_reason":null}]}
913
861
914− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" are primarily"},"finish_reason":null}]}
862+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":")."},"finish_reason":null}]}
915
863
916− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" from Go"},"finish_reason":null}]}
864+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" To"},"finish_reason":null}]}
917
865
918− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" training/tutorial"},"finish_reason":null}]}
866+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" narrow results"},"finish_reason":null}]}
919
867
920− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" repos"},"finish_reason":null}]}
868+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":", you"},"finish_reason":null}]}
921
869
922− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" (`Golang"},"finish_reason":null}]}
870+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" could:\n- Add"},"finish_reason":null}]}
923
871
924− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Training`)"},"finish_reason":null}]}
872+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" a repo"},"finish_reason":null}]}
925
873
926− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" and exercise"},"finish_reason":null}]}
874+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" filter"},"finish_reason":null}]}
927
875
928− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" collections"},"finish_reason":null}]}
876+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":": `func"},"finish_reason":null}]}
929
877
930− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" (`g"},"finish_reason":null}]}
878+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" main lang"},"finish_reason":null}]}
931
879
932− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"olings`). To"},"finish_reason":null}]}
880+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":":go"},"finish_reason":null}]}
933
881
934− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" narrow"},"finish_reason":null}]}
882+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" repo:github"},"finish_reason":null}]}
935
883
936− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" results to"},"finish_reason":null}]}
884+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":".com/g"},"finish_reason":null}]}
937
885
938− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" production"},"finish_reason":null}]}
886+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"olang"},"finish_reason":null}]}
939
887
940− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" code"},"finish_reason":null}]}
888+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"/go`\n"},"finish_reason":null}]}
941
889
942− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":", you"},"finish_reason":null}]}
890+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"- Add"},"finish_reason":null}]}
943
891
944− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" could add repo"},"finish_reason":null}]}
892+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" a file"},"finish_reason":null}]}
945
893
946− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" filters"},"finish_reason":null}]}
894+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" pattern"},"finish_reason":null}]}
947
895
948− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" ("},"finish_reason":null}]}
896+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":": `"},"finish_reason":null}]}
949
897
950− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"e.g"},"finish_reason":null}]}
898+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"func main lang"},"finish_reason":null}]}
951
899
952− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"., `-"},"finish_reason":null}]}
900+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":":go"},"finish_reason":null}]}
953
901
954− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"repo"},"finish_reason":null}]}
902+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" file"},"finish_reason":null}]}
955
903
956− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":":G"},"finish_reason":null}]}
904+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":":cmd"},"finish_reason":null}]}
957
905
958− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"oes"},"finish_reason":null}]}
906+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}]}
959
907
960− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"ToEle"},"finish_reason":null}]}
908+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`\n- Use"},"finish_reason":null}]}
961
909
962− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"ven -"},"finish_reason":null}]}
910+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" more specific terms"},"finish_reason":null}]}
963
911
964− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"repo:ma"},"finish_reason":null}]}
912+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" like"},"finish_reason":null}]}
965
913
966− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"uricio"},"finish_reason":null}]}
914+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `func"},"finish_reason":null}]}
967
915
968− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"abreu`)"},"finish_reason":null}]}
916+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" main()"},"finish_reason":null}]}
969
917
970− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" or search"},"finish_reason":null}]}
918+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" error"},"finish_reason":null}]}
971
919
972− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" for more"},"finish_reason":null}]}
920+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" lang"},"finish_reason":null}]}
973
921
974− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" specific patterns"},"finish_reason":null}]}
922+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":":go"},"finish_reason":null}]}
975
923
976− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"."},"finish_reason":null}]}
924+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`"},"finish_reason":null}]}
977
925
978− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
926+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
979
927
980− data: {"id":"chatcmpl-886ba4df675175dc008d9a5e","object":"chat.completion.chunk","created":1778601779,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":10569,"completion_tokens":397,"total_tokens":10966,"completion_tokens_details":{"reasoning_tokens":396}}}
928+ data: {"id":"chatcmpl-4b4d779dcd6b353fe6b4c696","object":"chat.completion.chunk","created":1778602974,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":4876,"completion_tokens":179,"total_tokens":12095,"prompt_tokens_details":{"cached_tokens":7040},"completion_tokens_details":{"reasoning_tokens":178}}}
981
929
982 data: [DONE]
930 data: [DONE]
983
931
@@ -986,4 +934,4 @@ interactions:
986 - text/event-stream
934 - text/event-stream
987 status: 200 OK
935 status: 200 OK
988 code: 200
936 code: 200
989− duration: 6.201306583s
937+ duration: 4.115899875s
internal/agent/testdata/TestCoderAgent/glm-5.1/update_a_file.yaml+958−184
@@ -2,6 +2,142 @@
2version: 2
2version: 2
3interactions:
3interactions:
4- id: 0
4- id: 0
5+ request:
6+ proto: HTTP/1.1
7+ proto_major: 1
8+ proto_minor: 1
9+ content_length: 33750
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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/update_a_file\\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\",\"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\":\"update the main.go file by changing the print to say hello from crush\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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-f9adff0542c019ee204ffef3","object":"chat.completion.chunk","created":1778602879,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
29+
30+ data: {"id":"chatcmpl-f9adff0542c019ee204ffef3","object":"chat.completion.chunk","created":1778602879,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"Let"},"finish_reason":null}]}
31+
32+ data: {"id":"chatcmpl-f9adff0542c019ee204ffef3","object":"chat.completion.chunk","created":1778602879,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" me"},"finish_reason":null}]}
33+
34+ data: {"id":"chatcmpl-f9adff0542c019ee204ffef3","object":"chat.completion.chunk","created":1778602879,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" find and"},"finish_reason":null}]}
35+
36+ data: {"id":"chatcmpl-f9adff0542c019ee204ffef3","object":"chat.completion.chunk","created":1778602879,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" read the main.go"},"finish_reason":null}]}
37+
38+ data: {"id":"chatcmpl-f9adff0542c019ee204ffef3","object":"chat.completion.chunk","created":1778602879,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" file first"},"finish_reason":null}]}
39+
40+ data: {"id":"chatcmpl-f9adff0542c019ee204ffef3","object":"chat.completion.chunk","created":1778602879,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
41+
42+ data: {"id":"chatcmpl-f9adff0542c019ee204ffef3","object":"chat.completion.chunk","created":1778602879,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_1c826621fe604567b9986757","type":"function","index":0,"function":{"name":"glob","arguments":""}}]},"finish_reason":null}]}
43+
44+ data: {"id":"chatcmpl-f9adff0542c019ee204ffef3","object":"chat.completion.chunk","created":1778602879,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
45+
46+ data: {"id":"chatcmpl-f9adff0542c019ee204ffef3","object":"chat.completion.chunk","created":1778602879,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
47+
48+ data: {"id":"chatcmpl-f9adff0542c019ee204ffef3","object":"chat.completion.chunk","created":1778602879,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"pattern\": "}}]},"finish_reason":null}]}
49+
50+ data: {"id":"chatcmpl-f9adff0542c019ee204ffef3","object":"chat.completion.chunk","created":1778602879,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"**"}}]},"finish_reason":null}]}
51+
52+ data: {"id":"chatcmpl-f9adff0542c019ee204ffef3","object":"chat.completion.chunk","created":1778602879,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/"}}]},"finish_reason":null}]}
53+
54+ data: {"id":"chatcmpl-f9adff0542c019ee204ffef3","object":"chat.completion.chunk","created":1778602879,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"main.go\""}}]},"finish_reason":null}]}
55+
56+ data: {"id":"chatcmpl-f9adff0542c019ee204ffef3","object":"chat.completion.chunk","created":1778602879,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
57+
58+ data: {"id":"chatcmpl-f9adff0542c019ee204ffef3","object":"chat.completion.chunk","created":1778602879,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
59+
60+ data: {"id":"chatcmpl-f9adff0542c019ee204ffef3","object":"chat.completion.chunk","created":1778602879,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7771,"completion_tokens":25,"total_tokens":7796,"completion_tokens_details":{"reasoning_tokens":11}}}
61+
62+ data: [DONE]
63+
64+ headers:
65+ Content-Type:
66+ - text/event-stream
67+ status: 200 OK
68+ code: 200
69+ duration: 1.642232666s
70+- id: 1
71+ request:
72+ proto: HTTP/1.1
73+ proto_major: 1
74+ proto_minor: 1
75+ content_length: 34117
76+ host: ""
77+ 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/update_a_file\\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\",\"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\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_1c826621fe604567b9986757\",\"function\":{\"arguments\":\"{\\\"pattern\\\": \\\"**/main.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"Let me find and read the main.go file first.\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/glm-5.1/update_a_file/main.go\",\"tool_call_id\":\"call_1c826621fe604567b9986757\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
78+ headers:
79+ Accept:
80+ - application/json
81+ Content-Type:
82+ - application/json
83+ User-Agent:
84+ - Charm-Crush/devel (https://charm.land/crush)
85+ url: https://hyper.charm.land/v1/chat/completions
86+ method: POST
87+ response:
88+ proto: HTTP/2.0
89+ proto_major: 2
90+ proto_minor: 0
91+ content_length: -1
92+ uncompressed: true
93+ body: |+
94+ data: {"id":"chatcmpl-631b0942bd9a982887845ca5","object":"chat.completion.chunk","created":1778602882,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
95+
96+ data: {"id":"chatcmpl-631b0942bd9a982887845ca5","object":"chat.completion.chunk","created":1778602882,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_5a22ba8e8d334aec807c16a0","type":"function","index":0,"function":{"name":"view","arguments":""}}]},"finish_reason":null}]}
97+
98+ data: {"id":"chatcmpl-631b0942bd9a982887845ca5","object":"chat.completion.chunk","created":1778602882,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
99+
100+ data: {"id":"chatcmpl-631b0942bd9a982887845ca5","object":"chat.completion.chunk","created":1778602882,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
101+
102+ data: {"id":"chatcmpl-631b0942bd9a982887845ca5","object":"chat.completion.chunk","created":1778602882,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"file_path\": \"/tmp"}}]},"finish_reason":null}]}
103+
104+ data: {"id":"chatcmpl-631b0942bd9a982887845ca5","object":"chat.completion.chunk","created":1778602882,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/c"}}]},"finish_reason":null}]}
105+
106+ data: {"id":"chatcmpl-631b0942bd9a982887845ca5","object":"chat.completion.chunk","created":1778602882,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"rush-test"}}]},"finish_reason":null}]}
107+
108+ data: {"id":"chatcmpl-631b0942bd9a982887845ca5","object":"chat.completion.chunk","created":1778602882,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}]}
109+
110+ data: {"id":"chatcmpl-631b0942bd9a982887845ca5","object":"chat.completion.chunk","created":1778602882,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}]}
111+
112+ data: {"id":"chatcmpl-631b0942bd9a982887845ca5","object":"chat.completion.chunk","created":1778602882,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent/g"}}]},"finish_reason":null}]}
113+
114+ data: {"id":"chatcmpl-631b0942bd9a982887845ca5","object":"chat.completion.chunk","created":1778602882,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"lm-"}}]},"finish_reason":null}]}
115+
116+ data: {"id":"chatcmpl-631b0942bd9a982887845ca5","object":"chat.completion.chunk","created":1778602882,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5.1"}}]},"finish_reason":null}]}
117+
118+ data: {"id":"chatcmpl-631b0942bd9a982887845ca5","object":"chat.completion.chunk","created":1778602882,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/update_a"}}]},"finish_reason":null}]}
119+
120+ data: {"id":"chatcmpl-631b0942bd9a982887845ca5","object":"chat.completion.chunk","created":1778602882,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}]}
121+
122+ data: {"id":"chatcmpl-631b0942bd9a982887845ca5","object":"chat.completion.chunk","created":1778602882,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main.go"}}]},"finish_reason":null}]}
123+
124+ data: {"id":"chatcmpl-631b0942bd9a982887845ca5","object":"chat.completion.chunk","created":1778602882,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\""}}]},"finish_reason":null}]}
125+
126+ data: {"id":"chatcmpl-631b0942bd9a982887845ca5","object":"chat.completion.chunk","created":1778602882,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
127+
128+ data: {"id":"chatcmpl-631b0942bd9a982887845ca5","object":"chat.completion.chunk","created":1778602882,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
129+
130+ data: {"id":"chatcmpl-631b0942bd9a982887845ca5","object":"chat.completion.chunk","created":1778602882,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7807,"completion_tokens":29,"total_tokens":7836,"completion_tokens_details":{"reasoning_tokens":28}}}
131+
132+ data: [DONE]
133+
134+ headers:
135+ Content-Type:
136+ - text/event-stream
137+ status: 200 OK
138+ code: 200
139+ duration: 2.885147375s
140+- id: 2
5 request:
141 request:
6 proto: HTTP/1.1
142 proto: HTTP/1.1
7 proto_major: 1
143 proto_major: 1
@@ -25,229 +161,869 @@ interactions:
25 content_length: -1
161 content_length: -1
26 uncompressed: true
162 uncompressed: true
27 body: |+
163 body: |+
28− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
164+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
29
165
30− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"We"},"finish_reason":null}]}
166+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
31
167
32− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" need"},"finish_reason":null}]}
168+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
33
169
34− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
170+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
35
171
36− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" output"},"finish_reason":null}]}
172+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
37
173
38− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
174+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Generate"},"finish_reason":null}]}
39
175
40− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
176+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
41
177
42− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
178+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
43
179
44− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" same"},"finish_reason":null}]}
180+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
45
181
46− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" language"},"finish_reason":null}]}
182+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
47
183
48− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
184+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
49
185
50− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"English"},"finish_reason":null}]}
186+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" following"},"finish_reason":null}]}
51
187
52− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")."},"finish_reason":null}]}
188+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
53
189
54− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Summ"},"finish_reason":null}]}
190+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":\n\n"},"finish_reason":null}]}
55
191
56− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ar"},"finish_reason":null}]}
192+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"update"},"finish_reason":null}]}
57
193
58− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ize"},"finish_reason":null}]}
194+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
59
195
60− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
196+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
61
197
62− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
198+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".go"},"finish_reason":null}]}
63
199
64− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Update"},"finish_reason":null}]}
200+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" file"},"finish_reason":null}]}
65
201
66− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
202+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" by"},"finish_reason":null}]}
67
203
68− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".go"},"finish_reason":null}]}
204+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" changing"},"finish_reason":null}]}
69
205
70− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
206+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
71
207
72− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" print"},"finish_reason":null}]}
208+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" print"},"finish_reason":null}]}
73
209
74− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
210+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
75
211
76− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"hello"},"finish_reason":null}]}
212+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" say"},"finish_reason":null}]}
77
213
78− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" from"},"finish_reason":null}]}
214+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" hello"},"finish_reason":null}]}
79
215
80− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" crush"},"finish_reason":null}]}
216+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" from"},"finish_reason":null}]}
81
217
82− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'\""},"finish_reason":null}]}
218+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" crush"},"finish_reason":null}]}
83
219
84− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Title"},"finish_reason":null}]}
220+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\n"},"finish_reason":null}]}
85
221
86− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" under"},"finish_reason":null}]}
222+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \u003c"},"finish_reason":null}]}
87
223
88− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
224+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"think"},"finish_reason":null}]}
89
225
90− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
226+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\u003e\n\n"},"finish_reason":null}]}
91
227
92− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
228+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\u003c/"},"finish_reason":null}]}
93
229
94− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
230+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"think"},"finish_reason":null}]}
95
231
96− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Something"},"finish_reason":null}]}
232+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\u003e"},"finish_reason":null}]}
97
233
98− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" like"},"finish_reason":null}]}
234+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"\n\n"},"finish_reason":null}]}
99
235
100− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
236+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"We"},"finish_reason":null}]}
101
237
102− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Update"},"finish_reason":null}]}
238+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" need"},"finish_reason":null}]}
103
239
104− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
240+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
105
241
106− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".go"},"finish_reason":null}]}
242+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" produce"},"finish_reason":null}]}
107
243
108− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
244+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
109
245
110− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" print"},"finish_reason":null}]}
246+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" short"},"finish_reason":null}]}
111
247
112− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" hello"},"finish_reason":null}]}
248+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
113
249
114− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" from"},"finish_reason":null}]}
250+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
115
251
116− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" crush"},"finish_reason":null}]}
252+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" same"},"finish_reason":null}]}
117
253
118− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
254+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" language"},"finish_reason":null}]}
119
255
120− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
256+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
121
257
122− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" within"},"finish_reason":null}]}
258+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"English"},"finish_reason":null}]}
123
259
124− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
260+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")."},"finish_reason":null}]}
125
261
126− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
262+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Under"},"finish_reason":null}]}
127
263
128− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
264+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
129
265
130− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" No"},"finish_reason":null}]}
266+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
131
267
132− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
268+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
133
269
134− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" okay"},"finish_reason":null}]}
270+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
135
271
136− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
272+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Summ"},"finish_reason":null}]}
137
273
138− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Return"},"finish_reason":null}]}
274+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ar"},"finish_reason":null}]}
139
275
140− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" just"},"finish_reason":null}]}
276+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ize"},"finish_reason":null}]}
141
277
142− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that"},"finish_reason":null}]}
278+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
143
279
144− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
280+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Something"},"finish_reason":null}]}
145
281
146− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
282+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" like"},"finish_reason":null}]}
147
283
148− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Update"},"finish_reason":null}]}
284+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
149
285
150− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" main"},"finish_reason":null}]}
286+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Update"},"finish_reason":null}]}
151
287
152− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}]}
288+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
153
289
154− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" to"},"finish_reason":null}]}
290+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".go"},"finish_reason":null}]}
155
291
156− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" print"},"finish_reason":null}]}
292+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
157
293
158− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" hello"},"finish_reason":null}]}
294+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" print"},"finish_reason":null}]}
159
295
160− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" from"},"finish_reason":null}]}
296+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
161
297
162− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" crush"},"finish_reason":null}]}
298+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"hello"},"finish_reason":null}]}
163
299
164− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
300+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" from"},"finish_reason":null}]}
165
301
166− data: {"id":"chatcmpl-b190cf1ebc9ab9733b9f1f4c","object":"chat.completion.chunk","created":1778601675,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":37,"completion_tokens":77,"total_tokens":290,"prompt_tokens_details":{"cached_tokens":176}}}
302+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" crush"},"finish_reason":null}]}
167
303
168− data: [DONE]
304+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'"},"finish_reason":null}]}
169
305
170− headers:
306+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
171− Content-Type:
307+
172− - text/event-stream
308+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
173− status: 200 OK
309+
174− code: 200
310+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
175− duration: 516.61525ms
311+
176−- id: 1
312+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
177− request:
313+
178− proto: HTTP/1.1
314+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
179− proto_major: 1
315+
180− proto_minor: 1
316+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Update"},"finish_reason":null}]}
181− content_length: 33750
317+
182− host: ""
318+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
183− 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/update_a_file\\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\",\"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\":\"update the main.go file by changing the print to say hello from crush\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
319+
184− headers:
320+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".go"},"finish_reason":null}]}
185− Accept:
321+
186− - application/json
322+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
187− Content-Type:
323+
188− - application/json
324+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" print"},"finish_reason":null}]}
189− User-Agent:
325+
190− - Charm-Crush/devel (https://charm.land/crush)
326+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
191− url: https://hyper.charm.land/v1/chat/completions
327+
192− method: POST
328+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"hello"},"finish_reason":null}]}
193− response:
329+
194− proto: HTTP/2.0
330+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" from"},"finish_reason":null}]}
195− proto_major: 2
331+
196− proto_minor: 0
332+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" crush"},"finish_reason":null}]}
197− content_length: -1
333+
198− uncompressed: true
334+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'\""},"finish_reason":null}]}
199− body: |+
335+
200− data: {"id":"chatcmpl-0757ac94af53c3fb25b4b78d","object":"chat.completion.chunk","created":1778601682,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
336+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ="},"finish_reason":null}]}
337+
338+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" length"},"finish_reason":null}]}
339+
340+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"?"},"finish_reason":null}]}
341+
342+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Let's"},"finish_reason":null}]}
343+
344+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
345+
346+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
347+
348+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Update"},"finish_reason":null}]}
349+
350+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
351+
352+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
353+
354+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
355+
356+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
357+
358+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
359+
360+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
361+
362+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
363+
364+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
365+
366+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".go"},"finish_reason":null}]}
367+
368+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
369+
370+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
371+
372+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
373+
374+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
375+
376+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
377+
378+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
379+
380+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
381+
382+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
383+
384+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
385+
386+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
387+
388+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
389+
390+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
391+
392+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
393+
394+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
395+
396+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
397+
398+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" print"},"finish_reason":null}]}
399+
400+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
401+
402+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
403+
404+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
405+
406+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
407+
408+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
409+
410+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
411+
412+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
413+
414+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
415+
416+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"hello"},"finish_reason":null}]}
417+
418+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
419+
420+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
421+
422+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
423+
424+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
425+
426+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
427+
428+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
429+
430+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
431+
432+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" from"},"finish_reason":null}]}
433+
434+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
435+
436+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
437+
438+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
439+
440+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
441+
442+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
443+
444+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
445+
446+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
447+
448+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" crush"},"finish_reason":null}]}
449+
450+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'("},"finish_reason":null}]}
451+
452+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
453+
454+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
455+
456+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" total"},"finish_reason":null}]}
457+
458+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ="},"finish_reason":null}]}
459+
460+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
461+
462+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
463+
464+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
465+
466+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
467+
468+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
469+
470+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
471+
472+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
473+
474+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
475+
476+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
477+
478+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
479+
480+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
481+
482+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
483+
484+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
485+
486+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
487+
488+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
489+
490+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
491+
492+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
493+
494+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
495+
496+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
497+
498+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
499+
500+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
501+
502+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
503+
504+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
505+
506+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
507+
508+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"+"},"finish_reason":null}]}
509+
510+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
511+
512+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ="},"finish_reason":null}]}
513+
514+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
515+
516+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"40"},"finish_reason":null}]}
517+
518+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"?"},"finish_reason":null}]}
519+
520+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Let's"},"finish_reason":null}]}
521+
522+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" recount"},"finish_reason":null}]}
523+
524+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
525+
526+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
201
527
202− data: {"id":"chatcmpl-0757ac94af53c3fb25b4b78d","object":"chat.completion.chunk","created":1778601682,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"Let"},"finish_reason":null}]}
528+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Update"},"finish_reason":null}]}
203
529
204− data: {"id":"chatcmpl-0757ac94af53c3fb25b4b78d","object":"chat.completion.chunk","created":1778601682,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" me"},"finish_reason":null}]}
530+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
205
531
206− data: {"id":"chatcmpl-0757ac94af53c3fb25b4b78d","object":"chat.completion.chunk","created":1778601682,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" read"},"finish_reason":null}]}
532+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
207
533
208− data: {"id":"chatcmpl-0757ac94af53c3fb25b4b78d","object":"chat.completion.chunk","created":1778601682,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" the main"},"finish_reason":null}]}
534+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
209
535
210− data: {"id":"chatcmpl-0757ac94af53c3fb25b4b78d","object":"chat.completion.chunk","created":1778601682,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":".go"},"finish_reason":null}]}
536+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
211
537
212− data: {"id":"chatcmpl-0757ac94af53c3fb25b4b78d","object":"chat.completion.chunk","created":1778601682,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" file first"},"finish_reason":null}]}
538+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
213
539
214− data: {"id":"chatcmpl-0757ac94af53c3fb25b4b78d","object":"chat.completion.chunk","created":1778601682,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
540+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
215
541
216− data: {"id":"chatcmpl-0757ac94af53c3fb25b4b78d","object":"chat.completion.chunk","created":1778601682,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_c7972dbf84cf4d40996ea0f5","type":"function","index":0,"function":{"name":"view","arguments":""}}]},"finish_reason":null}]}
542+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
217
543
218− data: {"id":"chatcmpl-0757ac94af53c3fb25b4b78d","object":"chat.completion.chunk","created":1778601682,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
544+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
219
545
220− data: {"id":"chatcmpl-0757ac94af53c3fb25b4b78d","object":"chat.completion.chunk","created":1778601682,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
546+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
221
547
222− data: {"id":"chatcmpl-0757ac94af53c3fb25b4b78d","object":"chat.completion.chunk","created":1778601682,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"file_path\": \"/tmp"}}]},"finish_reason":null}]}
548+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"main"},"finish_reason":null}]}
223
549
224− data: {"id":"chatcmpl-0757ac94af53c3fb25b4b78d","object":"chat.completion.chunk","created":1778601682,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/c"}}]},"finish_reason":null}]}
550+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".go"},"finish_reason":null}]}
225
551
226− data: {"id":"chatcmpl-0757ac94af53c3fb25b4b78d","object":"chat.completion.chunk","created":1778601682,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"rush"}}]},"finish_reason":null}]}
552+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
227
553
228− data: {"id":"chatcmpl-0757ac94af53c3fb25b4b78d","object":"chat.completion.chunk","created":1778601682,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}]}
554+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
229
555
230− data: {"id":"chatcmpl-0757ac94af53c3fb25b4b78d","object":"chat.completion.chunk","created":1778601682,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}]}
556+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
231
557
232− data: {"id":"chatcmpl-0757ac94af53c3fb25b4b78d","object":"chat.completion.chunk","created":1778601682,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"CoderAgent"}}]},"finish_reason":null}]}
558+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"14"},"finish_reason":null}]}
233
559
234− data: {"id":"chatcmpl-0757ac94af53c3fb25b4b78d","object":"chat.completion.chunk","created":1778601682,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/glm"}}]},"finish_reason":null}]}
560+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
235
561
236− data: {"id":"chatcmpl-0757ac94af53c3fb25b4b78d","object":"chat.completion.chunk","created":1778601682,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-5"}}]},"finish_reason":null}]}
562+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
237
563
238− data: {"id":"chatcmpl-0757ac94af53c3fb25b4b78d","object":"chat.completion.chunk","created":1778601682,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".1"}}]},"finish_reason":null}]}
564+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
239
565
240− data: {"id":"chatcmpl-0757ac94af53c3fb25b4b78d","object":"chat.completion.chunk","created":1778601682,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/update_a"}}]},"finish_reason":null}]}
566+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
241
567
242− data: {"id":"chatcmpl-0757ac94af53c3fb25b4b78d","object":"chat.completion.chunk","created":1778601682,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}]}
568+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"15"},"finish_reason":null}]}
243
569
244− data: {"id":"chatcmpl-0757ac94af53c3fb25b4b78d","object":"chat.completion.chunk","created":1778601682,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main.go\""}}]},"finish_reason":null}]}
570+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
245
571
246− data: {"id":"chatcmpl-0757ac94af53c3fb25b4b78d","object":"chat.completion.chunk","created":1778601682,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
572+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
247
573
248− data: {"id":"chatcmpl-0757ac94af53c3fb25b4b78d","object":"chat.completion.chunk","created":1778601682,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
574+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"to"},"finish_reason":null}]}
249
575
250− data: {"id":"chatcmpl-0757ac94af53c3fb25b4b78d","object":"chat.completion.chunk","created":1778601682,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7771,"completion_tokens":38,"total_tokens":7809,"completion_tokens_details":{"reasoning_tokens":9}}}
576+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
577+
578+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
579+
580+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
581+
582+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"17"},"finish_reason":null}]}
583+
584+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
585+
586+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
587+
588+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
589+
590+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
591+
592+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"18"},"finish_reason":null}]}
593+
594+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
595+
596+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
597+
598+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"print"},"finish_reason":null}]}
599+
600+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
601+
602+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
603+
604+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
605+
606+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"23"},"finish_reason":null}]}
607+
608+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
609+
610+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
611+
612+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
613+
614+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
615+
616+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"24"},"finish_reason":null}]}
617+
618+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
619+
620+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \"'"},"finish_reason":null}]}
621+
622+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"hello"},"finish_reason":null}]}
623+
624+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
625+
626+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
627+
628+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
629+
630+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"including"},"finish_reason":null}]}
631+
632+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" leading"},"finish_reason":null}]}
633+
634+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" apost"},"finish_reason":null}]}
635+
636+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"rophe"},"finish_reason":null}]}
637+
638+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
639+
640+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ="},"finish_reason":null}]}
641+
642+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"30"},"finish_reason":null}]}
643+
644+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
645+
646+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
647+
648+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
649+
650+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
651+
652+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"31"},"finish_reason":null}]}
653+
654+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
655+
656+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
657+
658+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"from"},"finish_reason":null}]}
659+
660+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
661+
662+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
663+
664+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
665+
666+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"35"},"finish_reason":null}]}
667+
668+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
669+
670+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
671+
672+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
673+
674+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
675+
676+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"36"},"finish_reason":null}]}
677+
678+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
679+
680+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
681+
682+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"cr"},"finish_reason":null}]}
683+
684+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ush"},"finish_reason":null}]}
685+
686+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'\""},"finish_reason":null}]}
687+
688+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
689+
690+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
691+
692+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"42"},"finish_reason":null}]}
693+
694+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
695+
696+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" So"},"finish_reason":null}]}
697+
698+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" total"},"finish_reason":null}]}
699+
700+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
701+
702+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"42"},"finish_reason":null}]}
703+
704+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
705+
706+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
707+
708+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" under"},"finish_reason":null}]}
709+
710+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
711+
712+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
713+
714+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
715+
716+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" no"},"finish_reason":null}]}
717+
718+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
719+
720+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"?"},"finish_reason":null}]}
721+
722+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Actually"},"finish_reason":null}]}
723+
724+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
725+
726+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" shouldn't"},"finish_reason":null}]}
727+
728+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" have"},"finish_reason":null}]}
729+
730+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
731+
732+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" or"},"finish_reason":null}]}
733+
734+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" col"},"finish_reason":null}]}
735+
736+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ons"},"finish_reason":null}]}
737+
738+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
739+
740+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" It"},"finish_reason":null}]}
741+
742+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" says"},"finish_reason":null}]}
743+
744+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" not"},"finish_reason":null}]}
745+
746+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
747+
748+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" use"},"finish_reason":null}]}
749+
750+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
751+
752+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
753+
754+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" The"},"finish_reason":null}]}
755+
756+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
757+
758+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" cannot"},"finish_reason":null}]}
759+
760+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" contain"},"finish_reason":null}]}
761+
762+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
763+
764+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
765+
766+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" The"},"finish_reason":null}]}
767+
768+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" phrase"},"finish_reason":null}]}
769+
770+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" includes"},"finish_reason":null}]}
771+
772+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" single"},"finish_reason":null}]}
773+
774+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
775+
776+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
777+
778+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
779+
780+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
781+
782+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quote"},"finish_reason":null}]}
783+
784+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
785+
786+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Should"},"finish_reason":null}]}
787+
788+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" avoid"},"finish_reason":null}]}
789+
790+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
791+
792+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Could"},"finish_reason":null}]}
793+
794+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" say"},"finish_reason":null}]}
795+
796+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
797+
798+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Update"},"finish_reason":null}]}
799+
800+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
801+
802+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".go"},"finish_reason":null}]}
803+
804+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
805+
806+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" print"},"finish_reason":null}]}
807+
808+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" hello"},"finish_reason":null}]}
809+
810+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" from"},"finish_reason":null}]}
811+
812+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" crush"},"finish_reason":null}]}
813+
814+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
815+
816+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
817+
818+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" no"},"finish_reason":null}]}
819+
820+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
821+
822+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
823+
824+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
825+
826+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
827+
828+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
829+
830+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Update"},"finish_reason":null}]}
831+
832+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
833+
834+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".go"},"finish_reason":null}]}
835+
836+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
837+
838+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" print"},"finish_reason":null}]}
839+
840+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" hello"},"finish_reason":null}]}
841+
842+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" from"},"finish_reason":null}]}
843+
844+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" crush"},"finish_reason":null}]}
845+
846+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
847+
848+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
849+
850+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
851+
852+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Update"},"finish_reason":null}]}
853+
854+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
855+
856+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
857+
858+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
859+
860+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
861+
862+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
863+
864+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
865+
866+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
867+
868+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
869+
870+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".go"},"finish_reason":null}]}
871+
872+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
873+
874+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
875+
876+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"14"},"finish_reason":null}]}
877+
878+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
879+
880+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
881+
882+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
883+
884+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
885+
886+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"15"},"finish_reason":null}]}
887+
888+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
889+
890+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
891+
892+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
893+
894+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
895+
896+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"17"},"finish_reason":null}]}
897+
898+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
899+
900+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
901+
902+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
903+
904+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
905+
906+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"18"},"finish_reason":null}]}
907+
908+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
909+
910+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" print"},"finish_reason":null}]}
911+
912+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
913+
914+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
915+
916+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"23"},"finish_reason":null}]}
917+
918+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
919+
920+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
921+
922+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
923+
924+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
925+
926+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"24"},"finish_reason":null}]}
927+
928+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
929+
930+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" hello"},"finish_reason":null}]}
931+
932+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
933+
934+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
935+
936+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"29"},"finish_reason":null}]}
937+
938+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
939+
940+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
941+
942+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
943+
944+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
945+
946+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"30"},"finish_reason":null}]}
947+
948+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
949+
950+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" from"},"finish_reason":null}]}
951+
952+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
953+
954+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
955+
956+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"34"},"finish_reason":null}]}
957+
958+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
959+
960+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
961+
962+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
963+
964+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
965+
966+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"35"},"finish_reason":null}]}
967+
968+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
969+
970+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" crush"},"finish_reason":null}]}
971+
972+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
973+
974+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
975+
976+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"40"},"finish_reason":null}]}
977+
978+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
979+
980+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Good"},"finish_reason":null}]}
981+
982+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
983+
984+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
985+
986+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" under"},"finish_reason":null}]}
987+
988+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
989+
990+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
991+
992+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
993+
994+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
995+
996+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Provide"},"finish_reason":null}]}
997+
998+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that"},"finish_reason":null}]}
999+
1000+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" as"},"finish_reason":null}]}
1001+
1002+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" single"},"finish_reason":null}]}
1003+
1004+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
1005+
1006+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
1007+
1008+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Update"},"finish_reason":null}]}
1009+
1010+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" main"},"finish_reason":null}]}
1011+
1012+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}]}
1013+
1014+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" to"},"finish_reason":null}]}
1015+
1016+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" print"},"finish_reason":null}]}
1017+
1018+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" hello"},"finish_reason":null}]}
1019+
1020+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" from"},"finish_reason":null}]}
1021+
1022+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" crush"},"finish_reason":null}]}
1023+
1024+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
1025+
1026+ data: {"id":"chatcmpl-e50a5dd86797ff05ac839ba1","object":"chat.completion.chunk","created":1778602878,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":153,"completion_tokens":439,"total_tokens":656,"prompt_tokens_details":{"cached_tokens":64}}}
251
1027
252 data: [DONE]
1028 data: [DONE]
253
1029
@@ -256,15 +1032,15 @@ interactions:
256 - text/event-stream
1032 - text/event-stream
257 status: 200 OK
1033 status: 200 OK
258 code: 200
1034 code: 200
259− duration: 7.904001708s
1035+ duration: 951.706708ms
260−- id: 2
1036+- id: 3
261 request:
1037 request:
262 proto: HTTP/1.1
1038 proto: HTTP/1.1
263 proto_major: 1
1039 proto_major: 1
264 proto_minor: 1
1040 proto_minor: 1
265− content_length: 34252
1041+ content_length: 34593
266 host: ""
1042 host: ""
267− 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/update_a_file\\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\",\"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\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_c7972dbf84cf4d40996ea0f5\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"Let me read the main.go file first.\"},{\"content\":\"<file>\\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</file>\\n\",\"tool_call_id\":\"call_c7972dbf84cf4d40996ea0f5\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
1043+ 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/update_a_file\\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\",\"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\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_1c826621fe604567b9986757\",\"function\":{\"arguments\":\"{\\\"pattern\\\": \\\"**/main.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"Let me find and read the main.go file first.\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/glm-5.1/update_a_file/main.go\",\"tool_call_id\":\"call_1c826621fe604567b9986757\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_5a22ba8e8d334aec807c16a0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"\"},{\"content\":\"<file>\\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 8|\\n</file>\\n\",\"tool_call_id\":\"call_5a22ba8e8d334aec807c16a0\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
268 headers:
1044 headers:
269 Accept:
1045 Accept:
270 - application/json
1046 - application/json
@@ -281,59 +1057,65 @@ interactions:
281 content_length: -1
1057 content_length: -1
282 uncompressed: true
1058 uncompressed: true
283 body: |+
1059 body: |+
284− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
1060+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
1061+
1062+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_78e0a49a677e42a99fb04971","type":"function","index":0,"function":{"name":"edit","arguments":""}}]},"finish_reason":null}]}
285
1063
286− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_2621f1453a094bdabc79a754","type":"function","index":0,"function":{"name":"edit","arguments":""}}]},"finish_reason":null}]}
1064+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
287
1065
288− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
1066+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
289
1067
290− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
1068+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"file_path\": "}}]},"finish_reason":null}]}
291
1069
292− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"file_path\": "}}]},"finish_reason":null}]}
1070+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/tmp"}}]},"finish_reason":null}]}
293
1071
294− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/tmp"}}]},"finish_reason":null}]}
1072+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/c"}}]},"finish_reason":null}]}
295
1073
296− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/c"}}]},"finish_reason":null}]}
1074+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"rush-test"}}]},"finish_reason":null}]}
297
1075
298− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"rush-test"}}]},"finish_reason":null}]}
1076+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}]}
299
1077
300− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}]}
1078+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}]}
301
1079
302− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"CoderAgent"}}]},"finish_reason":null}]}
1080+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent/g"}}]},"finish_reason":null}]}
303
1081
304− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/glm-"}}]},"finish_reason":null}]}
1082+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"lm-5"}}]},"finish_reason":null}]}
305
1083
306− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5.1/update"}}]},"finish_reason":null}]}
1084+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".1"}}]},"finish_reason":null}]}
307
1085
308− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a_file"}}]},"finish_reason":null}]}
1086+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/update_a"}}]},"finish_reason":null}]}
309
1087
310− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main.go\""}}]},"finish_reason":null}]}
1088+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}]}
311
1089
312− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":", "}}]},"finish_reason":null}]}
1090+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main.go"}}]},"finish_reason":null}]}
313
1091
314− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"new_string\": "}}]},"finish_reason":null}]}
1092+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\", "}}]},"finish_reason":null}]}
315
1093
316− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"\\tfmt.Println(\\\""}}]},"finish_reason":null}]}
1094+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"new_string\": "}}]},"finish_reason":null}]}
317
1095
318− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello from crush"}}]},"finish_reason":null}]}
1096+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"\\tfmt.Println"}}]},"finish_reason":null}]}
319
1097
320− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\\")"}}]},"finish_reason":null}]}
1098+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\"Hello from"}}]},"finish_reason":null}]}
321
1099
322− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\", "}}]},"finish_reason":null}]}
1100+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" crush\\\")"}}]},"finish_reason":null}]}
323
1101
324− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"old_string\": "}}]},"finish_reason":null}]}
1102+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\""}}]},"finish_reason":null}]}
325
1103
326− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"\\tfmt.Println(\\\"Hello"}}]},"finish_reason":null}]}
1104+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":", "}}]},"finish_reason":null}]}
327
1105
328− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":", World"}}]},"finish_reason":null}]}
1106+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"old_string\": \"\\tfmt"}}]},"finish_reason":null}]}
329
1107
330− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\\")\""}}]},"finish_reason":null}]}
1108+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println(\\\""}}]},"finish_reason":null}]}
331
1109
332− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
1110+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello, World"}}]},"finish_reason":null}]}
333
1111
334− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
1112+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\\")\""}}]},"finish_reason":null}]}
335
1113
336− data: {"id":"chatcmpl-93ffe58970d74aec43ed0e13","object":"chat.completion.chunk","created":1778601686,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":7856,"completion_tokens":55,"total_tokens":7911,"completion_tokens_details":{"reasoning_tokens":54}}}
1114+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
1115+
1116+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
1117+
1118+ data: {"id":"chatcmpl-65c233814cd80a3c35dfa4e8","object":"chat.completion.chunk","created":1778602887,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":856,"completion_tokens":55,"total_tokens":7951,"prompt_tokens_details":{"cached_tokens":7040},"completion_tokens_details":{"reasoning_tokens":54}}}
337
1119
338 data: [DONE]
1120 data: [DONE]
339
1121
@@ -342,15 +1124,15 @@ interactions:
342 - text/event-stream
1124 - text/event-stream
343 status: 200 OK
1125 status: 200 OK
344 code: 200
1126 code: 200
345− duration: 2.8873885s
1127+ duration: 3.895054s
346−- id: 3
1128+- id: 4
347 request:
1129 request:
348 proto: HTTP/1.1
1130 proto: HTTP/1.1
349 proto_major: 1
1131 proto_major: 1
350 proto_minor: 1
1132 proto_minor: 1
351− content_length: 34798
1133+ content_length: 35138
352 host: ""
1134 host: ""
353− 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/update_a_file\\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\",\"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\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_c7972dbf84cf4d40996ea0f5\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"Let me read the main.go file first.\"},{\"content\":\"<file>\\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</file>\\n\",\"tool_call_id\":\"call_c7972dbf84cf4d40996ea0f5\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_2621f1453a094bdabc79a754\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/update_a_file/main.go\\\", \\\"new_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"Hello from crush!\\\\\\\")\\\", \\\"old_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\"}\",\"name\":\"edit\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"\"},{\"content\":\"<result>\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/glm-5.1/update_a_file/main.go\\n</result>\\n\",\"tool_call_id\":\"call_2621f1453a094bdabc79a754\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
1135+ 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/update_a_file\\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\",\"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\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_1c826621fe604567b9986757\",\"function\":{\"arguments\":\"{\\\"pattern\\\": \\\"**/main.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"Let me find and read the main.go file first.\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/glm-5.1/update_a_file/main.go\",\"tool_call_id\":\"call_1c826621fe604567b9986757\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_5a22ba8e8d334aec807c16a0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"\"},{\"content\":\"<file>\\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 8|\\n</file>\\n\",\"tool_call_id\":\"call_5a22ba8e8d334aec807c16a0\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_78e0a49a677e42a99fb04971\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/update_a_file/main.go\\\", \\\"new_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"Hello from crush\\\\\\\")\\\", \\\"old_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\"}\",\"name\":\"edit\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"\"},{\"content\":\"<result>\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/glm-5.1/update_a_file/main.go\\n</result>\\n\",\"tool_call_id\":\"call_78e0a49a677e42a99fb04971\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
354 headers:
1136 headers:
355 Accept:
1137 Accept:
356 - application/json
1138 - application/json
@@ -367,39 +1149,31 @@ interactions:
367 content_length: -1
1149 content_length: -1
368 uncompressed: true
1150 uncompressed: true
369 body: |+
1151 body: |+
370− data: {"id":"chatcmpl-1dc6071e8f1300c6c1cacfae","object":"chat.completion.chunk","created":1778601690,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
1152+ data: {"id":"chatcmpl-7ef439500703496009f987d9","object":"chat.completion.chunk","created":1778602891,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
371−
372− data: {"id":"chatcmpl-1dc6071e8f1300c6c1cacfae","object":"chat.completion.chunk","created":1778601690,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Done"},"finish_reason":null}]}
373−
374− data: {"id":"chatcmpl-1dc6071e8f1300c6c1cacfae","object":"chat.completion.chunk","created":1778601690,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":". Changed the print"},"finish_reason":null}]}
375−
376− data: {"id":"chatcmpl-1dc6071e8f1300c6c1cacfae","object":"chat.completion.chunk","created":1778601690,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" message"},"finish_reason":null}]}
377−
378− data: {"id":"chatcmpl-1dc6071e8f1300c6c1cacfae","object":"chat.completion.chunk","created":1778601690,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" in"},"finish_reason":null}]}
379
1153
380− data: {"id":"chatcmpl-1dc6071e8f1300c6c1cacfae","object":"chat.completion.chunk","created":1778601690,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `"},"finish_reason":null}]}
1154+ data: {"id":"chatcmpl-7ef439500703496009f987d9","object":"chat.completion.chunk","created":1778602891,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Done"},"finish_reason":null}]}
381
1155
382− data: {"id":"chatcmpl-1dc6071e8f1300c6c1cacfae","object":"chat.completion.chunk","created":1778601690,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"main.go:6"},"finish_reason":null}]}
1156+ data: {"id":"chatcmpl-7ef439500703496009f987d9","object":"chat.completion.chunk","created":1778602891,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":". Updated"},"finish_reason":null}]}
383
1157
384− data: {"id":"chatcmpl-1dc6071e8f1300c6c1cacfae","object":"chat.completion.chunk","created":1778601690,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`"},"finish_reason":null}]}
1158+ data: {"id":"chatcmpl-7ef439500703496009f987d9","object":"chat.completion.chunk","created":1778602891,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `"},"finish_reason":null}]}
385
1159
386− data: {"id":"chatcmpl-1dc6071e8f1300c6c1cacfae","object":"chat.completion.chunk","created":1778601690,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" from"},"finish_reason":null}]}
1160+ data: {"id":"chatcmpl-7ef439500703496009f987d9","object":"chat.completion.chunk","created":1778602891,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"main.go"},"finish_reason":null}]}
387
1161
388− data: {"id":"chatcmpl-1dc6071e8f1300c6c1cacfae","object":"chat.completion.chunk","created":1778601690,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `\""},"finish_reason":null}]}
1162+ data: {"id":"chatcmpl-7ef439500703496009f987d9","object":"chat.completion.chunk","created":1778602891,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":":6"},"finish_reason":null}]}
389
1163
390− data: {"id":"chatcmpl-1dc6071e8f1300c6c1cacfae","object":"chat.completion.chunk","created":1778601690,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Hello, World"},"finish_reason":null}]}
1164+ data: {"id":"chatcmpl-7ef439500703496009f987d9","object":"chat.completion.chunk","created":1778602891,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"` to"},"finish_reason":null}]}
391
1165
392− data: {"id":"chatcmpl-1dc6071e8f1300c6c1cacfae","object":"chat.completion.chunk","created":1778601690,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"!\"` to `\""},"finish_reason":null}]}
1166+ data: {"id":"chatcmpl-7ef439500703496009f987d9","object":"chat.completion.chunk","created":1778602891,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" print `\""},"finish_reason":null}]}
393
1167
394− data: {"id":"chatcmpl-1dc6071e8f1300c6c1cacfae","object":"chat.completion.chunk","created":1778601690,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Hello from"},"finish_reason":null}]}
1168+ data: {"id":"chatcmpl-7ef439500703496009f987d9","object":"chat.completion.chunk","created":1778602891,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Hello from"},"finish_reason":null}]}
395
1169
396− data: {"id":"chatcmpl-1dc6071e8f1300c6c1cacfae","object":"chat.completion.chunk","created":1778601690,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" crush!\""},"finish_reason":null}]}
1170+ data: {"id":"chatcmpl-7ef439500703496009f987d9","object":"chat.completion.chunk","created":1778602891,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" crush\""},"finish_reason":null}]}
397
1171
398− data: {"id":"chatcmpl-1dc6071e8f1300c6c1cacfae","object":"chat.completion.chunk","created":1778601690,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`."},"finish_reason":null}]}
1172+ data: {"id":"chatcmpl-7ef439500703496009f987d9","object":"chat.completion.chunk","created":1778602891,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`."},"finish_reason":null}]}
399
1173
400− data: {"id":"chatcmpl-1dc6071e8f1300c6c1cacfae","object":"chat.completion.chunk","created":1778601690,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
1174+ data: {"id":"chatcmpl-7ef439500703496009f987d9","object":"chat.completion.chunk","created":1778602891,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
401
1175
402− data: {"id":"chatcmpl-1dc6071e8f1300c6c1cacfae","object":"chat.completion.chunk","created":1778601690,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":138,"completion_tokens":29,"total_tokens":7975,"prompt_tokens_details":{"cached_tokens":7808},"completion_tokens_details":{"reasoning_tokens":28}}}
1176+ data: {"id":"chatcmpl-7ef439500703496009f987d9","object":"chat.completion.chunk","created":1778602891,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":946,"completion_tokens":19,"total_tokens":8005,"prompt_tokens_details":{"cached_tokens":7040},"completion_tokens_details":{"reasoning_tokens":18}}}
403
1177
404 data: [DONE]
1178 data: [DONE]
405
1179
@@ -408,4 +1182,4 @@ interactions:
408 - text/event-stream
1182 - text/event-stream
409 status: 200 OK
1183 status: 200 OK
410 code: 200
1184 code: 200
411− duration: 3.548258583s
1185+ duration: 3.618314792s
internal/agent/testdata/TestCoderAgent/glm-5.1/write_tool.yaml+142−226
@@ -25,289 +25,199 @@ interactions:
25 content_length: -1
25 content_length: -1
26 uncompressed: true
26 uncompressed: true
27 body: |+
27 body: |+
28− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
28+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
29
29
30− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
30+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"We"},"finish_reason":null}]}
31
31
32− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
32+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" need"},"finish_reason":null}]}
33
33
34− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" asks"},"finish_reason":null}]}
34+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
35
35
36− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
36+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" produce"},"finish_reason":null}]}
37
37
38− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
38+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
39
39
40− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Generate"},"finish_reason":null}]}
40+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" short"},"finish_reason":null}]}
41
41
42− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
42+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
43
43
44− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
44+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
45
45
46− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
46+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"max"},"finish_reason":null}]}
47
47
48− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
48+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
49
49
50− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
50+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
51
51
52− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" following"},"finish_reason":null}]}
52+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
53
53
54− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
54+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
55
55
56− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
56+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" summar"},"finish_reason":null}]}
57
57
58− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" use"},"finish_reason":null}]}
58+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"izing"},"finish_reason":null}]}
59
59
60− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" write"},"finish_reason":null}]}
60+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
61
61
62− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
62+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
63
63
64− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" create"},"finish_reason":null}]}
64+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
65
65
66− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
66+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
67
67
68− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" new"},"finish_reason":null}]}
68+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"use"},"finish_reason":null}]}
69
69
70− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" file"},"finish_reason":null}]}
70+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" write"},"finish_reason":null}]}
71
71
72− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" called"},"finish_reason":null}]}
72+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
73
73
74− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" config"},"finish_reason":null}]}
74+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" create"},"finish_reason":null}]}
75
75
76− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".json"},"finish_reason":null}]}
76+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
77
77
78− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
78+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" new"},"finish_reason":null}]}
79
79
80− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
80+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" file"},"finish_reason":null}]}
81
81
82− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '{\""},"finish_reason":null}]}
82+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" called"},"finish_reason":null}]}
83
83
84− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"name"},"finish_reason":null}]}
84+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" config"},"finish_reason":null}]}
85
85
86− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\":"},"finish_reason":null}]}
86+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".json"},"finish_reason":null}]}
87
87
88− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
88+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
89
89
90− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"test"},"finish_reason":null}]}
90+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
91
91
92− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\","},"finish_reason":null}]}
92+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '{\""},"finish_reason":null}]}
93
93
94− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
94+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"name"},"finish_reason":null}]}
95
95
96− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"version"},"finish_reason":null}]}
96+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\":"},"finish_reason":null}]}
97
97
98− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\":"},"finish_reason":null}]}
98+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
99
99
100− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
100+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"test"},"finish_reason":null}]}
101
101
102− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
102+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\","},"finish_reason":null}]}
103
103
104− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
104+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
105
105
106− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"0"},"finish_reason":null}]}
106+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"version"},"finish_reason":null}]}
107
107
108− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
108+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\":"},"finish_reason":null}]}
109
109
110− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"0"},"finish_reason":null}]}
110+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
111
111
112− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"}"},"finish_reason":null}]}
112+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
113
113
114− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'"},"finish_reason":null}]}
114+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
115
115
116− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
116+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"0"},"finish_reason":null}]}
117
117
118− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" So"},"finish_reason":null}]}
118+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
119
119
120− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" output"},"finish_reason":null}]}
120+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"0"},"finish_reason":null}]}
121
121
122− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
122+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"}"},"finish_reason":null}]}
123
123
124− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
124+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"'"},"finish_reason":null}]}
125
125
126− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" under"},"finish_reason":null}]}
126+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
127
127
128− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
128+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Title"},"finish_reason":null}]}
129
129
130− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
130+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" likely"},"finish_reason":null}]}
131
131
132− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
132+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
133
133
134− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
134+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
135
135
136− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" one"},"finish_reason":null}]}
136+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Create"},"finish_reason":null}]}
137
137
138− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
138+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" config"},"finish_reason":null}]}
139
139
140− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
140+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".json"},"finish_reason":null}]}
141
141
142− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" no"},"finish_reason":null}]}
142+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
143
143
144− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
144+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" test"},"finish_reason":null}]}
145
145
146− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"/"},"finish_reason":null}]}
146+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" version"},"finish_reason":null}]}
147
147
148− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"col"},"finish_reason":null}]}
148+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
149
149
150− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ons"},"finish_reason":null}]}
150+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
151
151
152− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
152+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
153
153
154− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Should"},"finish_reason":null}]}
154+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
155
155
156− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
156+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
157
157
158− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" something"},"finish_reason":null}]}
158+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Create"},"finish_reason":null}]}
159
159
160− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" like"},"finish_reason":null}]}
160+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" config"},"finish_reason":null}]}
161
161
162− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
162+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".json"},"finish_reason":null}]}
163
163
164− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Create"},"finish_reason":null}]}
164+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
165
165
166− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" config"},"finish_reason":null}]}
166+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" test"},"finish_reason":null}]}
167
167
168− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".json"},"finish_reason":null}]}
168+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" version"},"finish_reason":null}]}
169
169
170− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
170+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
171
171
172− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" test"},"finish_reason":null}]}
172+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ="},"finish_reason":null}]}
173
173
174− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" settings"},"finish_reason":null}]}
174+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
175
175
176− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
176+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"34"},"finish_reason":null}]}
177
177
178− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
178+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
179
179
180− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" under"},"finish_reason":null}]}
180+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
181
181
182− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
182+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" fine"},"finish_reason":null}]}
183
183
184− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
184+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
185
185
186− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
186+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" No"},"finish_reason":null}]}
187
187
188− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" No"},"finish_reason":null}]}
188+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
189
189
190− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
190+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" or"},"finish_reason":null}]}
191
191
192− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
192+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" col"},"finish_reason":null}]}
193
193
194− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Should"},"finish_reason":null}]}
194+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ons"},"finish_reason":null}]}
195
195
196− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
196+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
197
197
198− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
198+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Let's"},"finish_reason":null}]}
199
199
200− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" English"},"finish_reason":null}]}
200+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" produce"},"finish_reason":null}]}
201
201
202− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" same"},"finish_reason":null}]}
202+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that"},"finish_reason":null}]}
203
203
204− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" language"},"finish_reason":null}]}
204+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
205
205
206− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
206+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Create"},"finish_reason":null}]}
207
207
208− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" We'll"},"finish_reason":null}]}
208+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" config"},"finish_reason":null}]}
209
209
210− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" output"},"finish_reason":null}]}
210+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":".json"},"finish_reason":null}]}
211
211
212− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
212+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" with"},"finish_reason":null}]}
213
213
214− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Create"},"finish_reason":null}]}
214+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" test"},"finish_reason":null}]}
215
215
216− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" config"},"finish_reason":null}]}
216+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" version"},"finish_reason":null}]}
217
217
218− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".json"},"finish_reason":null}]}
218+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
219
219
220− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
220+ data: {"id":"chatcmpl-b1413eedd3d546ece807e290","object":"chat.completion.chunk","created":1778602979,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":39,"completion_tokens":104,"total_tokens":335,"prompt_tokens_details":{"cached_tokens":192}}}
221−
222− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" test"},"finish_reason":null}]}
223−
224− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" name"},"finish_reason":null}]}
225−
226− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
227−
228− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" version"},"finish_reason":null}]}
229−
230− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
231−
232− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
233−
234− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
235−
236− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"45"},"finish_reason":null}]}
237−
238− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
239−
240− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"?"},"finish_reason":null}]}
241−
242− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Let's"},"finish_reason":null}]}
243−
244− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
245−
246− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
247−
248− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
249−
250− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Create"},"finish_reason":null}]}
251−
252− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" config"},"finish_reason":null}]}
253−
254− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".json"},"finish_reason":null}]}
255−
256− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
257−
258− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" test"},"finish_reason":null}]}
259−
260− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" name"},"finish_reason":null}]}
261−
262− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
263−
264− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" version"},"finish_reason":null}]}
265−
266− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
267−
268− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
269−
270− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
271−
272− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"44"},"finish_reason":null}]}
273−
274− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
275−
276− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" including"},"finish_reason":null}]}
277−
278− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" spaces"},"finish_reason":null}]}
279−
280− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
281−
282− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" No"},"finish_reason":null}]}
283−
284− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
285−
286− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
287−
288− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Good"},"finish_reason":null}]}
289−
290− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
291−
292− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Create"},"finish_reason":null}]}
293−
294− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" config"},"finish_reason":null}]}
295−
296− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":".json"},"finish_reason":null}]}
297−
298− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" with"},"finish_reason":null}]}
299−
300− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" test"},"finish_reason":null}]}
301−
302− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" name"},"finish_reason":null}]}
303−
304− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" and"},"finish_reason":null}]}
305−
306− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" version"},"finish_reason":null}]}
307−
308− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
309−
310− data: {"id":"chatcmpl-4d3f853b7af8f3c84cac305d","object":"chat.completion.chunk","created":1778601786,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":39,"completion_tokens":149,"total_tokens":380,"prompt_tokens_details":{"cached_tokens":192}}}
311
221
312 data: [DONE]
222 data: [DONE]
313
223
@@ -316,7 +226,7 @@ interactions:
316 - text/event-stream
226 - text/event-stream
317 status: 200 OK
227 status: 200 OK
318 code: 200
228 code: 200
319− duration: 517.092042ms
229+ duration: 721.489ms
320- id: 1
230- id: 1
321 request:
231 request:
322 proto: HTTP/1.1
232 proto: HTTP/1.1
@@ -341,61 +251,67 @@ interactions:
341 content_length: -1
251 content_length: -1
342 uncompressed: true
252 uncompressed: true
343 body: |+
253 body: |+
344− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
254+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
255+
256+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"Simple"},"finish_reason":null}]}
257+
258+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" task"},"finish_reason":null}]}
259+
260+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" - write"},"finish_reason":null}]}
345
261
346− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"Simple"},"finish_reason":null}]}
262+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
347
263
348− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" write"},"finish_reason":null}]}
264+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" file."},"finish_reason":null}]}
349
265
350− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" task"},"finish_reason":null}]}
266+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_9de06a03ddeb45adbdd5c841","type":"function","index":0,"function":{"name":"write","arguments":""}}]},"finish_reason":null}]}
351
267
352− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
268+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
353
269
354− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_e1f63f65a7934c268c133ced","type":"function","index":0,"function":{"name":"write","arguments":""}}]},"finish_reason":null}]}
270+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
355
271
356− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
272+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"content\": "}}]},"finish_reason":null}]}
357
273
358− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\"content\": "}}]},"finish_reason":null}]}
274+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"{\\\""}}]},"finish_reason":null}]}
359
275
360− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"{\\\"name\\\": \\\""}}]},"finish_reason":null}]}
276+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"name\\\":"}}]},"finish_reason":null}]}
361
277
362− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"test\\\", \\\""}}]},"finish_reason":null}]}
278+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \\\"test\\\", \\\""}}]},"finish_reason":null}]}
363
279
364− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"version\\\":"}}]},"finish_reason":null}]}
280+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"version\\\":"}}]},"finish_reason":null}]}
365
281
366− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \\\"1.0"}}]},"finish_reason":null}]}
282+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \\\"1."}}]},"finish_reason":null}]}
367
283
368− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".0"}}]},"finish_reason":null}]}
284+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"0.0"}}]},"finish_reason":null}]}
369
285
370− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\"}\", "}}]},"finish_reason":null}]}
286+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\"}\", "}}]},"finish_reason":null}]}
371
287
372− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"file_path\": "}}]},"finish_reason":null}]}
288+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"file_path\": "}}]},"finish_reason":null}]}
373
289
374− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/tmp/c"}}]},"finish_reason":null}]}
290+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/tmp/c"}}]},"finish_reason":null}]}
375
291
376− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"rush-test"}}]},"finish_reason":null}]}
292+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"rush-test"}}]},"finish_reason":null}]}
377
293
378− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}]}
294+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}]}
379
295
380− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}]}
296+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}]}
381
297
382− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent/glm"}}]},"finish_reason":null}]}
298+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}]}
383
299
384− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-5"}}]},"finish_reason":null}]}
300+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/glm"}}]},"finish_reason":null}]}
385
301
386− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".1"}}]},"finish_reason":null}]}
302+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-5"}}]},"finish_reason":null}]}
387
303
388− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/write_tool"}}]},"finish_reason":null}]}
304+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".1/write"}}]},"finish_reason":null}]}
389
305
390− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/config.json"}}]},"finish_reason":null}]}
306+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool/config"}}]},"finish_reason":null}]}
391
307
392− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\""}}]},"finish_reason":null}]}
308+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".json\""}}]},"finish_reason":null}]}
393
309
394− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
310+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
395
311
396− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
312+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
397
313
398− data: {"id":"chatcmpl-f7bcca66ded30f933b92ec88","object":"chat.completion.chunk","created":1778601790,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":745,"completion_tokens":53,"total_tokens":7838,"prompt_tokens_details":{"cached_tokens":7040},"completion_tokens_details":{"reasoning_tokens":4}}}
314+ data: {"id":"chatcmpl-bce442ea2980a2afdf5627d7","object":"chat.completion.chunk","created":1778602982,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":745,"completion_tokens":56,"total_tokens":7841,"prompt_tokens_details":{"cached_tokens":7040},"completion_tokens_details":{"reasoning_tokens":7}}}
399
315
400 data: [DONE]
316 data: [DONE]
401
317
@@ -404,15 +320,15 @@ interactions:
404 - text/event-stream
320 - text/event-stream
405 status: 200 OK
321 status: 200 OK
406 code: 200
322 code: 200
407− duration: 4.068339125s
323+ duration: 3.547536s
408- id: 2
324- id: 2
409 request:
325 request:
410 proto: HTTP/1.1
326 proto: HTTP/1.1
411 proto_major: 1
327 proto_major: 1
412 proto_minor: 1
328 proto_minor: 1
413− content_length: 34310
329+ content_length: 34319
414 host: ""
330 host: ""
415− 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/write_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\",\"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 write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_e1f63f65a7934c268c133ced\",\"function\":{\"arguments\":\"{\\\"content\\\": \\\"{\\\\\\\"name\\\\\\\": \\\\\\\"test\\\\\\\", \\\\\\\"version\\\\\\\": \\\\\\\"1.0.0\\\\\\\"}\\\", \\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/write_tool/config.json\\\"}\",\"name\":\"write\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"Simple write task.\"},{\"content\":\"<result>\\nFile successfully written: /tmp/crush-test/TestCoderAgent/glm-5.1/write_tool/config.json\\n</result>\",\"tool_call_id\":\"call_e1f63f65a7934c268c133ced\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
331+ 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 BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <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.\\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 files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</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/write_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\",\"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 write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_9de06a03ddeb45adbdd5c841\",\"function\":{\"arguments\":\"{\\\"content\\\": \\\"{\\\\\\\"name\\\\\\\": \\\\\\\"test\\\\\\\", \\\\\\\"version\\\\\\\": \\\\\\\"1.0.0\\\\\\\"}\\\", \\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/write_tool/config.json\\\"}\",\"name\":\"write\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"Simple task - write a file.\"},{\"content\":\"<result>\\nFile successfully written: /tmp/crush-test/TestCoderAgent/glm-5.1/write_tool/config.json\\n</result>\",\"tool_call_id\":\"call_9de06a03ddeb45adbdd5c841\",\"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_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 git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat &lt;&lt;'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n ## Summary\\n\\n &lt;1-3 bullet points>\\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</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 2000, 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 2000)\",\"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}"
416 headers:
332 headers:
417 Accept:
333 Accept:
418 - application/json
334 - application/json
@@ -429,17 +345,17 @@ interactions:
429 content_length: -1
345 content_length: -1
430 uncompressed: true
346 uncompressed: true
431 body: |+
347 body: |+
432− data: {"id":"chatcmpl-455277e88880268009582f0f","object":"chat.completion.chunk","created":1778601794,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
348+ data: {"id":"chatcmpl-eaeb3945487adcd2e51471ba","object":"chat.completion.chunk","created":1778603001,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
433
349
434− data: {"id":"chatcmpl-455277e88880268009582f0f","object":"chat.completion.chunk","created":1778601794,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Created"},"finish_reason":null}]}
350+ data: {"id":"chatcmpl-eaeb3945487adcd2e51471ba","object":"chat.completion.chunk","created":1778603001,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Created"},"finish_reason":null}]}
435
351
436− data: {"id":"chatcmpl-455277e88880268009582f0f","object":"chat.completion.chunk","created":1778601794,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `config"},"finish_reason":null}]}
352+ data: {"id":"chatcmpl-eaeb3945487adcd2e51471ba","object":"chat.completion.chunk","created":1778603001,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `config"},"finish_reason":null}]}
437
353
438− data: {"id":"chatcmpl-455277e88880268009582f0f","object":"chat.completion.chunk","created":1778601794,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":".json`."},"finish_reason":null}]}
354+ data: {"id":"chatcmpl-eaeb3945487adcd2e51471ba","object":"chat.completion.chunk","created":1778603001,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":".json`."},"finish_reason":null}]}
439
355
440− data: {"id":"chatcmpl-455277e88880268009582f0f","object":"chat.completion.chunk","created":1778601794,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
356+ data: {"id":"chatcmpl-eaeb3945487adcd2e51471ba","object":"chat.completion.chunk","created":1778603001,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
441
357
442− data: {"id":"chatcmpl-455277e88880268009582f0f","object":"chat.completion.chunk","created":1778601794,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":123,"completion_tokens":7,"total_tokens":7874,"prompt_tokens_details":{"cached_tokens":7744},"completion_tokens_details":{"reasoning_tokens":6}}}
358+ data: {"id":"chatcmpl-eaeb3945487adcd2e51471ba","object":"chat.completion.chunk","created":1778603001,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":827,"completion_tokens":7,"total_tokens":7874,"prompt_tokens_details":{"cached_tokens":7040},"completion_tokens_details":{"reasoning_tokens":6}}}
443
359
444 data: [DONE]
360 data: [DONE]
445
361
@@ -448,4 +364,4 @@ interactions:
448 - text/event-stream
364 - text/event-stream
449 status: 200 OK
365 status: 200 OK
450 code: 200
366 code: 200
451− duration: 3.99512075s
367+ duration: 18.064551584s
internal/agent/tools/grep.go+12−4
@@ -371,18 +371,26 @@ func fileContainsPattern(filePath string, pattern *regexp.Regexp) (bool, int, in
371 }
371 }
372 defer file.Close()
372 defer file.Close()
373
373
374− scanner := bufio.NewScanner(file)
374+ reader := bufio.NewReader(file)
375 lineNum := 0
375 lineNum := 0
376− for scanner.Scan() {
376+ for {
377+ line, err := reader.ReadString('\n')
377 lineNum++
378 lineNum++
378− line := scanner.Text()
379+ line = strings.TrimSuffix(line, "\n")
380+ line = strings.TrimSuffix(line, "\r")
379 if loc := pattern.FindStringIndex(line); loc != nil {
381 if loc := pattern.FindStringIndex(line); loc != nil {
380 charNum := loc[0] + 1
382 charNum := loc[0] + 1
381 return true, lineNum, charNum, line, nil
383 return true, lineNum, charNum, line, nil
382 }
384 }
385+ if err == io.EOF {
386+ break
387+ }
388+ if err != nil {
389+ return false, 0, 0, "", err
390+ }
383 }
391 }
384
392
385− return false, 0, 0, "", scanner.Err()
393+ return false, 0, 0, "", nil
386}
394}
387
395
388// isTextFile checks if a file is a text file by examining its MIME type.
396// isTextFile checks if a file is a text file by examining its MIME type.
internal/agent/tools/view.go+23−40
@@ -309,22 +309,29 @@ func readTextFile(filePath string, offset, limit, maxContentSize int) (string, b
309 }
309 }
310 defer file.Close()
310 defer file.Close()
311
311
312− scanner := NewLineScanner(file)
312+ reader := bufio.NewReader(file)
313− if offset > 0 {
313+ skipped := 0
314− skipped := 0
314+ for skipped < offset {
315− for skipped < offset && scanner.Scan() {
315+ _, err := reader.ReadString('\n')
316− skipped++
316+ if err != nil {
317− }
317+ if err == io.EOF {
318− if err = scanner.Err(); err != nil {
318+ return "", false, nil
319+ }
319 return "", false, err
320 return "", false, err
320 }
321 }
322+ skipped++
321 }
323 }
322
324
323 lines := make([]string, 0, min(limit, DefaultReadLimit))
325 lines := make([]string, 0, min(limit, DefaultReadLimit))
324 contentSize := 0
326 contentSize := 0
325
327
326− for len(lines) < limit && scanner.Scan() {
328+ for len(lines) < limit {
327− lineText := scanner.Text()
329+ lineText, err := reader.ReadString('\n')
330+ if err != nil && err != io.EOF {
331+ return "", false, err
332+ }
333+ lineText = strings.TrimSuffix(lineText, "\n")
334+ lineText = strings.TrimSuffix(lineText, "\r")
328 if len(lineText) > MaxLineLength {
335 if len(lineText) > MaxLineLength {
329 lineText = lineText[:MaxLineLength] + "..."
336 lineText = lineText[:MaxLineLength] + "..."
330 }
337 }
@@ -337,13 +344,16 @@ func readTextFile(filePath string, offset, limit, maxContentSize int) (string, b
337 }
344 }
338 contentSize = projectedSize
345 contentSize = projectedSize
339 lines = append(lines, lineText)
346 lines = append(lines, lineText)
347+ if err == io.EOF {
348+ break
349+ }
340 }
350 }
341
351
342 // Peek one more line only when we filled the limit.
352 // Peek one more line only when we filled the limit.
343− hasMore := len(lines) == limit && scanner.Scan()
353+ hasMore := false
344−
354+ if len(lines) == limit {
345− if err := scanner.Err(); err != nil {
355+ lineText, peekErr := reader.ReadString('\n')
346− return "", false, err
356+ hasMore = len(lineText) > 0 || peekErr == nil
347 }
357 }
348
358
349 return strings.Join(lines, "\n"), hasMore, nil
359 return strings.Join(lines, "\n"), hasMore, nil
@@ -385,33 +395,6 @@ func sniffImageMimeType(data []byte, fallback string) string {
385 return fallback
395 return fallback
386}
396}
387
397
388−type LineScanner struct {
389− scanner *bufio.Scanner
390−}
391−
392−func NewLineScanner(r io.Reader) *LineScanner {
393− scanner := bufio.NewScanner(r)
394− // Increase buffer size to handle large lines (e.g., minified JSON, HTML)
395− // Default is 64KB, set to 1MB
396− buf := make([]byte, 0, 64*1024)
397− scanner.Buffer(buf, 1024*1024)
398− return &LineScanner{
399− scanner: scanner,
400− }
401−}
402−
403−func (s *LineScanner) Scan() bool {
404− return s.scanner.Scan()
405−}
406−
407−func (s *LineScanner) Text() string {
408− return s.scanner.Text()
409−}
410−
411−func (s *LineScanner) Err() error {
412− return s.scanner.Err()
413−}
414−
415// isInSkillsPath checks if filePath is within any of the configured skills
398// isInSkillsPath checks if filePath is within any of the configured skills
416// directories. Returns true for files that can be read without permission
399// directories. Returns true for files that can be read without permission
417// prompts and without size limits.
400// prompts and without size limits.
internal/agent/tools/view_test.go+15
@@ -93,6 +93,21 @@ func TestReadTextFileTruncatesLongLines(t *testing.T) {
93 require.Equal(t, strings.Repeat("a", MaxLineLength)+"...", content)
93 require.Equal(t, strings.Repeat("a", MaxLineLength)+"...", content)
94}
94}
95
95
96+func TestReadTextFileLineExceeding1MB(t *testing.T) {
97+ t.Parallel()
98+
99+ tmpDir := t.TempDir()
100+ filePath := filepath.Join(tmpDir, "huge_line.txt")
101+
102+ hugeLine := strings.Repeat("A", 2*1024*1024) // 2MB — exceeds bufio.Scanner max
103+ require.NoError(t, os.WriteFile(filePath, []byte(hugeLine), 0o644))
104+
105+ content, hasMore, err := readTextFile(filePath, 0, 1, 0)
106+ require.NoError(t, err)
107+ require.False(t, hasMore)
108+ require.Equal(t, strings.Repeat("A", MaxLineLength)+"...", content)
109+}
110+
96func TestViewToolAllowsSmallSectionsOfLargeFiles(t *testing.T) {
111func TestViewToolAllowsSmallSectionsOfLargeFiles(t *testing.T) {
97 t.Parallel()
112 t.Parallel()
98
113