@yanlinglabs/winter-conformance 0.0.14 → 0.0.16
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +2 -2
- package/dist/official/differential-harness.d.ts +90 -0
- package/dist/official/task-frames-script.d.ts +95 -0
- package/goldens/advertised-set-round.trace.json +9 -3
- package/goldens/background-task-round.trace.json +7 -1
- package/goldens/bash-background-round.trace.json +11 -3
- package/goldens/canusetool-approved-round.trace.json +7 -1
- package/goldens/compaction-auto-round.trace.json +7 -1
- package/goldens/compaction-manual-round.trace.json +7 -1
- package/goldens/denied-tool-round.trace.json +7 -1
- package/goldens/hook-denied-round.trace.json +7 -1
- package/goldens/hooked-tool-round.trace.json +7 -1
- package/goldens/interrupt.trace.json +7 -1
- package/goldens/mcp-tool-round.trace.json +6 -0
- package/goldens/messaging-facet-round.trace.json +7 -1
- package/goldens/mode-switch-mid-session.trace.json +7 -1
- package/goldens/multi-turn.trace.json +11 -5
- package/goldens/p6-anthropic-fake.trace.json +9 -2
- package/goldens/p6-gemini-fake.trace.json +9 -2
- package/goldens/p6-openai-chat-fake.trace.json +9 -2
- package/goldens/p6-openai-responses-fake.trace.json +9 -2
- package/goldens/p6-resolution-failure.trace.json +7 -1
- package/goldens/plain-query.trace.json +9 -3
- package/goldens/resume.trace.json +18 -6
- package/goldens/sendmessage-child-round.trace.json +63 -7
- package/goldens/skill-invocation-round.trace.json +7 -1
- package/goldens/structured-exhaustion-round.trace.json +7 -1
- package/goldens/structured-output-round.trace.json +7 -1
- package/goldens/subagent-permission-round.trace.json +84 -10
- package/goldens/subagent-spawn-round.trace.json +61 -5
- package/goldens/tool-round.trace.json +7 -1
- package/goldens/toolsearch-select-round.trace.json +6 -0
- package/package.json +1 -1
|
@@ -48,7 +48,13 @@
|
|
|
48
48
|
],
|
|
49
49
|
"output_style": "default",
|
|
50
50
|
"skills": [],
|
|
51
|
-
"plugins": []
|
|
51
|
+
"plugins": [],
|
|
52
|
+
"agents": [
|
|
53
|
+
"claude",
|
|
54
|
+
"Explore",
|
|
55
|
+
"general-purpose",
|
|
56
|
+
"Plan"
|
|
57
|
+
]
|
|
52
58
|
}
|
|
53
59
|
},
|
|
54
60
|
{
|
|
@@ -65,7 +71,8 @@
|
|
|
65
71
|
"name": "Agent",
|
|
66
72
|
"input": {
|
|
67
73
|
"description": "equivalence probe",
|
|
68
|
-
"prompt": "child probe text"
|
|
74
|
+
"prompt": "child probe text",
|
|
75
|
+
"run_in_background": false
|
|
69
76
|
}
|
|
70
77
|
}
|
|
71
78
|
]
|
|
@@ -75,6 +82,55 @@
|
|
|
75
82
|
{
|
|
76
83
|
"sequence": 2,
|
|
77
84
|
"direction": "runtime-to-host",
|
|
85
|
+
"kind": "system/task_started",
|
|
86
|
+
"payload": {
|
|
87
|
+
"type": "system",
|
|
88
|
+
"subtype": "task_started",
|
|
89
|
+
"task_id": "TASKID_1",
|
|
90
|
+
"tool_use_id": "agent-call-1",
|
|
91
|
+
"description": "equivalence probe",
|
|
92
|
+
"subagent_type": "general-purpose",
|
|
93
|
+
"is_backgrounded": false,
|
|
94
|
+
"spawn_depth": 1,
|
|
95
|
+
"task_type": "local_agent",
|
|
96
|
+
"prompt": "child probe text"
|
|
97
|
+
}
|
|
98
|
+
},
|
|
99
|
+
{
|
|
100
|
+
"sequence": 3,
|
|
101
|
+
"direction": "runtime-to-host",
|
|
102
|
+
"kind": "system/task_updated",
|
|
103
|
+
"payload": {
|
|
104
|
+
"type": "system",
|
|
105
|
+
"subtype": "task_updated",
|
|
106
|
+
"task_id": "TASKID_1",
|
|
107
|
+
"patch": {
|
|
108
|
+
"status": "completed",
|
|
109
|
+
"end_time": "<end_time>"
|
|
110
|
+
}
|
|
111
|
+
}
|
|
112
|
+
},
|
|
113
|
+
{
|
|
114
|
+
"sequence": 4,
|
|
115
|
+
"direction": "runtime-to-host",
|
|
116
|
+
"kind": "system/task_notification",
|
|
117
|
+
"payload": {
|
|
118
|
+
"type": "system",
|
|
119
|
+
"subtype": "task_notification",
|
|
120
|
+
"task_id": "TASKID_1",
|
|
121
|
+
"tool_use_id": "agent-call-1",
|
|
122
|
+
"status": "completed",
|
|
123
|
+
"output_file": "/winter-fixture-tasks/TASKID_1.output",
|
|
124
|
+
"summary": "child finished",
|
|
125
|
+
"usage": {
|
|
126
|
+
"total_tokens": "<total_tokens>",
|
|
127
|
+
"tool_uses": 0
|
|
128
|
+
}
|
|
129
|
+
}
|
|
130
|
+
},
|
|
131
|
+
{
|
|
132
|
+
"sequence": 5,
|
|
133
|
+
"direction": "runtime-to-host",
|
|
78
134
|
"kind": "user",
|
|
79
135
|
"payload": {
|
|
80
136
|
"type": "user",
|
|
@@ -83,14 +139,14 @@
|
|
|
83
139
|
{
|
|
84
140
|
"type": "tool_result",
|
|
85
141
|
"tool_use_id": "agent-call-1",
|
|
86
|
-
"content": "{\"agentId\":\"<scrubbed>\",\"content\":[{\"type\":\"text\",\"text\":\"child finished\"}],\"totalToolUseCount\":0,\"totalDurationMs\":\"<scrubbed>\",\"resolvedModel\":\"winter-test/echo\",\"prompt\":\"child probe text\"}"
|
|
142
|
+
"content": "{\"agentId\":\"<scrubbed>\",\"agentType\":\"general-purpose\",\"content\":[{\"type\":\"text\",\"text\":\"child finished\"}],\"totalToolUseCount\":0,\"totalDurationMs\":\"<scrubbed>\",\"resolvedModel\":\"winter-test/echo\",\"prompt\":\"child probe text\"}"
|
|
87
143
|
}
|
|
88
144
|
]
|
|
89
145
|
}
|
|
90
146
|
}
|
|
91
147
|
},
|
|
92
148
|
{
|
|
93
|
-
"sequence":
|
|
149
|
+
"sequence": 6,
|
|
94
150
|
"direction": "runtime-to-host",
|
|
95
151
|
"kind": "assistant",
|
|
96
152
|
"payload": {
|
|
@@ -106,7 +162,7 @@
|
|
|
106
162
|
}
|
|
107
163
|
},
|
|
108
164
|
{
|
|
109
|
-
"sequence":
|
|
165
|
+
"sequence": 7,
|
|
110
166
|
"direction": "runtime-to-host",
|
|
111
167
|
"kind": "result",
|
|
112
168
|
"payload": {
|