@yanlinglabs/winter-conformance 0.0.17 → 0.0.20
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/goldens/advertised-set-round.trace.json +33 -1
- package/goldens/background-task-round.trace.json +33 -1
- package/goldens/bash-background-round.trace.json +33 -1
- package/goldens/canusetool-approved-round.trace.json +33 -1
- package/goldens/compaction-auto-round.trace.json +165 -5
- package/goldens/compaction-manual-round.trace.json +186 -5
- package/goldens/denied-tool-round.trace.json +33 -1
- package/goldens/hook-denied-round.trace.json +33 -1
- package/goldens/hooked-tool-round.trace.json +33 -1
- package/goldens/interrupt.trace.json +21 -0
- package/goldens/mcp-tool-round.trace.json +33 -1
- package/goldens/mode-switch-mid-session.trace.json +66 -2
- package/goldens/multi-turn.trace.json +66 -2
- package/goldens/p6-anthropic-fake.trace.json +25 -4
- package/goldens/p6-gemini-fake.trace.json +34 -1
- package/goldens/p6-openai-chat-fake.trace.json +35 -1
- package/goldens/p6-openai-responses-fake.trace.json +25 -4
- package/goldens/p6-resolution-failure.trace.json +21 -0
- package/goldens/plain-query.trace.json +33 -1
- package/goldens/resume.trace.json +66 -2
- package/goldens/sendmessage-child-round.trace.json +33 -1
- package/goldens/skill-invocation-round.trace.json +34 -2
- package/goldens/structured-exhaustion-round.trace.json +33 -1
- package/goldens/structured-output-round.trace.json +33 -1
- package/goldens/subagent-permission-round.trace.json +33 -1
- package/goldens/subagent-spawn-round.trace.json +33 -1
- package/goldens/tool-round.trace.json +33 -1
- package/goldens/toolsearch-select-round.trace.json +33 -1
- package/package.json +1 -1
|
@@ -210,7 +210,39 @@
|
|
|
210
210
|
"subtype": "success",
|
|
211
211
|
"is_error": false,
|
|
212
212
|
"result": "messaging done",
|
|
213
|
-
"
|
|
213
|
+
"usage": {
|
|
214
|
+
"output_tokens_details": {
|
|
215
|
+
"thinking_tokens": 0
|
|
216
|
+
},
|
|
217
|
+
"input_tokens": "<input_tokens>",
|
|
218
|
+
"cache_creation_input_tokens": "<cache_creation_input_tokens>",
|
|
219
|
+
"cache_read_input_tokens": "<cache_read_input_tokens>",
|
|
220
|
+
"output_tokens": "<output_tokens>",
|
|
221
|
+
"server_tool_use": {
|
|
222
|
+
"web_search_requests": 0,
|
|
223
|
+
"web_fetch_requests": 0
|
|
224
|
+
},
|
|
225
|
+
"service_tier": "standard",
|
|
226
|
+
"cache_creation": {
|
|
227
|
+
"ephemeral_1h_input_tokens": 0,
|
|
228
|
+
"ephemeral_5m_input_tokens": 0
|
|
229
|
+
},
|
|
230
|
+
"inference_geo": "",
|
|
231
|
+
"iterations": [],
|
|
232
|
+
"speed": "standard"
|
|
233
|
+
},
|
|
234
|
+
"permission_denials": [],
|
|
235
|
+
"modelUsage": {
|
|
236
|
+
"winter-test/echo": {
|
|
237
|
+
"inputTokens": "<inputTokens>",
|
|
238
|
+
"outputTokens": "<outputTokens>",
|
|
239
|
+
"cacheReadInputTokens": "<cacheReadInputTokens>",
|
|
240
|
+
"cacheCreationInputTokens": "<cacheCreationInputTokens>",
|
|
241
|
+
"webSearchRequests": 0,
|
|
242
|
+
"costUSD": 0,
|
|
243
|
+
"canonicalModel": "winter-test/echo"
|
|
244
|
+
}
|
|
245
|
+
}
|
|
214
246
|
}
|
|
215
247
|
}
|
|
216
248
|
]
|
|
@@ -94,7 +94,7 @@
|
|
|
94
94
|
{
|
|
95
95
|
"type": "tool_result",
|
|
96
96
|
"tool_use_id": "p5-skill-1",
|
|
97
|
-
"content": "
|
|
97
|
+
"content": "Base directory for this skill: /winter-home/skills/p5probe\n\nP5 SKILL BODY MARKER\n"
|
|
98
98
|
}
|
|
99
99
|
]
|
|
100
100
|
}
|
|
@@ -125,7 +125,39 @@
|
|
|
125
125
|
"subtype": "success",
|
|
126
126
|
"is_error": false,
|
|
127
127
|
"result": "skill done",
|
|
128
|
-
"
|
|
128
|
+
"usage": {
|
|
129
|
+
"output_tokens_details": {
|
|
130
|
+
"thinking_tokens": 0
|
|
131
|
+
},
|
|
132
|
+
"input_tokens": "<input_tokens>",
|
|
133
|
+
"cache_creation_input_tokens": "<cache_creation_input_tokens>",
|
|
134
|
+
"cache_read_input_tokens": "<cache_read_input_tokens>",
|
|
135
|
+
"output_tokens": "<output_tokens>",
|
|
136
|
+
"server_tool_use": {
|
|
137
|
+
"web_search_requests": 0,
|
|
138
|
+
"web_fetch_requests": 0
|
|
139
|
+
},
|
|
140
|
+
"service_tier": "standard",
|
|
141
|
+
"cache_creation": {
|
|
142
|
+
"ephemeral_1h_input_tokens": 0,
|
|
143
|
+
"ephemeral_5m_input_tokens": 0
|
|
144
|
+
},
|
|
145
|
+
"inference_geo": "",
|
|
146
|
+
"iterations": [],
|
|
147
|
+
"speed": "standard"
|
|
148
|
+
},
|
|
149
|
+
"permission_denials": [],
|
|
150
|
+
"modelUsage": {
|
|
151
|
+
"winter-test/echo": {
|
|
152
|
+
"inputTokens": "<inputTokens>",
|
|
153
|
+
"outputTokens": "<outputTokens>",
|
|
154
|
+
"cacheReadInputTokens": "<cacheReadInputTokens>",
|
|
155
|
+
"cacheCreationInputTokens": "<cacheCreationInputTokens>",
|
|
156
|
+
"webSearchRequests": 0,
|
|
157
|
+
"costUSD": 0,
|
|
158
|
+
"canonicalModel": "winter-test/echo"
|
|
159
|
+
}
|
|
160
|
+
}
|
|
129
161
|
}
|
|
130
162
|
}
|
|
131
163
|
]
|
|
@@ -184,7 +184,39 @@
|
|
|
184
184
|
"is_error": true,
|
|
185
185
|
"result": "Failed to provide valid structured output after 3 attempts",
|
|
186
186
|
"terminal_reason": "structured_output_retry_exhausted",
|
|
187
|
-
"
|
|
187
|
+
"usage": {
|
|
188
|
+
"output_tokens_details": {
|
|
189
|
+
"thinking_tokens": 0
|
|
190
|
+
},
|
|
191
|
+
"input_tokens": "<input_tokens>",
|
|
192
|
+
"cache_creation_input_tokens": "<cache_creation_input_tokens>",
|
|
193
|
+
"cache_read_input_tokens": "<cache_read_input_tokens>",
|
|
194
|
+
"output_tokens": "<output_tokens>",
|
|
195
|
+
"server_tool_use": {
|
|
196
|
+
"web_search_requests": 0,
|
|
197
|
+
"web_fetch_requests": 0
|
|
198
|
+
},
|
|
199
|
+
"service_tier": "standard",
|
|
200
|
+
"cache_creation": {
|
|
201
|
+
"ephemeral_1h_input_tokens": 0,
|
|
202
|
+
"ephemeral_5m_input_tokens": 0
|
|
203
|
+
},
|
|
204
|
+
"inference_geo": "",
|
|
205
|
+
"iterations": [],
|
|
206
|
+
"speed": "standard"
|
|
207
|
+
},
|
|
208
|
+
"permission_denials": [],
|
|
209
|
+
"modelUsage": {
|
|
210
|
+
"winter-test/echo": {
|
|
211
|
+
"inputTokens": "<inputTokens>",
|
|
212
|
+
"outputTokens": "<outputTokens>",
|
|
213
|
+
"cacheReadInputTokens": "<cacheReadInputTokens>",
|
|
214
|
+
"cacheCreationInputTokens": "<cacheCreationInputTokens>",
|
|
215
|
+
"webSearchRequests": 0,
|
|
216
|
+
"costUSD": 0,
|
|
217
|
+
"canonicalModel": "winter-test/echo"
|
|
218
|
+
}
|
|
219
|
+
}
|
|
188
220
|
}
|
|
189
221
|
}
|
|
190
222
|
]
|
|
@@ -108,7 +108,39 @@
|
|
|
108
108
|
"structured_output": {
|
|
109
109
|
"answer": 42
|
|
110
110
|
},
|
|
111
|
-
"
|
|
111
|
+
"usage": {
|
|
112
|
+
"output_tokens_details": {
|
|
113
|
+
"thinking_tokens": 0
|
|
114
|
+
},
|
|
115
|
+
"input_tokens": "<input_tokens>",
|
|
116
|
+
"cache_creation_input_tokens": "<cache_creation_input_tokens>",
|
|
117
|
+
"cache_read_input_tokens": "<cache_read_input_tokens>",
|
|
118
|
+
"output_tokens": "<output_tokens>",
|
|
119
|
+
"server_tool_use": {
|
|
120
|
+
"web_search_requests": 0,
|
|
121
|
+
"web_fetch_requests": 0
|
|
122
|
+
},
|
|
123
|
+
"service_tier": "standard",
|
|
124
|
+
"cache_creation": {
|
|
125
|
+
"ephemeral_1h_input_tokens": 0,
|
|
126
|
+
"ephemeral_5m_input_tokens": 0
|
|
127
|
+
},
|
|
128
|
+
"inference_geo": "",
|
|
129
|
+
"iterations": [],
|
|
130
|
+
"speed": "standard"
|
|
131
|
+
},
|
|
132
|
+
"permission_denials": [],
|
|
133
|
+
"modelUsage": {
|
|
134
|
+
"winter-test/echo": {
|
|
135
|
+
"inputTokens": "<inputTokens>",
|
|
136
|
+
"outputTokens": "<outputTokens>",
|
|
137
|
+
"cacheReadInputTokens": "<cacheReadInputTokens>",
|
|
138
|
+
"cacheCreationInputTokens": "<cacheCreationInputTokens>",
|
|
139
|
+
"webSearchRequests": 0,
|
|
140
|
+
"costUSD": 0,
|
|
141
|
+
"canonicalModel": "winter-test/echo"
|
|
142
|
+
}
|
|
143
|
+
}
|
|
112
144
|
}
|
|
113
145
|
}
|
|
114
146
|
]
|
|
@@ -244,7 +244,39 @@
|
|
|
244
244
|
"subtype": "success",
|
|
245
245
|
"is_error": false,
|
|
246
246
|
"result": "parent finished",
|
|
247
|
-
"
|
|
247
|
+
"usage": {
|
|
248
|
+
"output_tokens_details": {
|
|
249
|
+
"thinking_tokens": 0
|
|
250
|
+
},
|
|
251
|
+
"input_tokens": "<input_tokens>",
|
|
252
|
+
"cache_creation_input_tokens": "<cache_creation_input_tokens>",
|
|
253
|
+
"cache_read_input_tokens": "<cache_read_input_tokens>",
|
|
254
|
+
"output_tokens": "<output_tokens>",
|
|
255
|
+
"server_tool_use": {
|
|
256
|
+
"web_search_requests": 0,
|
|
257
|
+
"web_fetch_requests": 0
|
|
258
|
+
},
|
|
259
|
+
"service_tier": "standard",
|
|
260
|
+
"cache_creation": {
|
|
261
|
+
"ephemeral_1h_input_tokens": 0,
|
|
262
|
+
"ephemeral_5m_input_tokens": 0
|
|
263
|
+
},
|
|
264
|
+
"inference_geo": "",
|
|
265
|
+
"iterations": [],
|
|
266
|
+
"speed": "standard"
|
|
267
|
+
},
|
|
268
|
+
"permission_denials": [],
|
|
269
|
+
"modelUsage": {
|
|
270
|
+
"winter-test/echo": {
|
|
271
|
+
"inputTokens": "<inputTokens>",
|
|
272
|
+
"outputTokens": "<outputTokens>",
|
|
273
|
+
"cacheReadInputTokens": "<cacheReadInputTokens>",
|
|
274
|
+
"cacheCreationInputTokens": "<cacheCreationInputTokens>",
|
|
275
|
+
"webSearchRequests": 0,
|
|
276
|
+
"costUSD": 0,
|
|
277
|
+
"canonicalModel": "winter-test/echo"
|
|
278
|
+
}
|
|
279
|
+
}
|
|
248
280
|
}
|
|
249
281
|
}
|
|
250
282
|
]
|
|
@@ -172,7 +172,39 @@
|
|
|
172
172
|
"subtype": "success",
|
|
173
173
|
"is_error": false,
|
|
174
174
|
"result": "parent finished",
|
|
175
|
-
"
|
|
175
|
+
"usage": {
|
|
176
|
+
"output_tokens_details": {
|
|
177
|
+
"thinking_tokens": 0
|
|
178
|
+
},
|
|
179
|
+
"input_tokens": "<input_tokens>",
|
|
180
|
+
"cache_creation_input_tokens": "<cache_creation_input_tokens>",
|
|
181
|
+
"cache_read_input_tokens": "<cache_read_input_tokens>",
|
|
182
|
+
"output_tokens": "<output_tokens>",
|
|
183
|
+
"server_tool_use": {
|
|
184
|
+
"web_search_requests": 0,
|
|
185
|
+
"web_fetch_requests": 0
|
|
186
|
+
},
|
|
187
|
+
"service_tier": "standard",
|
|
188
|
+
"cache_creation": {
|
|
189
|
+
"ephemeral_1h_input_tokens": 0,
|
|
190
|
+
"ephemeral_5m_input_tokens": 0
|
|
191
|
+
},
|
|
192
|
+
"inference_geo": "",
|
|
193
|
+
"iterations": [],
|
|
194
|
+
"speed": "standard"
|
|
195
|
+
},
|
|
196
|
+
"permission_denials": [],
|
|
197
|
+
"modelUsage": {
|
|
198
|
+
"winter-test/echo": {
|
|
199
|
+
"inputTokens": "<inputTokens>",
|
|
200
|
+
"outputTokens": "<outputTokens>",
|
|
201
|
+
"cacheReadInputTokens": "<cacheReadInputTokens>",
|
|
202
|
+
"cacheCreationInputTokens": "<cacheCreationInputTokens>",
|
|
203
|
+
"webSearchRequests": 0,
|
|
204
|
+
"costUSD": 0,
|
|
205
|
+
"canonicalModel": "winter-test/echo"
|
|
206
|
+
}
|
|
207
|
+
}
|
|
176
208
|
}
|
|
177
209
|
}
|
|
178
210
|
]
|
|
@@ -121,7 +121,39 @@
|
|
|
121
121
|
"subtype": "success",
|
|
122
122
|
"is_error": false,
|
|
123
123
|
"result": "tool round done",
|
|
124
|
-
"
|
|
124
|
+
"usage": {
|
|
125
|
+
"output_tokens_details": {
|
|
126
|
+
"thinking_tokens": 0
|
|
127
|
+
},
|
|
128
|
+
"input_tokens": "<input_tokens>",
|
|
129
|
+
"cache_creation_input_tokens": "<cache_creation_input_tokens>",
|
|
130
|
+
"cache_read_input_tokens": "<cache_read_input_tokens>",
|
|
131
|
+
"output_tokens": "<output_tokens>",
|
|
132
|
+
"server_tool_use": {
|
|
133
|
+
"web_search_requests": 0,
|
|
134
|
+
"web_fetch_requests": 0
|
|
135
|
+
},
|
|
136
|
+
"service_tier": "standard",
|
|
137
|
+
"cache_creation": {
|
|
138
|
+
"ephemeral_1h_input_tokens": 0,
|
|
139
|
+
"ephemeral_5m_input_tokens": 0
|
|
140
|
+
},
|
|
141
|
+
"inference_geo": "",
|
|
142
|
+
"iterations": [],
|
|
143
|
+
"speed": "standard"
|
|
144
|
+
},
|
|
145
|
+
"permission_denials": [],
|
|
146
|
+
"modelUsage": {
|
|
147
|
+
"winter-test/echo": {
|
|
148
|
+
"inputTokens": "<inputTokens>",
|
|
149
|
+
"outputTokens": "<outputTokens>",
|
|
150
|
+
"cacheReadInputTokens": "<cacheReadInputTokens>",
|
|
151
|
+
"cacheCreationInputTokens": "<cacheCreationInputTokens>",
|
|
152
|
+
"webSearchRequests": 0,
|
|
153
|
+
"costUSD": 0,
|
|
154
|
+
"canonicalModel": "winter-test/echo"
|
|
155
|
+
}
|
|
156
|
+
}
|
|
125
157
|
}
|
|
126
158
|
}
|
|
127
159
|
]
|
|
@@ -187,7 +187,39 @@
|
|
|
187
187
|
"subtype": "success",
|
|
188
188
|
"is_error": false,
|
|
189
189
|
"result": "tool search done",
|
|
190
|
-
"
|
|
190
|
+
"usage": {
|
|
191
|
+
"output_tokens_details": {
|
|
192
|
+
"thinking_tokens": 0
|
|
193
|
+
},
|
|
194
|
+
"input_tokens": "<input_tokens>",
|
|
195
|
+
"cache_creation_input_tokens": "<cache_creation_input_tokens>",
|
|
196
|
+
"cache_read_input_tokens": "<cache_read_input_tokens>",
|
|
197
|
+
"output_tokens": "<output_tokens>",
|
|
198
|
+
"server_tool_use": {
|
|
199
|
+
"web_search_requests": 0,
|
|
200
|
+
"web_fetch_requests": 0
|
|
201
|
+
},
|
|
202
|
+
"service_tier": "standard",
|
|
203
|
+
"cache_creation": {
|
|
204
|
+
"ephemeral_1h_input_tokens": 0,
|
|
205
|
+
"ephemeral_5m_input_tokens": 0
|
|
206
|
+
},
|
|
207
|
+
"inference_geo": "",
|
|
208
|
+
"iterations": [],
|
|
209
|
+
"speed": "standard"
|
|
210
|
+
},
|
|
211
|
+
"permission_denials": [],
|
|
212
|
+
"modelUsage": {
|
|
213
|
+
"winter-test/echo": {
|
|
214
|
+
"inputTokens": "<inputTokens>",
|
|
215
|
+
"outputTokens": "<outputTokens>",
|
|
216
|
+
"cacheReadInputTokens": "<cacheReadInputTokens>",
|
|
217
|
+
"cacheCreationInputTokens": "<cacheCreationInputTokens>",
|
|
218
|
+
"webSearchRequests": 0,
|
|
219
|
+
"costUSD": 0,
|
|
220
|
+
"canonicalModel": "winter-test/echo"
|
|
221
|
+
}
|
|
222
|
+
}
|
|
191
223
|
}
|
|
192
224
|
}
|
|
193
225
|
]
|