@yanlinglabs/winter-conformance 0.0.16 → 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.
Files changed (31) hide show
  1. package/dist/official/web-tools-script.d.ts +118 -0
  2. package/goldens/advertised-set-round.trace.json +35 -1
  3. package/goldens/background-task-round.trace.json +35 -1
  4. package/goldens/bash-background-round.trace.json +35 -1
  5. package/goldens/canusetool-approved-round.trace.json +35 -1
  6. package/goldens/compaction-auto-round.trace.json +167 -5
  7. package/goldens/compaction-manual-round.trace.json +188 -5
  8. package/goldens/denied-tool-round.trace.json +35 -1
  9. package/goldens/hook-denied-round.trace.json +35 -1
  10. package/goldens/hooked-tool-round.trace.json +35 -1
  11. package/goldens/interrupt.trace.json +25 -0
  12. package/goldens/mcp-tool-round.trace.json +35 -1
  13. package/goldens/messaging-facet-round.trace.json +4 -0
  14. package/goldens/mode-switch-mid-session.trace.json +68 -2
  15. package/goldens/multi-turn.trace.json +68 -2
  16. package/goldens/p6-anthropic-fake.trace.json +27 -4
  17. package/goldens/p6-gemini-fake.trace.json +36 -1
  18. package/goldens/p6-openai-chat-fake.trace.json +37 -1
  19. package/goldens/p6-openai-responses-fake.trace.json +27 -4
  20. package/goldens/p6-resolution-failure.trace.json +23 -0
  21. package/goldens/plain-query.trace.json +35 -1
  22. package/goldens/resume.trace.json +70 -2
  23. package/goldens/sendmessage-child-round.trace.json +35 -1
  24. package/goldens/skill-invocation-round.trace.json +36 -2
  25. package/goldens/structured-exhaustion-round.trace.json +35 -1
  26. package/goldens/structured-output-round.trace.json +35 -1
  27. package/goldens/subagent-permission-round.trace.json +35 -1
  28. package/goldens/subagent-spawn-round.trace.json +35 -1
  29. package/goldens/tool-round.trace.json +35 -1
  30. package/goldens/toolsearch-select-round.trace.json +35 -1
  31. package/package.json +1 -1
@@ -39,6 +39,8 @@
39
39
  "TaskOutput",
40
40
  "TaskStop",
41
41
  "TaskUpdate",
42
+ "WebFetch",
43
+ "WebSearch",
42
44
  "Workflow",
43
45
  "Write"
44
46
  ],
@@ -82,7 +84,39 @@
82
84
  "subtype": "success",
83
85
  "is_error": false,
84
86
  "result": "reply 1",
85
- "permission_denials": []
87
+ "usage": {
88
+ "output_tokens_details": {
89
+ "thinking_tokens": 0
90
+ },
91
+ "input_tokens": "<input_tokens>",
92
+ "cache_creation_input_tokens": "<cache_creation_input_tokens>",
93
+ "cache_read_input_tokens": "<cache_read_input_tokens>",
94
+ "output_tokens": "<output_tokens>",
95
+ "server_tool_use": {
96
+ "web_search_requests": 0,
97
+ "web_fetch_requests": 0
98
+ },
99
+ "service_tier": "standard",
100
+ "cache_creation": {
101
+ "ephemeral_1h_input_tokens": 0,
102
+ "ephemeral_5m_input_tokens": 0
103
+ },
104
+ "inference_geo": "",
105
+ "iterations": [],
106
+ "speed": "standard"
107
+ },
108
+ "permission_denials": [],
109
+ "modelUsage": {
110
+ "winter-test/echo": {
111
+ "inputTokens": "<inputTokens>",
112
+ "outputTokens": "<outputTokens>",
113
+ "cacheReadInputTokens": "<cacheReadInputTokens>",
114
+ "cacheCreationInputTokens": "<cacheCreationInputTokens>",
115
+ "webSearchRequests": 0,
116
+ "costUSD": 0,
117
+ "canonicalModel": "winter-test/echo"
118
+ }
119
+ }
86
120
  }
87
121
  },
88
122
  {
@@ -110,7 +144,39 @@
110
144
  "subtype": "success",
111
145
  "is_error": false,
112
146
  "result": "reply 2",
113
- "permission_denials": []
147
+ "usage": {
148
+ "output_tokens_details": {
149
+ "thinking_tokens": 0
150
+ },
151
+ "input_tokens": "<input_tokens>",
152
+ "cache_creation_input_tokens": "<cache_creation_input_tokens>",
153
+ "cache_read_input_tokens": "<cache_read_input_tokens>",
154
+ "output_tokens": "<output_tokens>",
155
+ "server_tool_use": {
156
+ "web_search_requests": 0,
157
+ "web_fetch_requests": 0
158
+ },
159
+ "service_tier": "standard",
160
+ "cache_creation": {
161
+ "ephemeral_1h_input_tokens": 0,
162
+ "ephemeral_5m_input_tokens": 0
163
+ },
164
+ "inference_geo": "",
165
+ "iterations": [],
166
+ "speed": "standard"
167
+ },
168
+ "permission_denials": [],
169
+ "modelUsage": {
170
+ "winter-test/echo": {
171
+ "inputTokens": "<inputTokens>",
172
+ "outputTokens": "<outputTokens>",
173
+ "cacheReadInputTokens": "<cacheReadInputTokens>",
174
+ "cacheCreationInputTokens": "<cacheCreationInputTokens>",
175
+ "webSearchRequests": 0,
176
+ "costUSD": 0,
177
+ "canonicalModel": "winter-test/echo"
178
+ }
179
+ }
114
180
  }
115
181
  },
116
182
  {
@@ -138,7 +204,39 @@
138
204
  "subtype": "success",
139
205
  "is_error": false,
140
206
  "result": "reply 3",
141
- "permission_denials": []
207
+ "usage": {
208
+ "output_tokens_details": {
209
+ "thinking_tokens": 0
210
+ },
211
+ "input_tokens": "<input_tokens>",
212
+ "cache_creation_input_tokens": "<cache_creation_input_tokens>",
213
+ "cache_read_input_tokens": "<cache_read_input_tokens>",
214
+ "output_tokens": "<output_tokens>",
215
+ "server_tool_use": {
216
+ "web_search_requests": 0,
217
+ "web_fetch_requests": 0
218
+ },
219
+ "service_tier": "standard",
220
+ "cache_creation": {
221
+ "ephemeral_1h_input_tokens": 0,
222
+ "ephemeral_5m_input_tokens": 0
223
+ },
224
+ "inference_geo": "",
225
+ "iterations": [],
226
+ "speed": "standard"
227
+ },
228
+ "permission_denials": [],
229
+ "modelUsage": {
230
+ "winter-test/echo": {
231
+ "inputTokens": "<inputTokens>",
232
+ "outputTokens": "<outputTokens>",
233
+ "cacheReadInputTokens": "<cacheReadInputTokens>",
234
+ "cacheCreationInputTokens": "<cacheCreationInputTokens>",
235
+ "webSearchRequests": 0,
236
+ "costUSD": 0,
237
+ "canonicalModel": "winter-test/echo"
238
+ }
239
+ }
142
240
  }
143
241
  },
144
242
  {
@@ -166,7 +264,39 @@
166
264
  "subtype": "success",
167
265
  "is_error": false,
168
266
  "result": "reply 4",
169
- "permission_denials": []
267
+ "usage": {
268
+ "output_tokens_details": {
269
+ "thinking_tokens": 0
270
+ },
271
+ "input_tokens": "<input_tokens>",
272
+ "cache_creation_input_tokens": "<cache_creation_input_tokens>",
273
+ "cache_read_input_tokens": "<cache_read_input_tokens>",
274
+ "output_tokens": "<output_tokens>",
275
+ "server_tool_use": {
276
+ "web_search_requests": 0,
277
+ "web_fetch_requests": 0
278
+ },
279
+ "service_tier": "standard",
280
+ "cache_creation": {
281
+ "ephemeral_1h_input_tokens": 0,
282
+ "ephemeral_5m_input_tokens": 0
283
+ },
284
+ "inference_geo": "",
285
+ "iterations": [],
286
+ "speed": "standard"
287
+ },
288
+ "permission_denials": [],
289
+ "modelUsage": {
290
+ "winter-test/echo": {
291
+ "inputTokens": "<inputTokens>",
292
+ "outputTokens": "<outputTokens>",
293
+ "cacheReadInputTokens": "<cacheReadInputTokens>",
294
+ "cacheCreationInputTokens": "<cacheCreationInputTokens>",
295
+ "webSearchRequests": 0,
296
+ "costUSD": 0,
297
+ "canonicalModel": "winter-test/echo"
298
+ }
299
+ }
170
300
  }
171
301
  },
172
302
  {
@@ -194,7 +324,39 @@
194
324
  "subtype": "success",
195
325
  "is_error": false,
196
326
  "result": "reply 5",
197
- "permission_denials": []
327
+ "usage": {
328
+ "output_tokens_details": {
329
+ "thinking_tokens": 0
330
+ },
331
+ "input_tokens": "<input_tokens>",
332
+ "cache_creation_input_tokens": "<cache_creation_input_tokens>",
333
+ "cache_read_input_tokens": "<cache_read_input_tokens>",
334
+ "output_tokens": "<output_tokens>",
335
+ "server_tool_use": {
336
+ "web_search_requests": 0,
337
+ "web_fetch_requests": 0
338
+ },
339
+ "service_tier": "standard",
340
+ "cache_creation": {
341
+ "ephemeral_1h_input_tokens": 0,
342
+ "ephemeral_5m_input_tokens": 0
343
+ },
344
+ "inference_geo": "",
345
+ "iterations": [],
346
+ "speed": "standard"
347
+ },
348
+ "permission_denials": [],
349
+ "modelUsage": {
350
+ "winter-test/echo": {
351
+ "inputTokens": "<inputTokens>",
352
+ "outputTokens": "<outputTokens>",
353
+ "cacheReadInputTokens": "<cacheReadInputTokens>",
354
+ "cacheCreationInputTokens": "<cacheCreationInputTokens>",
355
+ "webSearchRequests": 0,
356
+ "costUSD": 0,
357
+ "canonicalModel": "winter-test/echo"
358
+ }
359
+ }
198
360
  }
199
361
  },
200
362
  {
@@ -232,6 +394,27 @@
232
394
  "subtype": "success",
233
395
  "is_error": false,
234
396
  "result": "Compacted the conversation. 8 message(s) retained alongside the summary.",
397
+ "usage": {
398
+ "output_tokens_details": {
399
+ "thinking_tokens": 0
400
+ },
401
+ "input_tokens": "<input_tokens>",
402
+ "cache_creation_input_tokens": "<cache_creation_input_tokens>",
403
+ "cache_read_input_tokens": "<cache_read_input_tokens>",
404
+ "output_tokens": "<output_tokens>",
405
+ "server_tool_use": {
406
+ "web_search_requests": 0,
407
+ "web_fetch_requests": 0
408
+ },
409
+ "service_tier": "standard",
410
+ "cache_creation": {
411
+ "ephemeral_1h_input_tokens": 0,
412
+ "ephemeral_5m_input_tokens": 0
413
+ },
414
+ "inference_geo": "",
415
+ "iterations": [],
416
+ "speed": "standard"
417
+ },
235
418
  "permission_denials": []
236
419
  }
237
420
  }
@@ -39,6 +39,8 @@
39
39
  "TaskOutput",
40
40
  "TaskStop",
41
41
  "TaskUpdate",
42
+ "WebFetch",
43
+ "WebSearch",
42
44
  "Workflow",
43
45
  "Write"
44
46
  ],
@@ -133,6 +135,27 @@
133
135
  "subtype": "success",
134
136
  "is_error": false,
135
137
  "result": "tool round done",
138
+ "usage": {
139
+ "output_tokens_details": {
140
+ "thinking_tokens": 0
141
+ },
142
+ "input_tokens": "<input_tokens>",
143
+ "cache_creation_input_tokens": "<cache_creation_input_tokens>",
144
+ "cache_read_input_tokens": "<cache_read_input_tokens>",
145
+ "output_tokens": "<output_tokens>",
146
+ "server_tool_use": {
147
+ "web_search_requests": 0,
148
+ "web_fetch_requests": 0
149
+ },
150
+ "service_tier": "standard",
151
+ "cache_creation": {
152
+ "ephemeral_1h_input_tokens": 0,
153
+ "ephemeral_5m_input_tokens": 0
154
+ },
155
+ "inference_geo": "",
156
+ "iterations": [],
157
+ "speed": "standard"
158
+ },
136
159
  "permission_denials": [
137
160
  {
138
161
  "tool_name": "test_tool",
@@ -141,7 +164,18 @@
141
164
  "probe": true
142
165
  }
143
166
  }
144
- ]
167
+ ],
168
+ "modelUsage": {
169
+ "winter-test/echo": {
170
+ "inputTokens": "<inputTokens>",
171
+ "outputTokens": "<outputTokens>",
172
+ "cacheReadInputTokens": "<cacheReadInputTokens>",
173
+ "cacheCreationInputTokens": "<cacheCreationInputTokens>",
174
+ "webSearchRequests": 0,
175
+ "costUSD": 0,
176
+ "canonicalModel": "winter-test/echo"
177
+ }
178
+ }
145
179
  }
146
180
  }
147
181
  ]
@@ -39,6 +39,8 @@
39
39
  "TaskOutput",
40
40
  "TaskStop",
41
41
  "TaskUpdate",
42
+ "WebFetch",
43
+ "WebSearch",
42
44
  "Workflow",
43
45
  "Write"
44
46
  ],
@@ -161,6 +163,27 @@
161
163
  "subtype": "success",
162
164
  "is_error": false,
163
165
  "result": "tool round done",
166
+ "usage": {
167
+ "output_tokens_details": {
168
+ "thinking_tokens": 0
169
+ },
170
+ "input_tokens": "<input_tokens>",
171
+ "cache_creation_input_tokens": "<cache_creation_input_tokens>",
172
+ "cache_read_input_tokens": "<cache_read_input_tokens>",
173
+ "output_tokens": "<output_tokens>",
174
+ "server_tool_use": {
175
+ "web_search_requests": 0,
176
+ "web_fetch_requests": 0
177
+ },
178
+ "service_tier": "standard",
179
+ "cache_creation": {
180
+ "ephemeral_1h_input_tokens": 0,
181
+ "ephemeral_5m_input_tokens": 0
182
+ },
183
+ "inference_geo": "",
184
+ "iterations": [],
185
+ "speed": "standard"
186
+ },
164
187
  "permission_denials": [
165
188
  {
166
189
  "tool_name": "test_tool",
@@ -169,7 +192,18 @@
169
192
  "probe": true
170
193
  }
171
194
  }
172
- ]
195
+ ],
196
+ "modelUsage": {
197
+ "winter-test/echo": {
198
+ "inputTokens": "<inputTokens>",
199
+ "outputTokens": "<outputTokens>",
200
+ "cacheReadInputTokens": "<cacheReadInputTokens>",
201
+ "cacheCreationInputTokens": "<cacheCreationInputTokens>",
202
+ "webSearchRequests": 0,
203
+ "costUSD": 0,
204
+ "canonicalModel": "winter-test/echo"
205
+ }
206
+ }
173
207
  }
174
208
  }
175
209
  ]
@@ -39,6 +39,8 @@
39
39
  "TaskOutput",
40
40
  "TaskStop",
41
41
  "TaskUpdate",
42
+ "WebFetch",
43
+ "WebSearch",
42
44
  "Workflow",
43
45
  "Write"
44
46
  ],
@@ -147,7 +149,39 @@
147
149
  "subtype": "success",
148
150
  "is_error": false,
149
151
  "result": "tool round done",
150
- "permission_denials": []
152
+ "usage": {
153
+ "output_tokens_details": {
154
+ "thinking_tokens": 0
155
+ },
156
+ "input_tokens": "<input_tokens>",
157
+ "cache_creation_input_tokens": "<cache_creation_input_tokens>",
158
+ "cache_read_input_tokens": "<cache_read_input_tokens>",
159
+ "output_tokens": "<output_tokens>",
160
+ "server_tool_use": {
161
+ "web_search_requests": 0,
162
+ "web_fetch_requests": 0
163
+ },
164
+ "service_tier": "standard",
165
+ "cache_creation": {
166
+ "ephemeral_1h_input_tokens": 0,
167
+ "ephemeral_5m_input_tokens": 0
168
+ },
169
+ "inference_geo": "",
170
+ "iterations": [],
171
+ "speed": "standard"
172
+ },
173
+ "permission_denials": [],
174
+ "modelUsage": {
175
+ "winter-test/echo": {
176
+ "inputTokens": "<inputTokens>",
177
+ "outputTokens": "<outputTokens>",
178
+ "cacheReadInputTokens": "<cacheReadInputTokens>",
179
+ "cacheCreationInputTokens": "<cacheCreationInputTokens>",
180
+ "webSearchRequests": 0,
181
+ "costUSD": 0,
182
+ "canonicalModel": "winter-test/echo"
183
+ }
184
+ }
151
185
  }
152
186
  }
153
187
  ]
@@ -39,6 +39,8 @@
39
39
  "TaskOutput",
40
40
  "TaskStop",
41
41
  "TaskUpdate",
42
+ "WebFetch",
43
+ "WebSearch",
42
44
  "Workflow",
43
45
  "Write"
44
46
  ]
@@ -84,6 +86,8 @@
84
86
  "TaskOutput",
85
87
  "TaskStop",
86
88
  "TaskUpdate",
89
+ "WebFetch",
90
+ "WebSearch",
87
91
  "Workflow",
88
92
  "Write"
89
93
  ],
@@ -120,6 +124,27 @@
120
124
  "subtype": "success",
121
125
  "is_error": false,
122
126
  "interrupted": true,
127
+ "usage": {
128
+ "output_tokens_details": {
129
+ "thinking_tokens": 0
130
+ },
131
+ "input_tokens": "<input_tokens>",
132
+ "cache_creation_input_tokens": "<cache_creation_input_tokens>",
133
+ "cache_read_input_tokens": "<cache_read_input_tokens>",
134
+ "output_tokens": "<output_tokens>",
135
+ "server_tool_use": {
136
+ "web_search_requests": 0,
137
+ "web_fetch_requests": 0
138
+ },
139
+ "service_tier": "standard",
140
+ "cache_creation": {
141
+ "ephemeral_1h_input_tokens": 0,
142
+ "ephemeral_5m_input_tokens": 0
143
+ },
144
+ "inference_geo": "",
145
+ "iterations": [],
146
+ "speed": "standard"
147
+ },
123
148
  "permission_denials": []
124
149
  }
125
150
  },
@@ -44,6 +44,8 @@
44
44
  "TaskStop",
45
45
  "TaskUpdate",
46
46
  "WaitForMcpServers",
47
+ "WebFetch",
48
+ "WebSearch",
47
49
  "Workflow",
48
50
  "Write",
49
51
  "mcp__t8mcpsdk__echo"
@@ -131,7 +133,39 @@
131
133
  "subtype": "success",
132
134
  "is_error": false,
133
135
  "result": "mcp sdk done",
134
- "permission_denials": []
136
+ "usage": {
137
+ "output_tokens_details": {
138
+ "thinking_tokens": 0
139
+ },
140
+ "input_tokens": "<input_tokens>",
141
+ "cache_creation_input_tokens": "<cache_creation_input_tokens>",
142
+ "cache_read_input_tokens": "<cache_read_input_tokens>",
143
+ "output_tokens": "<output_tokens>",
144
+ "server_tool_use": {
145
+ "web_search_requests": 0,
146
+ "web_fetch_requests": 0
147
+ },
148
+ "service_tier": "standard",
149
+ "cache_creation": {
150
+ "ephemeral_1h_input_tokens": 0,
151
+ "ephemeral_5m_input_tokens": 0
152
+ },
153
+ "inference_geo": "",
154
+ "iterations": [],
155
+ "speed": "standard"
156
+ },
157
+ "permission_denials": [],
158
+ "modelUsage": {
159
+ "winter-test/echo": {
160
+ "inputTokens": "<inputTokens>",
161
+ "outputTokens": "<outputTokens>",
162
+ "cacheReadInputTokens": "<cacheReadInputTokens>",
163
+ "cacheCreationInputTokens": "<cacheCreationInputTokens>",
164
+ "webSearchRequests": 0,
165
+ "costUSD": 0,
166
+ "canonicalModel": "winter-test/echo"
167
+ }
168
+ }
135
169
  }
136
170
  }
137
171
  ]
@@ -39,6 +39,8 @@
39
39
  "TaskOutput",
40
40
  "TaskStop",
41
41
  "TaskUpdate",
42
+ "WebFetch",
43
+ "WebSearch",
42
44
  "Workflow",
43
45
  "Write"
44
46
  ]
@@ -84,6 +86,8 @@
84
86
  "TaskOutput",
85
87
  "TaskStop",
86
88
  "TaskUpdate",
89
+ "WebFetch",
90
+ "WebSearch",
87
91
  "Workflow",
88
92
  "Write"
89
93
  ],
@@ -39,6 +39,8 @@
39
39
  "TaskOutput",
40
40
  "TaskStop",
41
41
  "TaskUpdate",
42
+ "WebFetch",
43
+ "WebSearch",
42
44
  "Workflow",
43
45
  "Write"
44
46
  ],
@@ -117,7 +119,39 @@
117
119
  "subtype": "success",
118
120
  "is_error": false,
119
121
  "result": "first done",
120
- "permission_denials": []
122
+ "usage": {
123
+ "output_tokens_details": {
124
+ "thinking_tokens": 0
125
+ },
126
+ "input_tokens": "<input_tokens>",
127
+ "cache_creation_input_tokens": "<cache_creation_input_tokens>",
128
+ "cache_read_input_tokens": "<cache_read_input_tokens>",
129
+ "output_tokens": "<output_tokens>",
130
+ "server_tool_use": {
131
+ "web_search_requests": 0,
132
+ "web_fetch_requests": 0
133
+ },
134
+ "service_tier": "standard",
135
+ "cache_creation": {
136
+ "ephemeral_1h_input_tokens": 0,
137
+ "ephemeral_5m_input_tokens": 0
138
+ },
139
+ "inference_geo": "",
140
+ "iterations": [],
141
+ "speed": "standard"
142
+ },
143
+ "permission_denials": [],
144
+ "modelUsage": {
145
+ "winter-test/echo": {
146
+ "inputTokens": "<inputTokens>",
147
+ "outputTokens": "<outputTokens>",
148
+ "cacheReadInputTokens": "<cacheReadInputTokens>",
149
+ "cacheCreationInputTokens": "<cacheCreationInputTokens>",
150
+ "webSearchRequests": 0,
151
+ "costUSD": 0,
152
+ "canonicalModel": "winter-test/echo"
153
+ }
154
+ }
121
155
  }
122
156
  },
123
157
  {
@@ -194,13 +228,45 @@
194
228
  "subtype": "success",
195
229
  "is_error": false,
196
230
  "result": "second done",
231
+ "usage": {
232
+ "output_tokens_details": {
233
+ "thinking_tokens": 0
234
+ },
235
+ "input_tokens": "<input_tokens>",
236
+ "cache_creation_input_tokens": "<cache_creation_input_tokens>",
237
+ "cache_read_input_tokens": "<cache_read_input_tokens>",
238
+ "output_tokens": "<output_tokens>",
239
+ "server_tool_use": {
240
+ "web_search_requests": 0,
241
+ "web_fetch_requests": 0
242
+ },
243
+ "service_tier": "standard",
244
+ "cache_creation": {
245
+ "ephemeral_1h_input_tokens": 0,
246
+ "ephemeral_5m_input_tokens": 0
247
+ },
248
+ "inference_geo": "",
249
+ "iterations": [],
250
+ "speed": "standard"
251
+ },
197
252
  "permission_denials": [
198
253
  {
199
254
  "tool_name": "mystery_tool",
200
255
  "tool_use_id": "c2",
201
256
  "tool_input": {}
202
257
  }
203
- ]
258
+ ],
259
+ "modelUsage": {
260
+ "winter-test/echo": {
261
+ "inputTokens": "<inputTokens>",
262
+ "outputTokens": "<outputTokens>",
263
+ "cacheReadInputTokens": "<cacheReadInputTokens>",
264
+ "cacheCreationInputTokens": "<cacheCreationInputTokens>",
265
+ "webSearchRequests": 0,
266
+ "costUSD": 0,
267
+ "canonicalModel": "winter-test/echo"
268
+ }
269
+ }
204
270
  }
205
271
  }
206
272
  ]