agent-scenario-loop 0.1.2 → 0.1.4
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 +9 -9
- package/app/profile-session.ts +352 -12
- package/dist/core/agent-summary.d.ts +3 -2
- package/dist/core/agent-summary.js +44 -2
- package/dist/core/artifact-contract.d.ts +28 -8
- package/dist/core/artifact-contract.js +676 -26
- package/dist/core/comparison.d.ts +57 -3
- package/dist/core/comparison.js +113 -1
- package/dist/core/planner.d.ts +32 -1
- package/dist/core/planner.js +144 -0
- package/dist/core/run-index.d.ts +4 -0
- package/dist/core/run-index.js +55 -1
- package/dist/core/schema-validator.d.ts +2 -0
- package/dist/core/schema-validator.js +2 -0
- package/dist/runner/android-adb-driver.d.ts +7 -2
- package/dist/runner/android-adb-driver.js +7 -1
- package/dist/runner/android-adb.d.ts +40 -5
- package/dist/runner/android-adb.js +1046 -664
- package/dist/runner/compare-latest.d.ts +8 -4
- package/dist/runner/compare-latest.js +24 -5
- package/dist/runner/example-android-live.d.ts +10 -1
- package/dist/runner/example-android-live.js +55 -0
- package/dist/runner/example-ios-live.d.ts +10 -1
- package/dist/runner/example-ios-live.js +55 -0
- package/dist/runner/ios-simctl.d.ts +6 -0
- package/dist/runner/ios-simctl.js +7 -0
- package/dist/runner/live-comparison.d.ts +2 -2
- package/dist/runner/live-comparison.js +2 -1
- package/dist/runner/live-proof-summary.d.ts +5 -4
- package/dist/runner/live-proof-summary.js +12 -2
- package/dist/runner/live-proof.d.ts +3 -2
- package/dist/runner/live-proof.js +9 -2
- package/dist/runner/profile-android.d.ts +16 -1
- package/dist/runner/profile-android.js +364 -26
- package/dist/runner/profile-ios.d.ts +13 -2
- package/dist/runner/profile-ios.js +341 -19
- package/dist/runner/profile-mobile.d.ts +39 -3
- package/dist/runner/profile-mobile.js +1054 -42
- package/dist/runner/validate-project.js +3 -0
- package/dist/scripts/consumer-rehearsal.d.ts +119 -0
- package/dist/scripts/consumer-rehearsal.js +757 -0
- package/dist/scripts/downstream-local-package-gate.d.ts +2 -0
- package/dist/scripts/downstream-local-package-gate.js +264 -0
- package/dist/scripts/package-smoke.d.ts +96 -0
- package/dist/scripts/package-smoke.js +2282 -0
- package/dist/scripts/release-readiness.d.ts +2 -0
- package/dist/scripts/release-readiness.js +520 -0
- package/docs/adapters.md +7 -1
- package/docs/api.md +2 -2
- package/docs/architecture.md +90 -0
- package/docs/authoring.md +39 -3
- package/docs/concepts.md +3 -24
- package/docs/consumer-rehearsal.md +31 -1
- package/docs/contracts.md +45 -101
- package/docs/external-adapter-protocol.md +219 -0
- package/docs/live-proofs.md +86 -3
- package/docs/principles.md +9 -15
- package/examples/mobile-app/README.md +12 -0
- package/examples/mobile-app/runner-manifests/evidence-provider.json +3 -3
- package/examples/mobile-app/runner-manifests/primary-runner.json +1 -0
- package/examples/mobile-app/scripts/asl-capture-profiler-provider.mjs +25 -0
- package/examples/runners/README.md +4 -3
- package/examples/runners/adb-android.json +1 -0
- package/examples/runners/agent-device-android.json +1 -0
- package/examples/runners/agent-device-ios.json +1 -0
- package/examples/runners/argent-android.json +1 -0
- package/examples/runners/argent-ios.json +1 -0
- package/examples/runners/axe-accessibility-provider.json +2 -2
- package/examples/runners/script-accessibility-provider.json +2 -2
- package/examples/runners/script-memory-provider.json +2 -2
- package/examples/runners/script-network-provider.json +2 -2
- package/examples/runners/script-profiler-provider.json +2 -2
- package/examples/runners/xcodebuildmcp-ios.json +1 -0
- package/package.json +12 -3
- package/schemas/causal-run.schema.json +85 -2
- package/schemas/comparison.schema.json +130 -2
- package/schemas/external-adapter-message.schema.json +693 -0
- package/schemas/health.schema.json +72 -0
- package/schemas/live-proof-set.schema.json +1 -1
- package/schemas/live-proof.schema.json +14 -6
- package/schemas/manifest.schema.json +515 -4
- package/schemas/profiler.schema.json +243 -0
- package/schemas/runner-capabilities.schema.json +28 -2
- package/schemas/scenario.schema.json +34 -2
- package/templates/evidence-provider.json +3 -3
- package/templates/primary-runner.json +1 -0
- package/templates/scripts/asl-capture-profiler-provider.mjs +20 -0
|
@@ -33,7 +33,7 @@
|
|
|
33
33
|
},
|
|
34
34
|
"comparisonStatus": {
|
|
35
35
|
"type": "string",
|
|
36
|
-
"enum": ["better", "worse", "unchanged", "mixed", "inconclusive"]
|
|
36
|
+
"enum": ["better", "worse", "unchanged", "mixed", "inconclusive", "low_confidence"]
|
|
37
37
|
},
|
|
38
38
|
"healthStatus": {
|
|
39
39
|
"type": "string",
|
|
@@ -46,6 +46,9 @@
|
|
|
46
46
|
"comparisonBasis": {
|
|
47
47
|
"$ref": "#/$defs/comparisonBasis"
|
|
48
48
|
},
|
|
49
|
+
"measurementPolicy": {
|
|
50
|
+
"$ref": "#/$defs/measurementPolicy"
|
|
51
|
+
},
|
|
49
52
|
"metricComparisons": {
|
|
50
53
|
"type": "array",
|
|
51
54
|
"items": {
|
|
@@ -135,6 +138,10 @@
|
|
|
135
138
|
"type": "string",
|
|
136
139
|
"pattern": "^[a-f0-9]{64}$"
|
|
137
140
|
},
|
|
141
|
+
"cohortHash": {
|
|
142
|
+
"type": "string",
|
|
143
|
+
"pattern": "^[a-f0-9]{64}$"
|
|
144
|
+
},
|
|
138
145
|
"selectedRunDir": {
|
|
139
146
|
"type": "string"
|
|
140
147
|
},
|
|
@@ -159,6 +166,10 @@
|
|
|
159
166
|
"trustedScenarioContractCandidates": {
|
|
160
167
|
"type": "integer",
|
|
161
168
|
"minimum": 0
|
|
169
|
+
},
|
|
170
|
+
"trustedCohortCandidates": {
|
|
171
|
+
"type": "integer",
|
|
172
|
+
"minimum": 0
|
|
162
173
|
}
|
|
163
174
|
}
|
|
164
175
|
},
|
|
@@ -185,12 +196,129 @@
|
|
|
185
196
|
},
|
|
186
197
|
"status": {
|
|
187
198
|
"type": "string",
|
|
188
|
-
"enum": ["better", "worse", "unchanged", "inconclusive"]
|
|
199
|
+
"enum": ["better", "worse", "unchanged", "inconclusive", "low_confidence"]
|
|
189
200
|
},
|
|
190
201
|
"notes": {
|
|
191
202
|
"type": "string"
|
|
192
203
|
}
|
|
193
204
|
}
|
|
205
|
+
},
|
|
206
|
+
"measurementPolicy": {
|
|
207
|
+
"type": "object",
|
|
208
|
+
"additionalProperties": false,
|
|
209
|
+
"required": ["baselineSelection", "samples", "tolerance", "confidence"],
|
|
210
|
+
"properties": {
|
|
211
|
+
"baselineSelection": {
|
|
212
|
+
"type": "object",
|
|
213
|
+
"additionalProperties": false,
|
|
214
|
+
"required": ["mode", "poisoningProtection"],
|
|
215
|
+
"properties": {
|
|
216
|
+
"mode": {
|
|
217
|
+
"type": "string",
|
|
218
|
+
"enum": ["explicit", "latestTrustedPrior"]
|
|
219
|
+
},
|
|
220
|
+
"poisoningProtection": {
|
|
221
|
+
"type": "object",
|
|
222
|
+
"additionalProperties": false,
|
|
223
|
+
"required": ["requirePassedHealth", "requirePassedVerdict", "requireMatchingScenarioId"],
|
|
224
|
+
"properties": {
|
|
225
|
+
"requirePassedHealth": {
|
|
226
|
+
"type": "boolean"
|
|
227
|
+
},
|
|
228
|
+
"requirePassedVerdict": {
|
|
229
|
+
"type": "boolean"
|
|
230
|
+
},
|
|
231
|
+
"requireMatchingScenarioId": {
|
|
232
|
+
"type": "boolean"
|
|
233
|
+
},
|
|
234
|
+
"comparisonLane": {
|
|
235
|
+
"type": "string"
|
|
236
|
+
},
|
|
237
|
+
"scenarioHash": {
|
|
238
|
+
"type": "string",
|
|
239
|
+
"pattern": "^[a-f0-9]{64}$"
|
|
240
|
+
},
|
|
241
|
+
"cohortHash": {
|
|
242
|
+
"type": "string",
|
|
243
|
+
"pattern": "^[a-f0-9]{64}$"
|
|
244
|
+
}
|
|
245
|
+
}
|
|
246
|
+
}
|
|
247
|
+
}
|
|
248
|
+
},
|
|
249
|
+
"samples": {
|
|
250
|
+
"type": "object",
|
|
251
|
+
"additionalProperties": false,
|
|
252
|
+
"required": ["baseline", "current"],
|
|
253
|
+
"properties": {
|
|
254
|
+
"baseline": {
|
|
255
|
+
"$ref": "#/$defs/samplePolicy"
|
|
256
|
+
},
|
|
257
|
+
"current": {
|
|
258
|
+
"$ref": "#/$defs/samplePolicy"
|
|
259
|
+
}
|
|
260
|
+
}
|
|
261
|
+
},
|
|
262
|
+
"tolerance": {
|
|
263
|
+
"type": "object",
|
|
264
|
+
"additionalProperties": false,
|
|
265
|
+
"required": ["timing"],
|
|
266
|
+
"properties": {
|
|
267
|
+
"timing": {
|
|
268
|
+
"type": "object",
|
|
269
|
+
"additionalProperties": false,
|
|
270
|
+
"required": ["absoluteMs", "relative"],
|
|
271
|
+
"properties": {
|
|
272
|
+
"absoluteMs": {
|
|
273
|
+
"type": "number",
|
|
274
|
+
"minimum": 0
|
|
275
|
+
},
|
|
276
|
+
"relative": {
|
|
277
|
+
"type": "number",
|
|
278
|
+
"minimum": 0
|
|
279
|
+
}
|
|
280
|
+
}
|
|
281
|
+
}
|
|
282
|
+
}
|
|
283
|
+
},
|
|
284
|
+
"confidence": {
|
|
285
|
+
"type": "object",
|
|
286
|
+
"additionalProperties": false,
|
|
287
|
+
"required": ["level", "minValidSamples"],
|
|
288
|
+
"properties": {
|
|
289
|
+
"level": {
|
|
290
|
+
"type": "string",
|
|
291
|
+
"enum": ["single_run", "multi_sample", "insufficient", "low_confidence"]
|
|
292
|
+
},
|
|
293
|
+
"minValidSamples": {
|
|
294
|
+
"type": "integer",
|
|
295
|
+
"minimum": 1
|
|
296
|
+
},
|
|
297
|
+
"reason": {
|
|
298
|
+
"type": "string"
|
|
299
|
+
}
|
|
300
|
+
}
|
|
301
|
+
}
|
|
302
|
+
}
|
|
303
|
+
},
|
|
304
|
+
"samplePolicy": {
|
|
305
|
+
"type": "object",
|
|
306
|
+
"additionalProperties": false,
|
|
307
|
+
"required": ["validSamples", "warmupSamples", "outliersExcluded"],
|
|
308
|
+
"properties": {
|
|
309
|
+
"validSamples": {
|
|
310
|
+
"type": "integer",
|
|
311
|
+
"minimum": 0
|
|
312
|
+
},
|
|
313
|
+
"warmupSamples": {
|
|
314
|
+
"type": "integer",
|
|
315
|
+
"minimum": 0
|
|
316
|
+
},
|
|
317
|
+
"outliersExcluded": {
|
|
318
|
+
"type": "integer",
|
|
319
|
+
"minimum": 0
|
|
320
|
+
}
|
|
321
|
+
}
|
|
194
322
|
}
|
|
195
323
|
}
|
|
196
324
|
}
|