@danceiny/gotry 0.0.1-rc.21 → 0.0.1-rc.24

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 (327) hide show
  1. package/README.md +102 -194
  2. package/README.zh-CN.md +115 -210
  3. package/bin/gotry-backend.js +53 -0
  4. package/bin/gotry-bootstrap.js +466 -35
  5. package/bin/gotry-inner.js +255 -36
  6. package/bin/gotry-process-liveness.d.ts +27 -0
  7. package/bin/gotry-process-liveness.js +97 -0
  8. package/bin/gotry-runtime-resolution.d.ts +1 -1
  9. package/bin/gotry-runtime-resolution.js +2 -2
  10. package/client/client.js +174 -0
  11. package/cordis.gotry-patch.yml +70 -93
  12. package/dist/capabilities/agent-reach-deep.js +45 -122
  13. package/dist/capabilities/agent-reach.js +63 -148
  14. package/dist/capabilities/anything.js +89 -75
  15. package/dist/capabilities/artifacts.js +123 -104
  16. package/dist/capabilities/channel-health.js +65 -45
  17. package/dist/capabilities/channel-registry.js +108 -87
  18. package/dist/capabilities/doctor.js +357 -235
  19. package/dist/capabilities/effect.js +223 -309
  20. package/dist/capabilities/fact-log.js +28 -14
  21. package/dist/capabilities/flyai.js +245 -156
  22. package/dist/capabilities/ground-transfer.js +509 -0
  23. package/dist/capabilities/hbcli.js +144 -148
  24. package/dist/capabilities/hotelbyte-transaction.js +194 -0
  25. package/dist/capabilities/incident-log.js +131 -61
  26. package/dist/capabilities/model-override.js +30 -10
  27. package/dist/capabilities/opensky.js +54 -43
  28. package/dist/capabilities/resilience.js +50 -32
  29. package/dist/capabilities/session/action-cache.js +50 -44
  30. package/dist/capabilities/session/adapters/ctrip-flight.js +119 -62
  31. package/dist/capabilities/session/adapters/ctrip-hotel.js +125 -110
  32. package/dist/capabilities/session/adapters/dida-portal.js +206 -0
  33. package/dist/capabilities/session/adapters/meituan-local.js +35 -54
  34. package/dist/capabilities/session/adapters/rail-12306.js +169 -112
  35. package/dist/capabilities/session/benchmark.js +85 -149
  36. package/dist/capabilities/session/extension-bridge.js +320 -259
  37. package/dist/capabilities/session/extension-channel.js +57 -76
  38. package/dist/capabilities/session/extension-distribution.js +115 -119
  39. package/dist/capabilities/session/extract.js +31 -21
  40. package/dist/capabilities/session/golden-score.js +55 -33
  41. package/dist/capabilities/session/health-watch.js +146 -154
  42. package/dist/capabilities/session/read-guard.js +55 -47
  43. package/dist/capabilities/session/static-flight-golden.js +49 -36
  44. package/dist/capabilities/session/transport.js +54 -61
  45. package/dist/capabilities/session/wizard.js +63 -93
  46. package/dist/capabilities/session-consent.js +143 -47
  47. package/dist/capabilities/session-login.js +95 -126
  48. package/dist/capabilities/session-search.js +391 -253
  49. package/dist/capabilities/sponsor-plugin.js +341 -0
  50. package/dist/capabilities/visa-policy.js +87 -73
  51. package/dist/capabilities/weather.js +163 -235
  52. package/dist/scripts/action-cache-tests.js +24 -59
  53. package/dist/scripts/agent-planning-turn-deadline-e2e.js +91 -142
  54. package/dist/scripts/agent-planning-turn-deadline-tests.js +80 -176
  55. package/dist/scripts/agent-reach-deep-tests.js +30 -40
  56. package/dist/scripts/agent-reach-tests.js +26 -18
  57. package/dist/scripts/agent-reach-wrapper-tests.js +46 -50
  58. package/dist/scripts/anything-tests.js +58 -62
  59. package/dist/scripts/artifact-client-contract-tests.js +69 -0
  60. package/dist/scripts/artifacts-capability-tests.js +235 -0
  61. package/dist/scripts/async-collect.js +26 -15
  62. package/dist/scripts/benchmark-environment-bridge-e2e.js +287 -684
  63. package/dist/scripts/benchmark-environment-bridge-tests.js +818 -3123
  64. package/dist/scripts/booking-copilot-availability-ledger-binding-tests.js +66 -279
  65. package/dist/scripts/booking-copilot-availability-policy-tests.js +153 -1257
  66. package/dist/scripts/booking-copilot-bin-proof-tests.js +22 -45
  67. package/dist/scripts/booking-copilot-crossrepo-fixture-server.js +64 -76
  68. package/dist/scripts/booking-copilot-dsh-core-proof-tests.js +69 -199
  69. package/dist/scripts/booking-copilot-dsh-planner-proof-tests.js +393 -759
  70. package/dist/scripts/booking-copilot-dsh-plugin-proof-tests.js +33 -75
  71. package/dist/scripts/booking-copilot-event-sequence-concurrency-proof-tests.js +60 -110
  72. package/dist/scripts/booking-copilot-gap-code-contract-proof-tests.js +28 -66
  73. package/dist/scripts/booking-copilot-operation-ledger-concurrency-proof-tests.js +72 -271
  74. package/dist/scripts/booking-copilot-receipt-ledger-concurrency-proof-tests.js +73 -275
  75. package/dist/scripts/booking-copilot-runtime-proof-tests.js +784 -3398
  76. package/dist/scripts/booking-copilot-server-proof-tests.js +63 -168
  77. package/dist/scripts/booking-copilot-startup-proof-tests.js +38 -124
  78. package/dist/scripts/booking-executor-tests.js +80 -0
  79. package/dist/scripts/booking-recovery-chain-tests.js +182 -0
  80. package/dist/scripts/booking-saga-tests.js +61 -123
  81. package/dist/scripts/booking-surface-contract-proof-tests.js +152 -1167
  82. package/dist/scripts/bootstrap-tests.js +1383 -128
  83. package/dist/scripts/build-changelog.js +89 -130
  84. package/dist/scripts/build-metrics-report.js +135 -143
  85. package/dist/scripts/changelog-tests.js +35 -82
  86. package/dist/scripts/channel-probe-tests.js +44 -116
  87. package/dist/scripts/channel-probe.js +84 -167
  88. package/dist/scripts/channel-registry-tests.js +97 -185
  89. package/dist/scripts/companion-tests.js +25 -70
  90. package/dist/scripts/dida-cookie-probe.js +87 -0
  91. package/dist/scripts/dida-sw-probe.js +114 -0
  92. package/dist/scripts/diff-test.js +17 -12
  93. package/dist/scripts/doctor-tests.js +428 -120
  94. package/dist/scripts/dsh-artifact-e2e.js +150 -0
  95. package/dist/scripts/dsh-artifact-web-e2e.js +443 -0
  96. package/dist/scripts/dsh-http-proxy-sse-proof.js +90 -0
  97. package/dist/scripts/dsh-runtime-closure-tests.js +110 -153
  98. package/dist/scripts/dsh-runtime-closure.js +75 -63
  99. package/dist/scripts/dsh-session-v3-migration-proof.js +106 -0
  100. package/dist/scripts/dsh-subprocess-local-proof.js +149 -0
  101. package/dist/scripts/dsh-target-closure-proof.js +178 -0
  102. package/dist/scripts/effect-tests.js +165 -552
  103. package/dist/scripts/engine-run.js +1 -3
  104. package/dist/scripts/engine-tests.js +16 -10
  105. package/dist/scripts/evaluation-cadence-tests.js +69 -242
  106. package/dist/scripts/evaluation-contract-tests.js +193 -499
  107. package/dist/scripts/extension-distribution-cli.js +19 -15
  108. package/dist/scripts/extension-distribution-tests.js +98 -211
  109. package/dist/scripts/extension-tests.js +366 -389
  110. package/dist/scripts/fact-gate-tests.js +725 -263
  111. package/dist/scripts/fixtures/extension-bridge-unref-child.mjs +21 -0
  112. package/dist/scripts/flight-hotel-anchor-363-registered-e2e.js +169 -0
  113. package/dist/scripts/flight-malformed-tests.js +159 -0
  114. package/dist/scripts/flyai-tests.js +325 -68
  115. package/dist/scripts/g5-guard-tests.js +131 -0
  116. package/dist/scripts/g5-guard.js +189 -0
  117. package/dist/scripts/gen-lunar-anchors.js +106 -0
  118. package/dist/scripts/gotry-backend-kernel-tests.js +79 -0
  119. package/dist/scripts/ground-transfer-tests.js +956 -0
  120. package/dist/scripts/hbcli-e2e-tests.js +71 -90
  121. package/dist/scripts/hbcli-live-optin-tests.js +96 -0
  122. package/dist/scripts/hbcli-release-contract-tests.js +122 -0
  123. package/dist/scripts/hbcli-tests.js +41 -115
  124. package/dist/scripts/health-watch-cli.js +42 -28
  125. package/dist/scripts/hotel-date-gate-tests.js +496 -0
  126. package/dist/scripts/hotelbyte-reconcile-tests.js +141 -0
  127. package/dist/scripts/hotelbyte-spawn-e2e-tests.js +373 -0
  128. package/dist/scripts/i18n-tests.js +16 -9
  129. package/dist/scripts/incident-tests.js +281 -87
  130. package/dist/scripts/issue-194-job-id-guard-tests.js +106 -0
  131. package/dist/scripts/issue-233-cancel-refund-commission-tests.js +392 -0
  132. package/dist/scripts/issue-271-liveness-tests.js +547 -0
  133. package/dist/scripts/issue-289-model-retry-real-tests.js +296 -0
  134. package/dist/scripts/issue-289-model-retry-tests.js +441 -0
  135. package/dist/scripts/issue-289-web-retry-e2e.js +630 -0
  136. package/dist/scripts/issue-338-home-city-e2e.js +577 -0
  137. package/dist/scripts/issue343-real-entry-e2e.js +160 -0
  138. package/dist/scripts/journey-tests.js +22 -27
  139. package/dist/scripts/kernel-manifest-evidence.js +109 -0
  140. package/dist/scripts/kernel-manifest-gate.js +126 -0
  141. package/dist/scripts/kernel-manifest-tests.js +212 -0
  142. package/dist/scripts/kernel-manifest-trace-entry.js +7 -0
  143. package/dist/scripts/kernel-manifest-trace-hook.mjs +28 -0
  144. package/dist/scripts/kernel-manifest.js +369 -0
  145. package/dist/scripts/ledger-repair-apply-tests.js +316 -0
  146. package/dist/scripts/ledger-repair-plan-tests.js +375 -0
  147. package/dist/scripts/ledger-tests.js +325 -340
  148. package/dist/scripts/ledger-workflow-crash.js +10 -20
  149. package/dist/scripts/map-tools-vendor-package-proof.js +206 -134
  150. package/dist/scripts/memory-capture-tests.js +242 -61
  151. package/dist/scripts/memory-decay-tests.js +18 -52
  152. package/dist/scripts/memory-lifecycle-tests.js +657 -0
  153. package/dist/scripts/memory-lifecycle.js +196 -0
  154. package/dist/scripts/memory-metrics.js +24 -12
  155. package/dist/scripts/memory-value-report.js +474 -222
  156. package/dist/scripts/memory-value-tests.js +328 -0
  157. package/dist/scripts/metrics-report-tests.js +62 -199
  158. package/dist/scripts/model-override-e2e.js +66 -105
  159. package/dist/scripts/nightly-evidence-tests.js +64 -89
  160. package/dist/scripts/nightly-evidence.js +108 -111
  161. package/dist/scripts/nudge-digest.js +39 -28
  162. package/dist/scripts/onboarding-tests.js +63 -88
  163. package/dist/scripts/opensky-check.js +18 -13
  164. package/dist/scripts/opensky-tests.js +28 -28
  165. package/dist/scripts/persona-surface-guard-tests.js +37 -12
  166. package/dist/scripts/pnpm-dsh-closure-proof.js +2 -5
  167. package/dist/scripts/policy-anchor-359-registered-e2e.js +214 -0
  168. package/dist/scripts/price-drift-tests.js +126 -227
  169. package/dist/scripts/price-drift-watch.js +209 -253
  170. package/dist/scripts/probe-poi-tests.js +52 -45
  171. package/dist/scripts/product-metrics.js +187 -273
  172. package/dist/scripts/publish-preverify.js +47 -41
  173. package/dist/scripts/realtime-pricing-tests.js +37 -76
  174. package/dist/scripts/replay-async.js +20 -18
  175. package/dist/scripts/replay-real.js +16 -18
  176. package/dist/scripts/replay.js +52 -82
  177. package/dist/scripts/session-attach-diagnose.js +16 -12
  178. package/dist/scripts/session-attach-poc.js +34 -37
  179. package/dist/scripts/session-benchmark.js +66 -147
  180. package/dist/scripts/session-dida-live-e2e.js +151 -0
  181. package/dist/scripts/session-extract-tests.js +14 -35
  182. package/dist/scripts/session-login.js +14 -13
  183. package/dist/scripts/session-tests.js +545 -583
  184. package/dist/scripts/sf-live-benchmark.js +92 -110
  185. package/dist/scripts/sf-live-cli-tests.js +2 -9
  186. package/dist/scripts/sf-soft-score-tests.js +19 -60
  187. package/dist/scripts/sf-summary-tests.js +149 -0
  188. package/dist/scripts/sf-summary.js +466 -84
  189. package/dist/scripts/skeleton-check.js +16 -14
  190. package/dist/scripts/skeleton-integration-test.js +11 -10
  191. package/dist/scripts/skills-contract-tests.js +51 -46
  192. package/dist/scripts/smoke-session-gate-tests.js +12 -20
  193. package/dist/scripts/smoke.js +541 -422
  194. package/dist/scripts/sponsor-reuse-tests.js +262 -0
  195. package/dist/scripts/state-cli-tests.js +226 -101
  196. package/dist/scripts/state-cli.js +549 -212
  197. package/dist/scripts/static-golden-tests.js +46 -180
  198. package/dist/scripts/time-eval-tests.js +210 -192
  199. package/dist/scripts/travel-timeline-tests.js +29 -93
  200. package/dist/scripts/turn-handoff-collect-tests.js +46 -93
  201. package/dist/scripts/turn-handoff-collect.js +71 -99
  202. package/dist/scripts/turn-policy-tests.js +28 -29
  203. package/dist/scripts/typed-contract-canary.js +77 -162
  204. package/dist/scripts/tz-resolver-sanity.js +50 -0
  205. package/dist/scripts/tz-resolver-tests.js +584 -0
  206. package/dist/scripts/unified-tests.js +23 -19
  207. package/dist/scripts/visa-policy-tests.js +31 -44
  208. package/dist/scripts/weather-tests.js +121 -543
  209. package/dist/scripts/wish-channel-gate-tests.js +29 -86
  210. package/dist/scripts/write-gate-tests.js +522 -0
  211. package/dist/scripts/z3-lifecycle-fault-tests.js +188 -0
  212. package/dist/scripts/z3-lifecycle-tests.js +170 -0
  213. package/dist/scripts/z3-race-repeat-tests.js +39 -0
  214. package/dist/scripts/z3-race-tests.js +18 -12
  215. package/dist/src/artifact-gate.js +652 -221
  216. package/dist/src/backend/kernel.js +91 -0
  217. package/dist/src/backend/modules/booking-copilot.js +55 -0
  218. package/dist/src/backend/modules/booking-executor.js +124 -0
  219. package/dist/src/backend/modules/session-search.js +194 -0
  220. package/dist/src/benchmark-agent-conformance.js +296 -262
  221. package/dist/src/benchmark-environment-bridge.js +298 -413
  222. package/dist/src/benchmark-headless-child-diagnostics.js +93 -100
  223. package/dist/src/benchmark-tool-isolation.js +94 -67
  224. package/dist/src/bookable-facts.js +299 -174
  225. package/dist/src/booking-saga.js +64 -120
  226. package/dist/src/booking-surface/availability-policy.js +443 -576
  227. package/dist/src/booking-surface/cancel-refund-commission.js +379 -0
  228. package/dist/src/booking-surface/contracts.js +24 -80
  229. package/dist/src/booking-surface/dsh-planner.js +510 -281
  230. package/dist/src/booking-surface/dsh-plugin.js +17 -1
  231. package/dist/src/booking-surface/error-codes.js +82 -10
  232. package/dist/src/booking-surface/index.js +0 -3
  233. package/dist/src/booking-surface/profile.js +10 -54
  234. package/dist/src/booking-surface/recovery-chain.js +367 -0
  235. package/dist/src/booking-surface/runtime.js +765 -891
  236. package/dist/src/booking-surface/server.js +200 -251
  237. package/dist/src/booking-surface/startup.js +58 -54
  238. package/dist/src/booking-surface/validation.js +150 -218
  239. package/dist/src/bridge.js +20 -13
  240. package/dist/src/companions.js +48 -74
  241. package/dist/src/contracts.js +21 -43
  242. package/dist/src/dsh-llm.js +82 -120
  243. package/dist/src/engine.js +253 -239
  244. package/dist/src/evaluation-cadence.js +72 -209
  245. package/dist/src/evaluation-contracts.js +220 -843
  246. package/dist/src/flight-pack-adapter.js +54 -0
  247. package/dist/src/flight-pack-contract.js +2 -0
  248. package/dist/src/gotry-backend.js +70 -0
  249. package/dist/src/hotel-date-gate.js +118 -0
  250. package/dist/src/i18n.js +18 -7
  251. package/dist/src/index.js +1425 -1629
  252. package/dist/src/journey.js +132 -81
  253. package/dist/src/ledger-repair-apply.js +538 -0
  254. package/dist/src/ledger-repair-plan.js +463 -0
  255. package/dist/src/loop.js +257 -166
  256. package/dist/src/memory-capture.js +180 -32
  257. package/dist/src/memory-decay.js +30 -14
  258. package/dist/src/memory-lifecycle.js +1310 -0
  259. package/dist/src/memory-utility.js +27 -40
  260. package/dist/src/mock-llm.js +36 -61
  261. package/dist/src/model.js +81 -36
  262. package/dist/src/realtime-pricing.js +63 -72
  263. package/dist/src/slot-spec.js +84 -106
  264. package/dist/src/state-ledger.js +310 -471
  265. package/dist/src/subagent-job-id-guard.js +58 -0
  266. package/dist/src/time-anchor.js +231 -33
  267. package/dist/src/tool-packet.js +20 -8
  268. package/dist/src/travel-slots.js +58 -35
  269. package/dist/src/travel-timeline.js +44 -63
  270. package/dist/src/turn-deadline.js +121 -127
  271. package/dist/src/turn-policy.js +61 -89
  272. package/dist/src/tz-resolver.js +143 -0
  273. package/dist/src/unified.js +504 -381
  274. package/dist/src/wish-pool.js +39 -14
  275. package/dist/src/write-gate.js +495 -0
  276. package/dist/src/z3-shared.js +273 -7
  277. package/extension/README.md +4 -3
  278. package/extension/background.js +125 -14
  279. package/extension/content-bridge.js +23 -1
  280. package/extension/content-main.js +15 -4
  281. package/extension/manifest.json +16 -8
  282. package/package.json +251 -220
  283. package/ts/capabilities/agent-reach.ts +4 -4
  284. package/ts/capabilities/anything.ts +1 -1
  285. package/ts/capabilities/artifacts.ts +46 -9
  286. package/ts/capabilities/flyai.ts +156 -37
  287. package/ts/capabilities/hbcli.ts +1 -1
  288. package/ts/capabilities/incident-log.ts +88 -59
  289. package/ts/capabilities/session/adapters/ctrip-flight.ts +99 -36
  290. package/ts/capabilities/session/adapters/dida-portal.ts +250 -0
  291. package/ts/capabilities/session/adapters/rail-12306.ts +123 -24
  292. package/ts/capabilities/session/extension-bridge.ts +226 -101
  293. package/ts/capabilities/session/extension-channel.ts +22 -9
  294. package/ts/capabilities/session/wizard.ts +2 -2
  295. package/ts/capabilities/session-consent.ts +98 -14
  296. package/ts/capabilities/session-login.ts +1 -0
  297. package/ts/capabilities/session-search.ts +315 -31
  298. package/ts/dsh-runtime/vendor/README.md +8 -4
  299. package/ts/dsh-runtime/vendor/dsh-map-tools/README.en.md +7 -1
  300. package/ts/dsh-runtime/vendor/dsh-map-tools/README.md +5 -3
  301. package/ts/dsh-runtime/vendor/dsh-map-tools/lib/settings-ns.js +1 -1
  302. package/ts/dsh-runtime/vendor/dsh-map-tools/lib/types/settings-ns.d.ts +1 -1
  303. package/ts/dsh-runtime/vendor/dsh-map-tools/package.json +6 -6
  304. package/ts/package.json +236 -16
  305. package/ts/scripts/map-tools-vendor-package-proof.ts +152 -31
  306. package/ts/scripts/state-cli.ts +418 -51
  307. package/ts/src/artifact-gate.ts +561 -15
  308. package/ts/src/benchmark-environment-bridge.ts +37 -20
  309. package/ts/src/bookable-facts.ts +183 -7
  310. package/ts/src/booking-surface/cancel-refund-commission.ts +488 -0
  311. package/ts/src/booking-surface/dsh-planner.ts +240 -32
  312. package/ts/src/booking-surface/dsh-plugin.js +17 -1
  313. package/ts/src/booking-surface/error-codes.ts +75 -0
  314. package/ts/src/booking-surface/recovery-chain.ts +409 -0
  315. package/ts/src/booking-surface/server.ts +84 -51
  316. package/ts/src/booking-surface/validation.ts +2 -0
  317. package/ts/src/contracts.ts +12 -2
  318. package/ts/src/dsh-llm.ts +4 -8
  319. package/ts/src/index.ts +609 -90
  320. package/ts/src/loop.ts +116 -7
  321. package/ts/src/memory-capture.ts +227 -3
  322. package/ts/src/mock-llm.ts +4 -8
  323. package/ts/src/model.ts +88 -2
  324. package/ts/src/state-ledger.ts +47 -29
  325. package/ts/src/subagent-job-id-guard.ts +72 -0
  326. package/ts/src/time-anchor.ts +217 -13
  327. package/ts/src/unified.ts +316 -54
@@ -0,0 +1,149 @@
1
+ import assert from 'node:assert/strict';
2
+ import { mkdtempSync, mkdirSync, readFileSync, rmSync, writeFileSync } from 'node:fs';
3
+ import { spawnSync } from 'node:child_process';
4
+ import { tmpdir } from 'node:os';
5
+ import { dirname, join, resolve } from 'node:path';
6
+ import { fileURLToPath } from 'node:url';
7
+ import { EXPECTED_QUERY_IDS } from './sf-summary.js';
8
+ const tsRoot = resolve(dirname(fileURLToPath(import.meta.url)), '..');
9
+ const cliPath = join(tsRoot, 'scripts', 'sf-summary.ts');
10
+ const tsxPath = join(tsRoot, 'node_modules', '.bin', 'tsx');
11
+ function record(queryId, batch, startedAt, source, verdict = 'hit') {
12
+ const isStatic = source === 'static';
13
+ const effective = source === 'manual' ? 'manual-golden' : isStatic ? 'static-openflights+manual-band' : 'vendor-x';
14
+ return {
15
+ query_id: queryId,
16
+ expected: { from: 'SYN', to: 'DST', date: '2026-10-01', kind: 'flight' },
17
+ requested_source: isStatic ? 'static' : source === 'manual' ? 'manual' : 'vendor-x',
18
+ effective_source: effective,
19
+ fallback_reason: isStatic && verdict === 'error' ? 'synthetic static route error' : null,
20
+ official_source: effective,
21
+ official_provenance: { source: 'synthetic fixture', batch },
22
+ manifest_sha256: `sha256:${batch}`,
23
+ batch_id: batch.startsWith('explicit-') ? batch : undefined,
24
+ started_at: startedAt,
25
+ official: { source: effective, verdict, latency_ms: 1 },
26
+ session: { verdict, price: verdict === 'hit' ? 100 : 0, route_segments: [], fetched_at: startedAt },
27
+ doubleSource: { state: 'comparable', mismatches: [] },
28
+ softScore: null,
29
+ sessionLatencyMs: 100,
30
+ sessionError: verdict === 'error' ? 'synthetic error' : null,
31
+ };
32
+ }
33
+ function writeJson(root, queryId, filename, value) {
34
+ const directory = join(root, queryId);
35
+ mkdirSync(directory, { recursive: true });
36
+ writeFileSync(join(directory, filename), JSON.stringify(value, null, 2));
37
+ }
38
+ function writeRaw(root, queryId, filename, value) {
39
+ const directory = join(root, queryId);
40
+ mkdirSync(directory, { recursive: true });
41
+ writeFileSync(join(directory, filename), value);
42
+ }
43
+ function writeBatch(root, filename, batch, source = 'manual', verdict = 'hit') {
44
+ EXPECTED_QUERY_IDS.forEach((queryId, index) => {
45
+ const second = (index + 1).toString().padStart(2, '0');
46
+ writeJson(root, queryId, filename, record(queryId, batch, `2026-09-09T10:00:${second}.000Z`, source, verdict));
47
+ });
48
+ }
49
+ function runCli(root) {
50
+ mkdirSync(join(root, 'home'), { recursive: true });
51
+ const result = spawnSync(process.execPath, [tsxPath, cliPath, '--evidence-root', root], {
52
+ cwd: tsRoot,
53
+ encoding: 'utf8',
54
+ env: {
55
+ ...process.env,
56
+ HOME: join(root, 'home'),
57
+ GOTRY_SESSION_LIVE: '0',
58
+ GOTRY_HBCLI_LIVE: '0',
59
+ GOTRY_HOTELBYTE_SKILLS_LIVE: '0',
60
+ },
61
+ });
62
+ const output = `${result.stdout ?? ''}${result.stderr ?? ''}`;
63
+ const pathMatch = /summary: (.+)/.exec(output);
64
+ assert.ok(pathMatch, `CLI must print its output path\n${output}`);
65
+ const summary = JSON.parse(readFileSync(pathMatch[1].trim(), 'utf8'));
66
+ return { exit: result.status ?? -1, output, summary };
67
+ }
68
+ function freshRoot() {
69
+ return mkdtempSync(join(tmpdir(), 'gotry-sf-summary-e2e-'));
70
+ }
71
+ const roots = [];
72
+ try {
73
+ // One canonical filename is one legacy batch, even though each producer
74
+ // record has a different per-query started_at.
75
+ const coherentRoot = freshRoot();
76
+ roots.push(coherentRoot);
77
+ writeBatch(coherentRoot, '2026-09-09T10-00-00-000Z.json', 'manual-batch');
78
+ const coherent = runCli(coherentRoot);
79
+ assert.equal(coherent.exit, 0, coherent.output);
80
+ assert.equal(coherent.summary.status, 'ok');
81
+ assert.equal(coherent.summary.total, 8);
82
+ assert.equal(coherent.summary.selected_batch.batch_id, '2026-09-09T10-00-00-000Z');
83
+ assert.equal(coherent.summary.selected_batch.identity_source, 'canonical_filename');
84
+ assert.equal(coherent.summary.started_at, '2026-09-09T10:00:00.000Z');
85
+ assert.notEqual(coherent.summary.generated_at, coherent.summary.started_at);
86
+ assert.equal(new Set(coherent.summary.records.map((item) => item.started_at)).size, 8);
87
+ // A newer static/error batch wins over an older manual hit and remains in
88
+ // the static bucket. An unsupported source is visible as unknown, never
89
+ // silently reclassified as FlyAI.
90
+ const sourceRoot = freshRoot();
91
+ roots.push(sourceRoot);
92
+ writeJson(sourceRoot, 'sf-01', '2026-01-01T10-00-00-000Z.json', record('sf-01', 'old-manual', '2026-01-01T10:00:01.000Z', 'manual', 'hit'));
93
+ writeBatch(sourceRoot, '2026-09-10T10-00-00-000Z.json', 'new-static', 'static', 'error');
94
+ writeJson(sourceRoot, 'sf-03', '2026-09-10T10-00-00-000Z.json', { ...record('sf-03', 'new-static', '2026-09-09T10:00:03.000Z', 'unknown', 'error'), requested_source: 'vendor-x', effective_source: 'vendor-x', official_source: 'vendor-x' });
95
+ const source = runCli(sourceRoot);
96
+ assert.equal(source.exit, 0, source.output);
97
+ const sourceQ1 = source.summary.records.find((item) => item.query_id === 'sf-01');
98
+ assert.equal(sourceQ1.effective_source, 'static-openflights+manual-band');
99
+ assert.equal(sourceQ1.session_verdict, 'error');
100
+ assert.deepEqual(source.summary.sources.manual_golden_query_ids, []);
101
+ assert.ok(source.summary.sources.static_query_ids.includes('sf-01'));
102
+ assert.ok(source.summary.sources.unknown_query_ids.includes('sf-03'));
103
+ assert.deepEqual(source.summary.sources.flyai_query_ids, []);
104
+ assert.equal(sourceQ1.requested_source, 'static');
105
+ assert.equal(sourceQ1.fallback_reason, 'synthetic static route error');
106
+ assert.deepEqual(sourceQ1.official_provenance, { source: 'synthetic fixture', batch: 'new-static' });
107
+ assert.equal(sourceQ1.manifest_sha256, 'sha256:new-static');
108
+ // A newest incomplete/corrupt filename batch is selected before JSON
109
+ // parsing can discard it; the older complete manual batch is not a fallback.
110
+ const corruptRoot = freshRoot();
111
+ roots.push(corruptRoot);
112
+ writeBatch(corruptRoot, '2026-01-01T10-00-00-000Z.json', 'old-complete', 'manual', 'hit');
113
+ const newest = '2026-09-11T10-00-00-000Z.json';
114
+ EXPECTED_QUERY_IDS.slice(0, 7).forEach((queryId, index) => writeJson(corruptRoot, queryId, newest, record(queryId, 'new-incomplete', `2026-09-11T10:00:0${index + 1}.000Z`, 'static', 'error')));
115
+ writeRaw(corruptRoot, 'sf-08', newest, '{ corrupt json');
116
+ const corrupt = runCli(corruptRoot);
117
+ assert.equal(corrupt.exit, 1, corrupt.output);
118
+ assert.equal(corrupt.summary.status, 'fail_closed');
119
+ assert.equal(corrupt.summary.selected_batch.batch_id, '2026-09-11T10-00-00-000Z');
120
+ assert.ok(corrupt.summary.missing_query_ids.includes('sf-08'));
121
+ assert.ok(corrupt.summary.selected_malformed_records.some((item) => item.file === `sf-08/${newest}`));
122
+ assert.equal(corrupt.summary.records.find((item) => item.query_id === 'sf-01').effective_source, 'static-openflights+manual-band');
123
+ // A malformed old batch is diagnostic only when a newer complete batch is
124
+ // independently reportable.
125
+ const oldCorruptRoot = freshRoot();
126
+ roots.push(oldCorruptRoot);
127
+ writeRaw(oldCorruptRoot, 'sf-01', '2026-01-01T10-00-00-000Z.json', '{ old corrupt');
128
+ writeBatch(oldCorruptRoot, '2026-09-12T10-00-00-000Z.json', 'new-complete', 'manual', 'hit');
129
+ const oldCorrupt = runCli(oldCorruptRoot);
130
+ assert.equal(oldCorrupt.exit, 0, oldCorrupt.output);
131
+ assert.equal(oldCorrupt.summary.selected_malformed_records.length, 0);
132
+ assert.equal(oldCorrupt.summary.malformed_records.length, 1);
133
+ // Historical records without a canonical filename or valid explicit batch
134
+ // capture time remain visible unmatched and cannot become the batch.
135
+ const legacyRoot = freshRoot();
136
+ roots.push(legacyRoot);
137
+ writeBatch(legacyRoot, '2026-09-13T10-00-00-000Z.json', 'new-complete', 'manual', 'hit');
138
+ writeJson(legacyRoot, 'sf-01', 'legacy.json', { ...record('sf-01', 'legacy', '2020-01-01T00:00:00.000Z', 'manual', 'hit'), batch_id: undefined, started_at: undefined });
139
+ const legacy = runCli(legacyRoot);
140
+ assert.equal(legacy.exit, 0, legacy.output);
141
+ assert.equal(legacy.summary.selected_batch.batch_id, '2026-09-13T10-00-00-000Z');
142
+ assert.ok(legacy.summary.unknown_batch_records.some((item) => item.file === 'sf-01/legacy.json'));
143
+ assert.equal(legacy.summary.records.find((item) => item.query_id === 'sf-01').batch_id, '2026-09-13T10-00-00-000Z');
144
+ console.log('SF SUMMARY CLI E2E: coherent filename batch, chronology, source provenance, missing/corrupt fail-closed, legacy unknown, and old/new isolation OK');
145
+ }
146
+ finally {
147
+ for (const root of roots)
148
+ rmSync(root, { recursive: true, force: true });
149
+ }