@openai/codex-security 0.8.2 → 0.8.3

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 (375) hide show
  1. package/README.md +43 -61
  2. package/_bundled_plugin/.app.json +4 -0
  3. package/_bundled_plugin/.mcp.json +1 -0
  4. package/_bundled_plugin/mcp/helpers.mjs.br.part-000 +0 -0
  5. package/_bundled_plugin/mcp/helpers.mjs.br.part-001 +0 -0
  6. package/_bundled_plugin/mcp/native/darwin-arm64/unix.node +0 -0
  7. package/_bundled_plugin/mcp/native/darwin-x64/unix.node +0 -0
  8. package/_bundled_plugin/mcp/native/linux-arm64-gnu/unix.node +0 -0
  9. package/_bundled_plugin/mcp/native/linux-arm64-musl/unix.node +0 -0
  10. package/_bundled_plugin/mcp/native/linux-x64-gnu/unix.node +0 -0
  11. package/_bundled_plugin/mcp/native/linux-x64-musl/unix.node +0 -0
  12. package/_bundled_plugin/mcp/native/win32-arm64/windows.node +0 -0
  13. package/_bundled_plugin/mcp/native/win32-x64/windows.node +0 -0
  14. package/_bundled_plugin/mcp/permission-profile-preflight.mjs +46 -12
  15. package/_bundled_plugin/mcp/server.mjs.br.part-000 +0 -0
  16. package/_bundled_plugin/mcp/server.mjs.br.part-001 +0 -0
  17. package/_bundled_plugin/mcp/server.mjs.br.part-002 +0 -0
  18. package/_bundled_plugin/references/artifact-storage.md +1 -1
  19. package/_bundled_plugin/references/core-scan.md +14 -5
  20. package/_bundled_plugin/references/default-severity-rubric.md +28 -0
  21. package/_bundled_plugin/references/finding-detail-fields.md +1 -0
  22. package/_bundled_plugin/references/threat-model.md +1 -0
  23. package/_bundled_plugin/scripts/deep_scan_workbench.py +23 -112
  24. package/_bundled_plugin/scripts/finalize_scan_contract.py +167 -153
  25. package/_bundled_plugin/scripts/finding_preview.py +5 -29
  26. package/_bundled_plugin/scripts/posix_scan_local_files.py +187 -0
  27. package/_bundled_plugin/scripts/report_projection.py +87 -136
  28. package/_bundled_plugin/scripts/validate_scan_contract.py +2 -6
  29. package/_bundled_plugin/scripts/windows_scan_local_files.py +212 -55
  30. package/_bundled_plugin/scripts/workbench/retained_coverage.py +8 -24
  31. package/_bundled_plugin/scripts/workbench/saved_coverage.py +143 -231
  32. package/_bundled_plugin/scripts/workbench_cli.py +102 -13
  33. package/_bundled_plugin/scripts/workbench_constants.py +9 -0
  34. package/_bundled_plugin/scripts/workbench_db.py +186 -360
  35. package/_bundled_plugin/scripts/workbench_finding_workflows.py +86 -4
  36. package/_bundled_plugin/scripts/workbench_native_indexes.py +17 -21
  37. package/_bundled_plugin/scripts/workbench_remediation.py +495 -11
  38. package/_bundled_plugin/scripts/workbench_scan_history.py +22 -25
  39. package/_bundled_plugin/scripts/workbench_scan_start.py +1 -1
  40. package/_bundled_plugin/scripts/workbench_scan_usage.py +25 -52
  41. package/_bundled_plugin/scripts/workbench_schema.py +1 -1
  42. package/_bundled_plugin/scripts/workbench_setup.py +239 -0
  43. package/_bundled_plugin/scripts/workbench_source_scopes.py +15 -23
  44. package/_bundled_plugin/scripts/workbench_target.py +213 -20
  45. package/_bundled_plugin/scripts/workbench_validation.py +1 -9
  46. package/_bundled_plugin/shared/workbench-history-repairs.json +7 -0
  47. package/_bundled_plugin/shared/workbench-migrations.json +19 -0
  48. package/_bundled_plugin/skills/attack-path-analysis/SKILL.md +1 -1
  49. package/_bundled_plugin/skills/attack-path-analysis/references/severity-policy.md +4 -68
  50. package/_bundled_plugin/skills/check-skills/SKILL.md +43 -0
  51. package/_bundled_plugin/skills/check-skills/agents/openai.yaml +4 -0
  52. package/_bundled_plugin/skills/cloud-findings/SKILL.md +2 -0
  53. package/_bundled_plugin/skills/fix-finding/SKILL.md +18 -1
  54. package/_bundled_plugin/skills/publish-findings/SKILL.md +64 -35
  55. package/_bundled_plugin/skills/publish-findings/references/wiz-import.md +2 -21
  56. package/_bundled_plugin/skills/threat-model-visualize/scripts/build_explorer.py +14 -8
  57. package/_bundled_plugin/skills/track-findings/SKILL.md +5 -3
  58. package/_bundled_plugin/skills/triage-finding/references/github-rest-intake.md +22 -68
  59. package/_bundled_plugin/skills/triage-finding/references/ticket-intake.md +6 -4
  60. package/dist/api.d.ts +6 -1
  61. package/dist/api.d.ts.map +1 -1
  62. package/dist/api.js +411 -160
  63. package/dist/api.js.map +1 -1
  64. package/dist/auth.js +6 -1
  65. package/dist/auth.js.map +1 -1
  66. package/dist/blackduck-findings.d.ts +8 -0
  67. package/dist/blackduck-findings.d.ts.map +1 -0
  68. package/dist/blackduck-findings.js +305 -0
  69. package/dist/blackduck-findings.js.map +1 -0
  70. package/dist/bulk-scan-discovery.d.ts.map +1 -1
  71. package/dist/bulk-scan-discovery.js +51 -36
  72. package/dist/bulk-scan-discovery.js.map +1 -1
  73. package/dist/classify-severity-records.d.ts +5 -0
  74. package/dist/classify-severity-records.d.ts.map +1 -1
  75. package/dist/classify-severity-records.js +6 -8
  76. package/dist/classify-severity-records.js.map +1 -1
  77. package/dist/classify-severity.d.ts +4 -1
  78. package/dist/classify-severity.d.ts.map +1 -1
  79. package/dist/classify-severity.js +28 -9
  80. package/dist/classify-severity.js.map +1 -1
  81. package/dist/cli.d.ts +3 -0
  82. package/dist/cli.d.ts.map +1 -1
  83. package/dist/cli.js +608 -258
  84. package/dist/cli.js.map +1 -1
  85. package/dist/codex-prompt.d.ts +2 -0
  86. package/dist/codex-prompt.d.ts.map +1 -1
  87. package/dist/codex-prompt.js +6 -0
  88. package/dist/codex-prompt.js.map +1 -1
  89. package/dist/component-scan.d.ts.map +1 -1
  90. package/dist/component-scan.js +6 -5
  91. package/dist/component-scan.js.map +1 -1
  92. package/dist/config.d.ts +2 -1
  93. package/dist/config.d.ts.map +1 -1
  94. package/dist/config.js +162 -40
  95. package/dist/config.js.map +1 -1
  96. package/dist/continuum-findings.d.ts +7 -0
  97. package/dist/continuum-findings.d.ts.map +1 -0
  98. package/dist/continuum-findings.js +157 -0
  99. package/dist/continuum-findings.js.map +1 -0
  100. package/dist/contract-values.d.ts +28 -0
  101. package/dist/contract-values.d.ts.map +1 -0
  102. package/dist/contract-values.js +75 -0
  103. package/dist/contract-values.js.map +1 -0
  104. package/dist/contract.d.ts +2 -20
  105. package/dist/contract.d.ts.map +1 -1
  106. package/dist/contract.js +58 -669
  107. package/dist/contract.js.map +1 -1
  108. package/dist/cost-model.d.ts.map +1 -1
  109. package/dist/cost-model.js +1 -4
  110. package/dist/cost-model.js.map +1 -1
  111. package/dist/cost.d.ts +19 -1
  112. package/dist/cost.d.ts.map +1 -1
  113. package/dist/cost.js +2120 -39
  114. package/dist/cost.js.map +1 -1
  115. package/dist/custom-validation-prompt.d.ts +1 -1
  116. package/dist/custom-validation-prompt.d.ts.map +1 -1
  117. package/dist/custom-validation-prompt.js +5 -0
  118. package/dist/custom-validation-prompt.js.map +1 -1
  119. package/dist/custom-validation.d.ts +2 -0
  120. package/dist/custom-validation.d.ts.map +1 -1
  121. package/dist/custom-validation.js +4 -0
  122. package/dist/custom-validation.js.map +1 -1
  123. package/dist/deduplication/deduplication-prompts.d.ts +4 -4
  124. package/dist/deduplication/deduplication-prompts.d.ts.map +1 -1
  125. package/dist/deduplication/deduplication-prompts.js +2 -2
  126. package/dist/deduplication/deduplication-prompts.js.map +1 -1
  127. package/dist/deduplication/deduplication-reviewer.d.ts +14 -11
  128. package/dist/deduplication/deduplication-reviewer.d.ts.map +1 -1
  129. package/dist/deduplication/deduplication-reviewer.js +11 -4
  130. package/dist/deduplication/deduplication-reviewer.js.map +1 -1
  131. package/dist/deduplication/deduplication.js.map +1 -1
  132. package/dist/deduplication/finding-schema.d.ts +19 -1
  133. package/dist/deduplication/finding-schema.d.ts.map +1 -1
  134. package/dist/deduplication/finding-schema.js +25 -0
  135. package/dist/deduplication/finding-schema.js.map +1 -1
  136. package/dist/deduplication/local.d.ts.map +1 -1
  137. package/dist/deduplication/local.js +3 -8
  138. package/dist/deduplication/local.js.map +1 -1
  139. package/dist/deduplication/records.d.ts +8 -2
  140. package/dist/deduplication/records.d.ts.map +1 -1
  141. package/dist/deduplication/records.js +36 -8
  142. package/dist/deduplication/records.js.map +1 -1
  143. package/dist/deep-scan.d.ts +11 -0
  144. package/dist/deep-scan.d.ts.map +1 -1
  145. package/dist/deep-scan.js +235 -4
  146. package/dist/deep-scan.js.map +1 -1
  147. package/dist/default-severity-rubric.d.ts +1 -2
  148. package/dist/default-severity-rubric.d.ts.map +1 -1
  149. package/dist/default-severity-rubric.js +2 -66
  150. package/dist/default-severity-rubric.js.map +1 -1
  151. package/dist/endor-findings.d.ts.map +1 -1
  152. package/dist/endor-findings.js +7 -37
  153. package/dist/endor-findings.js.map +1 -1
  154. package/dist/errors.js +1 -1
  155. package/dist/errors.js.map +1 -1
  156. package/dist/external-findings-import.d.ts.map +1 -1
  157. package/dist/external-findings-import.js +5 -11
  158. package/dist/external-findings-import.js.map +1 -1
  159. package/dist/external-findings-local.d.ts +9 -0
  160. package/dist/external-findings-local.d.ts.map +1 -1
  161. package/dist/external-findings-local.js +325 -179
  162. package/dist/external-findings-local.js.map +1 -1
  163. package/dist/external-findings-publish.d.ts +12 -0
  164. package/dist/external-findings-publish.d.ts.map +1 -1
  165. package/dist/external-findings-publish.js +1202 -214
  166. package/dist/external-findings-publish.js.map +1 -1
  167. package/dist/external-findings-read.d.ts +8 -0
  168. package/dist/external-findings-read.d.ts.map +1 -1
  169. package/dist/external-findings-read.js +65 -54
  170. package/dist/external-findings-read.js.map +1 -1
  171. package/dist/external-findings.d.ts +2 -0
  172. package/dist/external-findings.d.ts.map +1 -1
  173. package/dist/external-findings.js +111 -0
  174. package/dist/external-findings.js.map +1 -1
  175. package/dist/external-import-contract.d.ts +29 -1
  176. package/dist/external-import-contract.d.ts.map +1 -1
  177. package/dist/external-import-contract.js +314 -44
  178. package/dist/external-import-contract.js.map +1 -1
  179. package/dist/external-import-models.d.ts +1 -1
  180. package/dist/external-import-models.d.ts.map +1 -1
  181. package/dist/external-import-models.js.map +1 -1
  182. package/dist/finding-normalization.d.ts +1 -1
  183. package/dist/finding-normalization.d.ts.map +1 -1
  184. package/dist/finding-normalization.js +46 -11
  185. package/dist/finding-normalization.js.map +1 -1
  186. package/dist/finding-retrieval.d.ts +3 -3
  187. package/dist/finding-retrieval.d.ts.map +1 -1
  188. package/dist/finding-retrieval.js.map +1 -1
  189. package/dist/finding-workflow.d.ts +6 -1
  190. package/dist/finding-workflow.d.ts.map +1 -1
  191. package/dist/finding-workflow.js +2 -2
  192. package/dist/finding-workflow.js.map +1 -1
  193. package/dist/git-remote.d.ts +4 -0
  194. package/dist/git-remote.d.ts.map +1 -1
  195. package/dist/git-remote.js +20 -0
  196. package/dist/git-remote.js.map +1 -1
  197. package/dist/github-advisories.d.ts +3 -12
  198. package/dist/github-advisories.d.ts.map +1 -1
  199. package/dist/github-advisories.js +9 -29
  200. package/dist/github-advisories.js.map +1 -1
  201. package/dist/github-dependabot-findings.d.ts.map +1 -1
  202. package/dist/github-dependabot-findings.js +7 -16
  203. package/dist/github-dependabot-findings.js.map +1 -1
  204. package/dist/github-findings.d.ts.map +1 -1
  205. package/dist/github-findings.js +344 -56
  206. package/dist/github-findings.js.map +1 -1
  207. package/dist/github.d.ts +17 -7
  208. package/dist/github.d.ts.map +1 -1
  209. package/dist/github.js +43 -30
  210. package/dist/github.js.map +1 -1
  211. package/dist/host-protocol.d.ts +2 -2
  212. package/dist/host-protocol.d.ts.map +1 -1
  213. package/dist/host-protocol.js.map +1 -1
  214. package/dist/host-records-protocol.d.ts +10 -11
  215. package/dist/host-records-protocol.d.ts.map +1 -1
  216. package/dist/host-records-protocol.js +69 -9
  217. package/dist/host-records-protocol.js.map +1 -1
  218. package/dist/hosted-scan.d.ts +15 -0
  219. package/dist/hosted-scan.d.ts.map +1 -1
  220. package/dist/hosted-scan.js +55 -33
  221. package/dist/hosted-scan.js.map +1 -1
  222. package/dist/index.d.ts +7 -0
  223. package/dist/index.d.ts.map +1 -1
  224. package/dist/index.js +6 -0
  225. package/dist/index.js.map +1 -1
  226. package/dist/inspector-findings.d.ts.map +1 -1
  227. package/dist/inspector-findings.js +13 -18
  228. package/dist/inspector-findings.js.map +1 -1
  229. package/dist/knowledge-base.js +18 -5
  230. package/dist/knowledge-base.js.map +1 -1
  231. package/dist/local-git-metadata.d.ts +5 -0
  232. package/dist/local-git-metadata.d.ts.map +1 -0
  233. package/dist/local-git-metadata.js +131 -0
  234. package/dist/local-git-metadata.js.map +1 -0
  235. package/dist/multiscan.d.ts.map +1 -1
  236. package/dist/multiscan.js +22 -12
  237. package/dist/multiscan.js.map +1 -1
  238. package/dist/opengrep-findings.d.ts.map +1 -1
  239. package/dist/opengrep-findings.js +34 -20
  240. package/dist/opengrep-findings.js.map +1 -1
  241. package/dist/patch-tui.d.ts.map +1 -1
  242. package/dist/patch-tui.js +90 -35
  243. package/dist/patch-tui.js.map +1 -1
  244. package/dist/private-finding-import.d.ts +246 -0
  245. package/dist/private-finding-import.d.ts.map +1 -0
  246. package/dist/private-finding-import.js +387 -0
  247. package/dist/private-finding-import.js.map +1 -0
  248. package/dist/project-config.d.ts.map +1 -1
  249. package/dist/project-config.js +2 -2
  250. package/dist/project-config.js.map +1 -1
  251. package/dist/provider-profile.d.ts +10 -2
  252. package/dist/provider-profile.d.ts.map +1 -1
  253. package/dist/provider-profile.js +72 -10
  254. package/dist/provider-profile.js.map +1 -1
  255. package/dist/publication.js +7 -1
  256. package/dist/publication.js.map +1 -1
  257. package/dist/reader-selection.d.ts +13 -0
  258. package/dist/reader-selection.d.ts.map +1 -0
  259. package/dist/reader-selection.js +81 -0
  260. package/dist/reader-selection.js.map +1 -0
  261. package/dist/record.d.ts +6 -1
  262. package/dist/record.d.ts.map +1 -1
  263. package/dist/record.js +53 -2
  264. package/dist/record.js.map +1 -1
  265. package/dist/remediation.d.ts +5 -0
  266. package/dist/remediation.d.ts.map +1 -1
  267. package/dist/remediation.js +30 -0
  268. package/dist/remediation.js.map +1 -1
  269. package/dist/result.d.ts +2 -0
  270. package/dist/result.d.ts.map +1 -1
  271. package/dist/result.js +3 -1
  272. package/dist/result.js.map +1 -1
  273. package/dist/runtime.d.ts +2 -1
  274. package/dist/runtime.d.ts.map +1 -1
  275. package/dist/runtime.js +95 -52
  276. package/dist/runtime.js.map +1 -1
  277. package/dist/scan-activity.js +40 -17
  278. package/dist/scan-activity.js.map +1 -1
  279. package/dist/scan-comparison.d.ts +1 -1
  280. package/dist/scan-comparison.d.ts.map +1 -1
  281. package/dist/scan-comparison.js +11 -13
  282. package/dist/scan-comparison.js.map +1 -1
  283. package/dist/scan-dashboard.d.ts +1 -0
  284. package/dist/scan-dashboard.d.ts.map +1 -1
  285. package/dist/scan-dashboard.js +16 -37
  286. package/dist/scan-dashboard.js.map +1 -1
  287. package/dist/scan-executor.d.ts +2 -0
  288. package/dist/scan-executor.d.ts.map +1 -1
  289. package/dist/scan-executor.js.map +1 -1
  290. package/dist/scan-history-renderer.d.ts.map +1 -1
  291. package/dist/scan-history-renderer.js +22 -9
  292. package/dist/scan-history-renderer.js.map +1 -1
  293. package/dist/scan-logs.d.ts.map +1 -1
  294. package/dist/scan-logs.js +5 -5
  295. package/dist/scan-logs.js.map +1 -1
  296. package/dist/scanner-import.d.ts +46 -6
  297. package/dist/scanner-import.d.ts.map +1 -1
  298. package/dist/scanner-import.js +208 -42
  299. package/dist/scanner-import.js.map +1 -1
  300. package/dist/scanner-repository-url.d.ts +14 -0
  301. package/dist/scanner-repository-url.d.ts.map +1 -0
  302. package/dist/scanner-repository-url.js +67 -0
  303. package/dist/scanner-repository-url.js.map +1 -0
  304. package/dist/semgrep-findings.d.ts.map +1 -1
  305. package/dist/semgrep-findings.js +20 -48
  306. package/dist/semgrep-findings.js.map +1 -1
  307. package/dist/semgrep-platform-findings.d.ts +12 -0
  308. package/dist/semgrep-platform-findings.d.ts.map +1 -0
  309. package/dist/semgrep-platform-findings.js +198 -0
  310. package/dist/semgrep-platform-findings.js.map +1 -0
  311. package/dist/severity-rubric.d.ts +20 -0
  312. package/dist/severity-rubric.d.ts.map +1 -0
  313. package/dist/severity-rubric.js +73 -0
  314. package/dist/severity-rubric.js.map +1 -0
  315. package/dist/severity-store.js +15 -5
  316. package/dist/severity-store.js.map +1 -1
  317. package/dist/snyk-findings.d.ts.map +1 -1
  318. package/dist/snyk-findings.js +21 -20
  319. package/dist/snyk-findings.js.map +1 -1
  320. package/dist/sonar-collector.d.ts +16 -0
  321. package/dist/sonar-collector.d.ts.map +1 -0
  322. package/dist/sonar-collector.js +383 -0
  323. package/dist/sonar-collector.js.map +1 -0
  324. package/dist/sonar-findings.d.ts +49 -0
  325. package/dist/sonar-findings.d.ts.map +1 -0
  326. package/dist/sonar-findings.js +288 -0
  327. package/dist/sonar-findings.js.map +1 -0
  328. package/dist/sonar-import.d.ts +111 -0
  329. package/dist/sonar-import.d.ts.map +1 -0
  330. package/dist/sonar-import.js +279 -0
  331. package/dist/sonar-import.js.map +1 -0
  332. package/dist/suggest-owners.d.ts.map +1 -1
  333. package/dist/suggest-owners.js +2 -1
  334. package/dist/suggest-owners.js.map +1 -1
  335. package/dist/targets.d.ts +3 -0
  336. package/dist/targets.d.ts.map +1 -1
  337. package/dist/targets.js +18 -12
  338. package/dist/targets.js.map +1 -1
  339. package/dist/terminal-columns.d.ts +4 -0
  340. package/dist/terminal-columns.d.ts.map +1 -0
  341. package/dist/terminal-columns.js +19 -0
  342. package/dist/terminal-columns.js.map +1 -0
  343. package/dist/validation-records.d.ts +0 -3
  344. package/dist/validation-records.d.ts.map +1 -1
  345. package/dist/validation-records.js +0 -16
  346. package/dist/validation-records.js.map +1 -1
  347. package/dist/veracode-findings.d.ts +7 -0
  348. package/dist/veracode-findings.d.ts.map +1 -0
  349. package/dist/veracode-findings.js +371 -0
  350. package/dist/veracode-findings.js.map +1 -0
  351. package/dist/windows-path.d.ts.map +1 -1
  352. package/dist/windows-path.js +1 -0
  353. package/dist/windows-path.js.map +1 -1
  354. package/dist/wiz-csv.d.ts +2 -2
  355. package/dist/wiz-csv.d.ts.map +1 -1
  356. package/dist/wiz-csv.js +1 -3
  357. package/dist/wiz-csv.js.map +1 -1
  358. package/dist/wiz-findings.d.ts +10 -2
  359. package/dist/wiz-findings.d.ts.map +1 -1
  360. package/dist/wiz-findings.js +88 -49
  361. package/dist/wiz-findings.js.map +1 -1
  362. package/docs/classify-severity-records.md +1 -1
  363. package/docs/cli.md +310 -477
  364. package/docs/dedupe-records.md +10 -0
  365. package/docs/findings-service.md +21 -8
  366. package/docs/hosted-scans.md +16 -1
  367. package/package.json +8 -9
  368. package/schemas/external-findings.schema.json +12 -1
  369. package/schemas/hosted-scan-v2.fixture.json +16 -1
  370. package/_bundled_plugin/scripts/validate_tracking_source.py +0 -82
  371. package/_bundled_plugin/scripts/workbench_local_dedupe.py +0 -136
  372. package/dist/deduplication/records-protocol.d.ts +0 -4
  373. package/dist/deduplication/records-protocol.d.ts.map +0 -1
  374. package/dist/deduplication/records-protocol.js +0 -49
  375. package/dist/deduplication/records-protocol.js.map +0 -1
@@ -5,6 +5,7 @@ from __future__ import annotations
5
5
  import copy
6
6
  import hashlib
7
7
  import json
8
+ from collections.abc import Iterator
8
9
  from pathlib import Path
9
10
  from typing import Any
10
11
 
@@ -95,16 +96,18 @@ def _coverage_comparison_row(row: Any, field: str) -> Any:
95
96
  return row
96
97
 
97
98
 
98
- def _aggregate_worker_coverage_rows(rows: list[Any], worker_id: str, field: str) -> list[Any]:
99
+ def _worker_coverage_sources(
100
+ rows: list[Any], worker_id: str, field: str
101
+ ) -> Iterator[tuple[Any, Any]]:
99
102
  """Match accepted aggregate IDs without changing raw recovery identities."""
100
103
  reserved = {
101
104
  row["id"] for row in rows if isinstance(row, dict) and isinstance(row.get("id"), str)
102
105
  }
103
106
  emitted: set[str] = set()
104
- projected = []
105
107
  for index, original in enumerate(rows):
106
- row = copy.deepcopy(original)
108
+ row = original
107
109
  if isinstance(row, dict) and field != "openQuestions":
110
+ row = row.copy()
108
111
  generated = not isinstance(row.get("id"), str)
109
112
  identity = str(index) if generated else row["id"]
110
113
  base = identity
@@ -116,23 +119,28 @@ def _aggregate_worker_coverage_rows(rows: list[Any], worker_id: str, field: str)
116
119
  reserved.add(identity)
117
120
  emitted.add(identity)
118
121
  row["id"] = identity
119
- projected.append(
120
- _coverage_comparison_row(_project_worker_coverage_row(row, worker_id, field), field)
121
- )
122
- return projected
122
+ qualified = _project_worker_coverage_row(row, worker_id, field)
123
+ yield _coverage_comparison_row(qualified, field), original
124
+
123
125
 
126
+ _Row = dict[str, Any]
127
+ _LegacySurfaceLink = tuple[_Row, str, _Row, _Row, _Row | None]
124
128
 
125
- def _prepare_worker_coverage_recovery(
129
+
130
+ def prepare_saved_coverage_projection(
126
131
  sources: list[tuple[str, dict[str, Any], str | None]],
127
132
  parent: dict[str, Any] | None,
128
133
  source_order: dict[str, tuple[int, int]],
129
134
  *,
130
- enabled: bool,
131
- receipt_resolver=None,
132
- ) -> tuple[
133
- bool, list[tuple[dict[str, Any], str, dict[str, Any], dict[str, Any], dict[str, Any] | None]]
134
- ]:
135
+ project_worker_coverage: bool,
136
+ receipt_resolver,
137
+ preserve_canonical_parent=False,
138
+ ) -> tuple[bool, list[_LegacySurfaceLink]]:
135
139
  """Put bound worker evidence in parent coordinates without changing source files."""
140
+ if preserve_canonical_parent:
141
+ return False, []
142
+ # Older parent publications use worker/id identities. Reconcile those copies
143
+ # against their bound sources before projecting accepted attempt provenance.
136
144
  workers = {owner for _, _, owner in sources if owner is not None}
137
145
  parents = [
138
146
  draft
@@ -145,8 +153,8 @@ def _prepare_worker_coverage_recovery(
145
153
  # Prefer the selected parent over historical copies of a task's surface.
146
154
  parents.insert(0, parent)
147
155
  fields = ("surfaces", "explicitExclusions", "deferred", "openQuestions")
148
- if not enabled:
149
- enabled = any(
156
+ if not project_worker_coverage:
157
+ project_worker_coverage = any(
150
158
  isinstance(row, dict)
151
159
  and isinstance(row.get("workerId"), str)
152
160
  and row["workerId"] in workers
@@ -156,135 +164,105 @@ def _prepare_worker_coverage_recovery(
156
164
  )
157
165
  for draft in parents
158
166
  for field in fields
159
- for row in (
160
- draft["reviewState"].get(field, [])
161
- if isinstance(draft["reviewState"].get(field, []), list)
162
- else []
163
- )
167
+ for row in _coverage_rows(draft["reviewState"], field)
164
168
  )
165
- if not enabled:
169
+ if not project_worker_coverage:
166
170
  return False, []
167
- projected: dict[str, list[Any]] = {field: [] for field in fields}
168
- surface_sources: list[tuple[dict[str, Any], dict[str, Any]]] = []
169
- task_sources: list[tuple[dict[str, Any], dict[str, Any]]] = []
170
- surface_links: list[
171
- tuple[dict[str, Any], str, dict[str, Any], dict[str, Any], dict[str, Any] | None]
172
- ] = []
171
+ missing = object()
172
+ original_owners = {}
173
+ projected: dict[str, list[tuple[Any, Any]]] = {field: [] for field in fields}
174
+ surface_links: list[_LegacySurfaceLink] = []
173
175
  for relative, draft, owner in sources:
174
176
  if owner is None:
175
177
  continue
176
- directory = Path(relative).parent
177
- if directory.name == "checkpoints":
178
- directory = directory.parent
179
178
  for field in fields:
180
- rows = draft["reviewState"].get(field, [])
181
- if not isinstance(rows, list):
182
- continue
179
+ rows = _coverage_rows(draft["reviewState"], field)
183
180
  for index, row in enumerate(rows):
184
181
  if field == "openQuestions" and isinstance(row, str):
185
182
  row = {"question": row}
186
183
  rows[index] = row
187
184
  if not isinstance(row, dict):
188
185
  continue
186
+ original_owners.setdefault(id(row), row.get("workerId", missing))
189
187
  row["workerId"] = owner
190
- if field == "surfaces" and receipt_resolver is not None:
191
- row["receiptRefs"] = receipt_resolver(relative, row, owner)
192
- elif field == "surfaces" and isinstance(row.get("receiptRefs"), list):
193
- refs = []
194
- for ref in row["receiptRefs"]:
195
- if isinstance(ref, str):
196
- try:
197
- normalized = _require_portable_relative_path(
198
- ref, "Worker coverage receipt"
199
- )
200
- except ContractError:
201
- pass # Leave malformed refs to the existing per-record recovery.
202
- else:
203
- if normalized.startswith("artifacts/"):
204
- ref = f"{directory.as_posix()}/{normalized}"
205
- refs.append(ref)
206
- row["receiptRefs"] = refs
207
188
  if field == "surfaces":
208
- row.setdefault("receiptRefs", [])
209
- aggregate_rows = _aggregate_worker_coverage_rows(rows, owner, field)
210
- projected[field].extend(aggregate_rows)
211
- if field in {"surfaces", "deferred"}:
212
- originals = surface_sources if field == "surfaces" else task_sources
213
- originals.extend(
214
- (aggregate, row)
215
- for aggregate, row in zip(aggregate_rows, rows)
216
- if isinstance(aggregate, dict) and isinstance(row, dict)
217
- )
189
+ row["receiptRefs"] = receipt_resolver(relative, row, owner)
190
+ projected[field].extend(_worker_coverage_sources(rows, owner, field))
191
+
192
+ def originals(field: str, row: Any):
193
+ comparison = _coverage_comparison_row(row, field)
194
+ return (
195
+ original
196
+ for aggregate, original in projected[field]
197
+ if aggregate is comparison or aggregate == comparison
198
+ )
199
+
218
200
  # A canonical aggregate contains copies of the same worker evidence. Let
219
201
  # the existing per-worker chronology reconcile those originals exactly once.
220
202
  # Keep parent-only evidence when its bound worker source is unavailable.
221
203
  for draft in parents:
222
- if not draft["reviewState"]:
204
+ review = draft["reviewState"]
205
+ if not review:
223
206
  continue
224
207
  for field in fields:
225
- rows = draft["reviewState"].get(field, [])
226
- if isinstance(rows, list):
227
- if field == "surfaces":
228
- tasks = draft["reviewState"].get("deferred", [])
229
- for row in rows:
230
- if not isinstance(row, dict) or not isinstance(row.get("id"), str):
231
- continue
232
- matching_sources = [
233
- original
234
- for aggregate, original in surface_sources
235
- if aggregate == _coverage_comparison_row(row, field)
236
- ]
237
- if not matching_sources:
238
- continue
239
- for task in tasks if isinstance(tasks, list) else []:
240
- if (
241
- isinstance(task, dict)
242
- and isinstance(task.get("surfaceIds"), list)
243
- and row["id"] in task["surfaceIds"]
244
- ):
245
- surface_links.extend(
246
- (
247
- task,
248
- row["id"],
249
- source,
250
- row,
251
- next(
252
- (
253
- original
254
- for aggregate, original in task_sources
255
- if aggregate == task
256
- ),
257
- None,
258
- ),
259
- )
260
- for source in matching_sources
261
- )
262
- draft["reviewState"][field] = [
263
- row
264
- for row in rows
265
- if _coverage_comparison_row(row, field) not in projected[field]
266
- ]
208
+ rows = review.get(field, [])
209
+ if not isinstance(rows, list):
210
+ continue
211
+ remaining = []
212
+ for row in rows:
213
+ matches = originals(field, row)
214
+ first = next(matches, missing)
215
+ if first is missing:
216
+ remaining.append(row)
217
+ continue
218
+ if (
219
+ field != "surfaces"
220
+ or not isinstance(row, dict)
221
+ or not isinstance(row.get("id"), str)
222
+ ):
223
+ continue
224
+ surface_sources = [first, *matches]
225
+ for task in _coverage_rows(review, "deferred"):
226
+ if (
227
+ isinstance(task, dict)
228
+ and isinstance(task.get("surfaceIds"), list)
229
+ and row["id"] in task["surfaceIds"]
230
+ ):
231
+ source_task = next(originals("deferred", task), None)
232
+ surface_links.extend(
233
+ (task, row["id"], source, row, source_task)
234
+ for source in surface_sources
235
+ )
236
+ review[field] = remaining
237
+ # A selected parent may also be the result registered for a worker.
238
+ # Restore the retained input rows after comparing the published worker IDs.
239
+ for _, draft, owner in sources:
240
+ if owner is not None:
241
+ for field in fields:
242
+ for row in _coverage_rows(draft["reviewState"], field):
243
+ if isinstance(row, dict):
244
+ previous = original_owners[id(row)]
245
+ if previous is missing:
246
+ row.pop("workerId", None)
247
+ else:
248
+ row["workerId"] = previous
267
249
  return True, surface_links
268
250
 
269
251
 
270
252
  class SavedCoverageProjection:
271
253
  """Keep worker source links stable while legacy and accepted rows converge."""
272
254
 
273
- def __init__(self, project_worker_coverage, legacy_surface_links, sources):
255
+ def __init__(self, project_worker_coverage, legacy_surface_links, projection_origins):
274
256
  self.project_worker_coverage = project_worker_coverage
275
257
  self.legacy_surface_links = legacy_surface_links
276
258
  self.legacy_source_outputs: dict[int, dict[str, Any]] = {}
277
259
  self.worker_row_owners: dict[int, str] = {}
278
260
  self.worker_surface_outputs: dict[tuple[str, str], dict[int, dict[str, Any]]] = {}
279
- self.source_owner_by_id = {
280
- id(row): owner
281
- for _, draft, owner in sources
282
- for field in ("surfaces", "deferred")
283
- for rows in (draft["reviewState"].get(field, []),)
284
- if isinstance(rows, list)
285
- for row in rows
286
- if isinstance(row, dict)
287
- }
261
+ self.projection_origins = projection_origins
262
+
263
+ def source_owner(self, row, fallback=None):
264
+ origin = self.projection_origins.get(id(row))
265
+ return origin[0] if origin is not None else fallback
288
266
 
289
267
  def record_coverage_owner(self, retained, original, owner, field):
290
268
  if self.project_worker_coverage and owner is not None and isinstance(retained, dict):
@@ -335,8 +313,8 @@ class SavedCoverageProjection:
335
313
  return None
336
314
 
337
315
  def linked_surface(self, surface, outputs, named_outputs):
316
+ owner = self.source_owner(surface, surface.get("workerId"))
338
317
  retained = outputs.get(id(surface))
339
- owner = self.source_owner_by_id.get(id(surface), surface.get("workerId"))
340
318
  if retained is None and isinstance(owner, str) and isinstance(surface.get("id"), str):
341
319
  matches = named_outputs.get((owner, surface["id"]), {})
342
320
  if len(matches) == 1:
@@ -395,32 +373,29 @@ class SavedCoverageProjection:
395
373
  coverage["surfaces"], retained, worker["id"], "surfaces", source, True
396
374
  )
397
375
 
398
- def linked_tasks(self, task, published_id, source_task, candidates):
399
- expected = None
400
- if source_task is not None:
401
- expected = self.legacy_source_outputs.get(id(source_task))
402
- if expected is None:
403
- expected = _project_worker_coverage_row(
404
- source_task, self.source_owner_by_id.get(id(source_task)), "deferred"
405
- )
406
- return [
407
- retained
408
- for owner, retained in candidates
409
- if retained == task
410
- or (
411
- expected is not None
412
- and (
413
- retained is expected
414
- or (
415
- owner == self.source_owner_by_id.get(id(source_task))
416
- and isinstance(retained, dict)
417
- and retained.get("id") == expected.get("id")
418
- and isinstance(retained.get("surfaceIds"), list)
419
- and published_id in retained["surfaceIds"]
376
+ def task_surface_links(self, candidates):
377
+ for task, published_id, surface, parent_surface, task_source in self.legacy_surface_links:
378
+ expected = None
379
+ if task_source is not None:
380
+ task_owner = self.source_owner(task_source)
381
+ expected = self.legacy_source_outputs.get(id(task_source))
382
+ if expected is None:
383
+ expected = _project_worker_coverage_row(task_source, task_owner, "deferred")
384
+ for owner, retained in candidates:
385
+ if retained == task or (
386
+ expected is not None
387
+ and (
388
+ retained is expected
389
+ or (
390
+ owner == task_owner
391
+ and isinstance(retained, dict)
392
+ and retained.get("id") == expected.get("id")
393
+ and isinstance(retained.get("surfaceIds"), list)
394
+ and published_id in retained["surfaceIds"]
395
+ )
420
396
  )
421
- )
422
- )
423
- ]
397
+ ):
398
+ yield retained, published_id, surface, parent_surface
424
399
 
425
400
  def finalize(
426
401
  self,
@@ -476,40 +451,31 @@ class SavedCoverageProjection:
476
451
  (self.worker_row_owners.get(id(row)), row)
477
452
  for row in (output_tasks if isinstance(output_tasks, list) else [])
478
453
  ]
479
- for task, published_id, surface, _, task_source in self.legacy_surface_links:
454
+ for task, published_id, surface, _ in self.task_surface_links(task_candidates):
480
455
  retained_surface = self.linked_surface(
481
- surface, self.legacy_source_outputs, self.worker_surface_outputs
456
+ surface,
457
+ self.legacy_source_outputs,
458
+ self.worker_surface_outputs,
482
459
  )
483
- if retained_surface is None or not isinstance(retained_surface.get("id"), str):
484
- continue
485
- for retained_task in self.linked_tasks(
486
- task, published_id, task_source, task_candidates
487
- ):
488
- _, links = retained_legacy_surface_links.setdefault(
489
- id(retained_task), (retained_task, {})
490
- )
460
+ if retained_surface is not None and isinstance(retained_surface.get("id"), str):
461
+ _, links = retained_legacy_surface_links.setdefault(id(task), (task, {}))
491
462
  links.setdefault(published_id, retained_surface)
492
463
  # A newer worker checkpoint may omit a surface still needed by a retained
493
464
  # task. Restore its parent copy only when no worker replacement survived.
494
- for task, published_id, surface, parent_surface, task_source in self.legacy_surface_links:
495
- for retained_task in self.linked_tasks(
496
- task, published_id, task_source, task_candidates
497
- ):
498
- _, links = retained_legacy_surface_links.setdefault(
499
- id(retained_task), (retained_task, {})
465
+ for task, published_id, surface, parent_surface in self.task_surface_links(task_candidates):
466
+ _, links = retained_legacy_surface_links.setdefault(id(task), (task, {}))
467
+ if published_id not in links and isinstance(coverage.get("surfaces"), list):
468
+ retained_surface = self.retain_coverage_row(
469
+ coverage["surfaces"], parent_surface, None, "surfaces"
500
470
  )
501
- if published_id not in links and isinstance(coverage.get("surfaces"), list):
502
- retained_surface = self.retain_coverage_row(
503
- coverage["surfaces"], parent_surface, None, "surfaces"
504
- )
505
- self.record_coverage_owner(
506
- retained_surface,
507
- surface,
508
- self.source_owner_by_id.get(id(surface), surface.get("workerId")),
509
- "surfaces",
510
- )
511
- _inherit_coverage_sources(retained_surface, [parent_surface], coverage_sources)
512
- links[published_id] = retained_surface
471
+ self.record_coverage_owner(
472
+ retained_surface,
473
+ surface,
474
+ self.source_owner(surface, surface.get("workerId")),
475
+ "surfaces",
476
+ )
477
+ _inherit_coverage_sources(retained_surface, [parent_surface], coverage_sources)
478
+ links[published_id] = retained_surface
513
479
  if self.project_worker_coverage:
514
480
  worker_surfaces: dict[tuple[str, str], dict[str, Any]] = {}
515
481
  named_surface_outputs = {
@@ -711,73 +677,19 @@ class SavedCoverageProjection:
711
677
  prospective_surfaces[id(row)] = projected
712
678
  bound = {
713
679
  (id(retained), published_id)
714
- for task, published_id, surface, _, task_source in self.legacy_surface_links
680
+ for retained, published_id, surface, _ in self.task_surface_links(prospective_tasks)
715
681
  if self.linked_surface(surface, prospective_surfaces, prospective_named) is not None
716
- for retained in self.linked_tasks(
717
- task, published_id, task_source, prospective_tasks
718
- )
719
682
  }
720
- for task, published_id, _, parent_surface, task_source in self.legacy_surface_links:
721
- for retained in self.linked_tasks(
722
- task, published_id, task_source, prospective_tasks
723
- ):
724
- key = (id(retained), published_id)
725
- if key not in bound:
726
- fallback_surfaces.append(parent_surface)
727
- bound.add(key)
683
+ for retained, published_id, _, parent_surface in self.task_surface_links(
684
+ prospective_tasks
685
+ ):
686
+ key = (id(retained), published_id)
687
+ if key not in bound:
688
+ fallback_surfaces.append(parent_surface)
689
+ bound.add(key)
728
690
  return fallback_surfaces
729
691
 
730
692
 
731
- def prepare_saved_coverage_projection(
732
- sources,
733
- parent,
734
- source_order,
735
- *,
736
- project_worker_coverage,
737
- receipt_resolver,
738
- preserve_canonical_parent=False,
739
- ):
740
- if preserve_canonical_parent:
741
- return SavedCoverageProjection(False, [], sources)
742
- # Older parent publications use worker/id identities. Reconcile those copies
743
- # against their bound sources before projecting accepted attempt provenance.
744
- projected_metadata = {
745
- id(row): ("workerId" in row, row.get("workerId"))
746
- for relative, draft, _ in sources
747
- for field in ("surfaces", "explicitExclusions", "deferred", "openQuestions")
748
- for rows in (draft["reviewState"].get(field, []),)
749
- if isinstance(rows, list)
750
- for row in rows
751
- if isinstance(row, dict)
752
- }
753
- project_worker_coverage, legacy_surface_links = _prepare_worker_coverage_recovery(
754
- sources,
755
- parent,
756
- source_order,
757
- enabled=project_worker_coverage,
758
- receipt_resolver=receipt_resolver,
759
- )
760
- for _, draft, _ in sources:
761
- for field in ("surfaces", "explicitExclusions", "deferred", "openQuestions"):
762
- rows = draft["reviewState"].get(field, [])
763
- if not isinstance(rows, list):
764
- continue
765
- for row in rows:
766
- if not isinstance(row, dict):
767
- continue
768
- present, value = projected_metadata.get(id(row), (False, None))
769
- if present:
770
- row["workerId"] = value
771
- else:
772
- row.pop("workerId", None)
773
- return SavedCoverageProjection(project_worker_coverage, legacy_surface_links, sources)
774
-
775
-
776
- def _deferred_rows(coverage: dict[str, Any]) -> list[Any]:
777
- rows = coverage.get("deferred", [])
778
- return rows if isinstance(rows, list) else []
779
-
780
-
781
693
  def _resolved_deferred_rows(draft: dict[str, Any], schema: dict[str, Any]) -> list[dict[str, Any]]:
782
694
  if draft.get("complete") is False:
783
695
  return []
@@ -786,7 +698,7 @@ def _resolved_deferred_rows(draft: dict[str, Any], schema: dict[str, Any]) -> li
786
698
  try:
787
699
  # Invalid closure metadata cannot discard the evidence it names.
788
700
  _validate_schema_node(rows, schema, "coverage.resolvedDeferred")
789
- _validate_resolved_deferred({**coverage, "deferred": _deferred_rows(coverage)})
701
+ _validate_resolved_deferred({**coverage, "deferred": _coverage_rows(coverage, "deferred")})
790
702
  except ContractError:
791
703
  return []
792
704
  return rows
@@ -855,7 +767,7 @@ def _merge_tied_parent_observations(
855
767
  output.append(copy.deepcopy(row))
856
768
  pending_ids = {
857
769
  identity
858
- for row in _deferred_rows(coverage)
770
+ for row in _coverage_rows(coverage, "deferred")
859
771
  if isinstance(row, dict)
860
772
  for identity in (row.get("id"), row.get("candidateId"))
861
773
  if isinstance(identity, str)