@cbartens/bkit 6.0.0 → 6.1.0

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/.bkit/README.md +154 -151
  2. package/.bkit/core/.agents/context.md +95 -29
  3. package/.bkit/core/.agents/docs.md +17 -15
  4. package/.bkit/core/.agents/plugins/bkit/hooks/bkit-gateguard.cjs +1 -0
  5. package/.bkit/core/.agents/plugins/bkit/hooks/bkit-guardrails.cjs +6 -5
  6. package/.bkit/core/.agents/plugins/bkit/hooks/bkit-readguard.cjs +1 -0
  7. package/.bkit/core/.agents/plugins/bkit/hooks/bkit-rules.cjs +65 -0
  8. package/.bkit/core/.agents/rules.md +108 -107
  9. package/.bkit/core/.agents/skills.md +63 -15
  10. package/.bkit/core/.bkit/README.md +154 -151
  11. package/.bkit/core/.bkit/authoring.md +714 -84
  12. package/.bkit/core/.bkit/cli.md +407 -0
  13. package/.bkit/core/.bkit/cloud.md +281 -193
  14. package/.bkit/core/.bkit/comparison.md +43 -41
  15. package/.bkit/core/.bkit/install.md +154 -84
  16. package/.bkit/core/.bkit/jsonl.md +193 -130
  17. package/.bkit/core/.bkit/pipeline.md +114 -114
  18. package/.bkit/core/.bkit/prompts.md +272 -165
  19. package/.bkit/core/.bkit/providers.md +457 -271
  20. package/.bkit/core/.bkit/router.md +69 -0
  21. package/.bkit/core/.bkit/templates.md +529 -256
  22. package/.bkit/core/.bkit/trackers.md +80 -52
  23. package/.bkit/core/.bkit/workflows.md +589 -504
  24. package/.bkit/core/.claude/hooks/bkit-gateguard.cjs +2 -2
  25. package/.bkit/core/.claude/hooks/bkit-guardrails.cjs +3 -3
  26. package/.bkit/core/.claude/hooks/bkit-preflight.sh +45 -14
  27. package/.bkit/core/.codex/hooks/bkit-guardrails.cjs +3 -3
  28. package/.bkit/core/.codex/hooks/bkit-rules.cjs +57 -0
  29. package/.bkit/core/.cursor/hooks/bkit-guardrails.cjs +7 -7
  30. package/.bkit/core/.cursor/hooks/bkit-preflight.sh +47 -12
  31. package/.bkit/core/.opencode/plugin/bkit-rules.js +89 -0
  32. package/.bkit/core/AGENTS.md +5 -73
  33. package/.bkit/core/docs/templates/bkit-audit-accessibility.md +127 -105
  34. package/.bkit/core/docs/templates/bkit-audit-adoption.md +104 -70
  35. package/.bkit/core/docs/templates/bkit-audit-agents.md +94 -72
  36. package/.bkit/core/docs/templates/bkit-audit-aio-seo.md +99 -78
  37. package/.bkit/core/docs/templates/bkit-audit-analytics.md +140 -82
  38. package/.bkit/core/docs/templates/bkit-audit-annotations.md +98 -72
  39. package/.bkit/core/docs/templates/bkit-audit-app-performance.md +121 -96
  40. package/.bkit/core/docs/templates/bkit-audit-app-store.md +157 -76
  41. package/.bkit/core/docs/templates/bkit-audit-architecture.md +113 -71
  42. package/.bkit/core/docs/templates/bkit-audit-ci-performance.md +75 -72
  43. package/.bkit/core/docs/templates/bkit-audit-config.md +122 -76
  44. package/.bkit/core/docs/templates/bkit-audit-cost.md +85 -74
  45. package/.bkit/core/docs/templates/bkit-audit-coverage.md +75 -68
  46. package/.bkit/core/docs/templates/bkit-audit-database.md +101 -70
  47. package/.bkit/core/docs/templates/bkit-audit-dead-code.md +164 -83
  48. package/.bkit/core/docs/templates/bkit-audit-deferrals.md +115 -86
  49. package/.bkit/core/docs/templates/bkit-audit-dependencies.md +264 -88
  50. package/.bkit/core/docs/templates/bkit-audit-documentation.md +118 -93
  51. package/.bkit/core/docs/templates/bkit-audit-duplication.md +139 -86
  52. package/.bkit/core/docs/templates/bkit-audit-failures.md +110 -81
  53. package/.bkit/core/docs/templates/bkit-audit-flakes.md +99 -74
  54. package/.bkit/core/docs/templates/bkit-audit-gates.md +105 -77
  55. package/.bkit/core/docs/templates/bkit-audit-issues.md +104 -80
  56. package/.bkit/core/docs/templates/bkit-audit-llm.md +131 -58
  57. package/.bkit/core/docs/templates/bkit-audit-logs.md +123 -100
  58. package/.bkit/core/docs/templates/bkit-audit-models.md +98 -53
  59. package/.bkit/core/docs/templates/bkit-audit-privacy.md +56 -52
  60. package/.bkit/core/docs/templates/bkit-audit-prompts.md +63 -54
  61. package/.bkit/core/docs/templates/bkit-audit-red-team.md +124 -68
  62. package/.bkit/core/docs/templates/bkit-audit-reliability.md +95 -70
  63. package/.bkit/core/docs/templates/bkit-audit-repo.md +169 -73
  64. package/.bkit/core/docs/templates/bkit-audit-security.md +206 -96
  65. package/.bkit/core/docs/templates/bkit-audit-slop.md +77 -70
  66. package/.bkit/core/docs/templates/bkit-audit-testing.md +162 -114
  67. package/.bkit/core/docs/templates/bkit-audit-usability.md +113 -71
  68. package/.bkit/core/docs/templates/bkit-plan.md +138 -132
  69. package/.bkit/core/engine/checks/after/auth.ts +40 -37
  70. package/.bkit/core/engine/checks/after/ci-yml.ts +65 -2
  71. package/.bkit/core/engine/checks/after/index.ts +12 -2
  72. package/.bkit/core/engine/checks/after/tools.ts +80 -33
  73. package/.bkit/core/engine/checks/before/context-fetch.ts +227 -33
  74. package/.bkit/core/engine/checks/before/env.ts +1 -1
  75. package/.bkit/core/engine/checks/before/index.ts +7 -0
  76. package/.bkit/core/engine/checks/before/repo.ts +40 -0
  77. package/.bkit/core/engine/checks/status-holes.ts +916 -123
  78. package/.bkit/core/engine/checks/tips/catalogue.ts +68 -17
  79. package/.bkit/core/engine/checks/tips/detect.ts +32 -0
  80. package/.bkit/core/engine/checks/tips/index.ts +47 -6
  81. package/.bkit/core/engine/cli.ts +238 -84
  82. package/.bkit/core/engine/commands/analysis.ts +128 -76
  83. package/.bkit/core/engine/commands/ci/ci.ts +363 -29
  84. package/.bkit/core/engine/commands/ci/pins.ts +172 -0
  85. package/.bkit/core/engine/commands/ci/push-gate.ts +223 -0
  86. package/.bkit/core/engine/commands/install/uninstall.ts +21 -27
  87. package/.bkit/core/engine/commands/install/upgrade.ts +32 -15
  88. package/.bkit/core/engine/commands/land.ts +126 -11
  89. package/.bkit/core/engine/commands/lib.ts +303 -6
  90. package/.bkit/core/engine/commands/registry.ts +6 -2
  91. package/.bkit/core/engine/commands/setup/setup.ts +1 -0
  92. package/.bkit/core/engine/commands/stats.ts +91 -35
  93. package/.bkit/core/engine/commands/workflow/branches.ts +1477 -117
  94. package/.bkit/core/engine/commands/workflow/challenge.ts +114 -39
  95. package/.bkit/core/engine/commands/workflow/completeness.ts +109 -0
  96. package/.bkit/core/engine/commands/workflow/context.ts +433 -55
  97. package/.bkit/core/engine/commands/workflow/counters.ts +244 -39
  98. package/.bkit/core/engine/commands/workflow/decisions.ts +61 -17
  99. package/.bkit/core/engine/commands/workflow/disk.ts +237 -55
  100. package/.bkit/core/engine/commands/workflow/fids.ts +19 -1
  101. package/.bkit/core/engine/commands/workflow/issues.ts +6 -0
  102. package/.bkit/core/engine/commands/workflow/ledgers.ts +458 -18
  103. package/.bkit/core/engine/commands/workflow/locks.ts +2 -0
  104. package/.bkit/core/engine/commands/workflow/plan-blocks.ts +124 -15
  105. package/.bkit/core/engine/commands/workflow/plans.ts +257 -0
  106. package/.bkit/core/engine/commands/workflow/prs.ts +12 -3
  107. package/.bkit/core/engine/commands/workflow/repo.ts +8 -0
  108. package/.bkit/core/engine/commands/workflow/roadmap.ts +56 -15
  109. package/.bkit/core/engine/commands/workflow/run-facts.ts +22 -31
  110. package/.bkit/core/engine/commands/workflow/runs.ts +652 -34
  111. package/.bkit/core/engine/commands/workflow/runtime.ts +3 -0
  112. package/.bkit/core/engine/commands/workflow/skills.ts +1 -0
  113. package/.bkit/core/engine/commands/workflow/status.ts +200 -17
  114. package/.bkit/core/engine/commands/workflow/step-table.ts +75 -33
  115. package/.bkit/core/engine/commands/workflow/steps.ts +635 -24
  116. package/.bkit/core/engine/commands/workflow/summary-findings.ts +177 -0
  117. package/.bkit/core/engine/commands/workflow/summary.ts +192 -46
  118. package/.bkit/core/engine/commands/workflow/tasks.ts +409 -0
  119. package/.bkit/core/engine/commands/workflow/test-blocks.ts +254 -0
  120. package/.bkit/core/engine/commands/workflow/tests-changed.ts +201 -0
  121. package/.bkit/core/engine/commands/workflow/tests.ts +1285 -356
  122. package/.bkit/core/engine/commands/workflow/workflows.ts +228 -43
  123. package/.bkit/core/engine/commands/workflow/worktrees.ts +389 -47
  124. package/.bkit/core/engine/install/cloud-env.ts +251 -121
  125. package/.bkit/core/engine/install/context-ci-workflow.ts +102 -0
  126. package/.bkit/core/engine/install/manifest.ts +60 -12
  127. package/.bkit/core/engine/install/modules/antigravity.ts +3 -2
  128. package/.bkit/core/engine/install/modules/cloud.ts +3 -3
  129. package/.bkit/core/engine/install/modules/codex.ts +15 -2
  130. package/.bkit/core/engine/install/modules/core.ts +956 -52
  131. package/.bkit/core/engine/install/modules/cursor.ts +6 -6
  132. package/.bkit/core/engine/install/modules/opencode.ts +16 -4
  133. package/.bkit/core/engine/install/template-notes.ts +130 -0
  134. package/.bkit/core/engine/install/version-file.ts +3 -2
  135. package/.bkit/core/engine/install/write.ts +5 -0
  136. package/.bkit/core/engine/ledgers/compact.ts +124 -0
  137. package/.bkit/core/engine/ledgers/journal.ts +291 -0
  138. package/.bkit/core/engine/ledgers/status.ts +160 -9
  139. package/.bkit/core/engine/ledgers/telemetry.ts +158 -21
  140. package/.bkit/core/engine/render/hosts.ts +114 -14
  141. package/.bkit/core/engine/shared/bkit-latest.ts +26 -4
  142. package/.bkit/core/engine/shared/dep-updater.ts +60 -0
  143. package/.bkit/core/engine/shared/egress.ts +1 -1
  144. package/.bkit/core/engine/shared/package-manager.ts +9 -0
  145. package/.bkit/core/engine/shared/settings.ts +92 -17
  146. package/.bkit/core/engine/shared/timeouts.ts +2 -0
  147. package/.bkit/core/engine/tools/cli-doc.ts +111 -0
  148. package/.bkit/core/engine/tools/grammar-density.ts +1 -1
  149. package/.bkit/core/engine/tools/instructions-sources.ts +15 -17
  150. package/.bkit/core/engine/tools/instructions.ts +94 -43
  151. package/.bkit/core/hooks/antigravity-hook.js +25 -10
  152. package/.bkit/core/hooks/gateguard-engine.js +53 -29
  153. package/.bkit/core/hooks/guardrails-shell.js +4 -4
  154. package/.bkit/core/hooks/guardrails-tiers.js +3 -3
  155. package/.bkit/core/hooks/preflight-linear.sh +9 -9
  156. package/.bkit/core/hooks/preflight-rules.sh +8 -0
  157. package/.bkit/core/hooks/readguard-engine.js +29 -10
  158. package/.bkit/core/hooks/session-rules-advisory.js +61 -0
  159. package/.bkit/core/prompts/bkit-audit-generate.md +187 -116
  160. package/.bkit/core/prompts/bkit-build-challenge-1.md +56 -37
  161. package/.bkit/core/prompts/bkit-build-challenge-2.md +65 -45
  162. package/.bkit/core/prompts/bkit-build-install-skills.md +38 -29
  163. package/.bkit/core/prompts/bkit-build-plan-convert.md +43 -32
  164. package/.bkit/core/prompts/bkit-build-plan-current.md +49 -39
  165. package/.bkit/core/prompts/bkit-build-plan-gaps-remediate.md +79 -55
  166. package/.bkit/core/prompts/bkit-build-plan-tasks.md +149 -0
  167. package/.bkit/core/prompts/bkit-build-plan-tests.md +120 -0
  168. package/.bkit/core/prompts/bkit-build-plan-verify.md +87 -50
  169. package/.bkit/core/prompts/bkit-debug-abort-handover.md +36 -35
  170. package/.bkit/core/prompts/bkit-debug-failure-diagnose.md +96 -64
  171. package/.bkit/core/prompts/bkit-debug-failure-remediate.md +54 -45
  172. package/.bkit/core/prompts/bkit-debug-failure-reproduce.md +42 -33
  173. package/.bkit/core/prompts/bkit-debug-failure-soak.md +53 -37
  174. package/.bkit/core/prompts/bkit-design-brainstorm-ideate-1.md +35 -30
  175. package/.bkit/core/prompts/bkit-design-brainstorm-ideate-2.md +34 -29
  176. package/.bkit/core/prompts/bkit-design-brainstorm-ideate-3.md +32 -28
  177. package/.bkit/core/prompts/bkit-design-generate.md +68 -52
  178. package/.bkit/core/prompts/bkit-design-organise.md +73 -35
  179. package/.bkit/core/prompts/bkit-design-review-1.md +58 -54
  180. package/.bkit/core/prompts/bkit-design-review-2.md +54 -50
  181. package/.bkit/core/prompts/bkit-design-spike.md +54 -47
  182. package/.bkit/core/prompts/bkit-design-update.md +42 -31
  183. package/.bkit/core/prompts/bkit-plan-generate.md +76 -58
  184. package/.bkit/core/prompts/bkit-plan-review-1.md +63 -49
  185. package/.bkit/core/prompts/bkit-plan-review-2.md +60 -48
  186. package/.bkit/core/prompts/bkit-plan-scope-check.md +53 -46
  187. package/.bkit/core/prompts/bkit-plan-update.md +70 -52
  188. package/.bkit/core/prompts/bkit-ship-conflict-resolve.md +82 -50
  189. package/.bkit/core/prompts/bkit-ship-deferred-sweep.md +80 -45
  190. package/.bkit/core/prompts/bkit-ship-update-docs.md +35 -29
  191. package/.bkit/core/prompts/bkit-utility-compress-markdown.md +55 -49
  192. package/.bkit/core/prompts/bkit-utility-update-decisions.md +76 -49
  193. package/.bkit/core/prompts/bkit-utility-update-deferrals.md +70 -41
  194. package/.bkit/core/prompts/bkit-utility-update-documentation.md +33 -30
  195. package/.bkit/core/prompts/bkit-utility-update-failures.md +73 -43
  196. package/.bkit/core/prompts/bkit-utility-update-knowledge.md +77 -50
  197. package/.bkit/core/prompts/bkit-utility-update-roadmap.md +77 -45
  198. package/.bkit/core/prompts/bkit-utility-update-tracker.md +144 -68
  199. package/.bkit/core/workflows/bkit-auto.md +53 -30
  200. package/.bkit/core/workflows/bkit-build.md +635 -304
  201. package/.bkit/core/workflows/bkit-debug.md +301 -148
  202. package/.bkit/core/workflows/bkit-design.md +167 -95
  203. package/.bkit/core/workflows/bkit-plan.md +172 -84
  204. package/.bkit/core/workflows/bkit-ship.md +299 -152
  205. package/.bkit/shared/.agents/plugins/bkit/hooks.json +10 -0
  206. package/.bkit/shared/.claude/bkit-cloud.md +12 -10
  207. package/.bkit/shared/.claude/settings.json +3 -0
  208. package/.bkit/shared/.codex/bkit-cloud.md +98 -0
  209. package/.bkit/shared/.codex/hooks.json +20 -0
  210. package/.bkit/shared/.cursor/bkit-cloud.md +3 -3
  211. package/.bkit/shared/.opencode/opencode.json +1 -1
  212. package/.bkit/shared/CLAUDE.md +5 -1
  213. package/.bkit/shared/GEMINI.md +4 -1
  214. package/.bkit/shared/docs/architecture.md +4 -7
  215. package/.bkit/shared/docs/data-schema.md +4 -7
  216. package/.bkit/shared/docs/deployments.md +239 -166
  217. package/.bkit/shared/docs/design.md +11 -12
  218. package/.bkit/shared/docs/noise.md +8 -7
  219. package/.bkit/shared/docs/observability.md +5 -8
  220. package/.bkit/shared/docs/security.md +35 -17
  221. package/.bkit/shared/docs/setup.md +29 -18
  222. package/.bkit/shared/docs/technology.md +3 -6
  223. package/.bkit/shared/docs/testing.md +282 -176
  224. package/.bkit/shared/gitignore +6 -2
  225. package/.bkit/templates/.claude/hooks/bkit-cloud-bootstrap.sh +15 -16
  226. package/.bkit/templates/.cursor/Dockerfile +12 -8
  227. package/.bkit/templates/.cursor/environment.json +1 -1
  228. package/.bkit/templates/.github/ISSUE_TEMPLATE/bkit-bug.yml +10 -8
  229. package/.bkit/templates/.github/ISSUE_TEMPLATE/bkit-change.yml +24 -12
  230. package/.bkit/templates/.github/ISSUE_TEMPLATE/bkit-idea.yml +3 -3
  231. package/.bkit/templates/.github/renovate.json5 +34 -6
  232. package/.bkit/templates/.github/workflows/bkit-ci.yml +53 -50
  233. package/.bkit/templates/.github/workflows/bkit-cloud.yml +13 -14
  234. package/.bkit/templates/.github/workflows/bkit-health.yml +97 -0
  235. package/.bkit/templates/.github/workflows/bkit-renovate.yml +5 -4
  236. package/.bkit/templates/.github/workflows/bkit-trivy.yml +5 -4
  237. package/.bkit/templates/.husky/pre-commit +2 -2
  238. package/.bkit/templates/.husky/pre-push +95 -35
  239. package/.bkit/templates/.prettierignore +6 -7
  240. package/.bkit/templates/.vale.ini +27 -27
  241. package/.bkit/templates/context/bkit-cloudrun.md +23 -15
  242. package/.bkit/templates/context/bkit-expo.md +70 -52
  243. package/.bkit/templates/context/bkit-github.md +93 -56
  244. package/.bkit/templates/context/bkit-inngest.md +21 -15
  245. package/.bkit/templates/context/bkit-maestro.md +22 -16
  246. package/.bkit/templates/context/bkit-playwright.md +23 -17
  247. package/.bkit/templates/context/bkit-resend.md +12 -10
  248. package/.bkit/templates/context/bkit-sentry.md +30 -20
  249. package/.bkit/templates/context/bkit-serena.md +8 -7
  250. package/.bkit/templates/context/bkit-stripe.md +14 -13
  251. package/.bkit/templates/context/bkit-supabase.md +16 -13
  252. package/.bkit/templates/context/bkit-tavily.md +14 -11
  253. package/.bkit/templates/context/bkit-vercel.md +27 -18
  254. package/.bkit/templates/docs/capabilities.md +15 -14
  255. package/.bkit/templates/scripts/ci/{check-accepted-divergences.mjs → bkit-check-accepted-divergences.mjs} +6 -3
  256. package/.bkit/templates/scripts/ci/{check-accepted-divergences.test.mjs → bkit-check-accepted-divergences.test.mjs} +3 -3
  257. package/.bkit/templates/scripts/ci/{check-capstone.mjs → bkit-check-capstone.mjs} +2 -2
  258. package/.bkit/templates/scripts/ci/{check-capstone.test.mjs → bkit-check-capstone.test.mjs} +4 -4
  259. package/.bkit/templates/scripts/ci/{check-dependency-audit.mjs → bkit-check-dependency-audit.mjs} +103 -18
  260. package/.bkit/templates/scripts/ci/{check-dependency-audit.test.mjs → bkit-check-dependency-audit.test.mjs} +31 -3
  261. package/.bkit/templates/scripts/ci/bkit-machine-lock.sh +387 -0
  262. package/.bkit/templates/scripts/ci/bkit-test-awake.mjs +75 -0
  263. package/.bkit/templates/scripts/ci/bkit-test-awake.test.mjs +160 -0
  264. package/.bkit/templates/scripts/ci/lanes/{resolve-push-base.mjs → bkit-resolve-push-base.mjs} +3 -3
  265. package/.bkit/templates/scripts/ci/lanes/{resolve-push-base.test.mjs → bkit-resolve-push-base.test.mjs} +4 -4
  266. package/.bkit/templates/scripts/cleanup/bkit-disk-prune.mjs +9 -1
  267. package/.bkit/templates/scripts/graphify/bkit-graph-drift.py +1 -1
  268. package/.bkit/templates/scripts/graphify/bkit-graph-eager.py +3 -3
  269. package/.bkit/templates/scripts/graphify/bkit-graph-embed.py +63 -0
  270. package/.bkit/templates/scripts/graphify/bkit-graph-imports.py +2 -2
  271. package/.bkit/templates/scripts/graphify/bkit-graph-pre-push.sh +69 -18
  272. package/.bkit/templates/scripts/graphify/bkit-graph-repair.py +3 -3
  273. package/.bkit/templates/scripts/graphify/bkit-graph-surface.py +1 -1
  274. package/.bkit/templates/scripts/graphify/bkit-graphify-graphml.py +1 -1
  275. package/.bkit/templates/scripts/graphify/bkit-graphify-rollup.py +197 -126
  276. package/.bkit/templates/scripts/graphify/bkit-graphify.sh +64 -41
  277. package/.bkit/templates/scripts/slop/bkit-slop-type-suppression.mjs +23 -7
  278. package/.bkit/templates/slop-scan.config.json +9 -2
  279. package/CHANGELOG.md +119 -0
  280. package/README.md +250 -76
  281. package/dist/checks/after/auth.js +36 -33
  282. package/dist/checks/after/ci-yml.js +52 -2
  283. package/dist/checks/after/index.js +12 -4
  284. package/dist/checks/after/tools.js +73 -33
  285. package/dist/checks/before/context-fetch.js +218 -33
  286. package/dist/checks/before/env.js +1 -1
  287. package/dist/checks/before/index.js +6 -2
  288. package/dist/checks/before/repo.js +35 -1
  289. package/dist/checks/status-holes.js +739 -114
  290. package/dist/checks/tips/catalogue.js +59 -17
  291. package/dist/checks/tips/detect.js +30 -0
  292. package/dist/checks/tips/index.js +48 -6
  293. package/dist/cli.js +222 -84
  294. package/dist/commands/analysis.js +77 -53
  295. package/dist/commands/ci/ci.js +302 -25
  296. package/dist/commands/ci/pins.js +142 -0
  297. package/dist/commands/ci/push-gate.js +194 -0
  298. package/dist/commands/install/uninstall.js +23 -27
  299. package/dist/commands/install/upgrade.js +21 -11
  300. package/dist/commands/land.js +126 -10
  301. package/dist/commands/lib.js +244 -5
  302. package/dist/commands/registry.js +6 -2
  303. package/dist/commands/setup/setup.js +1 -0
  304. package/dist/commands/stats.js +69 -30
  305. package/dist/commands/workflow/branches.js +1232 -111
  306. package/dist/commands/workflow/challenge.js +90 -37
  307. package/dist/commands/workflow/completeness.js +97 -0
  308. package/dist/commands/workflow/context.js +371 -51
  309. package/dist/commands/workflow/counters.js +206 -40
  310. package/dist/commands/workflow/decisions.js +60 -17
  311. package/dist/commands/workflow/disk.js +213 -55
  312. package/dist/commands/workflow/fids.js +18 -1
  313. package/dist/commands/workflow/issues.js +6 -0
  314. package/dist/commands/workflow/ledgers.js +372 -21
  315. package/dist/commands/workflow/locks.js +2 -0
  316. package/dist/commands/workflow/plan-blocks.js +78 -14
  317. package/dist/commands/workflow/plans.js +205 -0
  318. package/dist/commands/workflow/prs.js +12 -3
  319. package/dist/commands/workflow/repo.js +6 -0
  320. package/dist/commands/workflow/roadmap.js +50 -17
  321. package/dist/commands/workflow/run-facts.js +23 -28
  322. package/dist/commands/workflow/runs.js +530 -33
  323. package/dist/commands/workflow/runtime.js +3 -0
  324. package/dist/commands/workflow/skills.js +1 -0
  325. package/dist/commands/workflow/status.js +166 -19
  326. package/dist/commands/workflow/step-table.js +61 -29
  327. package/dist/commands/workflow/steps.js +542 -26
  328. package/dist/commands/workflow/summary-findings.js +117 -0
  329. package/dist/commands/workflow/summary.js +154 -41
  330. package/dist/commands/workflow/tasks.js +378 -0
  331. package/dist/commands/workflow/test-blocks.js +231 -0
  332. package/dist/commands/workflow/tests-changed.js +172 -0
  333. package/dist/commands/workflow/tests.js +1013 -321
  334. package/dist/commands/workflow/workflows.js +191 -38
  335. package/dist/commands/workflow/worktrees.js +310 -42
  336. package/dist/install/cloud-env.js +233 -99
  337. package/dist/install/context-ci-workflow.js +85 -0
  338. package/dist/install/manifest.js +57 -12
  339. package/dist/install/modules/antigravity.js +3 -2
  340. package/dist/install/modules/cloud.js +3 -3
  341. package/dist/install/modules/codex.js +12 -2
  342. package/dist/install/modules/core.js +851 -53
  343. package/dist/install/modules/cursor.js +6 -6
  344. package/dist/install/modules/opencode.js +11 -5
  345. package/dist/install/template-notes.js +116 -0
  346. package/dist/install/version-file.js +3 -2
  347. package/dist/ledgers/compact.js +87 -0
  348. package/dist/ledgers/journal.js +233 -0
  349. package/dist/ledgers/status.js +115 -5
  350. package/dist/ledgers/telemetry.js +121 -17
  351. package/dist/render/hosts.js +100 -14
  352. package/dist/shared/bkit-latest.js +26 -4
  353. package/dist/shared/dep-updater.js +49 -0
  354. package/dist/shared/egress.js +1 -1
  355. package/dist/shared/package-manager.js +6 -0
  356. package/dist/shared/settings.js +59 -10
  357. package/dist/shared/timeouts.js +2 -0
  358. package/dist/tools/cli-doc.js +97 -0
  359. package/dist/tools/grammar-density.js +1 -1
  360. package/dist/tools/instructions-sources.js +15 -16
  361. package/dist/tools/instructions.js +83 -39
  362. package/package.json +58 -42
  363. package/.bkit/core/.bkit/lite.md +0 -73
  364. package/.bkit/core/engine/commands/workflow/workstreams.ts +0 -172
  365. package/.bkit/core/prompts/bkit-build-plan-execute.md +0 -124
  366. package/.bkit/templates/scripts/ci/bkit-local-stack-lock.sh +0 -194
  367. package/dist/commands/workflow/workstreams.js +0 -149
  368. /package/.bkit/templates/.vale/styles/{House → Bkit}/Filler.yml +0 -0
  369. /package/.bkit/templates/.vale/styles/{House → Bkit}/Hedging.yml +0 -0
  370. /package/.bkit/templates/.vale/styles/{House → Bkit}/LLMSlop.yml +0 -0
  371. /package/.bkit/templates/.vale/styles/{House → Bkit}/Verbose.yml +0 -0
  372. /package/.bkit/templates/scripts/ci/{accepted-advisories.json → bkit-accepted-advisories.json} +0 -0
  373. /package/.bkit/templates/scripts/ci/{accepted-divergences.json → bkit-accepted-divergences.json} +0 -0
  374. /package/.bkit/templates/scripts/launchd/{launchd.env.example → bkit-launchd.env.example} +0 -0
  375. /package/.bkit/templates/scripts/launchd/{ai.bkit.launchd.plist → bkit-launchd.plist} +0 -0
@@ -8,35 +8,42 @@
8
8
  // ran (not executable / not found), so it is not recorded as a failing test.
9
9
  // The failure count comes from the JUnit reports the gate's runners write into
10
10
  // `{log}.reports/` (`BKIT_TEST_REPORT_DIR`), never from reading the log.
11
- //
12
- // bkit tests red / green — test-first evidence for build tasks. Both run one test
13
- // file through the consumer's `bkit:test:file` script and judge its JUnit report,
14
- // never its exit code alone: a misspelled path, a syntax error and an import of
15
- // unwritten code all exit non-zero exactly like a real failure. A red counts only
16
- // when the NAMED test ran and failed; green only when it ran and passed.
11
+ // bkit tests red / green — test-first evidence for build tasks. `red` runs every TEST FIRST
12
+ // test of one group's open tasks after the tests step wrote them and before any task code
13
+ // exists: one run per test file through the consumer's `bkit:test:file` script, each test
14
+ // judged by the JUnit report, never the exit code alone (a misspelled path, a syntax error
15
+ // and an import of unwritten code all exit non-zero exactly like a real failure). A red is
16
+ // the NAMED test failing, or its file failing to load; `green` reads the group's red row and
17
+ // needs the named test to run and pass.
17
18
  import { spawnSync } from "node:child_process";
19
+ import { createHash } from "node:crypto";
18
20
  import * as fs from "node:fs";
19
21
  import * as os from "node:os";
20
22
  import * as path from "node:path";
21
- import { BKIT_TEST_FILE_SCRIPT } from "../../install/manifest.js";
23
+ import { BKIT_LINT_FILE_SCRIPT, BKIT_TEST_FILE_SCRIPT } from "../../install/manifest.js";
22
24
  import { clampLogPath } from "../../ledgers/clamp-log.js";
23
- import { CommandError, EXIT, git, runGit } from "../lib.js";
25
+ import { appendLine, statusTimestamp, validateCiSelection, testRunProblem, } from "../../ledgers/status.js";
26
+ import { classifyLockExit, CommandError, EXIT, git, runGit, testsLockHolder, wholeNumber, } from "../lib.js";
24
27
  import { parseJson } from "../../shared/json.js";
25
28
  import { readPackageJson } from "../../shared/package-json.js";
26
- import { COULD_NOT_RUN_EXIT_CODES, scriptCommand } from "../../shared/package-manager.js";
29
+ import { COULD_NOT_RUN_EXIT_CODES, scriptCommand, testCommand, } from "../../shared/package-manager.js";
27
30
  import { CONFIG_DEFAULTS, readBkitConfig } from "../../shared/settings.js";
28
- import { FILE_FLAG, GROUP_FLAG, WORKFLOW_FLAG, positiveInt, readStatusRows, statusFile, str, } from "./status.js";
29
- import { fenceNeverClosed, parsePlanBlocks, reuseInventory, } from "./plan-blocks.js";
31
+ import { FILE_FLAG, GROUP_FLAG, WORKFLOW_FLAG, positiveInt, readStatusRows, readRuns, statusFile, str, } from "./status.js";
32
+ import { NO_MARKERS_REASON, derivedTestMatrix, fenceNeverClosed, parsePlanBlocks, reuseInventory, supersessionInventory, } from "./plan-blocks.js";
30
33
  import { writeStepRow } from "./steps.js";
31
34
  import { appendRecord, clampFile } from "./context.js";
35
+ import { testsChangedVerb } from "./tests-changed.js";
32
36
  /** Exit code: no candidate gate is declared in package.json. */
33
37
  export const EXIT_NO_GATE = 3;
34
38
  /** Exit code: the gate could not run (exit 126 / 127, or the package runner is missing). */
35
39
  export const EXIT_COULD_NOT_RUN = 4;
36
40
  /** Exit code: --artifact could not be written, trimmed or recorded. */
37
41
  export const EXIT_ARTIFACT_STEP = 5;
42
+ /** The status row type `tests run --file` appends, one per run. */
43
+ export const TEST_RUN_ROW = "test-run";
38
44
  /** The env var naming the folder every runner a gate calls writes its JUnit XML into. */
39
45
  export const REPORT_DIR_ENV = "BKIT_TEST_REPORT_DIR";
46
+ export { classifyLockExit } from "../lib.js";
40
47
  const NO_REPORT_HINT = `no JUnit report in $${REPORT_DIR_ENV} — failures unknown; turn on each test runner's JUnit ` +
41
48
  `reporter in the gate and point its output into $${REPORT_DIR_ENV} ` +
42
49
  "(.bkit/workflows.md § Local gate scripts)";
@@ -67,7 +74,8 @@ export const gateScope = (gate) => scriptCommand(gate).join(" ");
67
74
  export function runToLog(argv, cwd, log, env) {
68
75
  fs.mkdirSync(path.dirname(log), { recursive: true });
69
76
  const fd = fs.openSync(log, "w");
70
- const res = spawnSync(argv[0], argv.slice(1), {
77
+ const protectedArgv = testCommand(argv);
78
+ const res = spawnSync(protectedArgv[0], protectedArgv.slice(1), {
71
79
  cwd,
72
80
  stdio: ["ignore", fd, fd],
73
81
  env: env === undefined ? process.env : { ...process.env, ...env },
@@ -102,13 +110,286 @@ const tailLines = (file, n) => fs
102
110
  .replace(/\r?\n$/, "")
103
111
  .split(/\r?\n/)
104
112
  .slice(-n);
113
+ /**
114
+ * Append one `test-run` row to `file`. `run` numbers this step's test-run rows in the
115
+ * workflow's active run (since its last workflow-started row), this one included, so a
116
+ * gate re-run under the same attempt still shows.
117
+ */
118
+ function appendTestRun(file, r) {
119
+ const rows = readStatusRows(file);
120
+ let start = -1;
121
+ rows.forEach((x, i) => {
122
+ if (x.type === "workflow-started" && x.workflow === r.workflow)
123
+ start = i;
124
+ });
125
+ const run = rows
126
+ .slice(start + 1)
127
+ .filter((x) => x.type === TEST_RUN_ROW && x.workflow === r.workflow && x.step === r.step)
128
+ .length + 1;
129
+ const row = {
130
+ type: TEST_RUN_ROW,
131
+ workflow: r.workflow,
132
+ at: statusTimestamp(),
133
+ step: r.step,
134
+ ...(r.attempt === undefined ? {} : { attempt: r.attempt }),
135
+ run,
136
+ verdict: r.verdict,
137
+ exitCode: r.exitCode,
138
+ failures: r.failures,
139
+ scope: r.scope,
140
+ log: r.log,
141
+ ...(r.artifact === undefined ? {} : { artifact: r.artifact }),
142
+ ...(r.source === undefined ? {} : { source: r.source }),
143
+ ...r.evidence,
144
+ };
145
+ const problem = testRunProblem(row);
146
+ if (problem !== null)
147
+ throw new CommandError(EXIT.USAGE, problem);
148
+ fs.appendFileSync(file, appendLine(row));
149
+ return row;
150
+ }
105
151
  // ---------------------------------------------------------------------------
106
152
  // Test-first: JUnit reading, plan `Test first:` lines, red / green judgement
107
153
  // ---------------------------------------------------------------------------
108
154
  /** The env var naming the JUnit report path `bkit:test:file` must write. */
109
155
  export const REPORT_ENV = "BKIT_TEST_REPORT";
110
- /** The status row step a recorded red writes. */
111
- export const RED_STEP = "build-task-red";
156
+ /** The status row step a group's red writes: one row per `tests red` run, a state and blob per planned test. */
157
+ export const RED_STEP = "build-tests-red";
158
+ /**
159
+ * The states that count as a red: the test failed, its file did not load, the tests step
160
+ * vouched for its pass, or it is an existing test updated and passing, whose diff the
161
+ * verifier judges (it may add expectations, never remove or loosen one).
162
+ */
163
+ export const RED_PROVEN = new Set([
164
+ "red",
165
+ "red-not-loaded",
166
+ "passed-accepted",
167
+ "updated",
168
+ ]);
169
+ /** The `build-tests-red` rows of `workflow` in status.jsonl, in file order; `group` narrows. */
170
+ function redRows(file, workflow, group) {
171
+ if (!fs.existsSync(file))
172
+ return [];
173
+ return readStatusRows(file).filter((r) => r.type === "step-done" &&
174
+ r.workflow === workflow &&
175
+ r.step === RED_STEP &&
176
+ typeof r.group === "number" &&
177
+ (group === undefined || r.group === group));
178
+ }
179
+ /** A red row's `tests`, as written. */
180
+ export const redTestsOf = (row) => Array.isArray(row.tests) ? row.tests : [];
181
+ /** The key a planned test is looked up by: task numbers are unique across the plan. */
182
+ export const redKey = (task, test, name) => JSON.stringify([task, test, name]);
183
+ /** The number this group's next red row carries: its rows so far, plus one. */
184
+ function redAttempt(file, workflow, group) {
185
+ if (!fs.existsSync(file))
186
+ return 1;
187
+ return (readStatusRows(file).filter((r) => {
188
+ const row = r;
189
+ return (row.type === "step-done" &&
190
+ row.workflow === workflow &&
191
+ row.step === RED_STEP &&
192
+ row.group === group);
193
+ }).length + 1);
194
+ }
195
+ /**
196
+ * Every planned test the red rows recorded, keyed by task, file and name. A later row's entry
197
+ * wins, so a retry or a later task of the group overrides only the tests it ran, except that a
198
+ * proven red is never replaced by an unproven result for the same test lines. `group` narrows
199
+ * to one group.
200
+ */
201
+ export function redEntries(file, workflow, group) {
202
+ const out = new Map();
203
+ for (const row of redRows(file, workflow, group))
204
+ for (const t of redTestsOf(row)) {
205
+ const key = redKey(t.task, t.test, t.testName);
206
+ const earlier = out.get(key);
207
+ const keepsProof = earlier !== undefined &&
208
+ RED_PROVEN.has(earlier.state) &&
209
+ !RED_PROVEN.has(t.state) &&
210
+ typeof earlier.block === "string" &&
211
+ earlier.block === t.block;
212
+ if (!keepsProof)
213
+ out.set(key, t);
214
+ }
215
+ return out;
216
+ }
217
+ /**
218
+ * The planned tests of `group` a code step changed since their red: a test whose own lines
219
+ * (`testBlock`) no longer hash to the recorded block. A row with no block (written before
220
+ * per-test locking, or when no line carried the name) derives the block from the recorded
221
+ * blob; when that holds no block either, the whole file's blob is compared. Other edits to a
222
+ * test file are free.
223
+ */
224
+ export function touchedTests(top, file, workflow, group) {
225
+ const touched = [];
226
+ const texts = new Map();
227
+ const textOf = (test) => {
228
+ if (!texts.has(test)) {
229
+ const abs = path.join(top, test);
230
+ texts.set(test, fs.existsSync(abs) ? fs.readFileSync(abs, "utf-8") : null);
231
+ }
232
+ return texts.get(test);
233
+ };
234
+ for (const t of redEntries(file, workflow, group).values()) {
235
+ let block = t.block ?? null;
236
+ if (block === null)
237
+ block = blockHash(blobText(top, t.blob), t.testName);
238
+ if (block === null) {
239
+ if (git(top, ["hash-object", "--", t.test]) !== t.blob)
240
+ touched.push({ test: t.test, name: t.testName });
241
+ continue;
242
+ }
243
+ if (blockHash(textOf(t.test), t.testName) !== block)
244
+ touched.push({ test: t.test, name: t.testName });
245
+ }
246
+ return touched;
247
+ }
248
+ /** The text a recorded blob holds, untrimmed; null when the object store lacks it. */
249
+ function blobText(top, blob) {
250
+ if (blob === null)
251
+ return null;
252
+ const res = spawnSync("git", ["cat-file", "-p", blob], { cwd: top, encoding: "utf-8" });
253
+ return res.status === 0 ? res.stdout : null;
254
+ }
255
+ /** Leading whitespace width, a tab counting as one column. */
256
+ const indentOf = (line) => line.length - line.trimStart().length;
257
+ /** A line that only closes the block opened at its own indent. */
258
+ const CLOSER = /^(?:[)\]}]|end\b)/;
259
+ const escapeRegExp = (s) => s.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
260
+ /** A comment line: a name in it is prose, not the test. */
261
+ const COMMENT = /^(?:\/\/|\/\*|\*|#|--|<!--)/;
262
+ /** A line opening a suite (`describe`, `context`, `suite`, a class), not a test. */
263
+ const SUITE = /^(?:[\w$]+\.)?(?:describe|context|suite|class)\b/;
264
+ /**
265
+ * The first line `matches` that is no comment and opens no suite; else the first matching
266
+ * suite line, so a suite that alone carries the name still yields a block; else -1.
267
+ */
268
+ function testStart(lines, matches) {
269
+ let suite = -1;
270
+ for (let i = 0; i < lines.length; i++) {
271
+ const line = lines[i].trimStart();
272
+ if (!matches(lines[i]) || COMMENT.test(line))
273
+ continue;
274
+ if (!SUITE.test(line))
275
+ return i;
276
+ if (suite < 0)
277
+ suite = i;
278
+ }
279
+ return suite;
280
+ }
281
+ /**
282
+ * The lines of the test named `name` in `text`, or null when no line names it. The test
283
+ * starts on the first line naming it as a quoted string (else as a whole word) that is no
284
+ * comment and opens no suite, or on the line before when the name opens its line and that
285
+ * line ends with `(`; it runs through every deeper-indented line after the start, and one
286
+ * closing line (`}`, `)`, `]`, `end`) at the start's indent. Framework-agnostic: it needs
287
+ * only a name and indentation.
288
+ */
289
+ export function testBlock(text, name) {
290
+ if (text === null)
291
+ return null;
292
+ const span = testSpan(text, name);
293
+ return span === null
294
+ ? null
295
+ : text
296
+ .split("\n")
297
+ .slice(span.start - 1, span.end)
298
+ .join("\n");
299
+ }
300
+ /**
301
+ * The 1-based first and last line of the test named `name` in `text` (the lines
302
+ * `testBlock` returns), or null when no line names it.
303
+ */
304
+ export function testSpan(text, name) {
305
+ const lines = text.split("\n");
306
+ const quoted = [`"${name}"`, `'${name}'`, `\`${name}\``];
307
+ let at = testStart(lines, (l) => quoted.some((q) => l.includes(q)));
308
+ if (at < 0) {
309
+ const word = new RegExp(`(^|[^\\w])${escapeRegExp(name)}([^\\w]|$)`);
310
+ at = testStart(lines, (l) => word.test(l));
311
+ }
312
+ if (at < 0) {
313
+ // A suite path (`suite > test`, as a JUnit report names it): the last segment is the test.
314
+ const last = name.split(" > ").pop();
315
+ return last === name ? null : testSpan(text, last);
316
+ }
317
+ let start = at;
318
+ while (start > 0 &&
319
+ /^["'`]/.test(lines[start].trimStart()) &&
320
+ /\($/.test(lines[start - 1].trimEnd()))
321
+ start -= 1;
322
+ const base = indentOf(lines[start]);
323
+ let end = start;
324
+ for (let i = start + 1; i < lines.length; i++) {
325
+ const line = lines[i];
326
+ if (line.trim() === "")
327
+ continue;
328
+ if (indentOf(line) > base) {
329
+ end = i;
330
+ continue;
331
+ }
332
+ if (indentOf(line) === base && CLOSER.test(line.trimStart()))
333
+ end = i;
334
+ break;
335
+ }
336
+ return { start: start + 1, end: end + 1 };
337
+ }
338
+ /**
339
+ * The line diff of a test's own lines, `before` to `after`: unified lines (` `, `-`, `+`)
340
+ * over a longest common subsequence, and the counts of lines removed and added. A change
341
+ * that removes no line cannot have dropped an expectation; it can still have disabled one,
342
+ * which only a read of the added lines tells.
343
+ */
344
+ export function lineDiff(before, after) {
345
+ const a = before.split("\n");
346
+ const b = after.split("\n");
347
+ const lcs = Array.from({ length: a.length + 1 }, () => new Array(b.length + 1).fill(0));
348
+ for (let i = a.length - 1; i >= 0; i--)
349
+ for (let j = b.length - 1; j >= 0; j--)
350
+ lcs[i][j] =
351
+ a[i] === b[j] ? lcs[i + 1][j + 1] + 1 : Math.max(lcs[i + 1][j], lcs[i][j + 1]);
352
+ const out = [];
353
+ let removed = 0;
354
+ let added = 0;
355
+ let i = 0;
356
+ let j = 0;
357
+ while (i < a.length || j < b.length) {
358
+ if (i < a.length && j < b.length && a[i] === b[j]) {
359
+ out.push(` ${a[i]}`);
360
+ i++;
361
+ j++;
362
+ }
363
+ else if (i < a.length && (j >= b.length || lcs[i + 1][j] >= lcs[i][j + 1])) {
364
+ out.push(`-${a[i]}`);
365
+ removed++;
366
+ i++;
367
+ }
368
+ else {
369
+ out.push(`+${b[j]}`);
370
+ added++;
371
+ j++;
372
+ }
373
+ }
374
+ return { text: out.join("\n"), removed, added };
375
+ }
376
+ /** The sha-1 of a test's own lines (`testBlock`), or null when `text` holds no such test. */
377
+ export function blockHash(text, name) {
378
+ const block = testBlock(text, name);
379
+ return block === null ? null : createHash("sha1").update(block).digest("hex");
380
+ }
381
+ /** The commit the group started at: its `build-group-start` row's `parentSha`. */
382
+ function groupStartSha(file, workflow, group) {
383
+ if (!fs.existsSync(file))
384
+ return undefined;
385
+ const row = readStatusRows(file)
386
+ .filter((r) => r.type === "step-done" &&
387
+ r.workflow === workflow &&
388
+ r.step === "build-group-start" &&
389
+ r.group === group)
390
+ .at(-1);
391
+ return typeof row?.parentSha === "string" ? row.parentSha : undefined;
392
+ }
112
393
  const NO_TEST_FILE_HINT = `declare "${BKIT_TEST_FILE_SCRIPT}" in package.json: it runs the one test file passed as its ` +
113
394
  `argument and writes a JUnit report to $${REPORT_ENV} ` +
114
395
  "(.bkit/workflows.md § Local gate scripts)";
@@ -132,18 +413,21 @@ function attr(attrs, name) {
132
413
  const m = new RegExp(String.raw `\s${name}\s*=\s*(?:"([^"]*)"|'([^']*)')`).exec(attrs);
133
414
  return m ? decodeXml(m[1] ?? m[2] ?? "") : undefined;
134
415
  }
135
- /** Every `<testcase>` in a JUnit report: its name, outcome and first failure message. */
416
+ /** CDATA text as escaped character data, so a tag inside it never ends an element early. */
417
+ const escapeCdata = (xml) => xml.replace(/<!\[CDATA\[([\s\S]*?)\]\]>/g, (_, text) => text.replace(/&/g, "&amp;").replace(/</g, "&lt;").replace(/>/g, "&gt;"));
418
+ /** Every `<testcase>` in a JUnit report: its name, outcome, first failure message and detail. */
136
419
  export function parseJunit(xml) {
137
- const body = xml.replace(/<!\[CDATA\[[\s\S]*?\]\]>/g, "").replace(/<!--[\s\S]*?-->/g, "");
420
+ const body = escapeCdata(xml).replace(/<!--[\s\S]*?-->/g, "");
138
421
  const cases = [];
139
422
  const testcase = new RegExp(String.raw `<testcase${ATTRS}\s*(?:\/>|>([\s\S]*?)<\/testcase>)`, "g");
140
- const outcome = new RegExp(String.raw `<(failure|error|skipped)${ATTRS}`);
423
+ const outcome = new RegExp(String.raw `<(failure|error|skipped)${ATTRS}\s*(?:\/>|>([\s\S]*?)<\/\1>)`);
141
424
  for (const m of body.matchAll(testcase)) {
142
425
  const child = outcome.exec(m[2] ?? "");
143
426
  cases.push({
144
427
  name: attr(m[1] ?? "", "name") ?? "",
145
428
  state: child ? child[1] : "passed",
146
429
  message: child ? (attr(child[2] ?? "", "message") ?? "") : "",
430
+ detail: child ? decodeXml((child[3] ?? "").replace(/<[^>]*>/g, "")).trim() : "",
147
431
  });
148
432
  }
149
433
  return cases;
@@ -156,29 +440,40 @@ const caseNames = (cases) => cases.length === 0
156
440
  .slice(0, 5)
157
441
  .map((c) => `"${c.name}"`)
158
442
  .join(", ")}${cases.length > 5 ? ", …" : ""}`;
159
- /** Why a run is not a valid red for `want` (kind + reason), or null when it is one. */
160
- export function judgeRed(exitCode, cases, want) {
443
+ /** The stem a load error names: the test file's base name without its extension. */
444
+ const fileStem = (file) => path.posix.basename(file).replace(/\.[^.]*$/, "");
445
+ /**
446
+ * How `want` stood in a red run of `file`, from its JUnit report: `red` (the named test
447
+ * failed or errored), `red-not-loaded` (the file ran no test, or the only cases are failures
448
+ * named after the file itself: a load error, which an import of unwritten code is),
449
+ * `vacuous` (the named test passed, so it proves nothing before the task's code), `missing`
450
+ * (it did not run, or was skipped) or `no-report`.
451
+ */
452
+ export function judgeRed(cases, want, file) {
161
453
  if (cases === null)
162
454
  return {
163
- kind: "no-report",
164
- reason: `no JUnit report at $${REPORT_ENV} — ${BKIT_TEST_FILE_SCRIPT} must write one`,
455
+ state: "no-report",
456
+ detail: `no JUnit report at $${REPORT_ENV} — ${BKIT_TEST_FILE_SCRIPT} must write one`,
165
457
  };
166
458
  const named = cases.filter((c) => isNamedCase(c.name, want));
167
- if (named.length === 0)
168
- return { kind: "not-run", reason: `the named test "${want}" did not run; ${caseNames(cases)}` };
459
+ if (named.length === 0) {
460
+ const stem = fileStem(file);
461
+ if (cases.length === 0 || cases.every((c) => c.state !== "passed" && c.name.includes(stem)))
462
+ return {
463
+ state: "red-not-loaded",
464
+ detail: `\`${file}\` did not load${cases[0]?.message ? `: ${cases[0].message}` : ""}`,
465
+ };
466
+ return { state: "missing", detail: `"${want}" did not run; ${caseNames(cases)}` };
467
+ }
169
468
  if (named.some((c) => c.state === "passed"))
170
469
  return {
171
- kind: "passed",
172
- reason: `"${want}" passed — a red must fail before the task's code exists`,
470
+ state: "vacuous",
471
+ detail: `"${want}" passes at its red, so it proves nothing`,
173
472
  };
174
473
  if (named.some((c) => c.state === "skipped"))
175
- return { kind: "skipped", reason: `"${want}" was skipped, not run` };
176
- if (exitCode === 0)
177
- return {
178
- kind: "exit-mismatch",
179
- reason: `"${want}" failed in the report but the script exited 0`,
180
- };
181
- return null;
474
+ return { state: "missing", detail: `"${want}" was skipped, not run` };
475
+ const failed = named.find((c) => c.state !== "passed");
476
+ return { state: "red", detail: `${failed.state}${failed.message ? `: ${failed.message}` : ""}` };
182
477
  }
183
478
  /** Why a run is not green for `want`, or null when every case of the named test passed. */
184
479
  export function judgeGreen(cases, want) {
@@ -192,16 +487,37 @@ export function judgeGreen(cases, want) {
192
487
  ? null
193
488
  : `"${want}" ${bad.state}${bad.message ? `: ${bad.message}` : ""}`;
194
489
  }
195
- /** The task field naming a task's tests, and the one recording an accepted test-order gap. */
490
+ /** The task field naming a task's tests, and the one recording an accepted missing red. */
196
491
  export const TEST_FIRST = "**TEST FIRST:**";
197
492
  export const TEST_EXCEPTION = "**TEST EXCEPTION:**";
198
- /** Why `tests green` refuses a plan with no group and task blocks. */
199
- export const NO_MARKERS_REASON = "this plan has no task markers; run /bkit-build again to convert it";
200
493
  /** The plan caps `package.json` `bkit.workflows.tasks` sets for the checkout `cwd` sits in. */
201
494
  export const planCaps = (cwd) => readBkitConfig(toplevel(cwd)).tasks;
202
495
  /** The caps as the plan-check report and help state them. */
203
496
  export const capsText = (c) => `${c.maxPerGroup} tasks and ${c.maxTestsPerGroup} TEST FIRST tests per group; ${c.maxTestsPerTask} tests across ${c.maxTestFilesPerTask} test files per task`;
204
497
  /** A task block's TEST FIRST read as one `TestFirst`; a TEST EXCEPTION with no TEST FIRST is its `n/a`. */
498
+ /**
499
+ * Planned tests of open tasks whose name a test in their file already carries: the tests
500
+ * step cannot write a new test under that name, so it either updates the existing one or
501
+ * finds it passing. Reported only — the plan names the update, or a new name.
502
+ */
503
+ function existingTestNames(text, top) {
504
+ const out = [];
505
+ for (const t of parsePlanBlocks(text).tasks) {
506
+ if (t.done)
507
+ continue;
508
+ const s = testFirstOf(t);
509
+ if (s.kind !== "test")
510
+ continue;
511
+ for (const x of s.tests) {
512
+ const abs = path.join(top, x.test);
513
+ if (!fs.existsSync(abs))
514
+ continue;
515
+ if (testBlock(fs.readFileSync(abs, "utf-8"), x.name) !== null)
516
+ out.push({ line: t.testFirst?.line ?? t.line, task: t.task, test: x.test, name: x.name });
517
+ }
518
+ }
519
+ return out;
520
+ }
205
521
  function testFirstOf(t) {
206
522
  const { task, testFirst: tf, testException: exc } = t;
207
523
  const plain = (tests) => tests.map(({ test, name }) => ({ test, name }));
@@ -220,7 +536,7 @@ function testFirstOf(t) {
220
536
  * Each task block's TEST FIRST field (`plan-blocks.ts`): one test per sub-bullet (first
221
537
  * backticked span = file, second = test name), `n/a — {reason}`, missing, or malformed
222
538
  * (an entry with fewer than two spans, or no entry). A TEST EXCEPTION field names, in
223
- * the same entry form, the tests whose test-order gaps it accepts. `group` narrows to
539
+ * the same entry form, the tests whose missing reds it accepts. `group` narrows to
224
540
  * one group's tasks.
225
541
  */
226
542
  export function readTestFirst(plan, group) {
@@ -246,7 +562,8 @@ const kb1 = (bytes) => Math.round((bytes / 1024) * 10) / 10;
246
562
  * task-like text outside every block, a task without DONE WHEN or without TEST FIRST and
247
563
  * TEST EXCEPTION, a malformed TEST FIRST, a DEPENDS ON naming a missing task or one in a
248
564
  * later group, a group or task over a cap in `caps`, a CREATE file with no NEW Reuse
249
- * Inventory row.
565
+ * Inventory row, a `Derived Test Matrix` row naming no task / an undefined task / two
566
+ * tasks or a test-bearing task no row names, and a DELETE file with no Supersession row.
250
567
  */
251
568
  export function checkPlanText(text, caps = CONFIG_DEFAULTS.tasks) {
252
569
  const blocks = parsePlanBlocks(text);
@@ -320,6 +637,61 @@ export function checkPlanText(text, caps = CONFIG_DEFAULTS.tasks) {
320
637
  message: `TASK ${t.task}: CREATE in \`${c.file}\` has no NEW row naming it in the Reuse Inventory's File column`,
321
638
  });
322
639
  }
640
+ // The matrix maps each row to one task and each test-bearing task to a row. A plan with no
641
+ // matrix section yields no problem: the refusal is on a row, and issue-form plans carry none.
642
+ const matrix = derivedTestMatrix(text);
643
+ if (matrix !== null) {
644
+ if (matrix.taskColumn === null)
645
+ problems.push({
646
+ line: matrix.line,
647
+ kind: "matrix",
648
+ message: "the Derived Test Matrix header has no `Task` column; add one naming the task each row's test belongs to",
649
+ });
650
+ else {
651
+ const mapped = new Set();
652
+ for (const row of matrix.rows) {
653
+ const named = row.tasks.map((n) => `TASK ${n}`);
654
+ if (row.tasks.length === 0)
655
+ problems.push({
656
+ line: row.number,
657
+ kind: "matrix",
658
+ message: `Derived Test Matrix row maps to no task: name one in its \`Task\` cell`,
659
+ });
660
+ else if (row.tasks.length > 1)
661
+ problems.push({
662
+ line: row.number,
663
+ kind: "matrix",
664
+ message: `Derived Test Matrix row maps to ${named.join(" and ")}; name exactly one task`,
665
+ });
666
+ else {
667
+ const n = row.tasks[0];
668
+ if (!byTask.has(n))
669
+ problems.push({
670
+ line: row.number,
671
+ kind: "matrix",
672
+ message: `Derived Test Matrix row maps to TASK ${n}, which the plan does not define`,
673
+ });
674
+ mapped.add(n);
675
+ }
676
+ }
677
+ for (const t of blocks.tasks)
678
+ if (specs.get(t.task).kind === "test" && !mapped.has(t.task))
679
+ problems.push({
680
+ line: t.line,
681
+ kind: "matrix",
682
+ message: `TASK ${t.task} names TEST FIRST tests but no Derived Test Matrix row maps to it`,
683
+ });
684
+ }
685
+ }
686
+ const superseded = new Set((supersessionInventory(text) ?? []).flatMap((r) => r.files));
687
+ for (const t of blocks.tasks)
688
+ for (const d of t.delete)
689
+ if (!superseded.has(path.posix.normalize(d.file)))
690
+ problems.push({
691
+ line: d.line,
692
+ kind: "supersession",
693
+ message: `TASK ${t.task}: DELETE in \`${d.file}\` has no row naming it in the Supersession Inventory`,
694
+ });
323
695
  const groups = blocks.groups.map((g) => {
324
696
  const tests = sizes.filter((s) => s.group === g.group).reduce((n, s) => n + s.tests, 0);
325
697
  const bytes = Buffer.byteLength(lines.slice(g.line - 1, g.end).join("\n"));
@@ -475,28 +847,6 @@ export function planExistence(text, root) {
475
847
  }
476
848
  return out.sort((a, b) => a.line - b.line);
477
849
  }
478
- /** True when `after` keeps every non-blank line of `before`, in order, ignoring whitespace: lines were only added. */
479
- export function onlyAddsLines(before, after) {
480
- const norm = (text) => text
481
- .split("\n")
482
- .map((l) => l.replace(/\s+/g, ""))
483
- .filter(Boolean);
484
- const want = norm(before);
485
- let kept = 0;
486
- for (const line of norm(after))
487
- if (kept < want.length && line === want[kept])
488
- kept++;
489
- return kept === want.length;
490
- }
491
- /** `test` as a repo-relative path inside `top`; usage error when absolute, outside, or absent. */
492
- function repoTestPath(top, test) {
493
- const rel = path.relative(top, path.resolve(top, test));
494
- if (path.isAbsolute(test) || rel.startsWith("..") || rel === "")
495
- throw new CommandError(EXIT.USAGE, `--test must be a path inside the repo, got "${test}"`);
496
- if (!fs.statSync(path.join(top, rel), { throwIfNoEntry: false })?.isFile())
497
- throw new CommandError(EXIT.USAGE, `--test ${rel} is not a file`);
498
- return rel.split(path.sep).join("/");
499
- }
500
850
  /** Run one test file through `bkit:test:file`; the report is read and removed. */
501
851
  function runTestFile(top, test, log) {
502
852
  const dir = fs.mkdtempSync(path.join(os.tmpdir(), "bkit-test-report-"));
@@ -509,54 +859,56 @@ function runTestFile(top, test, log) {
509
859
  return { exitCode, cases };
510
860
  }
511
861
  const couldNotRunMessage = (exitCode) => `${gateScope(BKIT_TEST_FILE_SCRIPT)} could not run (exit ${exitCode}: ${exitCode === 126 ? "not executable" : "command not found"}) — no test executed`;
512
- /** The copy of the test file a red keeps beside its log. */
513
- export const snapshotPath = (log) => `${log.replace(/\.md$/, "")}.snapshot`;
514
862
  const toplevel = (cwd) => git(cwd, ["rev-parse", "--show-toplevel"]) ?? cwd;
515
863
  /** A fence longer than any backtick run in `text`. */
516
864
  const fenceFor = (text) => "`".repeat(Math.max(3, ...[...text.matchAll(/`+/g)].map((m) => m[0].length + 1)));
517
- /** Gaps about when a test was seen failing; no edit made after the task's code can close one. */
518
- export const TEST_ORDER_GAPS = new Set([
519
- "no-red",
520
- "late-red",
521
- "red-mismatch",
522
- "red-evidence-missing",
523
- "test-changed",
524
- ]);
865
+ /**
866
+ * Every gap the audit emits, and the verifier's `Fixable` for it: `null` = the
867
+ * answer needs a diff read, which only the verifier can make. A test with no proven red
868
+ * is no gap: the audit lists it as unproven, and the owner answers every unproven test
869
+ * once, at the end of the build.
870
+ */
871
+ const GAP_FIXABLE = {
872
+ "not-green": true,
873
+ "delete-still-referenced": null,
874
+ "no-test-first": false,
875
+ "test-first-malformed": false,
876
+ "test-first-unread": false,
877
+ "exception-refused": false,
878
+ };
879
+ /** One gap, with the `fixable` its kind settles and the ready-to-append log line. */
880
+ function gapOf(task, kind, detail, test) {
881
+ const fixable = GAP_FIXABLE[kind];
882
+ const subject = test === undefined ? "" : `\`${test.file}\` \`${test.name}\` — `;
883
+ return {
884
+ task,
885
+ kind,
886
+ detail,
887
+ fixable,
888
+ logLine: `${task === null ? "Plan" : `TASK ${task}`}: ${subject}${kind} — Fixable: ${fixable}`,
889
+ };
890
+ }
891
+ /** The report's verdict from its gaps: a decision one gap still needs (`null`) outranks one it refuses. */
892
+ const verdictOf = (gaps) => gaps.length === 0
893
+ ? "PASS"
894
+ : gaps.some((g) => g.fixable === null)
895
+ ? null
896
+ : gaps.some((g) => g.fixable === false)
897
+ ? "FAIL"
898
+ : "CONCERNS";
525
899
  /** The gap for a task whose only test field is a TEST EXCEPTION that is not honoured. */
526
900
  export const EXCEPTION_REFUSED = "exception-refused";
527
901
  /** The status row step plan-execute's finish writes; its commit carries the code of each task its log records DONE. */
528
- export const PLAN_EXECUTE_STEP = "build-plan-execute";
902
+ export const PLAN_TASKS_STEP = "build-plan-tasks";
529
903
  const repoRel = (top, cwd, p) => path.relative(top, path.resolve(cwd, p)).split(path.sep).join("/");
530
904
  /**
531
- * Per task, the first plan-execute step commit whose log records the task `DONE` — the
532
- * commit that first holds the task's code. `steps finish` writes the row then commits
533
- * everything, so a row's commit is the first commit after its `parentSha` touching the status file.
905
+ * The task numbers a plan-execute log records `DONE — TASK N` for, in log order. `verbs`
906
+ * widens the reader to the log's other closing lines (`BLOCKED`), so one parser serves
907
+ * every caller; the default reads `DONE` only, which is what "the task is done" means.
534
908
  */
535
- function taskCodeCommits(top, cwd, file, workflow) {
536
- const statusRel = repoRel(top, cwd, file);
537
- const commits = new Map();
538
- for (const r of readStatusRows(file)) {
539
- if (r.type !== "step-done" || r.workflow !== workflow || r.step !== PLAN_EXECUTE_STEP)
540
- continue;
541
- const log = Array.isArray(r.artifacts) ? r.artifacts.map(String)[0] : undefined;
542
- if (typeof r.parentSha !== "string" || log === undefined)
543
- continue;
544
- const range = `${r.parentSha}..HEAD`;
545
- const commit = git(top, ["rev-list", "--reverse", "--ancestry-path", range, "--", statusRel])
546
- ?.split("\n")
547
- .find(Boolean);
548
- const text = commit === undefined ? null : git(top, ["show", `${commit}:${repoRel(top, cwd, log)}`]);
549
- if (commit === undefined || text === null)
550
- continue;
551
- for (const n of doneTasks(text))
552
- if (!commits.has(n))
553
- commits.set(n, commit);
554
- }
555
- return commits;
556
- }
557
- /** The task numbers a plan-execute log records `DONE — TASK N` for, in log order. */
558
- export function doneTasks(log) {
559
- return [...log.matchAll(/^DONE\s*[—–-]+\s*TASK\s+(\d+)\b/gim)].map((m) => Number(m[1]));
909
+ export function doneTasks(log, verbs = ["DONE"]) {
910
+ const closing = verbs.map((v) => v.replace(/[.*+?^${}()|[\]\\]/g, "\\$&")).join("|");
911
+ return [...log.matchAll(new RegExp(`^(?:${closing})\\s*[—–-]+\\s*TASK\\s+(\\d+)\\b`, "gim"))].map((m) => Number(m[1]));
560
912
  }
561
913
  /**
562
914
  * Why a task's `TEST EXCEPTION` lines do not count, or null when they do: every
@@ -665,7 +1017,7 @@ function deleteGaps(top, planRel, tasks, planTasks) {
665
1017
  path.posix.basename(path.posix.normalize(c.file)) === path.posix.basename(file))
666
1018
  .map((c) => path.posix.normalize(c.file))
667
1019
  : [];
668
- const gap = (detail) => gaps.push({ task: t.task, kind: DELETE_STILL_REFERENCED, detail });
1020
+ const gap = (detail) => gaps.push(gapOf(t.task, DELETE_STILL_REFERENCED, detail));
669
1021
  const abs = path.join(top, file);
670
1022
  const exists = fs.statSync(abs, { throwIfNoEntry: false })?.isFile() === true;
671
1023
  let what;
@@ -698,21 +1050,87 @@ function deleteGaps(top, planRel, tasks, planTasks) {
698
1050
  }
699
1051
  return gaps;
700
1052
  }
701
- /**
702
- * The red rows of status.jsonl for this workflow, oldest first. Task numbers are unique
703
- * across the plan, so a red matches its task by number whatever group recorded it.
704
- */
705
- export function redRows(file, workflow) {
706
- return readStatusRows(file).filter((r) => {
707
- const row = r;
708
- return row.type === "step-done" && row.workflow === workflow && row.step === RED_STEP;
709
- });
1053
+ /** The `Updated` entry for a planned test: its own lines at `base` against the file now. */
1054
+ function updatedEntry(top, task, t, base) {
1055
+ const entry = { task, test: t.test, name: t.name, base, additive: null, diff: null };
1056
+ if (base === null)
1057
+ return entry;
1058
+ const shown = runGit(top, ["show", `${base}:${t.test}`]);
1059
+ const abs = path.join(top, t.test);
1060
+ if (!shown.ok || !fs.existsSync(abs))
1061
+ return entry;
1062
+ const was = testBlock(shown.stdout, t.name);
1063
+ const now = testBlock(fs.readFileSync(abs, "utf-8"), t.name);
1064
+ if (was === null || now === null)
1065
+ return entry;
1066
+ const d = lineDiff(was, now);
1067
+ return { ...entry, additive: d.removed === 0, diff: d.text };
1068
+ }
1069
+ /** Every PASSES line of a tests step's log: the tests the writer saw passing and vouches for. */
1070
+ function passesLines(log) {
1071
+ return [
1072
+ ...log.matchAll(/^PASSES\s*[—–-]+\s*TASK\s+(\d+):\s*`([^`]+)`\s+`([^`]+)`\s*:\s*(.+)$/gm),
1073
+ ].map((m) => ({
1074
+ task: Number(m[1]),
1075
+ test: m[2].trim(),
1076
+ name: m[3].trim(),
1077
+ reason: m[4].trim(),
1078
+ }));
1079
+ }
1080
+ /** Why a plan cannot be read for its tests (no file, no task markers, a fence never closed), or undefined. */
1081
+ const planRefusal = (plan, parsed) => plan === undefined
1082
+ ? `no plan file; ${NO_MARKERS_REASON}`
1083
+ : parsed.tasks.length === 0
1084
+ ? parsed.fenceOpen === undefined
1085
+ ? NO_MARKERS_REASON
1086
+ : fenceNeverClosed(parsed.fenceOpen)
1087
+ : undefined;
1088
+ /** A table cell: pipes escaped, line breaks folded. */
1089
+ const cell = (s) => s.replace(/\s+/g, " ").replace(/\|/g, "\\|").trim();
1090
+ function writeRedReport(log, o) {
1091
+ const red = o.tests.filter((t) => t.state === "red" || t.state === "red-not-loaded").length;
1092
+ const accepted = o.tests.filter((t) => t.state === "passed-accepted").length;
1093
+ const updated = o.tests.filter((t) => t.state === "updated").length;
1094
+ const out = [
1095
+ `Enforced: ${o.enforced}`,
1096
+ `Red: ${red}`,
1097
+ `Accepted: ${accepted}`,
1098
+ `Updated: ${updated}`,
1099
+ `Gaps: ${o.gaps.length}`,
1100
+ "",
1101
+ "<!-- verdict:end -->",
1102
+ "",
1103
+ `# Tests Red — group ${o.group}, attempt ${o.attempt}`,
1104
+ "",
1105
+ ];
1106
+ if (o.plan)
1107
+ out.push(`Plan: \`${o.plan}\``, "");
1108
+ if (!o.enforced)
1109
+ out.push(`Not enforced: ${o.reason}.`, "");
1110
+ if (o.tests.length > 0) {
1111
+ out.push("| Task | Test | State | Detail |", "| --- | --- | --- | --- |");
1112
+ for (const t of o.tests)
1113
+ out.push(`| ${t.task} | \`${t.test}\` "${cell(t.testName)}" | ${t.state} | ${cell(o.details.get(t) ?? "")} |`);
1114
+ out.push("");
1115
+ }
1116
+ out.push("## Gaps", "");
1117
+ if (o.gaps.length === 0)
1118
+ out.push("None.");
1119
+ for (const g of o.gaps)
1120
+ out.push(`- TASK ${g.task} \`${g.test}\` "${g.name}" \`${g.kind}\` — ${g.detail}`);
1121
+ for (const t of o.outputs) {
1122
+ const fence = fenceFor(t.text);
1123
+ out.push("", `## ${t.title}`, "", fence, t.text.replace(/\n$/, ""), fence);
1124
+ }
1125
+ fs.mkdirSync(path.dirname(log), { recursive: true });
1126
+ fs.writeFileSync(log, `${out.join("\n")}\n`);
710
1127
  }
711
1128
  function writeAuditReport(log, o) {
712
1129
  const out = [
713
1130
  `Enforced: ${o.enforced}`,
1131
+ `Verdict: ${o.verdict}`,
714
1132
  `Gaps: ${o.gaps.length}`,
715
- `Test order only: ${o.testOrderOnly}`,
1133
+ `Unproven: ${o.unproven.length}`,
716
1134
  "",
717
1135
  "<!-- verdict:end -->",
718
1136
  "",
@@ -723,30 +1141,45 @@ function writeAuditReport(log, o) {
723
1141
  if (!o.enforced)
724
1142
  out.push(`Not enforced: ${o.reason}.`, "");
725
1143
  if (o.rows.length > 0) {
726
- out.push("| Task | Test | Red | Changed since red | Green |", "| --- | --- | --- | --- | --- |");
1144
+ out.push("| Task | Test | Red | Green |", "| --- | --- | --- | --- |");
727
1145
  for (const r of o.rows)
728
- out.push(`| ${r.task} | ${r.test} | ${r.red} | ${r.changed} | ${r.green} |`);
1146
+ out.push(`| ${r.task} | ${r.test} | ${r.red} | ${r.green} |`);
729
1147
  out.push("");
730
1148
  }
731
1149
  out.push("## Gaps", "");
732
1150
  if (o.gaps.length === 0)
733
1151
  out.push("None.");
734
1152
  for (const g of o.gaps)
735
- out.push(`- ${g.task === null ? "Plan" : `Task ${g.task}`} \`${g.kind}\` — ${g.detail}`);
1153
+ out.push(`- ${g.task === null ? "Plan" : `Task ${g.task}`} \`${g.kind}\` — ${g.detail} — Fixable: ${g.fixable} — log: ${g.logLine}`);
736
1154
  if (o.exceptions.length > 0)
737
1155
  out.push("", "## Test exceptions", "");
738
1156
  for (const e of o.exceptions)
739
1157
  out.push(e.refusal === null
740
1158
  ? `- Task ${e.task} — honoured; cleared ${e.cleared.length > 0 ? e.cleared.join(", ") : "nothing"}`
741
1159
  : `- Task ${e.task} — not honoured: ${e.refusal}`);
742
- if (o.lateUnchecked.length > 0)
743
- out.push("", "## Late-red check", "");
744
- for (const task of o.lateUnchecked)
745
- out.push(`- Task ${task} — not checked: no plan-execute step commit's log records \`DONE — TASK ${task}\`, so when its code landed is unknown`);
746
- for (const d of o.diffs) {
747
- const fence = fenceFor(d.diff);
748
- out.push("", `## Diff since red — Task ${d.task} \`${d.test}\``, "", `${fence}diff`, d.diff, fence);
1160
+ if (o.landed.length > 0)
1161
+ out.push("", "## Already landed", "");
1162
+ for (const l of o.landed)
1163
+ out.push(`- Task ${l.task} \`${l.test}\` "${l.name}" — passed at the group's red, and the tests step accepted it: ${l.reason}; no red is due`);
1164
+ if (o.updated.length > 0)
1165
+ out.push("", "## Updated tests", "");
1166
+ for (const u of o.updated) {
1167
+ const since = u.base === null ? "" : ` since \`${u.base.slice(0, 9)}\``;
1168
+ const judged = u.additive === null
1169
+ ? "its lines at the base commit could not be read, so read the group diff"
1170
+ : u.additive
1171
+ ? "additive: no line of the test was removed, so no expectation was dropped — read the added lines for one that disables an earlier expectation"
1172
+ : "not additive: a line of the test was removed or changed — read the diff for an expectation removed or loosened";
1173
+ out.push(`- Task ${u.task} \`${u.test}\` "${u.name}" — an existing test the tests step changed${since}; the update may add expectations, never remove or loosen one. ${judged}`);
1174
+ if (u.diff !== null) {
1175
+ const fence = fenceFor(u.diff);
1176
+ out.push("", ` ${fence}diff`, ...u.diff.split("\n").map((l) => ` ${l}`), ` ${fence}`, "");
1177
+ }
749
1178
  }
1179
+ if (o.unproven.length > 0)
1180
+ out.push("", "## Unproven", "");
1181
+ for (const u of o.unproven)
1182
+ out.push(`- Task ${u.task} \`${u.test}\` "${u.name}" — ${u.detail}; the owner answers it at the end of the build`);
750
1183
  for (const t of o.outputs) {
751
1184
  const fence = fenceFor(t.tail);
752
1185
  out.push("", `## Runner output — \`${t.test}\``, "", fence, t.tail, fence);
@@ -758,8 +1191,10 @@ export const testsCommand = {
758
1191
  noun: "tests",
759
1192
  summary: "Run the deepest declared local gate, or one test file to record a red and audit a green.",
760
1193
  verbs: {
1194
+ changed: testsChangedVerb,
761
1195
  run: {
762
- summary: "Run the first declared --gate; exit 0 PASS, 1 FAIL, 4 could not run.",
1196
+ summary: "Run the first declared --gate, and with --file append a test-run status row for the run; exit 0 PASS, 1 FAIL, 4 could not run, 81 tests lock held.",
1197
+ use: "by-hand",
763
1198
  flags: [
764
1199
  {
765
1200
  name: "gate",
@@ -779,16 +1214,46 @@ export const testsCommand = {
779
1214
  type: "string",
780
1215
  help: `lines of the log echoed to stderr afterwards (default ${DEFAULT_TAIL}; 0 for none)`,
781
1216
  },
1217
+ {
1218
+ name: "lock-wait-s",
1219
+ type: "string",
1220
+ help: "whole-number lock wait >= 0, passed as LOCAL_STACK_LOCK_WAIT_S (default BKIT_LOCK_WAIT_S, else 60)",
1221
+ },
782
1222
  {
783
1223
  name: "artifact",
784
1224
  type: "string",
785
1225
  help: "copy the log here, trim the copy (debug-evidence) and record the clamp; needs --fid and --step",
786
1226
  },
787
1227
  { name: "fid", type: "string", help: "--artifact: feature id, for the clamp log" },
788
- { name: "step", type: "string", help: "--artifact: step name, for the clamp log" },
789
- { name: "attempt", type: "string", help: "--artifact: attempt, for the clamp log" },
1228
+ {
1229
+ name: "step",
1230
+ type: "string",
1231
+ help: "step name: the test-run row's (--file) and the clamp log's (--artifact)",
1232
+ },
1233
+ {
1234
+ name: "attempt",
1235
+ type: "string",
1236
+ help: "attempt: on the test-run row (--file) and in the clamp log's name (--artifact)",
1237
+ },
1238
+ {
1239
+ name: "file",
1240
+ type: "string",
1241
+ help: "status.jsonl: append one test-run row for this run, pass or fail; needs --workflow and --step",
1242
+ },
1243
+ { name: "workflow", type: "string", help: "--file: workflow name, for the test-run row" },
1244
+ { name: "ci-run", type: "string", help: "selected GitHub evidence run ID" },
1245
+ { name: "ci-url", type: "string", help: "selected GitHub evidence attempt URL" },
790
1246
  ],
791
1247
  output: {
1248
+ source: "ci for pinned red evidence; local for every executed gate",
1249
+ runAttempt: "selected CI attempt for a CI evidence round",
1250
+ ciGeneration: "active selection generation for a CI evidence round",
1251
+ ciRun: "selected CI run ID for a CI evidence round",
1252
+ ciUrl: "selected CI attempt URL for a CI evidence round",
1253
+ repo: "selected repository for a CI evidence round",
1254
+ workflowId: "selected workflow ID for a CI evidence round",
1255
+ workflowPath: "selected workflow path for a CI evidence round",
1256
+ headSha: "selected commit for a CI evidence round",
792
1257
  verdict: "PASS | FAIL (null when the gate could not run)",
793
1258
  exitCode: "the gate's exit code",
794
1259
  gate: "the script that ran",
@@ -799,14 +1264,20 @@ export const testsCommand = {
799
1264
  logBytes: "size of the saved output",
800
1265
  artifact: "--artifact as given, else null",
801
1266
  clamp: "the artifact's clamp record (raw = the log, source = scope), else null",
1267
+ row: `the ${TEST_RUN_ROW} row appended to --file ({type, workflow, at, step, attempt?, run, verdict, exitCode, failures, scope, log, artifact?}; run = this step's test-run rows in the workflow's active run, this one included), else null; a tests-lock wait writes no row`,
1268
+ lockHolder: "tests-lock holder when the wait gave up, else null",
802
1269
  },
803
- textOmit: ["clamp"],
1270
+ textOmit: ["clamp", "row"],
804
1271
  exitCodes: {
805
1272
  [EXIT_NO_GATE]: "no candidate gate is declared in package.json",
806
1273
  [EXIT_COULD_NOT_RUN]: "the gate could not run (exit 126 / 127): not a test failure",
807
1274
  [EXIT_ARTIFACT_STEP]: "--artifact could not be written, trimmed or recorded",
808
1275
  },
809
1276
  run: (ctx) => {
1277
+ const waitSource = ctx.flags.lockWaitS ?? process.env.BKIT_LOCK_WAIT_S;
1278
+ const waitS = wholeNumber(waitSource, ctx.flags.lockWaitS === undefined && process.env.BKIT_LOCK_WAIT_S !== undefined
1279
+ ? "lock-wait-s (BKIT_LOCK_WAIT_S)"
1280
+ : "lock-wait-s", 60);
810
1281
  const candidates = ctx.flags.gate;
811
1282
  const logArg = String(ctx.flags.log);
812
1283
  if (logArg === "")
@@ -817,6 +1288,98 @@ export const testsCommand = {
817
1288
  const attempt = positiveInt(ctx.flags.attempt, "attempt");
818
1289
  if (artifact !== undefined && (!fid || !step))
819
1290
  throw new CommandError(EXIT.USAGE, "--artifact needs --fid and --step");
1291
+ const statusArg = str(ctx.flags.file);
1292
+ const workflow = str(ctx.flags.workflow);
1293
+ if (statusArg !== undefined && (!workflow || !step))
1294
+ throw new CommandError(EXIT.USAGE, "--file needs --workflow and --step");
1295
+ const status = statusArg === undefined ? undefined : path.resolve(ctx.cwd, statusArg);
1296
+ if (status !== undefined && !fs.existsSync(status))
1297
+ throw new CommandError(EXIT.USAGE, `--file ${statusArg} does not exist (a test-run row never starts a log)`);
1298
+ if (ctx.flags.ciRun !== undefined || ctx.flags.ciUrl !== undefined) {
1299
+ const active = status === undefined ? undefined : readRuns(status).at(-1);
1300
+ const selection = active?.ciSelection;
1301
+ if (!status ||
1302
+ workflow !== "debug" ||
1303
+ active?.workflow !== "debug" ||
1304
+ active.status !== "IN_PROGRESS" ||
1305
+ !validateCiSelection(selection) ||
1306
+ selection.mode !== "ci" ||
1307
+ ctx.flags.ciRun !== selection.runId ||
1308
+ ctx.flags.ciUrl !== selection.runUrl ||
1309
+ !Number.isSafeInteger(active.ciGeneration) ||
1310
+ Number(active.ciGeneration) < 1 ||
1311
+ !artifact)
1312
+ throw new CommandError(EXIT.USAGE, "CI round needs an active matching debug selection and artifact");
1313
+ const fixed = active.steps.some((s) => s.status === "DONE" &&
1314
+ s.ciGeneration === active.ciGeneration &&
1315
+ ["debug-failure-remediate", "debug-failure-soak"].includes(s.step));
1316
+ if (!fixed) {
1317
+ const scope = `ci:${selection.runId}`;
1318
+ const text = [
1319
+ "Verdict: FAIL",
1320
+ "Source: ci",
1321
+ `Scope: ${scope}`,
1322
+ `Repository: ${selection.repo}`,
1323
+ `Workflow: ${selection.workflowPath} (${selection.workflowId})`,
1324
+ `Run: ${selection.runId}`,
1325
+ `Run attempt: ${selection.runAttempt}`,
1326
+ `CI generation: ${active.ciGeneration}`,
1327
+ `Commit: ${selection.headSha}`,
1328
+ `URL: ${selection.runUrl}`,
1329
+ "",
1330
+ "<!-- verdict:end -->",
1331
+ "",
1332
+ "# CI evidence",
1333
+ "",
1334
+ "The local gate was not run.",
1335
+ "",
1336
+ ].join("\n");
1337
+ for (const dest of new Set([artifact, logArg])) {
1338
+ const out = path.resolve(ctx.cwd, dest);
1339
+ fs.mkdirSync(path.dirname(out), { recursive: true });
1340
+ fs.writeFileSync(out, text);
1341
+ }
1342
+ const evidence = {
1343
+ gate: null,
1344
+ ciRun: selection.runId,
1345
+ ciUrl: selection.runUrl,
1346
+ runAttempt: selection.runAttempt,
1347
+ ciGeneration: active.ciGeneration,
1348
+ repo: selection.repo,
1349
+ workflowId: selection.workflowId,
1350
+ workflowPath: selection.workflowPath,
1351
+ headSha: selection.headSha,
1352
+ };
1353
+ const row = appendTestRun(status, {
1354
+ workflow,
1355
+ step: step,
1356
+ attempt,
1357
+ source: "ci",
1358
+ verdict: "FAIL",
1359
+ exitCode: null,
1360
+ failures: null,
1361
+ scope,
1362
+ log: logArg,
1363
+ artifact,
1364
+ evidence,
1365
+ });
1366
+ ctx.emit({
1367
+ source: "ci",
1368
+ verdict: "FAIL",
1369
+ scope,
1370
+ exitCode: null,
1371
+ failures: null,
1372
+ ...evidence,
1373
+ artifact,
1374
+ log: logArg,
1375
+ logBytes: Buffer.byteLength(text),
1376
+ reports: null,
1377
+ clamp: null,
1378
+ row,
1379
+ });
1380
+ return EXIT.NO;
1381
+ }
1382
+ }
820
1383
  const tailRaw = str(ctx.flags.tail) ?? String(DEFAULT_TAIL);
821
1384
  if (!/^[0-9]+$/.test(tailRaw)) {
822
1385
  throw new CommandError(EXIT.USAGE, `--tail must be a non-negative integer, got "${tailRaw}"`);
@@ -837,20 +1400,34 @@ export const testsCommand = {
837
1400
  const reports = freshReportDir(log);
838
1401
  ctx.log(`running ${scope} — full output in ${logArg}`);
839
1402
  const fetchedAt = new Date().toISOString().replace(/\.\d{3}Z$/, "Z");
840
- const exitCode = runToLog(scriptCommand(gate), top, log, { [REPORT_DIR_ENV]: reports });
841
- for (const line of Number(tailRaw) > 0 ? tailLines(log, Number(tailRaw)) : [])
1403
+ const who = ["bkit tests run", gate, fid, step].filter(Boolean).join(" ");
1404
+ const exitCode = runToLog(scriptCommand(gate), top, log, {
1405
+ [REPORT_DIR_ENV]: reports,
1406
+ LOCAL_STACK_LOCK_WAIT_S: String(waitS),
1407
+ LOCAL_STACK_LOCK_WHO: who,
1408
+ });
1409
+ const logText = fs.readFileSync(log, "utf-8");
1410
+ const lockExit = classifyLockExit({ exitCode, log: logText, who });
1411
+ const lockWait = lockExit === "lock-wait";
1412
+ const lockHolder = lockWait ? testsLockHolder(logText, who) : null;
1413
+ const lines = lockExit === "gate"
1414
+ ? Number(tailRaw) > 0
1415
+ ? tailLines(log, Number(tailRaw))
1416
+ : []
1417
+ : logText.split(/\r?\n/).filter((line) => line.startsWith("[machine-lock]"));
1418
+ for (const line of lines)
842
1419
  ctx.log(line);
843
- const couldNotRun = COULD_NOT_RUN_EXIT_CODES.has(exitCode);
844
- const verdict = couldNotRun ? null : exitCode === 0 ? "PASS" : "FAIL";
845
- const counted = countReportFailures(reports);
846
- if (counted === null)
1420
+ const couldNotRun = lockExit === "could-not-run" || COULD_NOT_RUN_EXIT_CODES.has(exitCode);
1421
+ const verdict = couldNotRun || lockWait ? null : exitCode === 0 ? "PASS" : "FAIL";
1422
+ const counted = lockExit === "gate" ? countReportFailures(reports) : null;
1423
+ if (counted === null && lockExit === "gate")
847
1424
  ctx.log(NO_REPORT_HINT);
848
1425
  else if (verdict === "FAIL" && counted === 0)
849
1426
  ctx.log(`the JUnit reports in $${REPORT_DIR_ENV} hold no failing case — the gate failed outside its reported tests; failures unknown`);
850
1427
  const failures = verdict === "PASS" ? 0 : counted !== null && counted > 0 ? counted : null;
851
1428
  let clamp = null;
852
1429
  let artifactFailed = null;
853
- if (artifact !== undefined) {
1430
+ if (artifact !== undefined && !lockWait) {
854
1431
  try {
855
1432
  const out = path.resolve(ctx.cwd, artifact);
856
1433
  fs.mkdirSync(path.dirname(out), { recursive: true });
@@ -872,7 +1449,22 @@ export const testsCommand = {
872
1449
  artifactFailed = err.message;
873
1450
  }
874
1451
  }
1452
+ const row = status === undefined || lockWait
1453
+ ? null
1454
+ : appendTestRun(status, {
1455
+ workflow: workflow,
1456
+ step: step,
1457
+ attempt,
1458
+ verdict,
1459
+ exitCode,
1460
+ failures,
1461
+ scope,
1462
+ log: logArg,
1463
+ artifact,
1464
+ source: "local",
1465
+ });
875
1466
  ctx.emit({
1467
+ source: "local",
876
1468
  verdict,
877
1469
  exitCode,
878
1470
  gate,
@@ -881,15 +1473,19 @@ export const testsCommand = {
881
1473
  reports: `${logArg}.reports`,
882
1474
  log: logArg,
883
1475
  logBytes: fs.statSync(log).size,
884
- artifact: artifact ?? null,
1476
+ artifact: lockWait ? null : (artifact ?? null),
885
1477
  clamp,
1478
+ row,
1479
+ lockHolder,
886
1480
  });
887
1481
  if (artifactFailed !== null) {
888
1482
  ctx.log(`--artifact ${artifact}: ${artifactFailed}`);
889
1483
  return EXIT_ARTIFACT_STEP;
890
1484
  }
1485
+ if (lockWait)
1486
+ return EXIT.AGENT_WAIT;
891
1487
  if (couldNotRun) {
892
- ctx.log(`${scope} could not run (exit ${exitCode}: ${exitCode === 126 ? "not executable" : "command not found"}) — no tests executed; this is not a FAIL verdict`);
1488
+ ctx.log(`${scope} could not run (exit ${exitCode}: ${lockExit === "could-not-run" ? "tests lock refused" : exitCode === 126 ? "not executable" : "command not found"}) — no tests executed; this is not a FAIL verdict`);
893
1489
  return EXIT_COULD_NOT_RUN;
894
1490
  }
895
1491
  ctx.log(`verdict ${verdict} (exit ${exitCode})`);
@@ -897,126 +1493,275 @@ export const testsCommand = {
897
1493
  },
898
1494
  },
899
1495
  red: {
900
- summary: "Run a task's new test before its code exists; exit 0 red recorded, 1 not a red (the named test did not run, passed, or was skipped).",
1496
+ summary: "Run every TEST FIRST test of one group's open tasks before any task code exists, and write one build-tests-red row holding a state and blob per planned test; a test an earlier row of the group proved red, its file unchanged since, is not run again. Exit 0 every test red, 1 a gap (a test passing, absent from its report, failing lint, or its file missing), 3 bkit:test:file undeclared (blobs recorded, nothing ran), 4 a script could not run.",
1497
+ use: "workflow",
901
1498
  flags: [
902
1499
  FILE_FLAG,
903
1500
  WORKFLOW_FLAG,
904
- GROUP_FLAG,
905
1501
  {
906
- name: "task",
907
- type: "string",
1502
+ ...GROUP_FLAG,
908
1503
  required: true,
909
- help: "plan task number (positive integer)",
1504
+ help: "the group whose planned tests run (positive integer)",
910
1505
  },
911
1506
  {
912
- name: "test",
1507
+ name: "plan",
913
1508
  type: "string",
914
1509
  required: true,
915
- help: "the test file, repo-relative — passed whole to bkit:test:file",
1510
+ repeatable: true,
1511
+ help: "candidate plan file; the first that exists is read",
916
1512
  },
917
1513
  {
918
- name: "name",
1514
+ name: "log",
919
1515
  type: "string",
920
1516
  required: true,
921
- help: "the test's name as the runner reports it, or its last segment",
1517
+ help: "file the red report is written to (directories are created)",
922
1518
  },
923
1519
  {
924
- name: "log",
1520
+ name: "writer-log",
925
1521
  type: "string",
926
- required: true,
927
- help: "file the runner output is saved to; the test file's copy lands beside it as .snapshot",
1522
+ help: "the tests step's log: a `PASSES — TASK N: `file` `name`: reason` line there accepts that test's pass as passed-accepted",
928
1523
  },
929
1524
  ],
930
1525
  output: {
931
- recorded: "true when the red row was written, or already recorded for this unchanged test",
932
- already: "true when an earlier red for this task, test and name stands (test unchanged); nothing ran",
933
- refused: "no-report | not-run | passed | skipped | exit-mismatch (when recorded is false)",
934
- reason: "why the run is not a red (when recorded is false)",
935
- exitCode: "the script's exit code",
936
- row: "the build-task-red row written (when recorded)",
937
- log: "where the runner output was saved (as given)",
1526
+ enforced: "false when bkit:test:file is not declared (the row records the blobs, every state unknown, exit 3) or the plan could not be read (no row, exit 1)",
1527
+ reason: "why test-first is not enforced",
1528
+ attempt: "this group's build-tests-red rows so far, this one included",
1529
+ tests: "[{task, test, testName, state, blob, reason?}] in plan order, the tests run now: state red | red-not-loaded | passed-accepted | vacuous | missing | no-report | lint | unknown; blob the test file's git blob as it stood (null when the file is missing); reason the tests step's, on passed-accepted",
1530
+ skipped: "planned tests an earlier row of the group proved red, their file unchanged since: not run again, and not on this row",
1531
+ gaps: "[{task, test, name, kind, detail}]: every planned test whose state is not red, red-not-loaded or passed-accepted; kind is the state",
1532
+ row: "the build-tests-red row written",
1533
+ log: "where the report was written (as given)",
938
1534
  },
939
1535
  exitCodes: {
940
- [EXIT_NO_GATE]: `${BKIT_TEST_FILE_SCRIPT} is not declared in package.json`,
941
- [EXIT_COULD_NOT_RUN]: "the script could not run (exit 126 / 127)",
1536
+ [EXIT_NO_GATE]: `${BKIT_TEST_FILE_SCRIPT} is not declared in package.json: the row holds the blobs with enforced false, and no test ran`,
1537
+ [EXIT_COULD_NOT_RUN]: "bkit:lint:file or bkit:test:file could not run (exit 126 / 127); nothing written",
942
1538
  },
943
1539
  run: (ctx) => {
944
1540
  const workflow = String(ctx.flags.workflow);
945
1541
  const group = positiveInt(ctx.flags.group, "group");
946
- const task = positiveInt(ctx.flags.task, "task");
947
- const name = String(ctx.flags.name).trim();
948
- if (name === "")
949
- throw new CommandError(EXIT.USAGE, "--name must be non-empty");
950
1542
  const logArg = String(ctx.flags.log);
951
1543
  if (logArg === "")
952
1544
  throw new CommandError(EXIT.USAGE, "--log must be non-empty");
1545
+ const log = path.resolve(ctx.cwd, logArg);
953
1546
  const top = toplevel(ctx.cwd);
954
- if (resolveGate(top, [BKIT_TEST_FILE_SCRIPT]) === null) {
955
- ctx.log(`${BKIT_TEST_FILE_SCRIPT} is not declared — ${NO_TEST_FILE_HINT}`);
956
- return EXIT_NO_GATE;
957
- }
958
- const test = repoTestPath(top, String(ctx.flags.test));
959
- const blob = git(top, ["hash-object", "--", test]);
1547
+ const exists = (p) => fs.existsSync(path.resolve(ctx.cwd, p));
1548
+ const plan = ctx.flags.plan.find(exists);
1549
+ const planText = plan ? fs.readFileSync(path.resolve(ctx.cwd, plan), "utf-8") : "";
1550
+ const parsed = parsePlanBlocks(planText);
960
1551
  const status = statusFile(ctx);
961
- const prior = fs.existsSync(status)
962
- ? redRows(status, workflow)
963
- .reverse()
964
- .find((r) => r.task === task && r.test === test && r.testName === name)
965
- : undefined;
966
- if (prior !== undefined && prior.testBlob === blob) {
967
- const priorLog = Array.isArray(prior.artifacts) ? String(prior.artifacts[0]) : null;
968
- ctx.emit({ recorded: true, already: true, row: prior, log: priorLog });
969
- ctx.log(`red already recorded for task ${task}: "${name}" (test unchanged since)`);
970
- return EXIT.OK;
971
- }
972
- const log = path.resolve(ctx.cwd, logArg);
973
- const { exitCode, cases } = runTestFile(top, test, log);
974
- if (COULD_NOT_RUN_EXIT_CODES.has(exitCode)) {
975
- ctx.log(couldNotRunMessage(exitCode));
976
- return EXIT_COULD_NOT_RUN;
977
- }
978
- const refusal = judgeRed(exitCode, cases, name);
979
- if (refusal !== null) {
980
- ctx.emit({
981
- recorded: false,
982
- refused: refusal.kind,
983
- reason: refusal.reason,
984
- exitCode,
985
- log: logArg,
1552
+ const attempt = redAttempt(status, workflow, group);
1553
+ const refusal = planRefusal(plan, parsed);
1554
+ if (refusal !== undefined) {
1555
+ writeRedReport(log, {
1556
+ enforced: false,
1557
+ reason: refusal,
1558
+ plan,
1559
+ group,
1560
+ attempt,
1561
+ tests: [],
1562
+ details: new Map(),
1563
+ gaps: [],
1564
+ outputs: [],
986
1565
  });
987
- ctx.log(`not a red (${refusal.kind}): ${refusal.reason} — full output in ${logArg}`);
1566
+ ctx.emit({ enforced: false, reason: refusal, attempt, tests: [], gaps: [], log: logArg });
1567
+ ctx.log(`test-first not enforced: ${refusal}`);
988
1568
  return EXIT.NO;
989
1569
  }
990
- const snapshot = snapshotPath(log);
991
- fs.copyFileSync(path.join(top, test), snapshot);
992
- const failed = cases.find((c) => isNamedCase(c.name, name));
1570
+ const g = parsed.groups.find((x) => x.group === group);
1571
+ if (g === undefined)
1572
+ throw new CommandError(EXIT.USAGE, `the plan has no GROUP ${group}`);
1573
+ if (g.tasks.length === 0)
1574
+ throw new CommandError(EXIT.USAGE, `GROUP ${group} has no tasks; nothing to run`);
1575
+ const done = new Set(parsed.tasks.filter((t) => t.done).map((t) => t.task));
1576
+ // A red an earlier row proved stands while the test's own lines are unchanged, so a
1577
+ // retry, a handover or a task added to the group runs only what is left, and an edit
1578
+ // to another test of the same file costs no proof. A test whose lines could not be
1579
+ // found, and rows from before per-test locking, stand while the whole file is unchanged.
1580
+ const proven = redEntries(status, workflow, group);
1581
+ const textOf = (test) => {
1582
+ const abs = path.join(top, test);
1583
+ return fs.existsSync(abs) ? fs.readFileSync(abs, "utf-8") : null;
1584
+ };
1585
+ const standing = (t) => {
1586
+ const earlier = proven.get(redKey(t.task, t.test, t.testName));
1587
+ if (earlier === undefined || !RED_PROVEN.has(earlier.state))
1588
+ return false;
1589
+ if (earlier.block === undefined || earlier.block === null)
1590
+ return git(top, ["hash-object", "--", t.test]) === earlier.blob;
1591
+ return blockHash(textOf(t.test), t.testName) === earlier.block;
1592
+ };
1593
+ const startSha = groupStartSha(status, workflow, group);
1594
+ /** The test's lines at the group's start commit: it existed before this group's tests step. */
1595
+ const blockAtStart = (t) => {
1596
+ if (startSha === undefined)
1597
+ return null;
1598
+ const shown = runGit(top, ["show", `${startSha}:${t.test}`]);
1599
+ return shown.ok ? blockHash(shown.stdout, t.testName) : null;
1600
+ };
1601
+ const tests = [];
1602
+ let skipped = 0;
1603
+ for (const s of readTestFirst(planText, group)) {
1604
+ if (s.kind !== "test" || done.has(s.task))
1605
+ continue;
1606
+ for (const t of s.tests) {
1607
+ const planned = {
1608
+ task: s.task,
1609
+ test: t.test,
1610
+ testName: t.name,
1611
+ state: "unknown",
1612
+ blob: null,
1613
+ };
1614
+ if (standing(planned))
1615
+ skipped += 1;
1616
+ else
1617
+ tests.push(planned);
1618
+ }
1619
+ }
1620
+ if (skipped > 0)
1621
+ ctx.log(`tests red: ${skipped} planned test(s) already red, not run again`);
1622
+ const enforced = resolveGate(top, [BKIT_TEST_FILE_SCRIPT]) !== null;
1623
+ const lint = resolveGate(top, [BKIT_LINT_FILE_SCRIPT]) !== null;
1624
+ if (enforced && !lint && tests.length > 0)
1625
+ ctx.log(`${BKIT_LINT_FILE_SCRIPT} is not declared — the tests are not linted before their red`);
1626
+ const writerLog = str(ctx.flags.writerLog);
1627
+ const writerPath = writerLog === undefined ? undefined : path.resolve(ctx.cwd, writerLog);
1628
+ const passes = writerPath !== undefined && fs.existsSync(writerPath)
1629
+ ? passesLines(fs.readFileSync(writerPath, "utf-8"))
1630
+ : [];
1631
+ const details = new Map();
1632
+ const outputs = [];
1633
+ const couldNotRun = (script, exitCode) => `${gateScope(script)} could not run (exit ${exitCode}: ${exitCode === 126 ? "not executable" : "command not found"}) — no test executed`;
1634
+ const dir = fs.mkdtempSync(path.join(os.tmpdir(), "bkit-tests-red-"));
1635
+ try {
1636
+ for (const file of [...new Set(tests.map((t) => t.test))]) {
1637
+ const mine = tests.filter((t) => t.test === file);
1638
+ if (!fs.existsSync(path.join(top, file))) {
1639
+ for (const t of mine) {
1640
+ t.state = "missing";
1641
+ details.set(t, `\`${file}\` does not exist`);
1642
+ }
1643
+ continue;
1644
+ }
1645
+ // `-w` stores the file in git: green and `steps finish` read the blob back later.
1646
+ const blob = git(top, ["hash-object", "-w", "--", file]);
1647
+ const text = textOf(file);
1648
+ for (const t of mine) {
1649
+ t.blob = blob;
1650
+ t.block = blockHash(text, t.testName);
1651
+ }
1652
+ if (!enforced)
1653
+ continue;
1654
+ const runLog = path.join(dir, "run.log");
1655
+ if (lint) {
1656
+ const linted = runToLog([...scriptCommand(BKIT_LINT_FILE_SCRIPT), file], top, runLog);
1657
+ outputs.push({
1658
+ title: `Lint output — \`${file}\``,
1659
+ text: fs.readFileSync(runLog, "utf-8"),
1660
+ });
1661
+ if (COULD_NOT_RUN_EXIT_CODES.has(linted)) {
1662
+ ctx.log(couldNotRun(BKIT_LINT_FILE_SCRIPT, linted));
1663
+ return EXIT_COULD_NOT_RUN;
1664
+ }
1665
+ if (linted !== 0) {
1666
+ for (const t of mine) {
1667
+ t.state = "lint";
1668
+ details.set(t, `${BKIT_LINT_FILE_SCRIPT} exited ${linted} on \`${file}\`: fix the test until it lints clean (output below)`);
1669
+ }
1670
+ continue;
1671
+ }
1672
+ }
1673
+ const { exitCode, cases } = runTestFile(top, file, runLog);
1674
+ outputs.push({
1675
+ title: `Runner output — \`${file}\``,
1676
+ text: fs.readFileSync(runLog, "utf-8"),
1677
+ });
1678
+ if (COULD_NOT_RUN_EXIT_CODES.has(exitCode)) {
1679
+ ctx.log(couldNotRun(BKIT_TEST_FILE_SCRIPT, exitCode));
1680
+ return EXIT_COULD_NOT_RUN;
1681
+ }
1682
+ for (const t of mine) {
1683
+ const judged = judgeRed(cases, t.testName, file);
1684
+ const accepted = judged.state === "vacuous"
1685
+ ? passes.find((p) => p.task === t.task && p.test === t.test && p.name === t.testName)
1686
+ : undefined;
1687
+ const before = judged.state === "vacuous" ? blockAtStart(t) : null;
1688
+ if (accepted !== undefined) {
1689
+ t.state = "passed-accepted";
1690
+ t.reason = accepted.reason;
1691
+ details.set(t, `passes; accepted by the tests step: ${accepted.reason}`);
1692
+ }
1693
+ else if (before !== null && before !== t.block) {
1694
+ t.state = "updated";
1695
+ t.base = startSha;
1696
+ details.set(t, `an existing test, changed since the group started (\`${startSha.slice(0, 9)}\`) and passing: the verifier judges its diff — it may add expectations, never remove or loosen one`);
1697
+ }
1698
+ else {
1699
+ t.state = judged.state;
1700
+ details.set(t, judged.detail);
1701
+ }
1702
+ }
1703
+ }
1704
+ }
1705
+ finally {
1706
+ fs.rmSync(dir, { recursive: true, force: true });
1707
+ }
1708
+ const gaps = [];
1709
+ for (const t of tests) {
1710
+ if (RED_PROVEN.has(t.state) || t.state === "unknown")
1711
+ continue;
1712
+ const gap = {
1713
+ task: t.task,
1714
+ test: t.test,
1715
+ name: t.testName,
1716
+ kind: t.state,
1717
+ detail: details.get(t) ?? t.state,
1718
+ };
1719
+ gaps.push(gap);
1720
+ ctx.log(`not a red (${gap.kind}): TASK ${gap.task} \`${gap.test}\` "${gap.name}" — ${gap.detail}`);
1721
+ }
1722
+ writeRedReport(log, {
1723
+ enforced,
1724
+ reason: enforced
1725
+ ? undefined
1726
+ : `\`${BKIT_TEST_FILE_SCRIPT}\` is not declared in package.json`,
1727
+ plan,
1728
+ group,
1729
+ attempt,
1730
+ tests,
1731
+ details,
1732
+ gaps,
1733
+ outputs,
1734
+ });
993
1735
  const written = writeStepRow(ctx.cwd, {
994
- file: statusFile(ctx),
1736
+ file: status,
995
1737
  workflow,
996
1738
  step: RED_STEP,
997
1739
  group,
998
- artifacts: [path.relative(ctx.cwd, log), path.relative(ctx.cwd, snapshot)],
999
- extras: {
1000
- task,
1001
- test,
1002
- testName: name,
1003
- testBlob: blob,
1004
- exitCode,
1005
- failure: failed.message.slice(0, 200),
1006
- },
1740
+ attempt,
1741
+ artifacts: [path.relative(ctx.cwd, log)],
1742
+ extras: { enforced, tests },
1007
1743
  commit: "none",
1008
1744
  }, ctx.log);
1009
- ctx.emit({ recorded: true, exitCode, row: written.row, log: logArg });
1010
- ctx.log(`red recorded for task ${task}: "${name}" failed (${failed.state})`);
1745
+ ctx.emit({ enforced, attempt, tests, skipped, gaps, row: written.row, log: logArg });
1746
+ if (gaps.length > 0) {
1747
+ ctx.log(`tests red: ${gaps.length} gap(s) — report in ${logArg}`);
1748
+ return EXIT.NO;
1749
+ }
1750
+ if (!enforced) {
1751
+ ctx.log(`${BKIT_TEST_FILE_SCRIPT} is not declared — ${NO_TEST_FILE_HINT}`);
1752
+ return EXIT_NO_GATE;
1753
+ }
1754
+ ctx.log(`tests red: ${tests.length} planned test(s) red — report in ${logArg}`);
1011
1755
  return EXIT.OK;
1012
1756
  },
1013
1757
  },
1014
1758
  green: {
1015
- summary: "Audit a plan's test-first evidence (a red per TEST FIRST test recorded before the task's code commit, the test only added to since, the named test passing now); exit 0 no gaps, 1 gaps or a plan with no task markers.",
1759
+ summary: "Audit a plan's test-first evidence (each TEST FIRST test red at its group's tests step, by the build-tests-red row, or accepted there as passing before any task code; the named test passing now); exit 0 no gaps, 1 gaps or a plan with no task markers.",
1760
+ use: "workflow",
1016
1761
  flags: [
1017
1762
  FILE_FLAG,
1018
1763
  WORKFLOW_FLAG,
1019
- { ...GROUP_FLAG, help: "audit only this plan group's tasks (positive integer)" },
1764
+ { ...GROUP_FLAG, help: "audit only this task group's tasks (positive integer)" },
1020
1765
  {
1021
1766
  name: "plan",
1022
1767
  type: "string",
@@ -1035,9 +1780,11 @@ export const testsCommand = {
1035
1780
  enforced: "false when the audit could not run: no plan file, a plan with no task markers (exit 1), or the test-file script undeclared (exit 0)",
1036
1781
  reason: "why test-first is not enforced",
1037
1782
  plan: "the plan file audited",
1038
- gaps: "[{task, kind, detail}]: no-test-first | test-first-malformed | test-first-unread (task null: a plan-level format problem) | no-red | late-red | red-mismatch | red-evidence-missing | test-changed | not-green | exception-refused (a task whose only test field is a TEST EXCEPTION not honoured) | delete-still-referenced (a DELETE line's file still exists, or its name is still found in the tree)",
1039
- testOrderOnly: "true when there are gaps and every one is a test-order gap (no-red | late-red | red-mismatch | red-evidence-missing | test-changed)",
1040
- lateRedUnchecked: "tasks with a red but no plan-execute step commit whose log records `DONE — TASK N`: the late-red check could not run for them",
1783
+ verdict: "PASS no gaps | FAIL a gap's fixable is false | CONCERNS every gap's fixable is true | null when a gap needs a diff read, or the audit could not run",
1784
+ gaps: "[{task, kind, detail, fixable, logLine}]: no-test-first | test-first-malformed | test-first-unread (task null: a plan-level format problem) | not-green | exception-refused (a task whose only test field is a TEST EXCEPTION not honoured) | delete-still-referenced (a DELETE line's file still exists, or its name is still found in the tree); fixable is null when the gap needs a diff read; logLine is the line the verifier appends",
1785
+ alreadyLanded: "[{task, test, name, reason}]: tests the tests step accepted as passing before any task code (passed-accepted on the red row); no red is due for them",
1786
+ unproven: "[{task, test, name, detail}]: tests with no proven red (no build-tests-red row, or a state other than red, red-not-loaded, updated or passed-accepted) and no honoured TEST EXCEPTION; never a gap — the owner answers them once, at the end of the build",
1787
+ updated: "[{task, test, name, base, additive, diff}]: existing tests the tests step changed (updated on the red row); base is the group's start commit; additive = the test's own lines since base gained lines and lost none (null when a side cannot be read), diff = their unified line diff; the verifier judges each diff — it may add expectations, never remove or loosen one",
1041
1788
  log: "where the report was written (as given)",
1042
1789
  },
1043
1790
  exitCodes: {
@@ -1058,13 +1805,7 @@ export const testsCommand = {
1058
1805
  const specs = readTestFirst(planText, group);
1059
1806
  // A plan with no task markers is an old-format plan: nothing it says can be audited,
1060
1807
  // and passing it would let its tests go unchecked.
1061
- const refusal = plan === undefined
1062
- ? `no plan file; ${NO_MARKERS_REASON}`
1063
- : parsed.tasks.length === 0
1064
- ? parsed.fenceOpen === undefined
1065
- ? NO_MARKERS_REASON
1066
- : fenceNeverClosed(parsed.fenceOpen)
1067
- : undefined;
1808
+ const refusal = planRefusal(plan, parsed);
1068
1809
  if (refusal === undefined && group !== undefined) {
1069
1810
  const g = parsed.groups.find((x) => x.group === group);
1070
1811
  if (g === undefined)
@@ -1077,12 +1818,13 @@ export const testsCommand = {
1077
1818
  ? `\`${BKIT_TEST_FILE_SCRIPT}\` is not declared in package.json`
1078
1819
  : undefined);
1079
1820
  const empty = {
1821
+ verdict: null,
1080
1822
  rows: [],
1081
1823
  gaps: [],
1082
- testOrderOnly: false,
1083
1824
  exceptions: [],
1084
- lateUnchecked: [],
1085
- diffs: [],
1825
+ landed: [],
1826
+ unproven: [],
1827
+ updated: [],
1086
1828
  outputs: [],
1087
1829
  };
1088
1830
  if (reason !== undefined) {
@@ -1091,22 +1833,25 @@ export const testsCommand = {
1091
1833
  enforced: false,
1092
1834
  reason,
1093
1835
  plan: plan ?? null,
1836
+ verdict: null,
1094
1837
  gaps: [],
1095
- testOrderOnly: false,
1096
- lateRedUnchecked: [],
1838
+ alreadyLanded: [],
1839
+ unproven: [],
1840
+ updated: [],
1097
1841
  log: logArg,
1098
1842
  });
1099
1843
  ctx.log(`test-first not enforced: ${reason}`);
1100
1844
  return refusal === undefined ? EXIT.OK : EXIT.NO;
1101
1845
  }
1102
- const reds = redRows(statusFile(ctx), workflow);
1846
+ const reds = redEntries(statusFile(ctx), workflow);
1847
+ const groupOf = (task) => parsed.tasks.find((b) => b.task === task)?.group;
1848
+ const landed = [];
1849
+ const unproven = [];
1850
+ const updated = [];
1103
1851
  const statusRel = repoRel(top, ctx.cwd, statusFile(ctx));
1104
- const codeCommits = taskCodeCommits(top, ctx.cwd, statusFile(ctx), workflow);
1105
1852
  const exceptions = [];
1106
- const lateUnchecked = new Set();
1107
1853
  const gaps = [];
1108
1854
  const rows = [];
1109
- const diffs = [];
1110
1855
  const outputs = [];
1111
1856
  const greens = new Map();
1112
1857
  /** One run per test file; null when the script could not run. */
@@ -1139,21 +1884,13 @@ export const testsCommand = {
1139
1884
  cleared: refused === null ? ["the task's `TEST FIRST` check"] : [],
1140
1885
  });
1141
1886
  if (refused !== null)
1142
- gaps.push({
1143
- task: s.task,
1144
- kind: EXCEPTION_REFUSED,
1145
- detail: `the task's only test field is a \`**TEST EXCEPTION:**\`, not honoured: ${refused}`,
1146
- });
1887
+ gaps.push(gapOf(s.task, EXCEPTION_REFUSED, `the task's only test field is a \`**TEST EXCEPTION:**\`, not honoured: ${refused}`));
1147
1888
  continue;
1148
1889
  }
1149
1890
  if (s.kind !== "test") {
1150
- gaps.push({
1151
- task: s.task,
1152
- kind: s.kind === "missing" ? "no-test-first" : "test-first-malformed",
1153
- detail: s.kind === "missing"
1154
- ? "the task has neither a `**TEST FIRST:**` nor a `**TEST EXCEPTION:**` field"
1155
- : "`**TEST FIRST:**` is neither `n/a — {reason}` nor one sub-bullet per test naming a backticked test file and test name",
1156
- });
1891
+ gaps.push(gapOf(s.task, s.kind === "missing" ? "no-test-first" : "test-first-malformed", s.kind === "missing"
1892
+ ? "the task has neither a `**TEST FIRST:**` nor a `**TEST EXCEPTION:**` field"
1893
+ : "`**TEST FIRST:**` is neither `n/a — {reason}` nor one sub-bullet per test naming a backticked test file and test name"));
1157
1894
  continue;
1158
1895
  }
1159
1896
  const excepted = s.exception;
@@ -1166,14 +1903,11 @@ export const testsCommand = {
1166
1903
  };
1167
1904
  if (exception !== undefined)
1168
1905
  exceptions.push(exception);
1169
- const taskReds = reds.filter((r) => r.task === s.task);
1170
- const planned = (r) => s.tests.some((t) => t.test === r.test && t.name === r.testName);
1171
1906
  for (const t of s.tests) {
1172
1907
  const row = {
1173
1908
  task: s.task,
1174
1909
  test: `\`${t.test}\` "${t.name}"`,
1175
- red: "missing",
1176
- changed: "—",
1910
+ red: "no row",
1177
1911
  green: "—",
1178
1912
  };
1179
1913
  rows.push(row);
@@ -1181,76 +1915,28 @@ export const testsCommand = {
1181
1915
  excepted.tests.some((e) => e.test === t.test && e.name === t.name)
1182
1916
  ? exception
1183
1917
  : undefined;
1184
- const gap = (kind, detail) => {
1185
- if (clearing !== undefined && TEST_ORDER_GAPS.has(kind))
1186
- clearing.cleared.push(`\`${kind}\` for \`${t.test}\` "${t.name}"`);
1918
+ const gap = (kind, detail) => gaps.push(gapOf(s.task, kind, detail, { file: t.test, name: t.name }));
1919
+ const noRed = (detail) => {
1920
+ if (clearing !== undefined)
1921
+ clearing.cleared.push(`the red for \`${t.test}\` "${t.name}"`);
1187
1922
  else
1188
- gaps.push({ task: s.task, kind, detail });
1923
+ unproven.push({ task: s.task, test: t.test, name: t.name, detail });
1189
1924
  };
1190
- const red = [...taskReds]
1191
- .reverse()
1192
- .find((r) => r.test === t.test && r.testName === t.name);
1193
- const unplanned = taskReds.filter((r) => !planned(r));
1194
- if (red === undefined && unplanned.length > 0) {
1195
- const recorded = [];
1196
- for (const r of unplanned) {
1197
- const rTest = String(r.test);
1198
- const rName = String(r.testName);
1199
- let now = "file missing";
1200
- if (fs.existsSync(path.join(top, rTest))) {
1201
- const run = greenRun(rTest);
1202
- if (run === null)
1203
- return EXIT_COULD_NOT_RUN;
1204
- const why = judgeGreen(run.cases, rName);
1205
- now = why === null ? "passes now" : `not passing: ${why}`;
1206
- }
1207
- recorded.push(`\`${rTest}\` "${rName}" (${now})`);
1208
- }
1209
- gap("red-mismatch", `no red for \`${t.test}\` "${t.name}"; reds recorded for ${recorded.join(", ")}`);
1925
+ const red = reds.get(redKey(s.task, t.test, t.name));
1926
+ if (red === undefined)
1927
+ noRed(`no tests step recorded a red for it (\`bkit tests red --group=${groupOf(s.task) ?? "N"}\`)`);
1928
+ else if (red.state === "passed-accepted") {
1929
+ row.red = red.state;
1930
+ landed.push({ task: s.task, test: t.test, name: t.name, reason: red.reason ?? "" });
1210
1931
  }
1211
- else if (red === undefined) {
1212
- gap("no-red", `no red recorded for "${t.name}" — the test was never seen failing before the code`);
1932
+ else if (RED_PROVEN.has(red.state)) {
1933
+ row.red = red.state;
1934
+ if (red.state === "updated")
1935
+ updated.push(updatedEntry(top, s.task, t, red.base ?? null));
1213
1936
  }
1214
1937
  else {
1215
- row.red = `recorded ${String(red.at)}`;
1216
- const code = codeCommits.get(s.task);
1217
- const on = typeof red.parentSha === "string" ? red.parentSha : undefined;
1218
- if (code === undefined || on === undefined)
1219
- lateUnchecked.add(s.task);
1220
- else if (runGit(top, ["merge-base", "--is-ancestor", code, on]).ok) {
1221
- row.red = `late — ${row.red}`;
1222
- gap("late-red", `the red for "${t.name}" was recorded on ${on.slice(0, 7)}, on or after ${code.slice(0, 7)}, the first commit whose plan-execute log records TASK ${s.task} DONE — the task's code already existed`);
1223
- }
1224
- const snap = (Array.isArray(red.artifacts) ? red.artifacts : [])
1225
- .map(String)
1226
- .find((a) => a.endsWith(".snapshot"));
1227
- const snapAbs = snap === undefined ? undefined : path.resolve(ctx.cwd, snap);
1228
- const testAbs = path.join(top, t.test);
1229
- if (snapAbs === undefined || !fs.existsSync(snapAbs)) {
1230
- row.changed = "unknown";
1231
- gap("red-evidence-missing", `the red's test snapshot ${snap ?? "(none recorded)"} is missing`);
1232
- }
1233
- else if (!fs.existsSync(testAbs)) {
1234
- row.changed = "deleted";
1235
- gap("test-changed", `\`${t.test}\` no longer exists`);
1236
- }
1237
- else if (!fs.readFileSync(snapAbs).equals(fs.readFileSync(testAbs))) {
1238
- const added = onlyAddsLines(fs.readFileSync(snapAbs, "utf-8"), fs.readFileSync(testAbs, "utf-8"));
1239
- row.changed = added ? "added lines only" : "yes";
1240
- if (!added)
1241
- gap("test-changed", `\`${t.test}\` differs from its red snapshot for "${t.name}" (diff below)`);
1242
- const diff = runGit(top, [
1243
- "diff",
1244
- "--no-index",
1245
- "--no-color",
1246
- "--",
1247
- path.relative(top, snapAbs),
1248
- t.test,
1249
- ]);
1250
- diffs.push({ task: s.task, test: t.test, diff: diff.stdout });
1251
- }
1252
- else
1253
- row.changed = "no";
1938
+ row.red = red.state;
1939
+ noRed(`the tests step left it as \`${red.state}\`, not red`);
1254
1940
  }
1255
1941
  if (!fs.existsSync(path.join(top, t.test))) {
1256
1942
  row.green = "file missing";
@@ -1271,37 +1957,37 @@ export const testsCommand = {
1271
1957
  }
1272
1958
  gaps.push(...deleteGaps(top, repoRel(top, ctx.cwd, plan), parsed.tasks.filter((t) => group === undefined || t.group === group), parsed.tasks));
1273
1959
  for (const e of parsed.errors)
1274
- gaps.push({
1275
- task: null,
1276
- kind: "test-first-unread",
1277
- detail: `\`${plan}:${e.line}\` ${e.message} — tests there were not audited; the plan's blocks need fixing`,
1278
- });
1279
- const testOrderOnly = gaps.length > 0 && gaps.every((g) => TEST_ORDER_GAPS.has(g.kind));
1960
+ gaps.push(gapOf(null, "test-first-unread", `\`${plan}:${e.line}\` ${e.message} — tests there were not audited; the plan's blocks need fixing`));
1961
+ const verdict = verdictOf(gaps);
1280
1962
  writeAuditReport(log, {
1281
1963
  enforced: true,
1282
1964
  plan,
1965
+ verdict,
1283
1966
  rows,
1284
1967
  gaps,
1285
- testOrderOnly,
1286
1968
  exceptions,
1287
- lateUnchecked: [...lateUnchecked].sort((a, b) => a - b),
1288
- diffs,
1969
+ landed,
1970
+ unproven,
1971
+ updated,
1289
1972
  outputs,
1290
1973
  });
1291
1974
  ctx.emit({
1292
1975
  enforced: true,
1293
1976
  plan,
1977
+ verdict,
1294
1978
  gaps,
1295
- testOrderOnly,
1296
- lateRedUnchecked: [...lateUnchecked].sort((a, b) => a - b),
1979
+ alreadyLanded: landed,
1980
+ unproven,
1981
+ updated,
1297
1982
  log: logArg,
1298
1983
  });
1299
- ctx.log(`test-first audit: ${gaps.length} gap(s) — report in ${logArg}`);
1984
+ ctx.log(`test-first audit: ${gaps.length} gap(s), ${unproven.length} unproven — report in ${logArg}`);
1300
1985
  return gaps.length === 0 ? EXIT.OK : EXIT.NO;
1301
1986
  },
1302
1987
  },
1303
1988
  "plan-check": {
1304
- summary: `Check a plan's group and task blocks: the block format, DONE WHEN and TEST FIRST on every task, DEPENDS ON order, the caps from package.json \`bkit.workflows.tasks\` (defaults: ${capsText(CONFIG_DEFAULTS.tasks)}), a Reuse Inventory NEW row per CREATE file, and that each READ / UPDATE / DELETE file and symbol exists; exit 0 no problems, 1 refused.`,
1989
+ summary: `Check a plan's group and task blocks: the block format, DONE WHEN and TEST FIRST on every task, DEPENDS ON order, the caps from package.json \`bkit.workflows.tasks\` (defaults: ${capsText(CONFIG_DEFAULTS.tasks)}), a Reuse Inventory NEW row per CREATE file, a Supersession Inventory row per DELETE, a \`Task\` on every Derived Test Matrix row and a row per test-bearing task, and that each READ / UPDATE / DELETE file and symbol exists; exit 0 no problems, 1 refused.`,
1990
+ use: "by-hand",
1305
1991
  flags: [
1306
1992
  {
1307
1993
  name: "plan",
@@ -1325,8 +2011,9 @@ export const testsCommand = {
1325
2011
  plan: "the plan file checked (as given)",
1326
2012
  groups: "[{group, title, tasks, tests, kb}]: each group's tasks, planned TEST FIRST tests and size",
1327
2013
  tasks: "[{task, group, tests, files}]: each task's planned tests and distinct test files",
1328
- problems: "[{line, kind, message}]: format | stray | field | depends | cap | inventory | markers — each refuses the plan",
2014
+ problems: "[{line, kind, message}]: format | stray | field | depends | cap | inventory | matrix | supersession | markers — each refuses the plan",
1329
2015
  existence: "[{line, task, message}]: READ / UPDATE / DELETE files or symbols not found; refuses only with --existence=refuse",
2016
+ existing: "[{line, task, test, name}]: planned tests of open tasks whose name a test in their file already carries; reported only, never refuses",
1330
2017
  log: "where the report was written (as given)",
1331
2018
  },
1332
2019
  run: (ctx) => {
@@ -1344,6 +2031,7 @@ export const testsCommand = {
1344
2031
  const caps = planCaps(ctx.cwd);
1345
2032
  const { groups, sizes, problems } = checkPlanText(text, caps);
1346
2033
  const existence = planExistence(text, toplevel(ctx.cwd));
2034
+ const existing = existingTestNames(text, toplevel(ctx.cwd));
1347
2035
  const refused = problems.length > 0 || (existenceArg === "refuse" && existence.length > 0);
1348
2036
  const out = [
1349
2037
  `Problems: ${problems.length}`,
@@ -1380,10 +2068,14 @@ export const testsCommand = {
1380
2068
  out.push("None.");
1381
2069
  for (const e of existence)
1382
2070
  out.push(`- \`${plan}:${e.line}\` — ${e.message}`);
2071
+ if (existing.length > 0)
2072
+ out.push("", "## Planned test names already in use (reported only)", "");
2073
+ for (const e of existing)
2074
+ out.push(`- \`${plan}:${e.line}\` TASK ${e.task}: \`${e.test}\` already holds a test named "${e.name}" — name the update to it in TEST FIRST, or give the new test a new name`);
1383
2075
  const log = path.resolve(ctx.cwd, logArg);
1384
2076
  fs.mkdirSync(path.dirname(log), { recursive: true });
1385
2077
  fs.writeFileSync(log, `${out.join("\n")}\n`);
1386
- ctx.emit({ plan, groups, tasks: sizes, problems, existence, log: logArg });
2078
+ ctx.emit({ plan, groups, tasks: sizes, problems, existence, existing, log: logArg });
1387
2079
  ctx.log(`plan check: ${problems.length} problem(s), ${existence.length} existence finding(s)${refused ? " — refused" : ""}; report in ${logArg}`);
1388
2080
  return refused ? EXIT.NO : EXIT.OK;
1389
2081
  },