@cbartens/bkit 5.5.1 → 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 (425) hide show
  1. package/.bkit/README.md +167 -154
  2. package/.bkit/core/.agents/context.md +95 -29
  3. package/.bkit/core/.agents/docs.md +18 -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 +112 -102
  9. package/.bkit/core/.agents/skills.md +63 -15
  10. package/.bkit/core/.bkit/README.md +167 -154
  11. package/.bkit/core/.bkit/authoring.md +747 -0
  12. package/.bkit/core/.bkit/cli.md +407 -0
  13. package/.bkit/core/.bkit/cloud.md +283 -195
  14. package/.bkit/core/.bkit/comparison.md +45 -43
  15. package/.bkit/core/.bkit/install.md +166 -95
  16. package/.bkit/core/.bkit/jsonl.md +339 -196
  17. package/.bkit/core/.bkit/pipeline.md +142 -145
  18. package/.bkit/core/.bkit/prompts.md +295 -264
  19. package/.bkit/core/.bkit/providers.md +460 -277
  20. package/.bkit/core/.bkit/router.md +69 -0
  21. package/.bkit/core/.bkit/templates.md +530 -256
  22. package/.bkit/core/.bkit/trackers.md +116 -65
  23. package/.bkit/core/.bkit/workflows.md +742 -618
  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 +6 -80
  33. package/.bkit/core/docs/templates/bkit-audit-accessibility.md +128 -130
  34. package/.bkit/core/docs/templates/bkit-audit-adoption.md +104 -94
  35. package/.bkit/core/docs/templates/bkit-audit-agents.md +96 -98
  36. package/.bkit/core/docs/templates/bkit-audit-aio-seo.md +100 -103
  37. package/.bkit/core/docs/templates/bkit-audit-analytics.md +141 -107
  38. package/.bkit/core/docs/templates/bkit-audit-annotations.md +99 -97
  39. package/.bkit/core/docs/templates/bkit-audit-app-performance.md +122 -121
  40. package/.bkit/core/docs/templates/bkit-audit-app-store.md +158 -101
  41. package/.bkit/core/docs/templates/bkit-audit-architecture.md +114 -96
  42. package/.bkit/core/docs/templates/bkit-audit-ci-performance.md +76 -97
  43. package/.bkit/core/docs/templates/bkit-audit-config.md +123 -101
  44. package/.bkit/core/docs/templates/bkit-audit-cost.md +86 -99
  45. package/.bkit/core/docs/templates/bkit-audit-coverage.md +76 -93
  46. package/.bkit/core/docs/templates/bkit-audit-database.md +102 -95
  47. package/.bkit/core/docs/templates/bkit-audit-dead-code.md +165 -108
  48. package/.bkit/core/docs/templates/bkit-audit-deferrals.md +115 -109
  49. package/.bkit/core/docs/templates/bkit-audit-dependencies.md +265 -113
  50. package/.bkit/core/docs/templates/bkit-audit-documentation.md +119 -118
  51. package/.bkit/core/docs/templates/bkit-audit-duplication.md +140 -111
  52. package/.bkit/core/docs/templates/bkit-audit-failures.md +111 -106
  53. package/.bkit/core/docs/templates/bkit-audit-flakes.md +100 -99
  54. package/.bkit/core/docs/templates/bkit-audit-gates.md +107 -103
  55. package/.bkit/core/docs/templates/bkit-audit-issues.md +105 -105
  56. package/.bkit/core/docs/templates/bkit-audit-llm.md +134 -85
  57. package/.bkit/core/docs/templates/bkit-audit-logs.md +124 -125
  58. package/.bkit/core/docs/templates/bkit-audit-models.md +99 -78
  59. package/.bkit/core/docs/templates/bkit-audit-privacy.md +56 -76
  60. package/.bkit/core/docs/templates/bkit-audit-prompts.md +63 -78
  61. package/.bkit/core/docs/templates/bkit-audit-red-team.md +125 -93
  62. package/.bkit/core/docs/templates/bkit-audit-reliability.md +97 -96
  63. package/.bkit/core/docs/templates/bkit-audit-repo.md +170 -98
  64. package/.bkit/core/docs/templates/bkit-audit-security.md +207 -121
  65. package/.bkit/core/docs/templates/bkit-audit-slop.md +78 -95
  66. package/.bkit/core/docs/templates/bkit-audit-testing.md +163 -139
  67. package/.bkit/core/docs/templates/bkit-audit-usability.md +114 -96
  68. package/.bkit/core/docs/templates/bkit-plan.md +158 -281
  69. package/.bkit/core/engine/checks/after/auth.ts +40 -37
  70. package/.bkit/core/engine/checks/after/ci-yml.ts +104 -31
  71. package/.bkit/core/engine/checks/after/github.ts +95 -17
  72. package/.bkit/core/engine/checks/after/index.ts +21 -8
  73. package/.bkit/core/engine/checks/after/suppression.ts +8 -5
  74. package/.bkit/core/engine/checks/after/tools.ts +125 -123
  75. package/.bkit/core/engine/checks/before/context-fetch.ts +227 -33
  76. package/.bkit/core/engine/checks/before/env.ts +3 -3
  77. package/.bkit/core/engine/checks/before/files.ts +5 -4
  78. package/.bkit/core/engine/checks/before/index.ts +25 -1
  79. package/.bkit/core/engine/checks/before/repo.ts +208 -2
  80. package/.bkit/core/engine/checks/status-holes.ts +916 -123
  81. package/.bkit/core/engine/checks/tips/catalogue.ts +82 -20
  82. package/.bkit/core/engine/checks/tips/detect.ts +66 -0
  83. package/.bkit/core/engine/checks/tips/index.ts +52 -11
  84. package/.bkit/core/engine/cli.ts +251 -130
  85. package/.bkit/core/engine/commands/analysis.ts +282 -199
  86. package/.bkit/core/engine/commands/ci/ci.ts +363 -29
  87. package/.bkit/core/engine/commands/ci/pins.ts +172 -0
  88. package/.bkit/core/engine/commands/ci/push-gate.ts +223 -0
  89. package/.bkit/core/engine/commands/comply.ts +77 -103
  90. package/.bkit/core/engine/commands/install/doctor.ts +2 -2
  91. package/.bkit/core/engine/commands/install/install.ts +57 -18
  92. package/.bkit/core/engine/commands/install/uninstall.ts +86 -55
  93. package/.bkit/core/engine/commands/install/upgrade.ts +32 -15
  94. package/.bkit/core/engine/commands/land.ts +139 -18
  95. package/.bkit/core/engine/commands/lib.ts +381 -22
  96. package/.bkit/core/engine/commands/registry.ts +10 -2
  97. package/.bkit/core/engine/commands/setup/setup.ts +8 -7
  98. package/.bkit/core/engine/commands/stats.ts +260 -0
  99. package/.bkit/core/engine/commands/tips.ts +10 -5
  100. package/.bkit/core/engine/commands/workflow/branches.ts +2215 -176
  101. package/.bkit/core/engine/commands/workflow/challenge.ts +748 -0
  102. package/.bkit/core/engine/commands/workflow/completeness.ts +109 -0
  103. package/.bkit/core/engine/commands/workflow/context.ts +1249 -47
  104. package/.bkit/core/engine/commands/workflow/counters.ts +483 -95
  105. package/.bkit/core/engine/commands/workflow/decisions.ts +585 -0
  106. package/.bkit/core/engine/commands/workflow/disk.ts +238 -56
  107. package/.bkit/core/engine/commands/workflow/fids.ts +811 -33
  108. package/.bkit/core/engine/commands/workflow/issues.ts +413 -64
  109. package/.bkit/core/engine/commands/workflow/ledgers.ts +1333 -36
  110. package/.bkit/core/engine/commands/workflow/locks.ts +28 -2
  111. package/.bkit/core/engine/commands/workflow/plan-blocks.ts +691 -0
  112. package/.bkit/core/engine/commands/workflow/plan-versions.ts +21 -0
  113. package/.bkit/core/engine/commands/workflow/plans.ts +257 -0
  114. package/.bkit/core/engine/commands/workflow/prs.ts +178 -33
  115. package/.bkit/core/engine/commands/workflow/repo.ts +66 -8
  116. package/.bkit/core/engine/commands/workflow/roadmap.ts +72 -22
  117. package/.bkit/core/engine/commands/workflow/run-facts.ts +492 -0
  118. package/.bkit/core/engine/commands/workflow/runs.ts +827 -79
  119. package/.bkit/core/engine/commands/workflow/runtime.ts +25 -1
  120. package/.bkit/core/engine/commands/workflow/skills.ts +1 -0
  121. package/.bkit/core/engine/commands/workflow/status.ts +329 -33
  122. package/.bkit/core/engine/commands/workflow/step-table.ts +381 -0
  123. package/.bkit/core/engine/commands/workflow/steps.ts +841 -105
  124. package/.bkit/core/engine/commands/workflow/summary-findings.ts +177 -0
  125. package/.bkit/core/engine/commands/workflow/summary.ts +544 -0
  126. package/.bkit/core/engine/commands/workflow/tasks.ts +409 -0
  127. package/.bkit/core/engine/commands/workflow/test-blocks.ts +254 -0
  128. package/.bkit/core/engine/commands/workflow/tests-changed.ts +201 -0
  129. package/.bkit/core/engine/commands/workflow/tests.ts +2124 -330
  130. package/.bkit/core/engine/commands/workflow/tracker.ts +1195 -0
  131. package/.bkit/core/engine/commands/workflow/workflows.ts +1197 -235
  132. package/.bkit/core/engine/commands/workflow/worktrees.ts +543 -24
  133. package/.bkit/core/engine/install/cloud-env.ts +251 -121
  134. package/.bkit/core/engine/install/context-ci-workflow.ts +102 -0
  135. package/.bkit/core/engine/install/manifest.ts +67 -17
  136. package/.bkit/core/engine/install/modules/antigravity.ts +3 -2
  137. package/.bkit/core/engine/install/modules/cloud.ts +24 -16
  138. package/.bkit/core/engine/install/modules/codex.ts +15 -2
  139. package/.bkit/core/engine/install/modules/core.ts +1196 -45
  140. package/.bkit/core/engine/install/modules/cursor.ts +6 -6
  141. package/.bkit/core/engine/install/modules/opencode.ts +18 -6
  142. package/.bkit/core/engine/install/template-notes.ts +130 -0
  143. package/.bkit/core/engine/install/version-file.ts +9 -4
  144. package/.bkit/core/engine/install/write.ts +5 -0
  145. package/.bkit/core/engine/ledgers/compact.ts +124 -0
  146. package/.bkit/core/engine/ledgers/journal.ts +291 -0
  147. package/.bkit/core/engine/ledgers/migrate.ts +92 -0
  148. package/.bkit/core/engine/ledgers/status.ts +249 -21
  149. package/.bkit/core/engine/ledgers/telemetry.ts +1397 -253
  150. package/.bkit/core/engine/render/hosts.ts +118 -14
  151. package/.bkit/core/engine/render/models.ts +12 -0
  152. package/.bkit/core/engine/shared/bkit-latest.ts +26 -4
  153. package/.bkit/core/engine/shared/branches.ts +4 -1
  154. package/.bkit/core/engine/shared/dep-updater.ts +60 -0
  155. package/.bkit/core/engine/shared/egress.ts +8 -1
  156. package/.bkit/core/engine/shared/json.ts +25 -7
  157. package/.bkit/core/engine/shared/package-manager.ts +9 -0
  158. package/.bkit/core/engine/shared/settings.ts +243 -31
  159. package/.bkit/core/engine/shared/text.ts +361 -0
  160. package/.bkit/core/engine/shared/timeouts.ts +2 -0
  161. package/.bkit/core/engine/tools/cli-doc.ts +111 -0
  162. package/.bkit/core/engine/tools/grammar-density.ts +215 -0
  163. package/.bkit/core/engine/tools/instructions-sources.ts +832 -0
  164. package/.bkit/core/engine/tools/instructions.ts +1802 -0
  165. package/.bkit/core/hooks/antigravity-hook.js +25 -10
  166. package/.bkit/core/hooks/gateguard-engine.js +54 -29
  167. package/.bkit/core/hooks/guardrails-shell.js +4 -5
  168. package/.bkit/core/hooks/guardrails-tiers.js +10 -4
  169. package/.bkit/core/hooks/preflight-linear.sh +9 -9
  170. package/.bkit/core/hooks/preflight-rules.sh +8 -0
  171. package/.bkit/core/hooks/readguard-engine.js +29 -10
  172. package/.bkit/core/hooks/session-rules-advisory.js +61 -0
  173. package/.bkit/core/prompts/bkit-audit-generate.md +202 -94
  174. package/.bkit/core/prompts/bkit-build-challenge-1.md +76 -34
  175. package/.bkit/core/prompts/bkit-build-challenge-2.md +85 -38
  176. package/.bkit/core/prompts/bkit-build-install-skills.md +50 -28
  177. package/.bkit/core/prompts/bkit-build-plan-convert.md +85 -0
  178. package/.bkit/core/prompts/bkit-build-plan-current.md +59 -36
  179. package/.bkit/core/prompts/bkit-build-plan-gaps-remediate.md +101 -36
  180. package/.bkit/core/prompts/bkit-build-plan-tasks.md +149 -0
  181. package/.bkit/core/prompts/bkit-build-plan-tests.md +120 -0
  182. package/.bkit/core/prompts/bkit-build-plan-verify.md +104 -43
  183. package/.bkit/core/prompts/bkit-debug-abort-handover.md +47 -32
  184. package/.bkit/core/prompts/bkit-debug-failure-diagnose.md +109 -57
  185. package/.bkit/core/prompts/bkit-debug-failure-remediate.md +65 -39
  186. package/.bkit/core/prompts/bkit-debug-failure-reproduce.md +53 -31
  187. package/.bkit/core/prompts/bkit-debug-failure-soak.md +65 -34
  188. package/.bkit/core/prompts/bkit-design-brainstorm-ideate-1.md +46 -31
  189. package/.bkit/core/prompts/bkit-design-brainstorm-ideate-2.md +45 -31
  190. package/.bkit/core/prompts/bkit-design-brainstorm-ideate-3.md +43 -30
  191. package/.bkit/core/prompts/bkit-design-generate.md +80 -46
  192. package/.bkit/core/prompts/bkit-design-organise.md +83 -32
  193. package/.bkit/core/prompts/bkit-design-review-1.md +70 -50
  194. package/.bkit/core/prompts/bkit-design-review-2.md +65 -46
  195. package/.bkit/core/prompts/bkit-design-spike.md +64 -40
  196. package/.bkit/core/prompts/bkit-design-update.md +53 -28
  197. package/.bkit/core/prompts/bkit-plan-generate.md +101 -29
  198. package/.bkit/core/prompts/bkit-plan-review-1.md +78 -41
  199. package/.bkit/core/prompts/bkit-plan-review-2.md +78 -35
  200. package/.bkit/core/prompts/bkit-plan-scope-check.md +116 -0
  201. package/.bkit/core/prompts/bkit-plan-update.md +86 -31
  202. package/.bkit/core/prompts/bkit-ship-conflict-resolve.md +94 -50
  203. package/.bkit/core/prompts/bkit-ship-deferred-sweep.md +91 -41
  204. package/.bkit/core/prompts/bkit-ship-update-docs.md +45 -24
  205. package/.bkit/core/prompts/bkit-utility-compress-markdown.md +65 -49
  206. package/.bkit/core/prompts/bkit-utility-update-decisions.md +87 -42
  207. package/.bkit/core/prompts/bkit-utility-update-deferrals.md +81 -37
  208. package/.bkit/core/prompts/bkit-utility-update-documentation.md +43 -25
  209. package/.bkit/core/prompts/bkit-utility-update-failures.md +84 -37
  210. package/.bkit/core/prompts/bkit-utility-update-knowledge.md +88 -42
  211. package/.bkit/core/prompts/bkit-utility-update-roadmap.md +92 -39
  212. package/.bkit/core/prompts/bkit-utility-update-tracker.md +159 -60
  213. package/.bkit/core/workflows/bkit-auto.md +89 -58
  214. package/.bkit/core/workflows/bkit-build.md +967 -517
  215. package/.bkit/core/workflows/bkit-debug.md +555 -387
  216. package/.bkit/core/workflows/bkit-design.md +319 -283
  217. package/.bkit/core/workflows/bkit-plan.md +319 -342
  218. package/.bkit/core/workflows/bkit-ship.md +525 -328
  219. package/.bkit/shared/.agents/plugins/bkit/hooks.json +10 -0
  220. package/.bkit/shared/.bkit/.env.example +2 -2
  221. package/.bkit/shared/.claude/bkit-cloud.md +12 -10
  222. package/.bkit/shared/.claude/settings.json +14 -0
  223. package/.bkit/shared/.codex/bkit-cloud.md +98 -0
  224. package/.bkit/shared/.codex/hooks.json +20 -0
  225. package/.bkit/shared/.cursor/bkit-cloud.md +3 -3
  226. package/.bkit/shared/.cursor/mcp.json +1 -1
  227. package/.bkit/shared/.cursor/rules/bkit-rules.mdc +1 -1
  228. package/.bkit/shared/.gitattributes +1 -1
  229. package/.bkit/shared/.mcp.json +1 -1
  230. package/.bkit/shared/.opencode/opencode.json +12 -1
  231. package/.bkit/shared/CLAUDE.md +6 -2
  232. package/.bkit/shared/GEMINI.md +5 -2
  233. package/.bkit/shared/docs/architecture.md +4 -7
  234. package/.bkit/shared/docs/data-schema.md +4 -7
  235. package/.bkit/shared/docs/deployments.md +241 -168
  236. package/.bkit/shared/docs/design.md +11 -12
  237. package/.bkit/shared/docs/noise.md +8 -7
  238. package/.bkit/shared/docs/observability.md +5 -8
  239. package/.bkit/shared/docs/security.md +35 -17
  240. package/.bkit/shared/docs/setup.md +29 -18
  241. package/.bkit/shared/docs/technology.md +3 -6
  242. package/.bkit/shared/docs/testing.md +289 -174
  243. package/.bkit/shared/gitignore +6 -2
  244. package/.bkit/templates/.claude/hooks/bkit-cloud-bootstrap.sh +15 -16
  245. package/.bkit/templates/.cursor/Dockerfile +12 -8
  246. package/.bkit/templates/.cursor/environment.json +1 -1
  247. package/.bkit/templates/.github/ISSUE_TEMPLATE/bkit-bug.yml +10 -8
  248. package/.bkit/templates/.github/ISSUE_TEMPLATE/bkit-change.yml +45 -12
  249. package/.bkit/templates/.github/ISSUE_TEMPLATE/bkit-idea.yml +3 -3
  250. package/.bkit/templates/.github/renovate.json5 +34 -6
  251. package/.bkit/templates/.github/workflows/bkit-ci.yml +54 -51
  252. package/.bkit/templates/.github/workflows/bkit-cloud.yml +34 -33
  253. package/.bkit/templates/.github/workflows/bkit-health.yml +97 -0
  254. package/.bkit/templates/.github/workflows/bkit-renovate.yml +5 -4
  255. package/.bkit/templates/.github/workflows/bkit-trivy.yml +5 -4
  256. package/.bkit/templates/.husky/pre-commit +2 -2
  257. package/.bkit/templates/.husky/pre-push +96 -36
  258. package/.bkit/templates/.prettierignore +6 -0
  259. package/.bkit/templates/.vale.ini +27 -27
  260. package/.bkit/templates/context/bkit-cloudrun.md +23 -15
  261. package/.bkit/templates/context/bkit-expo.md +70 -52
  262. package/.bkit/templates/context/bkit-github.md +93 -56
  263. package/.bkit/templates/context/bkit-inngest.md +21 -15
  264. package/.bkit/templates/context/bkit-maestro.md +22 -16
  265. package/.bkit/templates/context/bkit-playwright.md +23 -17
  266. package/.bkit/templates/context/bkit-resend.md +12 -10
  267. package/.bkit/templates/context/bkit-sentry.md +30 -20
  268. package/.bkit/templates/context/bkit-serena.md +8 -7
  269. package/.bkit/templates/context/bkit-stripe.md +14 -13
  270. package/.bkit/templates/context/bkit-supabase.md +16 -13
  271. package/.bkit/templates/context/bkit-tavily.md +14 -11
  272. package/.bkit/templates/context/bkit-vercel.md +27 -18
  273. package/.bkit/templates/docs/capabilities.md +15 -14
  274. package/.bkit/templates/scripts/ci/{check-accepted-divergences.mjs → bkit-check-accepted-divergences.mjs} +6 -3
  275. package/.bkit/templates/scripts/ci/{check-accepted-divergences.test.mjs → bkit-check-accepted-divergences.test.mjs} +3 -3
  276. package/.bkit/templates/scripts/ci/{check-capstone.mjs → bkit-check-capstone.mjs} +2 -2
  277. package/.bkit/templates/scripts/ci/{check-capstone.test.mjs → bkit-check-capstone.test.mjs} +4 -4
  278. package/.bkit/templates/scripts/ci/{check-dependency-audit.mjs → bkit-check-dependency-audit.mjs} +103 -18
  279. package/.bkit/templates/scripts/ci/{check-dependency-audit.test.mjs → bkit-check-dependency-audit.test.mjs} +31 -3
  280. package/.bkit/templates/scripts/ci/bkit-machine-lock.sh +387 -0
  281. package/.bkit/templates/scripts/ci/bkit-test-awake.mjs +75 -0
  282. package/.bkit/templates/scripts/ci/bkit-test-awake.test.mjs +160 -0
  283. package/.bkit/templates/scripts/ci/lanes/{resolve-push-base.mjs → bkit-resolve-push-base.mjs} +3 -3
  284. package/.bkit/templates/scripts/ci/lanes/{resolve-push-base.test.mjs → bkit-resolve-push-base.test.mjs} +4 -4
  285. package/.bkit/templates/scripts/cleanup/bkit-disk-prune.mjs +10 -2
  286. package/.bkit/templates/scripts/graphify/bkit-graph-drift.py +1 -1
  287. package/.bkit/templates/scripts/graphify/bkit-graph-eager.py +3 -3
  288. package/.bkit/templates/scripts/graphify/bkit-graph-embed.py +63 -0
  289. package/.bkit/templates/scripts/graphify/bkit-graph-imports.py +2 -2
  290. package/.bkit/templates/scripts/graphify/bkit-graph-pre-push.sh +69 -18
  291. package/.bkit/templates/scripts/graphify/bkit-graph-repair.py +3 -3
  292. package/.bkit/templates/scripts/graphify/bkit-graph-surface.py +1 -1
  293. package/.bkit/templates/scripts/graphify/bkit-graphify-graphml.py +1 -1
  294. package/.bkit/templates/scripts/graphify/bkit-graphify-rollup.py +197 -126
  295. package/.bkit/templates/scripts/graphify/bkit-graphify.sh +64 -41
  296. package/.bkit/templates/scripts/slop/bkit-slop-type-suppression.mjs +23 -7
  297. package/.bkit/templates/slop-scan.config.json +9 -2
  298. package/CHANGELOG.md +231 -0
  299. package/README.md +278 -89
  300. package/dist/checks/after/auth.js +36 -33
  301. package/dist/checks/after/ci-yml.js +91 -30
  302. package/dist/checks/after/github.js +91 -17
  303. package/dist/checks/after/index.js +22 -11
  304. package/dist/checks/after/suppression.js +8 -5
  305. package/dist/checks/after/tools.js +111 -114
  306. package/dist/checks/before/context-fetch.js +218 -33
  307. package/dist/checks/before/env.js +3 -3
  308. package/dist/checks/before/files.js +5 -3
  309. package/dist/checks/before/index.js +20 -3
  310. package/dist/checks/before/repo.js +197 -2
  311. package/dist/checks/status-holes.js +739 -114
  312. package/dist/checks/tips/catalogue.js +70 -19
  313. package/dist/checks/tips/detect.js +62 -0
  314. package/dist/checks/tips/index.js +51 -9
  315. package/dist/cli.js +234 -124
  316. package/dist/commands/analysis.js +174 -141
  317. package/dist/commands/ci/ci.js +302 -25
  318. package/dist/commands/ci/pins.js +142 -0
  319. package/dist/commands/ci/push-gate.js +194 -0
  320. package/dist/commands/comply.js +54 -91
  321. package/dist/commands/install/doctor.js +2 -2
  322. package/dist/commands/install/install.js +50 -19
  323. package/dist/commands/install/uninstall.js +82 -55
  324. package/dist/commands/install/upgrade.js +21 -11
  325. package/dist/commands/land.js +137 -17
  326. package/dist/commands/lib.js +295 -21
  327. package/dist/commands/registry.js +10 -2
  328. package/dist/commands/setup/setup.js +8 -7
  329. package/dist/commands/stats.js +175 -0
  330. package/dist/commands/tips.js +7 -3
  331. package/dist/commands/workflow/branches.js +1873 -152
  332. package/dist/commands/workflow/challenge.js +609 -0
  333. package/dist/commands/workflow/completeness.js +97 -0
  334. package/dist/commands/workflow/context.js +1045 -46
  335. package/dist/commands/workflow/counters.js +385 -86
  336. package/dist/commands/workflow/decisions.js +484 -0
  337. package/dist/commands/workflow/disk.js +214 -56
  338. package/dist/commands/workflow/fids.js +706 -33
  339. package/dist/commands/workflow/issues.js +349 -59
  340. package/dist/commands/workflow/ledgers.js +1123 -37
  341. package/dist/commands/workflow/locks.js +26 -2
  342. package/dist/commands/workflow/plan-blocks.js +501 -0
  343. package/dist/commands/workflow/plan-versions.js +22 -0
  344. package/dist/commands/workflow/plans.js +205 -0
  345. package/dist/commands/workflow/prs.js +154 -35
  346. package/dist/commands/workflow/repo.js +58 -8
  347. package/dist/commands/workflow/roadmap.js +58 -23
  348. package/dist/commands/workflow/run-facts.js +421 -0
  349. package/dist/commands/workflow/runs.js +670 -72
  350. package/dist/commands/workflow/runtime.js +15 -1
  351. package/dist/commands/workflow/skills.js +1 -0
  352. package/dist/commands/workflow/status.js +282 -34
  353. package/dist/commands/workflow/step-table.js +308 -0
  354. package/dist/commands/workflow/steps.js +703 -96
  355. package/dist/commands/workflow/summary-findings.js +117 -0
  356. package/dist/commands/workflow/summary.js +388 -0
  357. package/dist/commands/workflow/tasks.js +378 -0
  358. package/dist/commands/workflow/test-blocks.js +231 -0
  359. package/dist/commands/workflow/tests-changed.js +172 -0
  360. package/dist/commands/workflow/tests.js +1695 -305
  361. package/dist/commands/workflow/tracker.js +983 -0
  362. package/dist/commands/workflow/workflows.js +1014 -222
  363. package/dist/commands/workflow/worktrees.js +432 -26
  364. package/dist/install/cloud-env.js +233 -99
  365. package/dist/install/context-ci-workflow.js +85 -0
  366. package/dist/install/manifest.js +64 -17
  367. package/dist/install/modules/antigravity.js +3 -2
  368. package/dist/install/modules/cloud.js +25 -16
  369. package/dist/install/modules/codex.js +12 -2
  370. package/dist/install/modules/core.js +1090 -48
  371. package/dist/install/modules/cursor.js +6 -6
  372. package/dist/install/modules/opencode.js +13 -7
  373. package/dist/install/template-notes.js +116 -0
  374. package/dist/install/version-file.js +9 -4
  375. package/dist/ledgers/compact.js +87 -0
  376. package/dist/ledgers/journal.js +233 -0
  377. package/dist/ledgers/migrate.js +81 -0
  378. package/dist/ledgers/status.js +176 -13
  379. package/dist/ledgers/telemetry.js +1010 -125
  380. package/dist/render/hosts.js +104 -14
  381. package/dist/render/models.js +12 -0
  382. package/dist/shared/bkit-latest.js +26 -4
  383. package/dist/shared/branches.js +3 -1
  384. package/dist/shared/dep-updater.js +49 -0
  385. package/dist/shared/egress.js +8 -1
  386. package/dist/shared/json.js +20 -7
  387. package/dist/shared/package-manager.js +6 -0
  388. package/dist/shared/settings.js +181 -24
  389. package/dist/shared/text.js +333 -0
  390. package/dist/shared/timeouts.js +2 -0
  391. package/dist/tools/cli-doc.js +97 -0
  392. package/dist/tools/grammar-density.js +183 -0
  393. package/dist/tools/instructions-sources.js +720 -0
  394. package/dist/tools/instructions.js +1623 -0
  395. package/package.json +156 -51
  396. package/.bkit/core/.bkit/lite.md +0 -73
  397. package/.bkit/core/engine/commands/harvest.ts +0 -459
  398. package/.bkit/core/engine/commands/workflow/workstreams.ts +0 -166
  399. package/.bkit/core/engine/tools/wording.ts +0 -748
  400. package/.bkit/core/prompts/bkit-build-challenge-reconcile.md +0 -69
  401. package/.bkit/core/prompts/bkit-build-challenge-remediate.md +0 -71
  402. package/.bkit/core/prompts/bkit-build-challenge-tests.md +0 -74
  403. package/.bkit/core/prompts/bkit-build-plan-execute.md +0 -76
  404. package/.bkit/core/prompts/bkit-build-summary.md +0 -94
  405. package/.bkit/core/prompts/bkit-debug-summary.md +0 -96
  406. package/.bkit/core/prompts/bkit-design-summary.md +0 -107
  407. package/.bkit/core/prompts/bkit-plan-complexity-check.md +0 -67
  408. package/.bkit/core/prompts/bkit-plan-complexity-split.md +0 -88
  409. package/.bkit/core/prompts/bkit-plan-review-3.md +0 -93
  410. package/.bkit/core/prompts/bkit-plan-scope-check-1.md +0 -85
  411. package/.bkit/core/prompts/bkit-plan-scope-check-2.md +0 -85
  412. package/.bkit/core/prompts/bkit-plan-summary.md +0 -107
  413. package/.bkit/core/prompts/bkit-ship-summary.md +0 -78
  414. package/.bkit/templates/scripts/ci/bkit-local-stack-lock.sh +0 -194
  415. package/dist/commands/harvest.js +0 -353
  416. package/dist/commands/workflow/workstreams.js +0 -143
  417. package/dist/tools/wording.js +0 -680
  418. /package/.bkit/templates/.vale/styles/{House → Bkit}/Filler.yml +0 -0
  419. /package/.bkit/templates/.vale/styles/{House → Bkit}/Hedging.yml +0 -0
  420. /package/.bkit/templates/.vale/styles/{House → Bkit}/LLMSlop.yml +0 -0
  421. /package/.bkit/templates/.vale/styles/{House → Bkit}/Verbose.yml +0 -0
  422. /package/.bkit/templates/scripts/ci/{accepted-advisories.json → bkit-accepted-advisories.json} +0 -0
  423. /package/.bkit/templates/scripts/ci/{accepted-divergences.json → bkit-accepted-divergences.json} +0 -0
  424. /package/.bkit/templates/scripts/launchd/{launchd.env.example → bkit-launchd.env.example} +0 -0
  425. /package/.bkit/templates/scripts/launchd/{ai.bkit.launchd.plist → bkit-launchd.plist} +0 -0
@@ -1,55 +1,50 @@
1
- <!-- Note: Reports live at `docs/audits/{YYYYMM}/{slug}.md`. `{YYYYMM}` = UTC month of this run. `{slug}` = template basename without `bkit-audit-` and `.md`. **If** that month already has `{slug}.md` or `{slug}-{TIMESTAMP}.md` → write `{slug}-{TIMESTAMP}.md` (`{TIMESTAMP}` = `date -u +%Y%m%dT%H%M%SZ`). Never overwrite. The report is stamped with a `bkit:anchor` block recording the audited commit (`baseSha`) and branch (`baseRef`); never hand-author or edit it. `@bkit-audit-generate` fills this template. -->
2
-
3
1
  <!-- bkit:start -->
4
2
 
5
3
  {{BKIT_MANAGED_MARKER}}
6
4
 
5
+ <!-- Note: @bkit-audit-generate fills this template. The report lives at `docs/audits/{YYYYMM}/{slug}.md`, where `{YYYYMM}` is the UTC month of the run and `{slug}` is this file's name without `bkit-audit-` and `.md`. **If** that month already has `{slug}.md` or `{slug}-{TIMESTAMP}.md` → write `{slug}-{TIMESTAMP}.md`, where `{TIMESTAMP}` is the output of `date -u +%Y%m%dT%H%M%SZ`. NEVER overwrite an earlier report. The report is stamped with a `bkit:anchor` block that records the audited commit (`baseSha`) and branch (`baseRef`). NEVER write or edit that block by hand. -->
6
+
7
7
  # Model Audit
8
8
 
9
9
  > [!CAUTION]
10
- > **Purpose:** Each call site: latest capable model for the job; model and fallbacks live; choice in one registry.
10
+ > **Purpose:** For each call site: the latest capable model for the job, a live model with live fallbacks, and the choice kept in one registry.
11
11
  >
12
12
  > **Rules:**
13
13
  >
14
- > - Read-only audit; never edit code, config, or data.
15
- > - `Universal Instructions` apply to all projects; `Project Instructions` apply only to this project.
16
- > - Local audit instructions / overrides → `Project Instructions` below the bkit-managed block; universal instructions stay in-block.
17
- > - Any tools mentioned in `Universal Instructions` are examples only; swap for actual tools in final output; drop inapplicable.
18
- > - Use dense token-efficient phrasing; no filler / hedging / restating; tables > prose, bullets > paragraphs.
19
- > - Read `.agents/docs.md` → load docs for workflow / step / task; skip missing; cite docs inline where required.
20
- > - Every claim cites this run's evidence (`file:line`, or command / query and its output) and tool behind it; a previous report's figure, list, or status is a lead, not evidence.
21
- > - Read this document once at session start; do not trust session memory; do not re-read on every loop iteration.
22
- > - never edit the model registry, call wrappers, routing config, or call sites; the report proposes the replacement.
23
- > - Fallback probes use a synthetic fixture; NEVER send production user content, and NEVER write the spend ledger.
24
- > - never publish a number with no recorded source.
14
+ > - Never edit the model registry, call wrappers, routing config or call sites.
15
+ > - The report proposes the replacement.
16
+ > - Run fallback probes with a synthetic fixture.
17
+ > - NEVER send production user content.
18
+ > - Never write the spend ledger.
19
+ > - Never publish a number with no recorded source.
25
20
 
26
21
  ## Universal Instructions
27
22
 
28
23
  ### Context & Goals
29
24
 
30
- Config ids look identical delisted vs choice day. Target failure: **a stale entry indistinguishable from a working one until a fallback fires, which is the moment it has to work** — e.g. text-only model in a file chain, two chains sharing one fallback that then disappears, a floating alias that now names a different model. Pull live catalogue; do not remember or infer ids from version numbers.
25
+ A config id looks the same on the day it is delisted as on the day it was chosen. The failure this audit targets is a stale entry that looks the same as a working one until a fallback fires, which is the moment it has to work. Examples: a text-only model in a file chain, two chains that share one fallback that then disappears, a floating alias that now names a different model. Pull the live catalogue; do not remember ids, or infer them from version numbers.
31
26
 
32
- **Applies when:** code calls hosted model (chat, tools, vision, embeddings, any modality). None → one `N/A` row with evidence, never "clean".
27
+ **Applies when:** code calls a hosted model (chat, tools, vision, embeddings, any modality). **If** it does not → write one `N/A` row with its evidence, and never report the surface as "clean".
33
28
 
34
- **Cadence:** monthly. Extra pass when listed id delisted, call-sends capability lost, expiration or deprecation added, alias resolves to different canonical id, or new task/call site routes through fallback wrapper.
29
+ **Cadence:** Run once a month. Run an extra pass when a listed id is delisted, a capability the call sends is lost, an expiration or deprecation is added, an alias resolves to a different canonical id, or a new task or call site routes through the fallback wrapper.
35
30
 
36
- **Anchor Standards:** record version and date read. Newer version → `Standards` step reads what changed.
31
+ **Anchor Standards:**
37
32
 
38
- - Provider model-list APIs, including lifecycle and per-endpoint fields (e.g. OpenRouter models and endpoints APIs: `expiration_date`, `canonical_slug`, `knowledge_cutoff`; Anthropic, OpenAI, and Google model lists).
39
- - Provider routing controls (e.g. OpenRouter `require_parameters`, `quantizations`, `max_price`, `allow_fallbacks`, zero-retention).
40
- - Maker deprecation pages (e.g. Anthropic, OpenAI, Google), plus the equivalent for every other maker in a chain.
33
+ - Provider model-list APIs, including lifecycle and per-endpoint fields (e.g., OpenRouter models and endpoints APIs: `expiration_date`, `canonical_slug`, `knowledge_cutoff`; Anthropic, OpenAI, and Google model lists).
34
+ - Provider routing controls (e.g., OpenRouter `require_parameters`, `quantizations`, `max_price`, `allow_fallbacks`, zero-retention).
35
+ - Maker deprecation pages (e.g., Anthropic, OpenAI, Google), plus the equivalent for every other maker in a chain.
41
36
  - Model cards published by each model's maker.
42
37
  - NIST AI 600-1, Generative AI Profile, MEASURE, and MANAGE for third-party models.
43
- - OWASP Top 10 for LLM Applications, LLM03 Supply Chain; record the edition (e.g. 2025).
38
+ - OWASP Top 10 for LLM Applications, LLM03 Supply Chain; record the edition (e.g., 2025).
44
39
 
45
40
  ### Scope
46
41
 
47
- - Live provider catalogue = standard for every listed and proposed id.
48
- - Call-site fitness: capability, cost (catalogue price, not spend), latency, context, modality.
49
- - Deprecation, retirement, supersession, expiration.
50
- - Endpoints and fallbacks live, not model-summary claim.
51
- - One registry vs scattered ids.
52
- - Proposed registry and per-task routing; not applied this run.
42
+ - Judge every listed and proposed id against the live provider catalogue.
43
+ - Check each call site's fitness: capability, cost (catalogue price, not spend), latency, context and modality.
44
+ - Check deprecation, retirement, supersession and expiration.
45
+ - Check that endpoints and fallbacks are live, not only claimed in the model summary.
46
+ - Check whether ids live in one registry or are scattered.
47
+ - Propose a registry and per-task routing. This run does not apply them.
53
48
 
54
49
  ### Out of Scope
55
50
 
@@ -66,57 +61,83 @@ Config ids look identical delisted vs choice day. Target failure: **a stale entr
66
61
 
67
62
  ### Pre-Flight / Dependencies
68
63
 
69
- **Checkpoint:** Check off all core items. Check conditional items only when applicable. Each item: available → tool and version; missing → fallback, gap in `Not Checked`, fix in `Process Improvements`. Unnamed gap reads as passed. never abort for a missing capability.
70
-
71
- **Credentials:** probe direnv before marking a token / env var missing: `direnv exec . sh -c '[ -n "${VAR}" ] && echo set || echo unset'`; `unset` = missing. Run credentialed CLIs as `direnv exec . <cmd>`. No direnv (cloud session) → plain env check. Report names, never values.
72
-
73
64
  #### Core
74
65
 
75
- Always verify.
76
-
77
- - [ ] **Permissions:** Before Step 1 — one cheap read-only call per tool this run uses (every item below, every rule under `Project Instructions` `Permissions`), e.g. `gh run list --limit 1`, one MCP read, one anchor-standard fetch. Blocked / denied (here or in any step) → record call verbatim and narrow allow rule clearing it (e.g. `Bash(gh run list *)`) in `Not Checked`, `Process Improvements`, and `Project Instructions` `Permissions`; run every step the remaining tools allow; work needing blocked call → `Not Checked`. never stop the run for a blocked call; never retry or reword a blocked call to get past it.
78
- - [ ] **Catalogue Read:** Steps 3, 5, 6 — live model list per provider call sites use, e.g. OpenRouter `/api/v1/models`, Anthropic models API, OpenAI models API, Google models API. Fallback: maker docs only; live-endpoint claims = hypotheses.
79
- - [ ] **Web:** Steps 5, 10 — maker deprecation pages, model cards, anchor standards. Fallback: versions recorded as unread.
66
+ - [ ] **Permissions:** every blocked call is recorded.
67
+ - [ ] **Catalogue Read:** Steps 3, 5, 6 — the live model list for each provider the call sites use (e.g., OpenRouter `/api/v1/models`, Anthropic models API, OpenAI models API, Google models API). Fallback: read maker docs only, and treat live-endpoint claims as hypotheses.
68
+ - [ ] **Web:** Steps 5, 10 — maker deprecation pages, model cards, anchor standards. Fallback: record the versions as unread.
80
69
 
81
70
  #### Conditional
82
71
 
83
- Verify only when applicable.
84
-
85
- - [ ] **Language Server:** Typed call sites → Step 4 — references, e.g. Serena, `tsserver`. Fallback: text search; name it per claim.
86
- - [ ] **Endpoint API:** Provider exposes per-model endpoints → Step 6 — e.g. OpenRouter endpoints API. Fallback: model-summary fields only; say so.
87
- - [ ] **Usage Ledger:** A usage ledger exists → Step 6 — largest measured input per task. Fallback: catalogue context only; measured input `Not Checked`.
88
- - [ ] **Live Call:** Credential for a fixture call → Step 7. Fallback: endpoint metadata only; liveness `Not Checked`.
72
+ - [ ] **Language Server:** **If** call sites are typed → Step 4 — references (e.g., Serena, `tsserver`). Fallback: text search, and name the tool for each claim.
73
+ - [ ] **Endpoint API:** **If** the provider exposes per-model endpoints → Step 6 — the endpoint list (e.g., OpenRouter endpoints API). Fallback: read model-summary fields only, and say so.
74
+ - [ ] **Usage Ledger:** **If** a usage ledger exists → Step 6 — the largest measured input per task. Fallback: use catalogue context only, and mark measured input `Not Checked`.
75
+ - [ ] **Live Call:** **If** there is a credential for a fixture call → Step 7. Fallback: read endpoint metadata only, and mark liveness `Not Checked`.
89
76
 
90
77
  ### 🔒 Gate 1: Prerequisites Check
91
78
 
92
- **Checkpoint.** Verify and check `[x]` all applicable boxes above, then continue to `Probe Steps` without asking.
93
-
94
- - [ ] **Gaps named:** every missing item names its fallback and `Not Checked` entry.
95
- - [ ] **Gate 1 - Verified:** All Core items checked. All applicable Conditional items checked.
79
+ - [ ] **Gaps named:** every missing item names its fallback and its `Not Checked` entry.
80
+ - [ ] **Gate 1 — Verified:** every item above, every Core item and every applicable Conditional item is checked.
96
81
 
97
82
  ### Probe Steps
98
83
 
99
- - [ ] **Step 1 — Previous Run:** Audited commit = this report's `bkit:anchor` `baseSha`. Read newest prior report for this slug under `docs/audits/`; its commit = its `bkit:anchor` `baseSha`, else the HEAD its `Previous Run` recorded. Count findings fixed / still open; age of oldest open. Open after 2 runs → re-raise with age. **Done when:** closure rate in `Previous Run`, or run marked baseline.
100
- - [ ] **Step 2 — Detect:** Find every model call site (SDK calls, HTTP to a model API, config lists) and whether choice lives in one registry or literals at sites. Embeddings and other modalities count. Registry absent and ids inline = scatter is the finding; still audit ids. **Done when:** evidence in `Checked`, or `N/A` and STOP.
101
- - [ ] **Step 3 — Catalogue:** Pull live catalogue for each provider Step 2 found. Record date, URL, counts (full list, any constrained subset calls require, e.g. zero-retention). Every id proposed later must exist in this pull. **Done when:** date, source, and counts in `Catalogue`.
102
- - [ ] **Step 4 — Call Sites:** Derive each call site's requirements from code this run: modality, tools, and tool choice, structured output, reasoning, output cap, timeout. Do not copy a requirements table forward. Language-server references on each wrapper and each exported chain → every task routing through it; re-run empty results, corroborate with text search. Empty is inconclusive. Task added since previous report appears here only. **Done when:** `Call Sites` row per site: task · wrapper · requirements · chain · `file:line` · how derived.
103
- - [ ] **Step 5 — Lifecycle:** Hard filters on every listed id and candidate vs Step 3 pull + maker page. (a) Retention call sends (e.g. zero-retention): no matching endpoint → reject (id does not route). (b) `expiration_date` + maker deprecation page; reject id expiring before next refresh; reject preview, experimental, free-tier variants. (c) Tool-calling candidate whose reasoning cannot be switched off → reject (reasoning tokens exhaust the output budget, the model returns no tool call, and the wrapper surfaces a truncation error). (d) Alias or dated snapshot, and which canonical id it resolved to on the pull date. Prefer dated snapshots. An alias whose canonical id differs from the previous report = a model change: name `bkit-audit-llm`; do not run the eval here. (e) Model card URL, knowledge cutoff, open-weight licence, training-on-data policy, maker terms for products serving minors, hosting region for retention-satisfying endpoints. Children's data crossing borders → `bkit-audit-privacy`. **Done when:** `Lifecycle` row per id: filters · canonical id · card · verdict.
104
- - [ ] **Step 6 — Endpoints:** Model-level summary can pass Step 5 while no single endpoint does. Query endpoints, not summary. Require ≥1, ideally 2, satisfying retention constraint and every parameter call site sends (tools, tool choice including required value, file, structured output — as Step 4's table requires). Record whether call sets flag stopping router sending a parameter to provider that ignores it (e.g. `require_parameters`). Absent → propose in `Proposal`. Open weights: quantization per endpoint; propose pin or order where quality differs. Compare each endpoint's context length and max completion with largest measured input for that task (ledger when it has task; say when not). No output cap on tool-calling path = defect in current list; propose value per task. Latency and throughput per endpoint vs call timeout. Catalogue price = fitness comment on proposed row. Blended spend and fallback-rate dollars → `bkit-audit-cost`. Propose per-task price ceiling as routing config, not spend figure. **Done when:** `Endpoints` row per id: qualifying endpoints · parameters · context vs input · latency vs timeout · verdict.
105
- - [ ] **Step 7 — Fallbacks:** (a) Chain positions = different makers → one delisting or outage cannot collapse retry. Record router as single point of failure; whether any call constructs direct maker client. Diagram naming maker SDKs is not that client. (b) One synthetic fixture per chain position, under routing parameters production sends. Pass = position accepted call shape. Fail = finding. Proves fallback answers; does not score quality. Extraction accuracy, tool-call validity rate, hostile fixture → `bkit-audit-llm`. (c) Record whether anything counts how often a position fires. Nothing = finding; counter = `Process Improvements` proposal; spend consequence → `bkit-audit-cost`. **Done when:** `Fallbacks` row per position: maker · fixture result or skip · fire-rate measured · verdict.
106
- - [ ] **Step 8 — Registry:** Re-check current list, not only candidates. (1) Modality: every model in chain accepts input call site sends (image support does not satisfy file part). (2) Reasoning that cannot be switched off on tool-calling path. (3) Task group or list with no call site. References on export plus text search, including docs — search sees planning docs language server does not. Recommend delete unless plan in progress. Carrying lists for unbuilt feature = how registry goes stale. (4) Model ids outside registry. **Done when:** every hit = finding with `file:line`, or clean stated in `Registry`.
107
- - [ ] **Step 9 — Proposal:** Proposed list + per-task config (retention, required-parameters, quantization pin, price ceiling, output cap); catalogue price and context window as row comments. Chain order = judgement unless `bkit-audit-llm` scorecard cited — label which. Never an invented score. Apply order (report only, does not apply): (1) wrappers must pass per-task settings or nothing else applies; (2) retention routing pinned at the shared boundary before the model switch, so new models are validated under the routing they will run; (3) import registry, delete hardcoded lists, apply list + per-task config; (4) the eval audit's check before the list is treated as mergeable — do not change model, sampling, and fallback behaviour in one unmeasured step; (5) watch with named revert (current lists, by commit) + per-signal thresholds (format-error rate, fallback-fire count, task success). Cost per job → `bkit-audit-cost`. Open decision → one `Proposal` question + recommendation + what would settle it. Route: defect / filter-fail id → proposed list; missing routing param → per-task config; wrapper cannot pass settings → apply-order (1); model change (incl. alias move) → `bkit-audit-llm`; children's-data borders → `bkit-audit-privacy`; unwired group → delete recommendation. **Done when:** `Proposal` holds list, apply order, watch plan, any open question.
108
- - [ ] **Step 10 — Standards:** Confirm current version per anchor standard; read changes since previous report's version. `Standards Coverage`: one row per catalogue field, routing parameter, maker lifecycle rule, and third-party-model control this procedure relies on → checked (name step) / not applicable (why) / finding. Unapplied recommended practice → adopt (propose step) / reject (why) / not applicable. **Done when:** no empty row.
109
- - [ ] **Step 11 — Anything Else:** (a) Everything changed since previous report's commit touching model choice (registry, wrappers, call sites, routing parameters, embedding model id) → one-line verdict each. Read provider and maker changelogs since previous report for changed meaning of retention routing, reasoning, tool choice, or pricing. Flag catalogue anomalies on current ids: price jump, context cut, endpoint count fallen to one. (b) Bounded ~30 min pass: what senior ML platform engineer flags that no step asks; read since previous run (incidents, `bkit-audit-logs` reports, new `docs/failures.jsonl` rows, vendor status incidents) — what would no step catch? Include catalogue/changelog items surfaced unchecked, with query for next run. **Done when:** `Beyond the Steps` holds both passes, or `none`. Class seen on 2 runs → propose step in `Process Improvements`.
84
+ - [ ] **Step 1 — Previous Run:** **Done when:** `Previous Run` holds the closure rate, or the run is marked baseline.
85
+ - [ ] **Step 2 — Detect:** Find every model call site (SDK calls, HTTP to a model API, config lists), and whether the choice lives in one registry or as literals at the sites. Embeddings and other modalities count. **If** there is no registry **and** ids are inline → the scatter is the finding; still audit the ids. **Done when:** `Checked` holds evidence, or `N/A` is recorded → **STOP**.
86
+ - [ ] **Step 3 — Catalogue:** Pull the live catalogue for each provider Step 2 found. Record the date, the URL and the counts (the full list, and any constrained subset the calls require, e.g., zero-retention). Every id proposed later must exist in this pull. **Done when:** the date, source and counts are in `Catalogue`.
87
+ - [ ] **Step 4 — Call Sites:** Derive each call site's requirements from the code on this run: modality, tools and tool choice, structured output, reasoning, output cap, timeout. Do not copy a requirements table forward. Run language-server references on each wrapper and each exported chain to find every task that routes through it. Re-run empty results, and corroborate them with text search, because an empty result is inconclusive. A task added since the previous report shows up only through this step. **Done when:** `Call Sites` has a row per site: task · wrapper · requirements · chain · `file:line` · how derived.
88
+ - [ ] **Step 5 — Lifecycle:** Apply hard filters to every listed id and candidate, against the Step 3 pull and the maker page. (a) Retention the call sends (e.g., zero-retention). **If** no endpoint matches → reject the id, because it does not route. (b) `expiration_date` and the maker deprecation page. Reject an id that expires before the next refresh. Reject preview, experimental and free-tier variants. (c) **If** a tool-calling candidate's reasoning cannot be switched off → reject it. Reasoning tokens exhaust the output budget, the model returns no tool call, and the wrapper surfaces a truncation error. (d) Alias or dated snapshot, and which canonical id it resolved to on the pull date. Prefer dated snapshots. An alias whose canonical id differs from the previous report is a model change: name `bkit-audit-llm`, and do not run the eval here. (e) The model card URL, knowledge cutoff, open-weight licence, training-on-data policy, maker terms for products that serve minors, and the hosting region for retention-satisfying endpoints. Children's data crossing borders goes to `bkit-audit-privacy`. **Done when:** `Lifecycle` has a row per id: filters · canonical id · card · verdict.
89
+ - [ ] **Step 6 — Endpoints:** A model-level summary can pass Step 5 while no single endpoint does, so query the endpoints, not the summary. Require >=1 endpoint, ideally 2, that satisfies the retention constraint and every parameter the call site sends (tools, tool choice including the required value, file, structured output — as Step 4's table requires).
90
+ - Record whether the call sets the flag that stops the router sending a parameter to a provider that ignores it (e.g., `require_parameters`).
91
+ - **If** the flag is absent → propose it in `Proposal`.
92
+ - For open weights, record the quantization per endpoint, and propose a pin or an order where quality differs.
93
+ - Compare each endpoint's context length and max completion with the largest measured input for that task, taken from the ledger.
94
+ - **If** the ledger does not have the task → say so.
95
+ - No output cap on a tool-calling path is a defect in the current list; propose a value per task.
96
+ - Compare latency and throughput per endpoint with the call timeout.
97
+ - The catalogue price is a fitness comment on the proposed row. Blended spend and fallback-rate dollars belong to `bkit-audit-cost`.
98
+ - Propose a per-task price ceiling as routing config, not as a spend figure.
99
+
100
+ **Done when:** `Endpoints` has a row per id: qualifying endpoints · parameters · context vs input · latency vs timeout · verdict.
101
+
102
+ - [ ] **Step 7 — Fallbacks:** (a) Check that the chain positions come from different makers, so one delisting or outage cannot collapse the retry. Record the router as a single point of failure, and whether any call constructs a direct maker client. A diagram that names maker SDKs is not that client. (b) Run one synthetic fixture per chain position, under the routing parameters production sends. A pass means the position accepted the call shape. A fail is a finding. This proves the fallback answers; it does not score quality. Extraction accuracy, tool-call validity rate and the hostile fixture belong to `bkit-audit-llm`. (c) Record whether anything counts how often a position fires. **If** nothing does:
103
+ - Record it as a finding.
104
+ - Propose a counter in `Process Improvements`.
105
+ - Send the spend consequence to `bkit-audit-cost`.
106
+
107
+ **Done when:** `Fallbacks` has a row per position: maker · fixture result or skip · fire-rate measured · verdict.
108
+
109
+ - [ ] **Step 8 — Registry:** Re-check the current list, not only the candidates. (1) Modality: every model in the chain accepts the input the call site sends (image support does not satisfy a file part). (2) Reasoning that cannot be switched off on a tool-calling path. (3) A task group or list with no call site. Run references on the export plus text search, including docs, because text search sees planning docs that the language server does not. Recommend deleting it unless a plan is in progress, because carrying lists for an unbuilt feature is how a registry goes stale. (4) Model ids outside the registry. **Done when:** every hit is a finding with `file:line`, or `Registry` states that it is clean.
110
+ - [ ] **Step 9 — Proposal:** Write the proposed list and per-task config (retention, required-parameters, quantization pin, price ceiling, output cap), with the catalogue price and context window as row comments.
111
+ - Label the chain order as a judgement, or cite the `bkit-audit-llm` scorecard it comes from.
112
+ - Never invent a score.
113
+ - Give the apply order; the report does not apply it.
114
+ - (1) Wrappers must pass per-task settings, or nothing else applies.
115
+ - (2) Pin retention routing at the shared boundary before the model switch, so new models are validated under the routing they will run.
116
+ - (3) Import the registry, delete hardcoded lists, and apply the list and per-task config.
117
+ - (4) Run the eval audit's check before the list is treated as mergeable; do not change model, sampling and fallback behaviour in one unmeasured step.
118
+ - (5) Watch with a named revert (the current lists, by commit) and per-signal thresholds (format-error rate, fallback-fire count, task success). Cost per job belongs to `bkit-audit-cost`.
119
+ - **If** a decision is open → write one `Proposal` question with `Options: A) … / B) …` and a `Recommended: A) … — {reason}` naming the chosen letter, plus what would settle it.
120
+ - Route each finding:
121
+ - a defect or filter-fail id → the proposed list
122
+ - a missing routing param → per-task config
123
+ - a wrapper that cannot pass settings → apply-order (1)
124
+ - a model change (including an alias move) → `bkit-audit-llm`
125
+ - children's-data borders → `bkit-audit-privacy`
126
+ - an unwired group → a delete recommendation
127
+
128
+ **Done when:** `Proposal` holds the list, apply order, watch plan and any open question.
129
+
130
+ - [ ] **Step 10 — Standards:** Confirm the current version of each anchor standard, and read what changed since the previous report's version. Give `Standards Coverage` one row per catalogue field, routing parameter, maker lifecycle rule and third-party-model control this procedure relies on, each marked checked (naming the step), not applicable (saying why) or finding. Mark each recommended practice the project does not apply as adopt (with a proposed step), reject (saying why) or not applicable. **Done when:** no row is empty.
131
+ - [ ] **Step 11 — Anything Else:** (a) Give a one-line verdict on each change since the previous report's commit that touches model choice: the registry, wrappers, call sites, routing parameters and embedding model id. Read the provider and maker changelogs since the previous report for a changed meaning of retention routing, reasoning, tool choice or pricing. Flag catalogue anomalies on current ids: a price jump, a context cut, an endpoint count fallen to one. (b) In a bounded pass of about 30 minutes, note what a senior ML platform engineer would flag that no step asks about. Read what happened since the previous run (incidents, `bkit-audit-logs` reports, new `docs/failures.jsonl` rows, vendor status incidents), and ask what no step would catch. Include the catalogue and changelog items that surfaced unchecked, with a query for the next run. **Done when:** `Beyond the Steps` holds both passes, or says `none`. **If** one class of issue is seen on 2 runs → propose a step for it in `Process Improvements`.
110
132
 
111
133
  ### 🔒 Gate 2: Probes Check
112
134
 
113
- **Checkpoint.** Verify and check `[x]` all boxes below, then continue to `Findings` without asking.
114
-
115
- - [ ] **Steps complete:** every step `[x]`, or explicit skip with evidence the surface is absent.
116
- - [ ] **Evidence:** every finding cites re-checkable evidence and the tool behind it.
117
- - [ ] **IDs sourced:** every proposed id exists in this run's catalogue pull; no number without a recorded source.
118
- - [ ] **Registry untouched:** no edit to the registry, wrappers, routing config, or call sites.
119
- - [ ] **Gate 2 - Verified:** Every checkbox above independently verified and checked off.
135
+ - [ ] **Steps complete:** every step is `[x]`, or skipped with evidence that its surface is absent.
136
+ - [ ] **Evidence:** every finding cites evidence someone can check again, and the tool that produced it.
137
+ - [ ] **IDs sourced:** every proposed id exists in this run's catalogue pull.
138
+ - [ ] **Numbers sourced:** every number has a recorded source.
139
+ - [ ] **Registry untouched:** no edit was made to the registry, wrappers, routing config or call sites.
140
+ - [ ] **Gate 2 — Verified:** every item above holds.
120
141
 
121
142
  ## Findings
122
143
 
@@ -128,14 +149,14 @@ Verify only when applicable.
128
149
  | `MEDIUM` | Floating alias, or alias whose canonical id moved; context or output cap below measured input; only one qualifying endpoint; unwired model list still maintained; open-weight quantization not pinned; nothing records fallback fires |
129
150
  | `LOW` | Proposed row missing an inline lifecycle or price comment; doc names a model the registry does not, with no call site |
130
151
 
131
- Scale per `.bkit/jsonl.md` § Severity. Within a severity: a call that cannot be served first.
152
+ Within a severity, list a call that cannot be served first.
132
153
 
133
154
  <!-- prettier-ignore -->
134
155
  | ID | Severity | Location | Evidence | Expected |
135
156
  | --- | --- | --- | --- | --- |
136
157
  | PENDING | PENDING | PENDING | PENDING | PENDING |
137
158
 
138
- Empty and clean → one row `None`.
159
+ **If** the run finds nothing → write one row: `None`.
139
160
 
140
161
  ## Report
141
162
 
@@ -204,17 +225,17 @@ PENDING
204
225
 
205
226
  ### 🔒 Gate 3: Report Check
206
227
 
207
- **Checkpoint.** Verify and check `[x]` all boxes below, then stop.
208
-
209
- - [ ] **No placeholders:** Findings table and every `Report` section have no `PENDING`.
210
- - [ ] **Summary:** names count per severity, the catalogue date, and the counts.
211
- - [ ] **Series:** every series beside previous report's numbers, or marked baseline.
212
- - [ ] **Writes:** only this report and template `Project Instructions` changed; throwaway worktrees / remote targets removed.
213
- - [ ] **Process Improvements:** `Universal` = proposed step changes, template untouched; `Project` = edits applied below `bkit:end`; each `none` if empty.
214
- - [ ] **Suggested Issues:** every `MEDIUM`+ finding ID in exactly one row; every row has a `Next Step`.
215
- - [ ] **Gate 3 - Verified:** Every checkbox above independently verified and checked off.
216
-
217
- > `Project Instructions` below `bkit:end` are consumer-owned — `bkit install` never overwrites them, `bkit check` drift stays clean. Add project-specific tools, paths, commands, and checks there, keyed by section or step title; never results.
228
+ - [ ] **No placeholders:** no `PENDING` is left.
229
+ - [ ] **Summary:** `Summary` gives the count per severity.
230
+ - [ ] **Catalogue date:** `Summary` gives the catalogue date.
231
+ - [ ] **Counts:** `Summary` gives the counts.
232
+ - [ ] **Series:** the report shows every series beside the previous report's numbers, or marks the run as baseline.
233
+ - [ ] **Writes:** this run changed only this report, the template's `Project Instructions` and its own `docs/failures.jsonl` rows.
234
+ - [ ] **Throwaways removed:** every throwaway worktree or remote target is removed.
235
+ - [ ] **Process Improvements:** `Universal` and `Project` are both filled.
236
+ - [ ] **Suggested Issues:** every `MEDIUM`+ finding ID is in exactly one `Suggested Issues` row.
237
+ - [ ] **Next Step:** every `Suggested Issues` row has a `Next Step`.
238
+ - [ ] **Gate 3 — Verified:** every item above holds.
218
239
 
219
240
  <!-- bkit:end -->
220
241
 
@@ -1,54 +1,47 @@
1
- <!-- Note: Reports live at `docs/audits/{YYYYMM}/{slug}.md`. `{YYYYMM}` = UTC month of this run. `{slug}` = template basename without `bkit-audit-` and `.md`. **If** that month already has `{slug}.md` or `{slug}-{TIMESTAMP}.md` → write `{slug}-{TIMESTAMP}.md` (`{TIMESTAMP}` = `date -u +%Y%m%dT%H%M%SZ`). Never overwrite. The report is stamped with a `bkit:anchor` block recording the audited commit (`baseSha`) and branch (`baseRef`); never hand-author or edit it. `@bkit-audit-generate` fills this template. -->
2
-
3
1
  <!-- bkit:start -->
4
2
 
5
3
  {{BKIT_MANAGED_MARKER}}
6
4
 
5
+ <!-- Note: @bkit-audit-generate fills this template. The report lives at `docs/audits/{YYYYMM}/{slug}.md`, where `{YYYYMM}` is the UTC month of the run and `{slug}` is this file's name without `bkit-audit-` and `.md`. **If** that month already has `{slug}.md` or `{slug}-{TIMESTAMP}.md` → write `{slug}-{TIMESTAMP}.md`, where `{TIMESTAMP}` is the output of `date -u +%Y%m%dT%H%M%SZ`. NEVER overwrite an earlier report. The report is stamped with a `bkit:anchor` block that records the audited commit (`baseSha`) and branch (`baseRef`). NEVER write or edit that block by hand. -->
6
+
7
7
  # Privacy Audit
8
8
 
9
9
  > [!CAUTION]
10
- > **Purpose:** Lifecycle of personal data — what is held, where it goes, how long it stays, whether deletion removes the person, whether what people are told matches the code.
10
+ > **Purpose:** The lifecycle of personal data — what is held, where it goes, how long it stays, whether deletion removes the person, and whether what people are told matches the code.
11
11
  >
12
12
  > **Rules:**
13
13
  >
14
- > - Read-only audit; never edit code, config, or data.
15
- > - `Universal Instructions` apply to all projects; `Project Instructions` apply only to this project.
16
- > - Local audit instructions / overrides → `Project Instructions` below the bkit-managed block; universal instructions stay in-block.
17
- > - Any tools mentioned in `Universal Instructions` are examples only; swap for actual tools in final output; drop inapplicable.
18
- > - Use dense token-efficient phrasing; no filler / hedging / restating; tables > prose, bullets > paragraphs.
19
- > - Read `.agents/docs.md` → load docs for workflow / step / task; skip missing; cite docs inline where required.
20
- > - Every claim cites this run's evidence (`file:line`, or command / query and its output) and tool behind it; a previous report's figure, list, or status is a lead, not evidence.
21
- > - Read this document once at session start; do not trust session memory; do not re-read on every loop iteration.
22
- > - Name each field and where it lives; never copy a personal-data value into the report.
14
+ > - Name each field and where it lives.
15
+ > - NEVER copy a personal-data value into the report.
23
16
 
24
17
  ## Universal Instructions
25
18
 
26
19
  ### Context & Goals
27
20
 
28
- Privacy rules land with features; nothing re-reads them together. Drift: new table without retention; processor missing from list; deletion cascades only through tables that existed when written; privacy policy describes older app. None fail a test. Most findings = owner decisions (keep / prune / anonymise), not code changes.
21
+ Privacy rules land with features, and nothing re-reads them together. The failure this audit targets is the drift that follows. Examples: a new table without retention, a processor missing from the list, a deletion that cascades only through the tables that existed when it was written, a privacy policy that describes an older app. None of these fails a test. Most findings are owner decisions (keep / prune / anonymise), not code changes.
29
22
 
30
- **Applies when:** system holds personal data (accounts, contact details, content about people). None → one `N/A` row with evidence, never "clean".
23
+ **Applies when:** the system holds personal data (accounts, contact details, content about people). **If** it does not → write one `N/A` row with its evidence, and never report the surface as "clean".
31
24
 
32
- **Cadence:** once before launch, then ≥ yearly (run can serve as annual privacy review). Extra pass when migration adds personal-data tables / columns, or a new processor lands.
25
+ **Cadence:** Run once before launch, then at least once a year; a run can serve as the annual privacy review. Run an extra pass when a migration adds personal-data tables / columns, or a new processor lands.
33
26
 
34
- **Anchor Standards:** record version and date read. Newer version → `Standards` step reads what changed. Covers regimes `Regimes` finds apply and guidance they rely on; statutes also record compilation.
27
+ **Anchor Standards:** The standards are the regimes that `Regimes` finds apply, and the guidance they rely on. For statutes, also record the compilation.
35
28
 
36
29
  - GDPR and UK GDPR.
37
30
  - ePrivacy Art 5(3) and EDPB Guidelines 2/2023.
38
31
  - EDPB DPIA criteria (WP248 rev.01).
39
- - Children's rules (e.g. COPPA, ICO Age Appropriate Design Code).
40
- - National / state laws (e.g. Australian Privacy Act, CCPA).
32
+ - Children's rules (e.g., COPPA, ICO Age Appropriate Design Code).
33
+ - National / state laws (e.g., Australian Privacy Act, CCPA).
41
34
 
42
35
  ### Scope
43
36
 
44
- - Applicable regimes and changes.
45
- - Every personal-data store: DB rows, file storage, derived data (embeddings), logs, device storage.
46
- - Children's data: age knowledge, consent, defaults.
47
- - Impact assessments.
48
- - Every recipient system and contract / transfer basis.
49
- - Retention, deletion, other rights.
50
- - Privacy policy, in-app copy, store declarations vs code.
51
- - Breach readiness.
37
+ - Find the applicable regimes and their changes.
38
+ - Map every personal-data store: DB rows, file storage, derived data (embeddings), logs and device storage.
39
+ - Check children's data: age knowledge, consent and defaults.
40
+ - Check impact assessments.
41
+ - List every recipient system, and its contract / transfer basis.
42
+ - Check retention, deletion and the other rights.
43
+ - Compare the privacy policy, in-app copy and store declarations with the code.
44
+ - Check breach readiness.
52
45
 
53
46
  ### Out of Scope
54
47
 
@@ -63,57 +56,45 @@ Privacy rules land with features; nothing re-reads them together. Drift: new tab
63
56
 
64
57
  ### Pre-Flight / Dependencies
65
58
 
66
- **Checkpoint:** Check off all core items. Check conditional items only when applicable. Each item: available → tool and version; missing → fallback, gap in `Not Checked`, fix in `Process Improvements`. Unnamed gap reads as passed. never abort for a missing capability.
67
-
68
- **Credentials:** probe direnv before marking a token / env var missing: `direnv exec . sh -c '[ -n "${VAR}" ] && echo set || echo unset'`; `unset` = missing. Run credentialed CLIs as `direnv exec . <cmd>`. No direnv (cloud session) → plain env check. Report names, never values.
69
-
70
59
  #### Core
71
60
 
72
- Always verify.
73
-
74
- - [ ] **Permissions:** Before Step 1 — one cheap read-only call per tool this run uses (every item below, every rule under `Project Instructions` `Permissions`), e.g. `gh run list --limit 1`, one MCP read, one anchor-standard fetch. Blocked / denied (here or in any step) → record call verbatim and narrow allow rule clearing it (e.g. `Bash(gh run list *)`) in `Not Checked`, `Process Improvements`, and `Project Instructions` `Permissions`; run every step the remaining tools allow; work needing blocked call → `Not Checked`. never stop the run for a blocked call; never retry or reword a blocked call to get past it.
75
- - [ ] **Published Policy:** Step 10 — privacy policy and in-app privacy copy readable (repo file or live URL). Fallback: unreadable → `Not Checked`; no policy = finding.
76
- - [ ] **Web:** Steps 2, 6, 12 — regulator and law sources, vendor sub-processor pages, anchor standards. Fallback: regime changes and versions recorded as unread.
61
+ - [ ] **Permissions:** every blocked call is recorded.
62
+ - [ ] **Published Policy:** Step 10 — the privacy policy and in-app privacy copy, readable from a repo file or a live URL. Fallback: **If** they are unreadable → mark them `Not Checked`. **If** there is no policy → it is a finding.
63
+ - [ ] **Web:** Steps 2, 6, 12 — regulator and law sources, vendor sub-processor pages, anchor standards. Fallback: record regime changes and versions as unread.
77
64
 
78
65
  #### Conditional
79
66
 
80
- Verify only when applicable.
81
-
82
- - [ ] **Live Catalogue:** Hosted DB → Steps 3, 7 — read-only listing of non-row stores and purge jobs, e.g. platform MCP `execute_sql`. Fallback: migrations only; live state = hypothesis.
83
- - [ ] **Vendor Settings:** Third-party processors → Steps 6, 7 — retention, scrubbing, region, e.g. vendor dashboard, API, MCP. Fallback: code and docs only; vendor settings `Not Checked`.
84
- - [ ] **Agreements:** Processors → Steps 6, 11 — signed processing agreements and breach-notice terms, e.g. repo copies, contract store. Fallback: public vendor terms; signed status `Not Checked`.
67
+ - [ ] **Live Catalogue:** **If** there is a hosted DB → Steps 3, 7 — a read-only listing of non-row stores and purge jobs (e.g., platform MCP `execute_sql`). Fallback: read migrations only, and treat live state as a hypothesis.
68
+ - [ ] **Vendor Settings:** **If** there are third-party processors → Steps 6, 7 — retention, scrubbing and region (e.g., vendor dashboard, API, MCP). Fallback: read code and docs only, and mark vendor settings `Not Checked`.
69
+ - [ ] **Agreements:** **If** there are processors → Steps 6, 11 — signed processing agreements and breach-notice terms (e.g., repo copies, contract store). Fallback: read public vendor terms, and mark signed status `Not Checked`.
85
70
 
86
71
  ### 🔒 Gate 1: Prerequisites Check
87
72
 
88
- **Checkpoint.** Verify and check `[x]` all applicable boxes above, then continue to `Probe Steps` without asking.
89
-
90
- - [ ] **Gaps named:** every missing item names its fallback and `Not Checked` entry.
91
- - [ ] **Gate 1 - Verified:** All Core items checked. All applicable Conditional items checked.
73
+ - [ ] **Gaps named:** every missing item names its fallback and its `Not Checked` entry.
74
+ - [ ] **Gate 1 — Verified:** every item above, every Core item and every applicable Conditional item is checked.
92
75
 
93
76
  ### Probe Steps
94
77
 
95
- - [ ] **Step 1 — Previous Run:** Audited commit = this report's `bkit:anchor` `baseSha`. Read newest prior report for this slug under `docs/audits/`; its commit = its `bkit:anchor` `baseSha`, else the HEAD its `Previous Run` recorded. Count findings fixed / still open; age of oldest open. Open after 2 runs → re-raise with age. **Done when:** closure rate in `Previous Run`, or run marked baseline.
96
- - [ ] **Step 2 — Regimes:** Per candidate regime: applies? why (user locations, turnover / volume thresholds, exemptions and their exceptions, child-directed or actual knowledge). Non-binding regime → mark which checks run as good practice. List law / regulator / code changes since previous report's date, with source links. **Done when:** `Regimes` row per regime: applies · why · changes.
97
- - [ ] **Step 3 — Inventory:** Schema and code. Per table / column / payload: what, whose (user / non-user member / third party named in content), why held, where documented; strictly necessary? default? Optional on by default or model-prompt data beyond task need = finding. Group by purpose → record-of-processing: lawful basis, subjects, recipients, transfer destination and mechanism, security measure. Consent purposes → consent record and withdrawal path. Third parties in content → legitimate-interests assessment and notify decision. Non-row stores: file storage, device caches, derived data (embeddings as personal as source text). Device storage (cookies, local storage, native caches, SDK identifiers) → strictly necessary vs needs consent. **Done when:** `Inventory` lists every store; store no doc mentions = finding.
98
- - [ ] **Step 4 — Children:** When product can hold children's data, state every run: how child is known (field / role / parent statement / not at all) and where; consent path per age band and rule setting it; child defaults (visibility, location, sharing, automated processing); age-threshold crossing (re-consent / role change / nothing); parent monitoring of a child (most children's rules require telling the child). **Done when:** answers in `Inventory`, or evidence product cannot hold children's data in `Checked`.
99
- - [ ] **Step 5 — Assessments:** Current impact assessment (DPIA / PIA) per inventory purpose; list uncovered. Children, new tech (language models), third-party data in content usually meet threshold. Features since previous report's commit vs assessment register; unassessed feature = finding. **Done when:** every purpose has assessment or finding.
100
- - [ ] **Step 6 — Recipients:** Find in code (SDK imports, outbound hosts), not docs: hosting, DB, error tracking, background jobs, email, payments, maps, model providers, anything new. Per recipient: what, why, how long kept. Verify every vendor-side control docs claim (e.g. zero-retention model calls, error-tracker scrub list) in code and tests. Per processor: processing agreement signed (children's-data assurance if required); sub-processor list URL, last checked, change notice; region and transfer mechanism; processor chain (routers fan out); exit plan (export, deletion on exit, replacement). **Done when:** `Recipients` row per system; undocumented one = finding.
101
- - [ ] **Step 7 — Retention:** Per inventory row: what deletes / anonymises it (scheduled job / worker / cascade / nothing); stated period vs enforcing mechanism. Good answer = period, enforcing job, and lawful basis. "Nothing removes it" = finding only without a recorded decision in `docs/decisions.jsonl`. Exception: children's data needs a deletion timeframe regardless — most children's rules forbid indefinite keeping. Published retention policy required → check inventory against published text. **Done when:** `Retention` row per store: period · mechanism, or "no decision".
102
- - [ ] **Step 8 — Deletion:** Read account and tenant deletion code against inventory. Stores reached vs missed: email- / name-keyed rows, file objects, rows in other tenants naming the person. External systems from `Recipients`: does deleting our row delete theirs (payment customers, error-tracker user context, job payloads, backups)? Every run: after deleting a user, what still maps their id back to a person? Deletion test must go red on a missed store — "user can no longer sign in" is not a deletion test. **Done when:** `Deletion` lists every store reached / missed.
103
- - [ ] **Step 9 — Rights:** Per right, how it works today or that it doesn't: access and export (machine-readable where required); correction; partial erasure keeping the account (incl. parent for child); request from a third party named in content; objection and restriction; requester verification (incl. parent for child); response deadline per applicable regime; request log and complaints route. Automated actions with real effect (e.g. a model creating / changing / deleting user data) → "significant effect: yes / no" and reasoning. Right with no exercise path = owner decision, not defect. **Done when:** `Rights` line per right.
104
- - [ ] **Step 10 — Claims:** Read the privacy policy linked from sign-up and in-app privacy copy; compare each claim with `Inventory`, `Recipients`, `Retention`, `Deletion`, `Rights`. Unnamed processor, wrong retention period, unkept promise, unmentioned significant automated decision = finding. Store privacy declarations likewise once listings exist. Child members possible → child-readable policy and collection notices; notice to child when a parent can monitor. Terms, refund wording, accessibility statement likewise. **Done when:** `Claims` row per claim: matches / finding.
105
- - [ ] **Step 11 — Breaches:** Written breach plan per applicable regime: regulator clock and when affected people are told; internal log of every breach (notifiable or not); each processor's notice duty and speed from its agreement. Children's regime requires a written security programme → named coordinator, ≥ yearly risk assessment, tested safeguards. **Done when:** every requirement met or finding.
106
- - [ ] **Step 12 — Standards:** Confirm current version per anchor standard; read changes since previous report's version. `Standards Coverage`: one row per standard and each obligation this procedure relies on → checked (name step) / not applicable (why) / finding. Unapplied recommended practice → adopt (propose step) / reject (why) / not applicable. **Done when:** no empty row.
107
- - [ ] **Step 13 — Anything Else:** (a) Everything changed since previous report's commit touching personal data (migrations, tables / columns, routes and server actions, SDKs and outbound hosts, buckets, consent screens, privacy copy) → one-line verdict each. (b) Bounded ~30 min pass: what senior privacy counsel flags that no step asks; read what happened since previous run (incidents, new `docs/failures.jsonl` rows) — what would no step catch? End with what a regulator would ask that this run cannot answer and legal questions for owner / counsel. **Done when:** `Beyond the Steps` holds both passes and regulator questions, or `none`. Class seen on 2 runs → propose step in `Process Improvements`.
78
+ - [ ] **Step 1 — Previous Run:** **Done when:** `Previous Run` holds the closure rate, or the run is marked baseline.
79
+ - [ ] **Step 2 — Regimes:** For each candidate regime, decide whether it applies, and why: user locations, turnover / volume thresholds, exemptions and their exceptions, a child-directed service or actual knowledge. **If** a regime is not binding → mark which checks run as good practice. List the law / regulator / code changes since the previous report's date, with source links. **Done when:** `Regimes` has a row per regime: applies · why · changes.
80
+ - [ ] **Step 3 — Inventory:** Read the schema and code. For each table / column / payload, record what it holds, whose data it is (user / non-user member / third party named in content), why it is held, where it is documented, whether it is strictly necessary, and its default. Optional data that is on by default, or model-prompt data beyond the task's need, is a finding. Group the rows by purpose into a record of processing: lawful basis, subjects, recipients, transfer destination and mechanism, and security measure. **If** a purpose rests on consent → record the consent record and the withdrawal path. **If** content names third parties → record the legitimate-interests assessment and the notify decision. Cover non-row stores: file storage, device caches and derived data (embeddings are as personal as their source text). Classify device storage (cookies, local storage, native caches, SDK identifiers) as strictly necessary or as needing consent. **Done when:** `Inventory` lists every store, and a store no doc mentions is a finding.
81
+ - [ ] **Step 4 — Children:** **If** the product can hold children's data → state on every run: how a child is known (field / role / parent statement / not at all) and where; the consent path per age band, and the rule that sets it; the child defaults (visibility, location, sharing, automated processing); what happens when a child crosses an age threshold (re-consent / role change / nothing); and parent monitoring of a child (most children's rules require telling the child). **Done when:** the answers are in `Inventory`, or evidence that the product cannot hold children's data is in `Checked`.
82
+ - [ ] **Step 5 — Assessments:** Find the current impact assessment (DPIA / PIA) for each inventory purpose, and list the purposes none covers. Children, new technology (language models) and third-party data in content usually meet the threshold. Compare the features added since the previous report's commit with the assessment register; an unassessed feature is a finding. **Done when:** every purpose has an assessment or a finding.
83
+ - [ ] **Step 6 — Recipients:** Find recipients in code (SDK imports, outbound hosts), not docs: hosting, DB, error tracking, background jobs, email, payments, maps, model providers, and anything new. For each recipient, record what it receives, why, and how long it keeps it. Verify in code and tests every vendor-side control the docs claim (e.g., zero-retention model calls, an error-tracker scrub list). For each processor, record whether a processing agreement is signed (with a children's-data assurance if required); the sub-processor list URL, when it was last checked, and the change notice; the region and transfer mechanism; the processor chain (routers fan out); and the exit plan (export, deletion on exit, replacement). **Done when:** `Recipients` has a row per system, and an undocumented one is a finding.
84
+ - [ ] **Step 7 — Retention:** For each inventory row, record what deletes or anonymises it (scheduled job / worker / cascade / nothing), and compare the stated period with the enforcing mechanism. A good answer gives the period, the enforcing job and the lawful basis. "Nothing removes it" is a finding only when there is no recorded decision in `docs/decisions.jsonl`. The exception: children's data needs a deletion timeframe regardless, because most children's rules forbid keeping it indefinitely. **If** a published retention policy is required → check the inventory against the published text. **Done when:** `Retention` has a row per store: period · mechanism, or "no decision".
85
+ - [ ] **Step 8 — Deletion:** Read the account and tenant deletion code against the inventory. Record the stores reached and missed: email- / name-keyed rows, file objects, and rows in other tenants that name the person. For the external systems in `Recipients`, check whether deleting our row deletes theirs (payment customers, error-tracker user context, job payloads, backups). On every run, ask what still maps a deleted user's id back to a person. A deletion test must go red on a missed store; "user can no longer sign in" is not a deletion test. **Done when:** `Deletion` lists every store reached / missed.
86
+ - [ ] **Step 9 — Rights:** For each right, record how it works today, or that it does not: access and export (machine-readable where required); correction; partial erasure that keeps the account (including by a parent for a child); a request from a third party named in content; objection and restriction; requester verification (including a parent for a child); the response deadline per applicable regime; and the request log and complaints route. **If** an automated action has a real effect (e.g., a model creating / changing / deleting user data) → record "significant effect: yes / no" and the reasoning. A right with no exercise path is an owner decision, not a defect. **Done when:** `Rights` has a line per right.
87
+ - [ ] **Step 10 — Claims:** Read the privacy policy linked from sign-up and the in-app privacy copy, and compare each claim with `Inventory`, `Recipients`, `Retention`, `Deletion` and `Rights`. An unnamed processor, a wrong retention period, an unkept promise or an unmentioned significant automated decision is a finding. Check the store privacy declarations the same way once listings exist. **If** child members are possible → check for a child-readable policy and collection notices, and for a notice to the child when a parent can monitor. Check the terms, refund wording and accessibility statement the same way. **Done when:** `Claims` has a row per claim: matches / finding.
88
+ - [ ] **Step 11 — Breaches:** Check for a written breach plan per applicable regime: the regulator clock and when affected people are told; an internal log of every breach, notifiable or not; and each processor's notice duty and speed from its agreement. **If** a children's regime requires a written security programme → check for a named coordinator, a risk assessment at least yearly, and tested safeguards. **Done when:** every requirement is met or has a finding.
89
+ - [ ] **Step 12 — Standards:** Confirm the current version of each anchor standard, and read what changed since the previous report's version. Give `Standards Coverage` one row per standard and per obligation this procedure relies on, each marked checked (naming the step), not applicable (saying why) or finding. Mark each recommended practice the project does not apply as adopt (with a proposed step), reject (saying why) or not applicable. **Done when:** no row is empty.
90
+ - [ ] **Step 13 — Anything Else:** (a) Give a one-line verdict on each change since the previous report's commit that touches personal data: migrations, tables / columns, routes and server actions, SDKs and outbound hosts, buckets, consent screens and privacy copy. (b) In a bounded pass of about 30 minutes, note what a senior privacy counsel would flag that no step asks about. Read what happened since the previous run (incidents, new `docs/failures.jsonl` rows), and ask what no step would catch. End with what a regulator would ask that this run cannot answer, and the legal questions for the owner / counsel. **Done when:** `Beyond the Steps` holds both passes and the regulator questions, or says `none`. **If** one class of issue is seen on 2 runs → propose a step for it in `Process Improvements`.
108
91
 
109
92
  ### 🔒 Gate 2: Probes Check
110
93
 
111
- **Checkpoint.** Verify and check `[x]` all boxes below, then continue to `Findings` without asking.
112
-
113
- - [ ] **Steps complete:** every step `[x]`, or explicit skip with evidence the surface is absent.
114
- - [ ] **Evidence:** every finding cites re-checkable evidence and the tool behind it.
115
- - [ ] **No values:** no personal-data value anywhere in the report.
116
- - [ ] **Gate 2 - Verified:** Every checkbox above independently verified and checked off.
94
+ - [ ] **Steps complete:** every step is `[x]`, or skipped with evidence that its surface is absent.
95
+ - [ ] **Evidence:** every finding cites evidence someone can check again, and the tool that produced it.
96
+ - [ ] **No values:** no personal-data value appears anywhere in the report.
97
+ - [ ] **Gate 2 — Verified:** every item above holds.
117
98
 
118
99
  ## Findings
119
100
 
@@ -125,14 +106,14 @@ Verify only when applicable.
125
106
  | `MEDIUM` | Doc describes a store / processor wrongly; purpose without impact assessment; right without exercise path; missing breach-plan element |
126
107
  | `LOW` | Undocumented field already covered by deletion, retention, and processor list; wording drift changing no obligation |
127
108
 
128
- Scale per `.bkit/jsonl.md` § Severity. Within a severity: children's data first. No users yet → do not lower severity for empty production tables.
109
+ Within a severity, list children's data first. **If** there are no users yet → do not lower the severity for empty production tables.
129
110
 
130
111
  <!-- prettier-ignore -->
131
112
  | ID | Severity | Location | Evidence | Expected |
132
113
  | --- | --- | --- | --- | --- |
133
114
  | PENDING | PENDING | PENDING | PENDING | PENDING |
134
115
 
135
- Empty and clean → one row `None`.
116
+ **If** the run finds nothing → write one row: `None`.
136
117
 
137
118
  ## Report
138
119
 
@@ -205,17 +186,16 @@ PENDING
205
186
 
206
187
  ### 🔒 Gate 3: Report Check
207
188
 
208
- **Checkpoint.** Verify and check `[x]` all boxes below, then stop.
209
-
210
- - [ ] **No placeholders:** Findings table and every `Report` section have no `PENDING`.
211
- - [ ] **Summary:** names count per severity.
212
- - [ ] **Annual Review:** states whether this run serves as the annual privacy review and whether everyone with children's-data access completed privacy training.
213
- - [ ] **Writes:** only this report and template `Project Instructions` changed; throwaway worktrees / remote targets removed.
214
- - [ ] **Process Improvements:** `Universal` = proposed step changes, template untouched; `Project` = edits applied below `bkit:end`; each `none` if empty.
215
- - [ ] **Suggested Issues:** every `MEDIUM`+ finding ID in exactly one row; every row has a `Next Step`.
216
- - [ ] **Gate 3 - Verified:** Every checkbox above independently verified and checked off.
217
-
218
- > `Project Instructions` below `bkit:end` are consumer-owned — `bkit install` never overwrites them, `bkit check` drift stays clean. Add project-specific tools, paths, commands, and checks there, keyed by section or step title; never results.
189
+ - [ ] **No placeholders:** no `PENDING` is left.
190
+ - [ ] **Summary:** `Summary` gives the count per severity.
191
+ - [ ] **Annual Review:** `Annual Review` states whether this run serves as the annual privacy review.
192
+ - [ ] **Training:** `Annual Review` states whether everyone with children's-data access completed privacy training.
193
+ - [ ] **Writes:** this run changed only this report, the template's `Project Instructions` and its own `docs/failures.jsonl` rows.
194
+ - [ ] **Throwaways removed:** every throwaway worktree or remote target is removed.
195
+ - [ ] **Process Improvements:** `Universal` and `Project` are both filled.
196
+ - [ ] **Suggested Issues:** every `MEDIUM`+ finding ID is in exactly one `Suggested Issues` row.
197
+ - [ ] **Next Step:** every `Suggested Issues` row has a `Next Step`.
198
+ - [ ] **Gate 3 — Verified:** every item above holds.
219
199
 
220
200
  <!-- bkit:end -->
221
201