onto-mcp 0.3.2 → 0.4.1

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 (300) hide show
  1. package/.onto/processes/reconstruct/actionable-ontology-seed-recomposition-design.md +447 -0
  2. package/.onto/processes/reconstruct/foundry-style-ontology-seed-contract.md +934 -0
  3. package/.onto/processes/reconstruct/reconstruct-boundary-contract.md +303 -725
  4. package/.onto/processes/reconstruct/reconstruct-contract-registry.yaml +1645 -0
  5. package/.onto/processes/reconstruct/reconstruct-execution-ux-contract.md +26 -22
  6. package/.onto/processes/reconstruct/source-profile-contract.md +49 -23
  7. package/.onto/processes/reconstruct/source-profiles/code.md +6 -3
  8. package/.onto/processes/reconstruct/source-profiles/database.md +5 -2
  9. package/.onto/processes/reconstruct/source-profiles/document.md +5 -2
  10. package/.onto/processes/reconstruct/source-profiles/spreadsheet.md +5 -4
  11. package/.onto/processes/review/review-execution-ux-contract.md +40 -0
  12. package/.onto/processes/shared/pipeline-execution-ledger-contract.md +26 -10
  13. package/.onto/processes/shared/target-material-kind-contract.md +29 -16
  14. package/AGENTS.md +6 -4
  15. package/README.md +149 -76
  16. package/dist/cli.js +8 -8
  17. package/dist/core-api/reconstruct-api.js +117 -31
  18. package/dist/core-api/review-api.js +47 -0
  19. package/dist/core-runtime/cli/codex-review-unit-executor.js +39 -2
  20. package/dist/core-runtime/cli/complete-review-session.js +2 -2
  21. package/dist/core-runtime/cli/mock-review-unit-executor.js +1 -1
  22. package/dist/core-runtime/cli/review-invoke.js +9 -9
  23. package/dist/core-runtime/cli/run-review-prompt-execution.js +39 -5
  24. package/dist/core-runtime/cli/spawn-watcher.js +266 -47
  25. package/dist/core-runtime/cli/start-review-session.js +3 -3
  26. package/dist/core-runtime/llm/llm-caller.js +11 -0
  27. package/dist/core-runtime/llm/llm-tool-loop.js +2 -0
  28. package/dist/core-runtime/observability/runtime-stream-observation.js +118 -0
  29. package/dist/core-runtime/onboard/cli-host.js +174 -0
  30. package/dist/core-runtime/onboard/host-target.js +22 -0
  31. package/dist/core-runtime/onboard/json-config-host.js +122 -0
  32. package/dist/core-runtime/onboard/path-scan.js +26 -0
  33. package/dist/core-runtime/onboard/prompt.js +51 -0
  34. package/dist/core-runtime/onboard/register.js +214 -0
  35. package/dist/core-runtime/onboard/types.js +27 -0
  36. package/dist/core-runtime/reconstruct/actionable-seed-validation.js +1777 -0
  37. package/dist/core-runtime/reconstruct/artifact-types.js +10 -4
  38. package/dist/core-runtime/reconstruct/contract-registry.js +623 -0
  39. package/dist/core-runtime/reconstruct/domain-id.js +10 -0
  40. package/dist/core-runtime/reconstruct/governing-snapshot.js +716 -0
  41. package/dist/core-runtime/reconstruct/material-profile-validation.js +191 -0
  42. package/dist/core-runtime/reconstruct/materialize-preparation.js +49 -11
  43. package/dist/core-runtime/reconstruct/pipeline-execution-ledger.js +269 -79
  44. package/dist/core-runtime/reconstruct/post-seed-validation.js +1194 -51
  45. package/dist/core-runtime/reconstruct/record.js +104 -20
  46. package/dist/core-runtime/reconstruct/run.js +2107 -413
  47. package/dist/core-runtime/reconstruct/seed-claim-projections.js +268 -0
  48. package/dist/core-runtime/reconstruct/source-profiles.js +93 -4
  49. package/dist/core-runtime/reconstruct/terminal-validation.js +807 -0
  50. package/dist/core-runtime/review/review-invocation-runner.js +4 -4
  51. package/dist/mcp/server.js +110 -38
  52. package/dist/mcp/tool-schemas.js +20 -6
  53. package/package.json +8 -17
  54. package/scripts/onto-review-watch.sh +486 -0
  55. package/scripts/onto-runtime-watch.sh +122 -0
  56. package/scripts/postinstall-hint.js +22 -0
  57. package/.onto/processes/reconstruct/top-level-concept-discovery-contract.md +0 -387
  58. package/dist/core-runtime/cli/bootstrap-review-binding.js +0 -186
  59. package/dist/core-runtime/cli/codex-nested-dispatch.test.js +0 -390
  60. package/dist/core-runtime/cli/codex-nested-teamlead-executor.test.js +0 -335
  61. package/dist/core-runtime/cli/coordinator-helpers.js +0 -583
  62. package/dist/core-runtime/cli/coordinator-state-machine-deliberation.test.js +0 -167
  63. package/dist/core-runtime/cli/coordinator-state-machine.js +0 -794
  64. package/dist/core-runtime/cli/e2e-codex-multi-agent-fixes.test.js +0 -615
  65. package/dist/core-runtime/cli/e2e-start-review-session.test.js +0 -312
  66. package/dist/core-runtime/cli/health.js +0 -44
  67. package/dist/core-runtime/cli/inline-http-review-unit-executor.test.js +0 -567
  68. package/dist/core-runtime/cli/materialize-review-execution-preparation.js +0 -104
  69. package/dist/core-runtime/cli/migrate-session-roots.js +0 -118
  70. package/dist/core-runtime/cli/repo-layout-migration-replace.smoke.test.js +0 -106
  71. package/dist/core-runtime/cli/review-invoke-auto-resolution.test.js +0 -268
  72. package/dist/core-runtime/cli/review-invoke-coordinator-topology.test.js +0 -136
  73. package/dist/core-runtime/cli/review-invoke-resolver-caching.test.js +0 -201
  74. package/dist/core-runtime/cli/review-invoke-topology-dispatch.test.js +0 -192
  75. package/dist/core-runtime/cli/session-root-guard.js +0 -168
  76. package/dist/core-runtime/cli/spawn-watcher.test.js +0 -457
  77. package/dist/core-runtime/cli/strip-wrapping-code-fence.test.js +0 -79
  78. package/dist/core-runtime/cli/teamcreate-lens-deliberation-executor.js +0 -412
  79. package/dist/core-runtime/cli/teamcreate-lens-deliberation-executor.test.js +0 -351
  80. package/dist/core-runtime/cli/topology-executor-mapping.js +0 -139
  81. package/dist/core-runtime/cli/topology-executor-mapping.test.js +0 -173
  82. package/dist/core-runtime/cli/write-review-interpretation.js +0 -81
  83. package/dist/core-runtime/config/onto-config-cli.js +0 -278
  84. package/dist/core-runtime/config/onto-config-key-path.js +0 -288
  85. package/dist/core-runtime/config/onto-config-key-path.test.js +0 -195
  86. package/dist/core-runtime/config/onto-config-preview.js +0 -108
  87. package/dist/core-runtime/config/onto-config-preview.test.js +0 -132
  88. package/dist/core-runtime/discovery/config-chain.js +0 -118
  89. package/dist/core-runtime/discovery/config-chain.test.js +0 -103
  90. package/dist/core-runtime/discovery/config-profile.js +0 -199
  91. package/dist/core-runtime/discovery/config-profile.test.js +0 -233
  92. package/dist/core-runtime/discovery/host-detection.test.js +0 -186
  93. package/dist/core-runtime/discovery/installation-paths.test.js +0 -65
  94. package/dist/core-runtime/discovery/lens-registry.test.js +0 -81
  95. package/dist/core-runtime/discovery/path-normalization.test.js +0 -22
  96. package/dist/core-runtime/discovery/plugin-path.js +0 -72
  97. package/dist/core-runtime/discovery/plugin-path.test.js +0 -95
  98. package/dist/core-runtime/evolve/adapters/code-product/compile/compile-defense.js +0 -344
  99. package/dist/core-runtime/evolve/adapters/code-product/compile/compile-defense.test.js +0 -915
  100. package/dist/core-runtime/evolve/adapters/code-product/compile/compile.js +0 -564
  101. package/dist/core-runtime/evolve/adapters/code-product/compile/compile.test.js +0 -708
  102. package/dist/core-runtime/evolve/adapters/code-product/parsers/brief-parser.js +0 -165
  103. package/dist/core-runtime/evolve/adapters/code-product/parsers/brief-parser.test.js +0 -227
  104. package/dist/core-runtime/evolve/adapters/code-product/validators/validate.js +0 -59
  105. package/dist/core-runtime/evolve/adapters/code-product/validators/validate.test.js +0 -205
  106. package/dist/core-runtime/evolve/adapters/methodology/adapter.js +0 -16
  107. package/dist/core-runtime/evolve/adapters/methodology/adapter.test.js +0 -9
  108. package/dist/core-runtime/evolve/adapters/methodology/perspectives/authority-consistency.js +0 -298
  109. package/dist/core-runtime/evolve/adapters/methodology/perspectives/authority-consistency.test.js +0 -70
  110. package/dist/core-runtime/evolve/adapters/methodology/scope-types/process.js +0 -46
  111. package/dist/core-runtime/evolve/adapters/methodology/scope-types/process.test.js +0 -73
  112. package/dist/core-runtime/evolve/adapters/registry.js +0 -47
  113. package/dist/core-runtime/evolve/adapters/registry.test.js +0 -67
  114. package/dist/core-runtime/evolve/cli.js +0 -256
  115. package/dist/core-runtime/evolve/commands/align.js +0 -194
  116. package/dist/core-runtime/evolve/commands/align.test.js +0 -82
  117. package/dist/core-runtime/evolve/commands/apply.js +0 -161
  118. package/dist/core-runtime/evolve/commands/apply.test.js +0 -138
  119. package/dist/core-runtime/evolve/commands/close.js +0 -39
  120. package/dist/core-runtime/evolve/commands/close.test.js +0 -99
  121. package/dist/core-runtime/evolve/commands/defer.js +0 -40
  122. package/dist/core-runtime/evolve/commands/defer.test.js +0 -134
  123. package/dist/core-runtime/evolve/commands/draft.js +0 -323
  124. package/dist/core-runtime/evolve/commands/draft.test.js +0 -178
  125. package/dist/core-runtime/evolve/commands/e2e-evolve-full-cycle.test.js +0 -208
  126. package/dist/core-runtime/evolve/commands/error-messages.js +0 -125
  127. package/dist/core-runtime/evolve/commands/error-messages.test.js +0 -167
  128. package/dist/core-runtime/evolve/commands/propose-align.js +0 -222
  129. package/dist/core-runtime/evolve/commands/propose-align.test.js +0 -136
  130. package/dist/core-runtime/evolve/commands/reconstruct.js +0 -330
  131. package/dist/core-runtime/evolve/commands/reconstruct.test.js +0 -278
  132. package/dist/core-runtime/evolve/commands/shared.js +0 -22
  133. package/dist/core-runtime/evolve/commands/stale-check.js +0 -103
  134. package/dist/core-runtime/evolve/commands/stale-check.test.js +0 -84
  135. package/dist/core-runtime/evolve/commands/start.js +0 -887
  136. package/dist/core-runtime/evolve/commands/start.test.js +0 -396
  137. package/dist/core-runtime/evolve/config/project-config.js +0 -99
  138. package/dist/core-runtime/evolve/config/project-config.test.js +0 -170
  139. package/dist/core-runtime/evolve/renderers/align-packet.js +0 -280
  140. package/dist/core-runtime/evolve/renderers/align-packet.test.js +0 -332
  141. package/dist/core-runtime/evolve/renderers/draft-packet.js +0 -303
  142. package/dist/core-runtime/evolve/renderers/draft-packet.test.js +0 -377
  143. package/dist/core-runtime/evolve/renderers/format.js +0 -5
  144. package/dist/core-runtime/evolve/renderers/scope-md.js +0 -237
  145. package/dist/core-runtime/evolve/renderers/scope-md.test.js +0 -306
  146. package/dist/core-runtime/govern/cli.js +0 -369
  147. package/dist/core-runtime/govern/cli.test.js +0 -314
  148. package/dist/core-runtime/govern/drift-engine.js +0 -103
  149. package/dist/core-runtime/govern/drift-engine.test.js +0 -319
  150. package/dist/core-runtime/govern/promote-principle.js +0 -206
  151. package/dist/core-runtime/govern/promote-principle.test.js +0 -368
  152. package/dist/core-runtime/govern/queue.js +0 -81
  153. package/dist/core-runtime/govern/types.js +0 -16
  154. package/dist/core-runtime/install/cli.js +0 -530
  155. package/dist/core-runtime/install/detect.js +0 -128
  156. package/dist/core-runtime/install/detect.test.js +0 -155
  157. package/dist/core-runtime/install/gitignore-update.js +0 -74
  158. package/dist/core-runtime/install/gitignore-update.test.js +0 -64
  159. package/dist/core-runtime/install/install-integration.test.js +0 -373
  160. package/dist/core-runtime/install/prompts.js +0 -389
  161. package/dist/core-runtime/install/prompts.test.js +0 -293
  162. package/dist/core-runtime/install/types.js +0 -26
  163. package/dist/core-runtime/install/validation.js +0 -295
  164. package/dist/core-runtime/install/validation.test.js +0 -313
  165. package/dist/core-runtime/install/writer.js +0 -254
  166. package/dist/core-runtime/install/writer.test.js +0 -218
  167. package/dist/core-runtime/learning/extractor.js +0 -461
  168. package/dist/core-runtime/learning/feedback.js +0 -179
  169. package/dist/core-runtime/learning/health-report.js +0 -165
  170. package/dist/core-runtime/learning/health-report.test.js +0 -169
  171. package/dist/core-runtime/learning/loader.js +0 -388
  172. package/dist/core-runtime/learning/loader.test.js +0 -102
  173. package/dist/core-runtime/learning/promote/apply-state.js +0 -240
  174. package/dist/core-runtime/learning/promote/audit-obligation.js +0 -195
  175. package/dist/core-runtime/learning/promote/collector.js +0 -432
  176. package/dist/core-runtime/learning/promote/degraded-state.js +0 -125
  177. package/dist/core-runtime/learning/promote/domain-doc-proposer.js +0 -166
  178. package/dist/core-runtime/learning/promote/e2e-promote.test.js +0 -6385
  179. package/dist/core-runtime/learning/promote/health-snapshot.js +0 -150
  180. package/dist/core-runtime/learning/promote/insight-reclassifier.js +0 -544
  181. package/dist/core-runtime/learning/promote/judgment-auditor.js +0 -517
  182. package/dist/core-runtime/learning/promote/panel-reviewer.js +0 -1158
  183. package/dist/core-runtime/learning/promote/promote-executor.js +0 -1675
  184. package/dist/core-runtime/learning/promote/promoter.js +0 -307
  185. package/dist/core-runtime/learning/promote/retirement.js +0 -122
  186. package/dist/core-runtime/learning/promote/types.js +0 -23
  187. package/dist/core-runtime/learning/prompt-sections.js +0 -51
  188. package/dist/core-runtime/learning/shared/artifact-registry-init.js +0 -45
  189. package/dist/core-runtime/learning/shared/artifact-registry.js +0 -254
  190. package/dist/core-runtime/learning/shared/audit-obligation-kernel.js +0 -73
  191. package/dist/core-runtime/learning/shared/audit-state.js +0 -99
  192. package/dist/core-runtime/learning/shared/duplicate-check.js +0 -28
  193. package/dist/core-runtime/learning/shared/llm-caller.js +0 -831
  194. package/dist/core-runtime/learning/shared/llm-caller.test.js +0 -601
  195. package/dist/core-runtime/learning/shared/llm-tool-loop.js +0 -393
  196. package/dist/core-runtime/learning/shared/mode.js +0 -25
  197. package/dist/core-runtime/learning/shared/paths.js +0 -84
  198. package/dist/core-runtime/learning/shared/paths.test.js +0 -79
  199. package/dist/core-runtime/learning/shared/patterns.js +0 -37
  200. package/dist/core-runtime/learning/shared/recoverability.js +0 -355
  201. package/dist/core-runtime/learning/shared/recovery-context.js +0 -374
  202. package/dist/core-runtime/learning/shared/scope.js +0 -1
  203. package/dist/core-runtime/learning/shared/semantic-classifier.js +0 -94
  204. package/dist/core-runtime/learning/shared/specs/apply-execution-state-spec.js +0 -42
  205. package/dist/core-runtime/learning/shared/specs/audit-state-spec.js +0 -37
  206. package/dist/core-runtime/learning/shared/specs/backup-metadata-spec.js +0 -39
  207. package/dist/core-runtime/learning/shared/specs/emergency-log-spec.js +0 -41
  208. package/dist/core-runtime/learning/shared/specs/layout-version-spec.js +0 -38
  209. package/dist/core-runtime/learning/shared/specs/promote-decisions-spec.js +0 -43
  210. package/dist/core-runtime/learning/shared/specs/promote-report-spec.js +0 -113
  211. package/dist/core-runtime/learning/shared/specs/prune-log-spec.js +0 -36
  212. package/dist/core-runtime/learning/shared/specs/recovery-resolution-spec.js +0 -48
  213. package/dist/core-runtime/learning/shared/specs/restore-manifest-spec.js +0 -43
  214. package/dist/core-runtime/learning/shared/specs/spec-helpers.js +0 -64
  215. package/dist/core-runtime/learning/usage-tracker.js +0 -190
  216. package/dist/core-runtime/learning/usage-tracker.test.js +0 -176
  217. package/dist/core-runtime/onboard/detect-review-axes.js +0 -122
  218. package/dist/core-runtime/onboard/detect-review-axes.test.js +0 -127
  219. package/dist/core-runtime/onboard/write-review-block.js +0 -188
  220. package/dist/core-runtime/onboard/write-review-block.test.js +0 -240
  221. package/dist/core-runtime/readers/brownfield-builder.js +0 -150
  222. package/dist/core-runtime/readers/brownfield-builder.test.js +0 -136
  223. package/dist/core-runtime/readers/code-chunk-collector.js +0 -53
  224. package/dist/core-runtime/readers/code-chunk-collector.test.js +0 -136
  225. package/dist/core-runtime/readers/file-utils.js +0 -240
  226. package/dist/core-runtime/readers/file-utils.test.js +0 -146
  227. package/dist/core-runtime/readers/lexicon-citation-check.js +0 -93
  228. package/dist/core-runtime/readers/lexicon-citation-check.test.js +0 -77
  229. package/dist/core-runtime/readers/mcp-figma.js +0 -30
  230. package/dist/core-runtime/readers/mcp-figma.test.js +0 -82
  231. package/dist/core-runtime/readers/mcp-generic.js +0 -31
  232. package/dist/core-runtime/readers/mcp-generic.test.js +0 -76
  233. package/dist/core-runtime/readers/ontology-index.js +0 -148
  234. package/dist/core-runtime/readers/ontology-index.test.js +0 -245
  235. package/dist/core-runtime/readers/ontology-query.js +0 -168
  236. package/dist/core-runtime/readers/ontology-query.test.js +0 -311
  237. package/dist/core-runtime/readers/ontology-resolve.js +0 -48
  238. package/dist/core-runtime/readers/ontology-resolve.test.js +0 -48
  239. package/dist/core-runtime/readers/patterns/index.js +0 -7
  240. package/dist/core-runtime/readers/review-log.js +0 -213
  241. package/dist/core-runtime/readers/review-log.test.js +0 -313
  242. package/dist/core-runtime/readers/scan-local.js +0 -102
  243. package/dist/core-runtime/readers/scan-local.test.js +0 -102
  244. package/dist/core-runtime/readers/scan-tarball.js +0 -121
  245. package/dist/core-runtime/readers/scan-tarball.test.js +0 -283
  246. package/dist/core-runtime/readers/scan-vault.js +0 -34
  247. package/dist/core-runtime/readers/scan-vault.test.js +0 -81
  248. package/dist/core-runtime/readers/types.js +0 -42
  249. package/dist/core-runtime/readers/types.test.js +0 -94
  250. package/dist/core-runtime/readers/viewpoint-collectors.js +0 -229
  251. package/dist/core-runtime/reconstruct/seed-candidate-validation.js +0 -385
  252. package/dist/core-runtime/review/citation-audit.test.js +0 -165
  253. package/dist/core-runtime/review/execution-plan-resolver.js +0 -247
  254. package/dist/core-runtime/review/execution-plan-resolver.test.js +0 -243
  255. package/dist/core-runtime/review/execution-topology-resolver-axis-first.test.js +0 -246
  256. package/dist/core-runtime/review/execution-topology-resolver.js +0 -401
  257. package/dist/core-runtime/review/execution-topology-resolver.test.js +0 -315
  258. package/dist/core-runtime/review/inline-context-embedder.test.js +0 -154
  259. package/dist/core-runtime/review/legacy-mode-policy.js +0 -88
  260. package/dist/core-runtime/review/materializers-effort-persist.test.js +0 -79
  261. package/dist/core-runtime/review/ontology-path-classifier.js +0 -179
  262. package/dist/core-runtime/review/ontology-path-classifier.test.js +0 -216
  263. package/dist/core-runtime/review/packet-boundary-policy.test.js +0 -107
  264. package/dist/core-runtime/review/participating-lens-paths.test.js +0 -73
  265. package/dist/core-runtime/review/review-config-legacy-translate.js +0 -244
  266. package/dist/core-runtime/review/review-config-legacy-translate.test.js +0 -161
  267. package/dist/core-runtime/review/review-config-validator.js +0 -289
  268. package/dist/core-runtime/review/review-config-validator.test.js +0 -236
  269. package/dist/core-runtime/review/shape-pipeline-audit.test.js +0 -311
  270. package/dist/core-runtime/review/shape-to-topology-id.js +0 -117
  271. package/dist/core-runtime/review/shape-to-topology-id.test.js +0 -132
  272. package/dist/core-runtime/review/topology-shape-derivation.js +0 -155
  273. package/dist/core-runtime/review/topology-shape-derivation.test.js +0 -195
  274. package/dist/core-runtime/scope-runtime/constants.js +0 -12
  275. package/dist/core-runtime/scope-runtime/constraint-pool.js +0 -166
  276. package/dist/core-runtime/scope-runtime/constraint-pool.test.js +0 -674
  277. package/dist/core-runtime/scope-runtime/domain-validation-log.js +0 -135
  278. package/dist/core-runtime/scope-runtime/domain-validation-log.test.js +0 -156
  279. package/dist/core-runtime/scope-runtime/eval-persistence.js +0 -65
  280. package/dist/core-runtime/scope-runtime/eval-persistence.test.js +0 -84
  281. package/dist/core-runtime/scope-runtime/event-pipeline.js +0 -64
  282. package/dist/core-runtime/scope-runtime/event-pipeline.test.js +0 -450
  283. package/dist/core-runtime/scope-runtime/event-store.js +0 -39
  284. package/dist/core-runtime/scope-runtime/event-store.test.js +0 -95
  285. package/dist/core-runtime/scope-runtime/gate-guard.js +0 -348
  286. package/dist/core-runtime/scope-runtime/gate-guard.test.js +0 -1047
  287. package/dist/core-runtime/scope-runtime/hash.js +0 -4
  288. package/dist/core-runtime/scope-runtime/hash.test.js +0 -33
  289. package/dist/core-runtime/scope-runtime/id.js +0 -4
  290. package/dist/core-runtime/scope-runtime/id.test.js +0 -17
  291. package/dist/core-runtime/scope-runtime/reducer.js +0 -297
  292. package/dist/core-runtime/scope-runtime/reducer.test.js +0 -759
  293. package/dist/core-runtime/scope-runtime/scope-manager.js +0 -161
  294. package/dist/core-runtime/scope-runtime/state-machine.js +0 -309
  295. package/dist/core-runtime/scope-runtime/state-machine.test.js +0 -704
  296. package/dist/core-runtime/scope-runtime/types.js +0 -116
  297. package/dist/core-runtime/scope-runtime/types.test.js +0 -69
  298. package/dist/core-runtime/translate/render-for-user.js +0 -169
  299. package/dist/core-runtime/translate/render-for-user.test.js +0 -122
  300. package/dist/providers/capability-contract.js +0 -1
@@ -7,8 +7,8 @@
7
7
  ## 1. Position
8
8
 
9
9
  `reconstruct` can take a long time because the host LLM must read source
10
- observations, run reconstruct lens judgments, choose the next unjudged source
11
- frontier, propose Seed meaning, assess competency questions, and explain
10
+ observations, run reconstruct lens judgments, choose the next unjudged
11
+ source frontier, propose seed meaning, assess competency questions, and explain
12
12
  unresolved gaps. The user-facing experience must therefore expose new
13
13
  information as it is discovered, not only meta status such as "still running".
14
14
 
@@ -34,18 +34,18 @@ The brief must include:
34
34
  test/fixture-only profile if a non-product harness is running, with the
35
35
  completion claim allowed for that profile
36
36
  - model/provider: provider family or realization label without secrets
37
- - domain: selected domain, no-domain mode, or pending domain-context selection
37
+ - domain: selected domain, no-domain mode, or pending domain competency admission
38
38
  - material: `target_material_kind`, target input kind, and unsupported-material
39
39
  status if known
40
40
  - exploration loop: initial source frontier, round budget if any, and frontier
41
41
  validation policy
42
42
  - reconstruction direction: what the reconstruct run will try to explain, and
43
43
  what it will treat as out of scope
44
- - ownership boundary: runtime observes and validates; reconstruct lenses judge
45
- meaning and source gaps; the user or host confirmation controls Seed
44
+ - ownership boundary: runtime observes and validates; reconstruct lens judgments judge
45
+ meaning and source gaps; the user or host confirmation controls seed
46
46
  acceptance
47
47
  - skipped or deferred stages that already narrow downstream authority, such as
48
- live lens judgment, source-frontier exploration, domain-context selection,
48
+ live lens judgment, source-frontier exploration, domain competency admission,
49
49
  user confirmation, or competency-question assessment
50
50
 
51
51
  The opening brief should be declarative. It should not ask the user to approve
@@ -78,9 +78,12 @@ Progress updates should prefer facts such as:
78
78
  - per-lens judgment status and newly named semantic gaps
79
79
  - source frontier refs requested, accepted, rejected, already observed,
80
80
  unsupported, or out of bounds
81
- - domain context refs and snapshot id
82
- - Seed claim count by entity, relation, action, property, and rule
83
- - claim realization stance counts
81
+ - domain competency admission refs and governing snapshot id
82
+ - seed layer count by object, actor, action, workflow, permission, and data
83
+ binding
84
+ - candidate disposition count by disposition
85
+ - ontology-facing handoff readiness, canonical readiness projection, or
86
+ limitation count
84
87
  - confirmation state counts
85
88
  - competency question count and assessment status counts
86
89
  - failure classification counts
@@ -89,9 +92,10 @@ Progress updates should prefer facts such as:
89
92
  - current halt reason and reusable artifact refs when halted
90
93
  - skipped/deferred stage reason and downstream authority impact
91
94
 
92
- Progress updates should avoid pretending that intermediate semantic claims are
93
- final. Before Seed confirmation, claims are candidates. Before competency
94
- question assessment, quality statements are preliminary.
95
+ Progress updates should avoid pretending that intermediate semantic content is
96
+ final. Before seed confirmation, seed content is candidate content. Before
97
+ competency-question assessment and handoff validation, quality statements are
98
+ preliminary.
95
99
 
96
100
  ## 4. Decision Points
97
101
 
@@ -104,9 +108,8 @@ Decision points:
104
108
  - material kind is unsupported or mixed in a way that changes adapter behavior
105
109
  - source frontier expansion would exceed the declared boundary, adapter support,
106
110
  or round/cost budget
107
- - domain context selection changes the interpretation standard
108
- - Seed claim confirmation requires accepted, rejected, partial, or deferred
109
- state
111
+ - domain competency admission changes the interpretation standard
112
+ - seed confirmation requires accepted, rejected, partial, or deferred state
110
113
  - unresolved material questions require a final direction: continue, defer, or
111
114
  accept with disclosed limits
112
115
 
@@ -118,7 +121,7 @@ The host should phrase choices by outcome, not internal jargon.
118
121
  separate:
119
122
 
120
123
  - confirmed Seed content
121
- - claim realization summary
124
+ - candidate disposition summary
122
125
  - competency question assessment summary
123
126
  - material failures and unsafe-to-trust gaps
124
127
  - revision proposals and action candidates
@@ -132,9 +135,10 @@ of `reconstruct-record.yaml`, `reconstruct-run-manifest.yaml`, and the
132
135
  stage-owned artifacts.
133
136
 
134
137
  Full integral exploration wording is allowed only when the run manifest records
135
- the full profile and the required exploration, domain-context, Seed,
136
- confirmation, competency-question, assessment, failure, revision, metrics, stop,
137
- and final-output stages are trusted or explicitly skipped with trusted reasons.
138
+ the full profile and the required exploration, domain competency admission, Seed,
139
+ confirmation, competency-question, assessment, failure, revision, metrics,
140
+ handoff-validation, and final-output stages are trusted or explicitly skipped
141
+ with trusted reasons.
138
142
 
139
143
  ## 6. Halted Or Partial Runs
140
144
 
@@ -151,9 +155,9 @@ If a run halts, the output should still be useful:
151
155
  trusted artifacts
152
156
 
153
157
  A halted run may provide candidate Seed content only if the corresponding
154
- artifact and validation refs exist. It may not imply Seed confirmation, CQ
155
- assessment, failure classification, revision proposal, stop decision, or final
156
- ontology direction unless those artifacts exist.
158
+ artifact and validation refs exist. It may not imply seed confirmation, CQ
159
+ assessment, failure classification, revision proposal, terminal handoff readiness, or
160
+ final ontology direction unless those artifacts exist.
157
161
 
158
162
  ## 7. Runtime Payload Expectations
159
163
 
@@ -1,6 +1,7 @@
1
1
  # Reconstruct Source Profile Contract
2
2
 
3
- > Status: design contract, partially wired runtime.
3
+ > Contract status: active.
4
+ > Runtime support status authority: `reconstruct-contract-registry.yaml#source_profile_records`.
4
5
  > Purpose: define target-material observation contracts for `reconstruct`.
5
6
 
6
7
  ## 1. Canonical Seat
@@ -11,14 +12,14 @@ Source profiles live under:
11
12
  .onto/processes/reconstruct/source-profiles/
12
13
  ```
13
14
 
14
- The historical `explorers/` folder is archived and must not be revived as an
15
- active runtime path. `SourceProfile` is the current name because the file guides
16
- runtime observation. It is not an autonomous semantic explorer.
15
+ `SourceProfileDefinition` is the contract-owned source profile file. A
16
+ `SelectedSourceProfile` is the runtime-owned selection recorded after material
17
+ classification. Neither concept owns semantic interpretation.
17
18
 
18
- In the integral exploration design, source profiles still belong to the runtime
19
- observation side. Reconstruct lenses may ask for additional source refs through
20
- a validated source frontier, but the profile itself does not decide which source
21
- is semantically important.
19
+ In the integral exploration design, source profiles belong to the runtime
20
+ observation side. Reconstruct lens judgments may ask for additional
21
+ source refs through a validated source frontier, but the profile itself does not
22
+ decide which source is semantically important.
22
23
 
23
24
  Source profiles are keyed by `target_material_kind`, the shared runtime axis
24
25
  defined in `.onto/authority/core-lexicon.yaml`. They must not use `source_kind`
@@ -29,16 +30,25 @@ to mean code, spreadsheet, document, or database because review already uses
29
30
  The cross-process goal and validation rules for this axis are defined in
30
31
  `.onto/processes/shared/target-material-kind-contract.md`.
31
32
 
32
- Current source profiles:
33
-
34
- | Target material kind | Profile |
35
- |---|---|
36
- | `code` | `.onto/processes/reconstruct/source-profiles/code.md` |
37
- | `spreadsheet` | `.onto/processes/reconstruct/source-profiles/spreadsheet.md` |
38
- | `database` | `.onto/processes/reconstruct/source-profiles/database.md` |
39
- | `document` | `.onto/processes/reconstruct/source-profiles/document.md` |
40
- | `mixed` | no standalone parser profile; requires per-member profiles or explicit unsupported/halt behavior |
41
- | `unknown` | no profile; runtime must halt or ask for clarification |
33
+ The current profile record set is owned by
34
+ `.onto/processes/reconstruct/reconstruct-contract-registry.yaml#source_profile_records`.
35
+ That registry is the executable authority for profile ids, definition refs,
36
+ definition hashes, contract status, runtime implementation status, schema
37
+ version, profile version, and migration status. This source-profile contract
38
+ defines what a profile means; it does not independently publish current support
39
+ status.
40
+
41
+ Profile migration continuity is also registry-owned. `source_profile_records`
42
+ must record `supersedes`, `replaced_by`, `split_from`, `split_into`,
43
+ `merged_from`, and `merged_into` so old profile snapshots can be replayed,
44
+ compared, or migrated without guessing how a previous profile id maps to the
45
+ current registry.
46
+
47
+ `contract_status` means whether a profile definition or public material-kind
48
+ contract is authoritative. `runtime_implementation_status` means whether the
49
+ current runtime can execute that profile. A profile can be contract-active while
50
+ its runtime adapter is still planned or unsupported, but that status must be read
51
+ from `source_profile_records`.
42
52
 
43
53
  ## 2. Profile Responsibility
44
54
 
@@ -52,11 +62,15 @@ A source profile may define:
52
62
  - scan targets
53
63
  - safe frontier-ref shapes for this material kind
54
64
  - correct and incorrect observation examples
55
- - current support status and explicit unsupported cases
65
+ - profile-specific unsupported cases that do not claim current runtime status
66
+ - profile-specific `candidate_subkind` and `disposition_detail` qualifiers
56
67
 
57
68
  A source profile must not define rules that convert source structure into
58
69
  ontology concepts or rules that choose the next source based on ontology
59
- meaning.
70
+ meaning. A source profile must not define or override `contract_status`,
71
+ `runtime_implementation_status`, `schema_version`, `profile_version`, or
72
+ `migration_status`; those values and source-profile migration mapping fields
73
+ belong to `source_profile_records`.
60
74
 
61
75
  Examples:
62
76
 
@@ -75,7 +89,7 @@ profile may guide observation scope, but the adapter schema is the runtime
75
89
  contract that fixes returned fields and observation ids.
76
90
 
77
91
  When a source adapter is invoked after the first round, it consumes only
78
- runtime-validated source frontier refs. It must not accept lens prose or
92
+ runtime-validated source frontier refs. It must not accept lens-judgment prose or
79
93
  semantic labels as source locations.
80
94
 
81
95
  The future adapter contract must fail explicitly when:
@@ -117,13 +131,25 @@ validates it before any additional observation occurs.
117
131
  Adding a new target material kind requires:
118
132
 
119
133
  1. A new source profile under `.onto/processes/reconstruct/source-profiles/`.
120
- 2. Runtime adapter support or an explicit unsupported status.
134
+ 2. A `source_profile_records` entry that declares profile id, definition ref or
135
+ explicit null-ref behavior, definition hash, contract status, runtime
136
+ implementation status, schema version, profile version, migration status,
137
+ and source-profile migration mapping fields.
121
138
  3. Tests for target material detection, observation shape, source frontier
122
139
  validation, unsupported inputs, and directive evidence-ref validation.
123
- 4. MCP schema updates only after the runtime contract is implemented.
140
+ 4. `reconstruct-contract-registry.yaml` updates when artifact authority,
141
+ validation gates, root candidate kinds, root dispositions, material kinds,
142
+ source profile records, source profile definition refs, runtime
143
+ implementation status values, or support-status migration behavior change.
144
+ 5. MCP schema updates only after the runtime contract is implemented.
124
145
 
125
146
  The source profile alone does not make a target material kind supported.
126
147
 
148
+ Profile-specific refinements must use qualifiers. A source profile may introduce
149
+ `candidate_subkind` or `disposition_detail` values for its material kind. It may
150
+ not introduce a new root candidate kind, root disposition, or material kind
151
+ without a contract and registry change.
152
+
127
153
  ## 6. Mixed Material Rule
128
154
 
129
155
  `mixed` is a public `TargetMaterialKind` value, but it is not a material parser.
@@ -2,9 +2,12 @@
2
2
 
3
3
  > Target material kind: `code`
4
4
 
5
- ## Support Status
5
+ ## Registry Record
6
6
 
7
- Design profile only. Runtime adapter support is not wired in the current repo.
7
+ Current profile id, contract status, runtime implementation status, schema
8
+ version, profile version, migration status, and definition hash are owned by
9
+ `.onto/processes/reconstruct/reconstruct-contract-registry.yaml#source_profile_records`.
10
+ This file defines code observation semantics only.
8
11
 
9
12
  ## Target Material Identification Hints
10
13
 
@@ -59,7 +62,7 @@ status field definition -- src/payment.ts:14
59
62
  - What user-visible workflow does this code support?
60
63
  - Is this code a service, library, script, UI, integration, or test harness?
61
64
  - Are there related repositories or documents that define the domain language?
62
- - Is there a legacy migration or compatibility constraint?
65
+ - Is there a compatibility or migration constraint?
63
66
 
64
67
  ## Scan Targets
65
68
 
@@ -2,9 +2,12 @@
2
2
 
3
3
  > Target material kind: `database`
4
4
 
5
- ## Support Status
5
+ ## Registry Record
6
6
 
7
- Design profile only. Runtime adapter support is not wired in the current repo.
7
+ Current profile id, contract status, runtime implementation status, schema
8
+ version, profile version, migration status, and definition hash are owned by
9
+ `.onto/processes/reconstruct/reconstruct-contract-registry.yaml#source_profile_records`.
10
+ This file defines database observation semantics only.
8
11
 
9
12
  ## Target Material Identification Hints
10
13
 
@@ -2,9 +2,12 @@
2
2
 
3
3
  > Target material kind: `document`
4
4
 
5
- ## Support Status
5
+ ## Registry Record
6
6
 
7
- Design profile only. Runtime adapter support is not wired in the current repo.
7
+ Current profile id, contract status, runtime implementation status, schema
8
+ version, profile version, migration status, and definition hash are owned by
9
+ `.onto/processes/reconstruct/reconstruct-contract-registry.yaml#source_profile_records`.
10
+ This file defines document observation semantics only.
8
11
 
9
12
  ## Target Material Identification Hints
10
13
 
@@ -2,11 +2,12 @@
2
2
 
3
3
  > Target material kind: `spreadsheet`
4
4
 
5
- ## Support Status
5
+ ## Registry Record
6
6
 
7
- Design profile only. Planned first runtime support should cover `.xlsx` and
8
- `.csv`. Other spreadsheet formats such as `.xls` and `.ods` must fail explicitly
9
- until adapter support is implemented.
7
+ Current profile id, contract status, runtime implementation status, schema
8
+ version, profile version, migration status, and definition hash are owned by
9
+ `.onto/processes/reconstruct/reconstruct-contract-registry.yaml#source_profile_records`.
10
+ This file defines spreadsheet observation semantics only.
10
11
 
11
12
  ## Target Material Identification Hints
12
13
 
@@ -185,6 +185,46 @@ If a user later chooses `accept_risk`, that accepted disposition belongs in a
185
185
  separate decision/closure record or future workflow surface. Review presentation
186
186
  may show the candidate; it must not present the candidate as already accepted.
187
187
 
188
+ ### 5.1 Patch-Loop Eligibility Judgement
189
+
190
+ When a material issue appears and the host is considering patch-and-rerun, the
191
+ host LLM should make a short patch-loop eligibility judgement before continuing.
192
+
193
+ This is an operational judgement, not a runtime artifact, schema field, enum, or
194
+ deterministic gate. Runtime remains responsible for preserving snapshot and
195
+ artifact truth; the LLM explains whether repeating the review is still a
196
+ bounded closure loop.
197
+
198
+ The judgement should answer four questions:
199
+
200
+ 1. Is the principal target artifact or design surface materially the same?
201
+ 2. Is the review intent still the same closure problem?
202
+ 3. Is the evidence boundary unchanged?
203
+ 4. Is there patch lineage from the prior issue to the current change?
204
+
205
+ For the first review in a possible loop, the LLM can only classify an
206
+ `initial_loop_candidate`. Trend judgement requires at least a second review in
207
+ the same series.
208
+
209
+ From the second review onward, compare the current issue artifacts with the
210
+ prior review result:
211
+
212
+ | Pattern | Meaning | Loop disposition |
213
+ |---|---|---|
214
+ | `closed` | Prior root issue disappeared. | Continue only if new local residue remains. |
215
+ | `narrowed` | Same root issue remains with smaller scope or weaker severity. | Continue if patch scope stays local. |
216
+ | `new-local` | New issue is a local consequence of the closure patch. | Continue if severity and scope are bounded. |
217
+ | `new-structural` | Issue requires a new authority seat, concept, lifecycle, or ownership split. | Stop and ask. |
218
+ | `boundary-expanding` | Review must expand to runtime, schema, tests, docs, or another material kind. | Stop and treat as a new review. |
219
+ | `reopened` | A supposedly closed root issue reappears. | Stop unless the user explicitly chooses another loop. |
220
+ | `plateau` | Material issue count, severity, or root risk does not decrease across repeated runs. | Stop and ask. |
221
+
222
+ Automatic patch looping is appropriate only for `closed`, `narrowed`, or
223
+ bounded `new-local` patterns, and only when the user has authorized that
224
+ operating mode. `new-structural`, `boundary-expanding`, `reopened`, and
225
+ `plateau` patterns must not be hidden behind `continue_review`; they require a
226
+ user-facing decision or a new review boundary.
227
+
188
228
  ---
189
229
 
190
230
  ## 6. Start And Progress Output
@@ -130,16 +130,32 @@ ledger.
130
130
 
131
131
  ### Reconstruct
132
132
 
133
- `reconstruct` units follow stable `ReconstructStageId` values:
134
-
135
- - material profiling;
136
- - source inventory;
137
- - source observation;
138
- - LLM-authored directive production;
139
- - runtime directive validation;
140
- - Seed candidate, confirmation, competency-question, assessment,
141
- failure-classification, revision, metrics, stop-decision, final-output, and
142
- record assembly stages as the contract enables them.
133
+ `reconstruct` units are runtime projections of the active reconstruct registry
134
+ and the TypeScript stage contract. The registry owns artifact, gate, predicate,
135
+ readiness, and validator authority; the TypeScript stage id list and ledger
136
+ specs are implementation projections that must stay aligned with those registry
137
+ authorities and must not introduce independent semantic authority. The current
138
+ unit families are:
139
+
140
+ - material profile and material-profile validation;
141
+ - source inventory, source observation, source-observation directive, and
142
+ directive validation;
143
+ - per-round source frontier, frontier validation, observation delta, delta
144
+ validation, perspective judgments, exploration synthesis, and observation
145
+ re-entry validation;
146
+ - candidate inventory, candidate disposition, and candidate-disposition
147
+ validation;
148
+ - `ontology-seed.yaml` and `ontology-seed-validation.yaml`;
149
+ - competency questions, competency-question validation, assessment, and
150
+ assessment validation;
151
+ - seed confirmation and seed-confirmation validation;
152
+ - query proofs, visualization proofs, graph-exploration proofs, and their
153
+ runtime validations when the corresponding downstream capability is claimed;
154
+ - failure classification, revision proposal, reconstruct metrics, and their
155
+ validations where applicable;
156
+ - reconstruct run manifest and run-manifest validation;
157
+ - handoff decision and handoff-decision validation before final output and
158
+ reconstruct-record projection.
143
159
 
144
160
  Runtime validation units are the trust gates for LLM-authored artifacts. A
145
161
  semantic artifact can exist but remain untrusted until its validation unit
@@ -97,12 +97,16 @@ cross-material interpretation belongs to the LLM after runtime observation.
97
97
  | Artifact | Required change |
98
98
  |---|---|
99
99
  | `review-target-profile.yaml` | Preserve `target_material_kind`, detection confidence, confidence basis, and unsupported-material state. |
100
- | `target-material-profile.yaml` | New reconstruct runtime artifact for material candidates, selected material kind, selected profiles, and support state. |
100
+ | `target-material-profile.yaml` | New reconstruct runtime artifact for material candidates, selected material kind, selected profile snapshots, per-member selected profile ids for `mixed`, `contract_status`, `runtime_implementation_status`, and support state. |
101
101
  | `source-inventory.yaml` | Preserve material-specific inventory units and scan boundaries. |
102
102
  | `source-observations.yaml` | Include stable observation ids, material kind, adapter id, location, and structural data. |
103
103
  | `source-observation-directive-validation.yaml` | Preserve runtime validation of LLM-selected observation refs against `source-observations.yaml`. |
104
- | `seed-candidate-validation.yaml` | Preserve runtime validation that LLM-authored Seed claims cite selected runtime observations without runtime generating ontology meaning. |
105
- | `reconstruct-record.yaml` | Preserve refs to material profile, inventory, observations, directives, metrics, and final disposition. |
104
+ | `candidate-disposition-validation.yaml` | Preserve runtime validation that every salient material-derived candidate has one allowed disposition before seed promotion. |
105
+ | `ontology-seed-validation.yaml` | Preserve runtime validation that LLM-authored seed claims cite selected runtime observations, close ids, and do not require runtime to generate ontology meaning. |
106
+ | `query-proofs-validation.yaml` | Preserve runtime validation of executable query/API proof refs when queryability is claimed. |
107
+ | `reconstruct-run-manifest.pre-handoff-validation.yaml` | Preserve selected registry, contract, source profile, validator, reference-standard, version, and migration snapshot consistency before terminal handoff. |
108
+ | `reconstruct-run-manifest.post-publication-validation.yaml` | Preserve complete manifest consistency after final output and record refs exist. |
109
+ | `reconstruct-record.yaml` | Preserve refs to material profile, inventory, observations, directives, seed, validations, handoff, manifest validation, metrics, and final disposition. |
106
110
  | future `evolve-target-profile.yaml` | Preserve target refs, `target_material_kind`, support status, and boundary refs before any evolve adapter dispatch. |
107
111
 
108
112
  Artifact names remain contract-owned. Runtime implementation must either match
@@ -110,21 +114,26 @@ these shapes or update the owning contract before code lands.
110
114
 
111
115
  ## 6. Runtime Replacement Steps
112
116
 
113
- Implementation should proceed in this order:
117
+ Implementation should proceed in this order. This table defines dependency
118
+ order only; it is not the authority for current material support. Current
119
+ reconstruct profile support, adapter readiness, profile versions, migration
120
+ status, and definition hashes are owned by
121
+ `.onto/processes/reconstruct/reconstruct-contract-registry.yaml#source_profile_records`
122
+ and must be copied into the runtime `target-material-profile.yaml` snapshot.
114
123
 
115
- | Step | Status |
124
+ | Step | Runtime boundary replaced |
116
125
  |---|---|
117
- | Add a shared `target_material_kind` detection helper. | implemented |
118
- | Extend `review-target-profile.yaml` schema and materializer. | implemented |
119
- | Add reconstruct source profile loader. | implemented |
120
- | Add unsupported/fail-loud behavior for `unknown` and unsupported formats. | implemented for the current minimal adapter contract: unknown and unsupported refs are recorded and skipped without adapter dispatch |
121
- | Implement one minimal source adapter, preferably `document` or `spreadsheet`. | implemented: minimal structural observers write source observations for concrete material refs |
122
- | Define `source-observations.yaml` schema with stable observation ids. | implemented for preparation helper |
123
- | Validate directive evidence refs against observation ids. | implemented for `SourceObservationDirective` |
124
- | Validate Seed candidate claims against selected observation evidence refs. | implemented for `SeedCandidateDirective` helper |
125
- | Assemble reconstruct artifact refs into `reconstruct-record.yaml`. | implemented as record helper |
126
- | Add a reconstruct Core API facade over bounded runtime helpers. | implemented for preparation, profile listing, directive validation, and record assembly |
127
- | Add MCP schemas only after runtime contracts and tests exist. | implemented for `onto.list_source_profiles`, `onto.observe_source`, and `onto.validate_reconstruct_directive`; metrics remain future |
126
+ | Add a shared `target_material_kind` detection helper. | Target refs can be classified without semantic interpretation. |
127
+ | Extend `review-target-profile.yaml` schema and materializer. | Review target profiles can preserve material kind and unsupported state. |
128
+ | Add reconstruct source profile loader. | Reconstruct can dereference selected source-profile records from the registry. |
129
+ | Add unsupported/fail-loud behavior for `unknown` and unsupported formats. | Unsupported refs are recorded or halted before adapter dispatch. |
130
+ | Implement one minimal source adapter for a concrete material kind. | A selected concrete profile can produce structural observations without ontology meaning. |
131
+ | Define `source-observations.yaml` schema with stable observation ids. | LLM-authored artifacts can cite runtime observations by stable ids. |
132
+ | Validate directive evidence refs against observation ids. | Source-observation directives cannot cite non-existent runtime evidence. |
133
+ | Validate candidate disposition and ontology seed claims against selected observation evidence refs. | Candidate promotion and seed claims remain grounded in selected observations. |
134
+ | Assemble reconstruct artifact refs into `reconstruct-record.yaml`. | Terminal records can preserve refs to material profile, inventory, observations, validations, manifest validation, and handoff result. |
135
+ | Add a reconstruct Core API facade over bounded runtime helpers. | Host surfaces can call preparation, profile listing, directive validation, and record assembly through a stable API. |
136
+ | Add MCP schemas only after runtime contracts and tests exist. | Public tool schemas expose bounded runtime facts and artifact refs. |
128
137
 
129
138
  Each step should replace one deterministic boundary. LLM-owned semantic
130
139
  judgment remains outside the runtime replacement steps.
@@ -137,6 +146,10 @@ Runtime must validate:
137
146
  - `unknown` does not dispatch a material adapter
138
147
  - `mixed` records per-member material kinds and one of the support states in
139
148
  section 4.1 before adapter dispatch
149
+ - `target-material-profile.yaml` snapshots every selected source profile from
150
+ `source_profile_records`, including `profile_id`, `definition_ref`,
151
+ `definition_sha256`, `contract_status`, `runtime_implementation_status`,
152
+ `schema_version`, `profile_version`, and `migration_status`
140
153
  - unsupported formats halt or degrade explicitly
141
154
  - source observations do not claim ontology facts such as entity, relation,
142
155
  business rule, aggregate root, or policy meaning
package/AGENTS.md CHANGED
@@ -60,10 +60,12 @@ target material 관련 작업 시 추가로 읽을 문서:
60
60
  `reconstruct` 작업 시 추가로 읽을 문서:
61
61
 
62
62
  1. [reconstruct-boundary-contract.md](/Users/kangmin/cowork/onto-mcp/.onto/processes/reconstruct/reconstruct-boundary-contract.md)
63
- 2. [reconstruct-execution-ux-contract.md](/Users/kangmin/cowork/onto-mcp/.onto/processes/reconstruct/reconstruct-execution-ux-contract.md)
64
- 3. [top-level-concept-discovery-contract.md](/Users/kangmin/cowork/onto-mcp/.onto/processes/reconstruct/top-level-concept-discovery-contract.md)
65
- 4. [source-profile-contract.md](/Users/kangmin/cowork/onto-mcp/.onto/processes/reconstruct/source-profile-contract.md)
66
- 5. selected source profile under `.onto/processes/reconstruct/source-profiles/`
63
+ 2. [actionable-ontology-seed-recomposition-design.md](/Users/kangmin/cowork/onto-mcp/.onto/processes/reconstruct/actionable-ontology-seed-recomposition-design.md)
64
+ 3. [foundry-style-ontology-seed-contract.md](/Users/kangmin/cowork/onto-mcp/.onto/processes/reconstruct/foundry-style-ontology-seed-contract.md)
65
+ 4. [reconstruct-contract-registry.yaml](/Users/kangmin/cowork/onto-mcp/.onto/processes/reconstruct/reconstruct-contract-registry.yaml)
66
+ 5. [reconstruct-execution-ux-contract.md](/Users/kangmin/cowork/onto-mcp/.onto/processes/reconstruct/reconstruct-execution-ux-contract.md)
67
+ 6. [source-profile-contract.md](/Users/kangmin/cowork/onto-mcp/.onto/processes/reconstruct/source-profile-contract.md)
68
+ 7. selected source profile under `.onto/processes/reconstruct/source-profiles/`
67
69
 
68
70
  ---
69
71