kenaz 0.3.21 → 0.3.23

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 (481) hide show
  1. package/core/.claude/commands/Ansuz.md +2 -0
  2. package/core/.claude/hooks/__tests__/peer-session-fill.test.js +37 -0
  3. package/core/.claude/hooks/_ansuz-conversation.js +32 -1
  4. package/core/.claude/hooks/_user-scope.js +1 -1
  5. package/core/.claude/hooks/core-resolve.js +1 -1
  6. package/core/.claude/hooks/peer-optin.test.js +74 -0
  7. package/core/.claude/hooks/peer-session-fill.js +38 -0
  8. package/core/.claude/hooks/turn-context.js +5 -4
  9. package/core/.claude/hooks/worktree-create.js +6 -6
  10. package/core/.claude/hooks/worktree-remove.js +4 -4
  11. package/core/.claude/settings.json +9 -0
  12. package/core/.collaboration/core/reconcile.js +16 -1
  13. package/core/.collaboration/core/task-2467-lifecycle.test.js +63 -0
  14. package/core/.collaboration/core/task-api.js +37 -7
  15. package/core/.formation/bifrost/launch.js +1 -1
  16. package/core/.formation/bifrost/openai/codex-hook-shim.js +21 -4
  17. package/core/.formation/bifrost/openai/codex-peer-pull.test.js +42 -0
  18. package/core/.formation/bifrost/provider-launch.js +2 -1
  19. package/core/.formation/tools/kenaz-stats.js +1 -1
  20. package/core/.formation/tools/post-complete/git-merge.js +1 -1
  21. package/core/.formation/tools/prompt.js +1 -1
  22. package/core/.kenaz/specialist/ansuz_rules.yaml +7 -51
  23. package/core/.kenaz/specialist/ansuz_session_handoff.schema.json +2 -6
  24. package/core/.rule/general/project-self-containment.yaml +2 -2
  25. package/core/.specialist/Amelia/README.md +1 -1
  26. package/core/.specialist/Amelia/rule.yaml +1 -1
  27. package/core/.specialist/Ansuz/RULES.md +1 -1
  28. package/core/.specialist/Ansuz/concepts/commitment_layer.yaml +1 -1
  29. package/core/.specialist/Ansuz/concepts/evolvable_guardrails.yaml +1 -1
  30. package/core/.specialist/Ansuz/knowledge.yaml +1 -3
  31. package/core/.specialist/tools/__tests__/task-2409-lessons.test.js +10 -0
  32. package/core/.specialist/tools/__tests__/task-2427-harvest.test.js +25 -0
  33. package/core/.specialist/tools/ansuz-boot-fast.js +1 -1
  34. package/core/.specialist/tools/failure-detector.js +4 -4
  35. package/core/.specialist/tools/handoff-doc.js +1 -1
  36. package/core/.specialist/tools/lessons.js +2 -2
  37. package/core/CLAUDE.md +5 -5
  38. package/core/KENAZ_CORE_VERSION +1 -1
  39. package/core/dashboard/scripts/install-kenaz-cli.js +471 -0
  40. package/core/dev/scripts/check-file-size.js +1 -1
  41. package/core/dev/scripts/ci-feedback.js +1 -1
  42. package/core/dev/scripts/gc-agent-worktrees.js +11 -11
  43. package/core/dev/scripts/kenaz-session.js +3 -3
  44. package/core/dev/scripts/peer-identity-e2e.js +3 -3
  45. package/core/dev/scripts/run-rust-tests.js +2 -2
  46. package/core/dev/scripts/skill-routing-replay.js +3 -3
  47. package/core/dev/scripts/task1961/selftest.js +2 -2
  48. package/core/dev/scripts/windows-hide-guard.test.js +97 -0
  49. package/core/plugins/kenaz/commands/Ansuz.md +2 -0
  50. package/core/plugins/kenaz/guidance.md +2 -0
  51. package/core/plugins/kenaz/hooks/core-resolve.js +1 -1
  52. package/core/plugins/kenaz/hooks/hooks.json +9 -0
  53. package/core/plugins/kenaz/hooks/kenaz-hook.js +53 -4
  54. package/core/plugins/kenaz/scripts/kenaz.test.js +72 -5
  55. package/core/plugins/kenaz/scripts/ygg.js +40 -4
  56. package/core/plugins/kenaz/scripts/ygg.test.js +63 -3
  57. package/core/plugins/kenaz-peer/hooks/register.test.ts +59 -2
  58. package/core/plugins/kenaz-peer/hooks/register.ts +24 -1
  59. package/lib/cli.js +9 -5
  60. package/package.json +6 -6
  61. package/vendor/install-kenaz-cli.js +21 -6
  62. package/core/.kenaz/designs/METAPLASTICITY_CONFIDENCE_DESIGN.md +0 -537
  63. package/core/.kenaz/designs/REFLEX_INITIATOR_DESIGN.md +0 -501
  64. package/core/.kenaz/designs/TASK_1385_handoff_mcp_design.md +0 -426
  65. package/core/.kenaz/designs/TASK_932_hippocampus_consolidation.md +0 -103
  66. package/core/.kenaz/designs/TASK_934_efe_signal_engine.md +0 -97
  67. package/core/.kenaz/designs/TASK_935_self_evolution_framework.md +0 -154
  68. package/core/.kenaz/designs/VISION_cognitive_architecture_roadmap.md +0 -159
  69. package/core/.kenaz/designs/metaplasticity_simulation_results.json +0 -696
  70. package/core/.kenaz/main-memory/README.md +0 -230
  71. package/core/.kenaz/main-memory/kenaz/cortex/001_cortex_overview.md +0 -168
  72. package/core/.kenaz/main-memory/kenaz/cortex/001_rag_engine_overview.md +0 -30
  73. package/core/.kenaz/main-memory/kenaz/memory-system/001_three_tier_architecture.md +0 -361
  74. package/core/.kenaz/main-memory/kenaz/pipeline/001_task_execution_flow.md +0 -117
  75. package/core/.kenaz/main-memory/kenaz/pipeline/001_task_granularity.md +0 -154
  76. package/core/.kenaz/main-memory/kenaz/pipeline/002_team_priority.md +0 -51
  77. package/core/.kenaz/main-memory/kenaz/pipeline/003_feature_id_system.md +0 -46
  78. package/core/.kenaz/main-memory/kenaz/rules/001_gen_007_self_containment.md +0 -108
  79. package/core/.kenaz/main-memory/kenaz/rules/001_rule_priority_system.md +0 -121
  80. package/core/.kenaz/main-memory/kenaz/rules/002_agt_006_pre_check.md +0 -0
  81. package/core/.kenaz/main-memory/kenaz/rules/003_ppl_002_task_archival.md +0 -48
  82. package/core/.kenaz/main-memory/kenaz/system/001_dual_track_task_system.md +0 -197
  83. package/core/.kenaz/main-memory/knowledge/patterns/001_json_bom_issue.md +0 -78
  84. package/core/.kenaz/main-memory/knowledge/patterns/001_leader_worker_pattern.md +0 -0
  85. package/core/.kenaz/main-memory/knowledge/patterns/002_scope_path_conflict.md +0 -115
  86. package/core/.kenaz/main-memory/knowledge/patterns/002_task_dependency_resolution.md +0 -223
  87. package/core/.kenaz/main-memory/knowledge/patterns/003_question_protocol.md +0 -242
  88. package/core/.kenaz/main-memory/knowledge/patterns/004_user_insight_value.md +0 -111
  89. package/core/.kenaz/main-memory/knowledge/patterns/005_file_lock_pattern.md +0 -274
  90. package/core/.kenaz/main-memory/knowledge/references/001_ppl_rules.md +0 -28
  91. package/core/.kenaz/main-memory/knowledge/solutions/001_json_bom_issue.md +0 -137
  92. package/core/.kenaz/main-memory/knowledge/solutions/001_team_invocation.md +0 -0
  93. package/core/.kenaz/main-memory/knowledge/solutions/002_passive_monitoring.md +0 -0
  94. package/core/.kenaz/main-memory/knowledge/solutions/003_windows_file_race_condition.md +0 -239
  95. package/core/.kenaz/main-memory/registry.json +0 -326
  96. package/core/.kenaz/main-memory/version.yaml +0 -58
  97. package/core/.kenaz/specialist/memory_guard_fired.json +0 -1
  98. package/core/.kenaz/specialist/memory_guard_trigger_cache.json +0 -1
  99. package/core/.kenaz/specialist/memory_source_priority.yaml +0 -260
  100. package/core/.kenaz/specialist/prompt_1775.txt +0 -317
  101. package/core/.kenaz/specialist/prompt_1776.txt +0 -326
  102. package/core/.kenaz/specialist/prompt_1791.txt +0 -320
  103. package/core/.kenaz/specialist/prompt_1792.txt +0 -320
  104. package/core/.kenaz/specialist/prompt_1795.txt +0 -281
  105. package/core/.kenaz/specialist/prompt_1813.txt +0 -332
  106. package/core/.kenaz/specialist/prompt_1814.txt +0 -401
  107. package/core/.kenaz/specialist/prompt_1815.txt +0 -394
  108. package/core/.kenaz/specialist/prompt_1816.txt +0 -437
  109. package/core/.kenaz/specialist/prompt_1818.txt +0 -361
  110. package/core/.kenaz/specialist/prompt_1819.txt +0 -421
  111. package/core/.kenaz/specialist/prompt_1821.txt +0 -345
  112. package/core/.kenaz/specialist/prompt_1822.txt +0 -313
  113. package/core/.kenaz/specialist/prompt_1824.txt +0 -348
  114. package/core/.kenaz/specialist/prompt_1826.txt +0 -388
  115. package/core/.kenaz/specialist/rune_efe_salience_gap.md +0 -21
  116. package/core/.kenaz/specialist/task1825_update.json +0 -43
  117. package/core/.kenaz/specialist/taskgen/consolidation_i.json +0 -38
  118. package/core/.kenaz/specialist/taskgen/csharp_a.json +0 -44
  119. package/core/.kenaz/specialist/taskgen/csharp_b.json +0 -40
  120. package/core/.kenaz/specialist/taskgen/embedding_e.json +0 -34
  121. package/core/.kenaz/specialist/taskgen/hygiene_fg.json +0 -39
  122. package/core/.kenaz/specialist/taskgen/pathology_h.json +0 -36
  123. package/core/.kenaz/specialist/taskgen/unity_noise_d.json +0 -38
  124. package/core/.kenaz/specialist/taskgen/visibility_c.json +0 -38
  125. package/core/.specialist/Ansuz/decisions/ADR-requirement-graph-layer.md +0 -390
  126. package/core/.specialist/Ansuz/self_model_seed.backup.json +0 -100
  127. package/core/.specialist/ansuz_session_handoff.json +0 -96
  128. package/core/dev/ALAYA_FIELD_FEEDBACK_DESIGN.md +0 -126
  129. package/core/dev/ANSUZ_SCAFFOLD_DIET_2026-09-20.md +0 -231
  130. package/core/dev/ANSUZ_STARTUP_INJECTION_REVIEW.md +0 -355
  131. package/core/dev/ANSUZ_WORKFLOW_MODERNIZATION.md +0 -143
  132. package/core/dev/CORTEX_META_GRAPH_ASSESSMENT.md +0 -99
  133. package/core/dev/FREYA_DOWNSTREAM_BUGS_2026-09-19.md +0 -44
  134. package/core/dev/GLOBAL_MEMORY_IDENTITY_CONSOLIDATION.md +0 -263
  135. package/core/dev/GUARD_EFFECTIVENESS_DESIGN.md +0 -180
  136. package/core/dev/HEALTH_GATE_VARIANCE_ASSESSMENT.md +0 -271
  137. package/core/dev/HOOK_DIET_2026-09-21.md +0 -126
  138. package/core/dev/JEV_INTEGRATION_PLAN.md +0 -189
  139. package/core/dev/KENAZ_AGENT_CONNECT_v1_SPEC.md +0 -139
  140. package/core/dev/MOBILE_DESIGN_SPEC.md +0 -569
  141. package/core/dev/MULTI_ANSUZ_SPEC.md +0 -136
  142. package/core/dev/MUNINN_RETIREMENT.md +0 -115
  143. package/core/dev/PHASE3_ATTRIBUTION_POPULATION_DIAGNOSIS.md +0 -211
  144. package/core/dev/PHASE3_P3-2B_TASKLEVEL_PROBE.md +0 -83
  145. package/core/dev/PHASE3_P3-2_POPULATION_DISJOINTNESS.md +0 -83
  146. package/core/dev/PHASE3_P3-2_REMEASURE_REPORT.md +0 -231
  147. package/core/dev/PREDICTION_GROUNDING_DESIGN.md +0 -376
  148. package/core/dev/PRODUCT_SPEC.md +0 -317
  149. package/core/dev/PROJECT_REGISTRY_DUPLICATE_ASSESSMENT.md +0 -86
  150. package/core/dev/STARTUP_TIMELINE_TASK_1995.md +0 -181
  151. package/core/dev/SYNAPSE_WORKER_PER_PROJECT.md +0 -881
  152. package/core/dev/TASK_1680_P3-3_DISPATCH_SPEC.md +0 -96
  153. package/core/dev/TASK_1684_CALIBRATION_IMPACT_ANALYSIS.md +0 -170
  154. package/core/dev/TASK_1684_FORK_A_GOODHART_DESIGN.md +0 -171
  155. package/core/dev/TASK_1684_P3_2_REMEASURE_VALIDATION.md +0 -262
  156. package/core/dev/TASK_1903_SIGNAL_AUC_MEASUREMENT.md +0 -207
  157. package/core/dev/TASK_1904_BRANCH_INTEGRITY_AUDIT.md +0 -146
  158. package/core/dev/ansuz-eval/README.md +0 -38
  159. package/core/dev/ansuz-eval/build-fixtures.js +0 -87
  160. package/core/dev/ansuz-eval/grade.js +0 -96
  161. package/core/dev/ansuz-eval/grader.test.js +0 -117
  162. package/core/dev/ansuz-eval/tasks.md +0 -32
  163. package/core/dev/archive/ansuz/BOOT_FULL.md +0 -141
  164. package/core/dev/archive/ansuz/agents/ansuz-boot.md +0 -176
  165. package/core/dev/archive/ansuz/designs/alaya-passive-surfacing.md +0 -84
  166. package/core/dev/archive/ansuz/designs/cc_memory_indexing.md +0 -307
  167. package/core/dev/archive/ansuz/designs/check_guard.md +0 -322
  168. package/core/dev/archive/ansuz/designs/consequence_loop.md +0 -227
  169. package/core/dev/archive/ansuz/designs/mcp_kuzudb_lock_architecture.md +0 -312
  170. package/core/dev/archive/ansuz/designs/phase0_git_enrichment.md +0 -278
  171. package/core/dev/archive/ansuz/designs/refactor_mcp_tools_synapse.md +0 -490
  172. package/core/dev/archive/ansuz/designs/semantic_markdown_extraction.md +0 -167
  173. package/core/dev/archive/ansuz/designs/task_1372_prompt_injects_into.md +0 -193
  174. package/core/dev/archive/ansuz/designs/thought_stack.md +0 -286
  175. package/core/dev/archive/ansuz/investigations/reachability_unified_api_2026-04-11.md +0 -330
  176. package/core/dev/archive/ansuz/investigations/synapse_orphans_indexing_bug_2026-04-11.md +0 -352
  177. package/core/dev/archive/ansuz/investigations/synapse_orphans_reindex_verification_2026-04-11.md +0 -48
  178. package/core/dev/archive/ansuz/investigations/synapse_orphans_verification_2026-04-11.md +0 -170
  179. package/core/dev/archive/ansuz/legacy/kernel.yaml +0 -399
  180. package/core/dev/archive/ansuz/legacy/phases/phase_0.yaml +0 -418
  181. package/core/dev/archive/ansuz/legacy/phases/phase_1.yaml +0 -376
  182. package/core/dev/archive/ansuz/legacy/phases/phase_10.yaml +0 -35
  183. package/core/dev/archive/ansuz/legacy/phases/phase_11.yaml +0 -582
  184. package/core/dev/archive/ansuz/legacy/phases/phase_2.yaml +0 -94
  185. package/core/dev/archive/ansuz/legacy/phases/phase_3.yaml +0 -274
  186. package/core/dev/archive/ansuz/legacy/phases/phase_4.yaml +0 -67
  187. package/core/dev/archive/ansuz/legacy/phases/phase_5.yaml +0 -32
  188. package/core/dev/archive/ansuz/legacy/phases/phase_6.yaml +0 -91
  189. package/core/dev/archive/ansuz/legacy/phases/phase_7.yaml +0 -58
  190. package/core/dev/archive/ansuz/legacy/phases/phase_8.yaml +0 -146
  191. package/core/dev/archive/ansuz/legacy/phases/phase_9.yaml +0 -424
  192. package/core/dev/archive/ansuz/specs/INDEX_bifrost_hook_parity.yaml +0 -92
  193. package/core/dev/archive/ansuz/specs/active-inference-formation.yaml +0 -453
  194. package/core/dev/archive/ansuz/specs/brief_TASK_1228_userpromptsubmit.yaml +0 -191
  195. package/core/dev/archive/ansuz/specs/brief_TASK_1229_pretooluse_posttooluse.yaml +0 -250
  196. package/core/dev/archive/ansuz/specs/brief_TASK_1230_sessionstart_stop.yaml +0 -301
  197. package/core/dev/archive/ansuz/specs/brief_TASK_1231_verification.yaml +0 -272
  198. package/core/dev/archive/skills/feature_agent/SKILL.md +0 -289
  199. package/core/dev/design/PHASE4_DESIGN.md +0 -559
  200. package/core/dev/design/dashboard_docs_integration_PLAN.md +0 -388
  201. package/core/dev/design/matrix_format_ABBREVIATIONS.md +0 -655
  202. package/core/dev/design/matrix_format_DESIGN_SPEC.md +0 -601
  203. package/core/dev/design/matrix_format_DISCUSSION_SUMMARY.md +0 -484
  204. package/core/dev/design/matrix_format_EXAMPLE_memory.matrix +0 -13
  205. package/core/dev/design/matrix_format_EXAMPLE_project_status.matrix +0 -9
  206. package/core/dev/design/matrix_format_EXAMPLE_tasks.matrix +0 -14
  207. package/core/dev/design/matrix_format_SYNTAX_BNF.md +0 -754
  208. package/core/dev/design/matrix_format_TOKEN_COMPARISON.md +0 -484
  209. package/core/dev/design/matrix_v2_COGNITIVE_DESIGN.md +0 -503
  210. package/core/dev/design/matrix_v2_DISCUSSION_SUMMARY.md +0 -414
  211. package/core/dev/design/matrix_v2_EXAMPLE.matrix +0 -67
  212. package/core/dev/designs/EXPANDABLE_CARD_DESIGN_SPEC.md +0 -509
  213. package/core/dev/jev-eval/ACTIVE_CORRECTION.md +0 -52
  214. package/core/dev/jev-eval/ANNOTATION_GUIDE.md +0 -68
  215. package/core/dev/jev-eval/BASELINE_COMPARISON.md +0 -45
  216. package/core/dev/jev-eval/CONTEXT_REVIEW.md +0 -31
  217. package/core/dev/jev-eval/EVALUATION_STATUS.md +0 -39
  218. package/core/dev/jev-eval/HISTORICAL_CORPUS.md +0 -33
  219. package/core/dev/jev-eval/PACKAGING_VERIFICATION.md +0 -42
  220. package/core/dev/jev-eval/README.md +0 -101
  221. package/core/dev/jev-eval/THALAMUS_RANKING.md +0 -58
  222. package/core/dev/jev-eval/VALIDATION_PROGRESS.md +0 -54
  223. package/core/dev/jev-eval/cli.mjs +0 -50
  224. package/core/dev/jev-eval/context.mjs +0 -183
  225. package/core/dev/jev-eval/corpus.mjs +0 -186
  226. package/core/dev/jev-eval/fixtures/conversation-review.seed.jsonl +0 -6
  227. package/core/dev/jev-eval/fixtures/synthetic.jsonl +0 -11
  228. package/core/dev/jev-eval/metrics.mjs +0 -67
  229. package/core/dev/jev-eval/muninn-baseline.mjs +0 -119
  230. package/core/dev/jev-eval/providers.mjs +0 -95
  231. package/core/dev/jev-eval/reports/annotation-pilot-2026-09-20.json +0 -32
  232. package/core/dev/jev-eval/reports/context-review-2026-09-20.json +0 -48
  233. package/core/dev/jev-eval/reports/conversation-review.pending.json +0 -151
  234. package/core/dev/jev-eval/reports/history-corpus-2026-09-20.json +0 -52
  235. package/core/dev/jev-eval/reports/length-probe-2026-09-20.json +0 -133
  236. package/core/dev/jev-eval/reports/live-smoke-2026-09-20.json +0 -616
  237. package/core/dev/jev-eval/reports/muninn-baseline-2026-09-20.json +0 -52
  238. package/core/dev/jev-eval/reports/resilience-2026-09-20.json +0 -520
  239. package/core/dev/jev-eval/reports/rules-baseline.json +0 -197
  240. package/core/dev/jev-eval/reports/synthetic-review.pending.json +0 -357
  241. package/core/dev/jev-eval/resilience.mjs +0 -71
  242. package/core/dev/jev-eval/review.mjs +0 -78
  243. package/core/dev/jev-eval/schema.mjs +0 -87
  244. package/core/dev/jev-eval/test/context.test.mjs +0 -95
  245. package/core/dev/jev-eval/test/corpus.test.mjs +0 -102
  246. package/core/dev/jev-eval/test/eval.test.mjs +0 -146
  247. package/core/dev/jev-eval/test/muninn-baseline.test.mjs +0 -71
  248. package/core/dev/jev-eval/test/resilience.test.mjs +0 -72
  249. package/core/dev/jev-eval/test/review.test.mjs +0 -61
  250. package/core/dev/pipeline/PHASE3_PLANNING_SUMMARY.md +0 -338
  251. package/core/dev/pipeline/PROGRESS.md +0 -113
  252. package/core/dev/pipeline/PROGRESS_template.md +0 -860
  253. package/core/dev/pipeline/QA_REPORT_F008.md +0 -431
  254. package/core/dev/pipeline/QA_REPORT_LOCAL_CLAUDE_DIAGNOSIS.md +0 -583
  255. package/core/dev/pipeline/README.md +0 -210
  256. package/core/dev/pipeline/WORKFLOW_GUIDE.md +0 -824
  257. package/core/dev/pipeline/archived/TASK_015_tauri_init.yaml +0 -53
  258. package/core/dev/pipeline/archived/TASK_016_tauri_commands.yaml +0 -54
  259. package/core/dev/pipeline/archived/TASK_017_rust_pty.yaml +0 -54
  260. package/core/dev/pipeline/archived/TASK_018_tauri_bundle.yaml +0 -53
  261. package/core/dev/pipeline/archived/TASK_019_release_workflow.yaml +0 -56
  262. package/core/dev/pipeline/archived/TASK_020_update_ui.yaml +0 -54
  263. package/core/dev/pipeline/archived/TASK_021_update_notification_ui.yaml +0 -55
  264. package/core/dev/pipeline/archived/TASK_022_remove_node_pty.yaml +0 -65
  265. package/core/dev/pipeline/archived/TASK_023_api_routes_migration.yaml +0 -86
  266. package/core/dev/pipeline/archived/TASK_024_feature_id_system.yaml +0 -51
  267. package/core/dev/pipeline/archived/TASK_025_executable_acceptance.yaml +0 -66
  268. package/core/dev/pipeline/archived/TASK_026_spec_versioning.yaml +0 -56
  269. package/core/dev/pipeline/archived/TASK_027_drift_detection.yaml +0 -60
  270. package/core/dev/pipeline/archived/TASK_028_tauri_pty_manager.yaml +0 -60
  271. package/core/dev/pipeline/archived/TASK_029_tauri_pty_commands.yaml +0 -62
  272. package/core/dev/pipeline/archived/TASK_030_frontend_session_adapter.yaml +0 -54
  273. package/core/dev/pipeline/archived/TASK_031_terminal_tauri_events.yaml +0 -56
  274. package/core/dev/pipeline/archived/TASK_041_scheduler_data_models.yaml +0 -54
  275. package/core/dev/pipeline/archived/TASK_042_path_lock_manager.yaml +0 -53
  276. package/core/dev/pipeline/archived/TASK_043_process_manager.yaml +0 -57
  277. package/core/dev/pipeline/archived/TASK_044_git_integration.yaml +0 -85
  278. package/core/dev/pipeline/archived/TASK_045_task_queue_manager.yaml +0 -54
  279. package/core/dev/pipeline/archived/TASK_046_scheduler_dispatcher.yaml +0 -60
  280. package/core/dev/pipeline/archived/TASK_047_tauri_scheduler_commands.yaml +0 -55
  281. package/core/dev/pipeline/archived/TASK_048_realtime_status_push.yaml +0 -92
  282. package/core/dev/pipeline/archived/TASK_049_frontend_scheduler_integration.yaml +0 -58
  283. package/core/dev/pipeline/archived/TASK_050_error_recovery.yaml +0 -56
  284. package/core/dev/pipeline/archived/TASK_051_optimization_proposals_backend.yaml +0 -53
  285. package/core/dev/pipeline/archived/TASK_052_optimization_proposals_ui.yaml +0 -58
  286. package/core/dev/pipeline/archived/TASK_053_optimization_proposals_diff_view.yaml +0 -54
  287. package/core/dev/pipeline/archived/TASK_054_multi_project_scheduler_state.yaml +0 -76
  288. package/core/dev/pipeline/archived/TASK_055_scheduler_api_project_scope.yaml +0 -64
  289. package/core/dev/pipeline/archived/TASK_056_frontend_scheduler_project_scope.yaml +0 -62
  290. package/core/dev/pipeline/archived/TASK_057_scheduler_module_structure.yaml +0 -54
  291. package/core/dev/pipeline/archived/TASK_058_scheduler_models_extract.yaml +0 -51
  292. package/core/dev/pipeline/archived/TASK_059_scheduler_core_extract.yaml +0 -51
  293. package/core/dev/pipeline/archived/TASK_060_scheduler_commands_extract.yaml +0 -51
  294. package/core/dev/pipeline/archived/TASK_061_scheduler_specialized_commands.yaml +0 -53
  295. package/core/dev/pipeline/archived/TASK_062_process_manager_module_structure.yaml +0 -56
  296. package/core/dev/pipeline/archived/TASK_063_process_manager_core_extract.yaml +0 -56
  297. package/core/dev/pipeline/archived/TASK_064_recovery_module_structure.yaml +0 -57
  298. package/core/dev/pipeline/archived/TASK_065_recovery_core_extract.yaml +0 -56
  299. package/core/dev/pipeline/archived/TASK_066_self_enhancement_scheduler_models.yaml +0 -60
  300. package/core/dev/pipeline/archived/TASK_067_agents_section_quick_actions.yaml +0 -53
  301. package/core/dev/pipeline/archived/TASK_067_self_enhancement_scheduler_core.yaml +0 -65
  302. package/core/dev/pipeline/archived/TASK_068_agent_workflow_rule_enhancement.yaml +0 -46
  303. package/core/dev/pipeline/archived/TASK_068_self_enhancement_tauri_commands.yaml +0 -61
  304. package/core/dev/pipeline/archived/TASK_069_agent_wizard_responsive.yaml +0 -46
  305. package/core/dev/pipeline/archived/TASK_069_self_enhancement_ui.yaml +0 -62
  306. package/core/dev/pipeline/archived/TASK_070_preview_panel_redesign.yaml +0 -62
  307. package/core/dev/pipeline/archived/TASK_070_self_enhancement_integration.yaml +0 -57
  308. package/core/dev/pipeline/archived/TASK_071_preview_panel_qa.yaml +0 -98
  309. package/core/dev/pipeline/archived/TASK_071_single_agent_config.yaml +0 -57
  310. package/core/dev/pipeline/archived/TASK_072_preview_modal_esc_fix.yaml +0 -71
  311. package/core/dev/pipeline/archived/TASK_072_product_review_module.yaml +0 -57
  312. package/core/dev/pipeline/archived/TASK_073_agents_page_component_refactor.yaml +0 -68
  313. package/core/dev/pipeline/archived/TASK_073_rename_single_agent.yaml +0 -64
  314. package/core/dev/pipeline/archived/TASK_074_preview_mode_ui_diagnosis.yaml +0 -71
  315. package/core/dev/pipeline/archived/TASK_074_single_agent_ui_toggle.yaml +0 -56
  316. package/core/dev/pipeline/archived/TASK_075_agents_page_component_refactor.yaml +0 -69
  317. package/core/dev/pipeline/archived/TASK_075_single_agent_integration_test.yaml +0 -75
  318. package/core/dev/pipeline/archived/TASK_076_preview_mode_ui_diagnosis.yaml +0 -70
  319. package/core/dev/pipeline/archived/TASK_076_single_agent_continuous_mode.yaml +0 -65
  320. package/core/dev/pipeline/archived/TASK_077_failure_directory_structure.yaml +0 -51
  321. package/core/dev/pipeline/archived/TASK_077_single_agent_typescript_types.yaml +0 -59
  322. package/core/dev/pipeline/archived/TASK_078_fail_001_agent_no_output.yaml +0 -53
  323. package/core/dev/pipeline/archived/TASK_078_single_agent_ui_simplify.yaml +0 -74
  324. package/core/dev/pipeline/archived/TASK_079_dashboard_rwd_responsive.yaml +0 -63
  325. package/core/dev/pipeline/archived/TASK_079_fail_002_json_bom.yaml +0 -56
  326. package/core/dev/pipeline/archived/TASK_080_fail_003_queue_pollution.yaml +0 -56
  327. package/core/dev/pipeline/archived/TASK_080_http_server_module.yaml +0 -55
  328. package/core/dev/pipeline/archived/TASK_081_failure_logging_tools.yaml +0 -57
  329. package/core/dev/pipeline/archived/TASK_081_http_api_routes.yaml +0 -62
  330. package/core/dev/pipeline/archived/TASK_082_frontend_api_adapter.yaml +0 -51
  331. package/core/dev/pipeline/archived/TASK_082_integrate_failure_to_workflow.yaml +0 -60
  332. package/core/dev/pipeline/archived/TASK_083_cleanup_nextjs_api.yaml +0 -48
  333. package/core/dev/pipeline/archived/TASK_083_task_queue_cleanup.yaml +0 -67
  334. package/core/dev/pipeline/archived/TASK_084_rust_dead_code_cleanup.yaml +0 -66
  335. package/core/dev/pipeline/archived/TASK_084_scheduler_sync_logic_fix.yaml +0 -68
  336. package/core/dev/pipeline/archived/TASK_085_http_api_web_mode_fixes.yaml +0 -46
  337. package/core/dev/pipeline/archived/TASK_085_memory_consolidation_0204_0205.yaml +0 -98
  338. package/core/dev/pipeline/archived/TASK_086_collapsible_preview_panel.yaml +0 -161
  339. package/core/dev/pipeline/archived/TASK_086_web_mode_feature_parity.yaml +0 -62
  340. package/core/dev/pipeline/archived/TASK_087_manual_memory_archival.yaml +0 -163
  341. package/core/dev/pipeline/archived/TASK_087_mobile_http_control.yaml +0 -68
  342. package/core/dev/pipeline/archived/TASK_088_fail_003_to_ppl_002_rule.yaml +0 -63
  343. package/core/dev/pipeline/archived/TASK_088_mobile_http_qa.yaml +0 -121
  344. package/core/dev/pipeline/archived/TASK_089_agent_collaboration_topic.yaml +0 -60
  345. package/core/dev/pipeline/archived/TASK_089_web_mode_monitor_fix.yaml +0 -58
  346. package/core/dev/pipeline/archived/TASK_090_cli_detection_fix.yaml +0 -61
  347. package/core/dev/pipeline/archived/TASK_090_ui_ux_lessons_topic.yaml +0 -63
  348. package/core/dev/pipeline/archived/TASK_091_expandable_card_design.yaml +0 -56
  349. package/core/dev/pipeline/archived/TASK_091_move_agent_section_components.yaml +0 -65
  350. package/core/dev/pipeline/archived/TASK_092_expandable_card_component.yaml +0 -60
  351. package/core/dev/pipeline/archived/TASK_092_refactor_agent_create_wizard.yaml +0 -84
  352. package/core/dev/pipeline/archived/TASK_093_taskcard_detail_integration.yaml +0 -57
  353. package/core/dev/pipeline/archived/TASK_093_update_barrel_exports_test.yaml +0 -84
  354. package/core/dev/pipeline/archived/TASK_094_ai_agent_generation_enhancement.yaml +0 -115
  355. package/core/dev/pipeline/archived/TASK_094_proposalcard_detail_integration.yaml +0 -55
  356. package/core/dev/pipeline/archived/TASK_095_preview_fixes.yaml +0 -129
  357. package/core/dev/pipeline/archived/TASK_095_single_agent_task_selector.yaml +0 -60
  358. package/core/dev/pipeline/archived/TASK_096_agents_page_ux_improvements.yaml +0 -163
  359. package/core/dev/pipeline/archived/TASK_096_single_agent_status_sync.yaml +0 -60
  360. package/core/dev/pipeline/archived/TASK_097_local_claude_error_logging.yaml +0 -59
  361. package/core/dev/pipeline/archived/TASK_097_single_agent_monitor_events.yaml +0 -59
  362. package/core/dev/pipeline/archived/TASK_098_product_manager_team_phase2.yaml +0 -60
  363. package/core/dev/pipeline/archived/TASK_098_single_agent_refactor_test.yaml +0 -58
  364. package/core/dev/pipeline/archived/TASK_099_backend_team_creation.yaml +0 -258
  365. package/core/dev/pipeline/archived/TASK_100_frontend_team_creation.yaml +0 -61
  366. package/core/dev/pipeline/archived/TASK_101_orchestrator_system.yaml +0 -403
  367. package/core/dev/pipeline/archived/TASK_102_designer_sre_teams.yaml +0 -90
  368. package/core/dev/pipeline/archived/TASK_103_integration_testing.yaml +0 -86
  369. package/core/dev/pipeline/archived/TASK_128_integration_testing.yaml +0 -83
  370. package/core/dev/pipeline/archived/TASK_134_cortex_v2_phase3_file_watcher.yaml +0 -65
  371. package/core/dev/pipeline/archived/TASK_134_team_http_api.yaml +0 -96
  372. package/core/dev/pipeline/archived/TASK_135_cortex_v2_phase3_git_monitor.yaml +0 -63
  373. package/core/dev/pipeline/archived/TASK_136_cortex_v2_phase3_change_analyzer.yaml +0 -69
  374. package/core/dev/pipeline/archived/TASK_137_cortex_v2_phase3_cache_invalidator.yaml +0 -67
  375. package/core/dev/pipeline/archived/TASK_137_team_orchestrator_integration.yaml +0 -93
  376. package/core/dev/pipeline/archived/TASK_138_cortex_v2_phase3_distributed_cache.yaml +0 -68
  377. package/core/dev/pipeline/archived/TASK_138_matrix_folder_structure.yaml +0 -61
  378. package/core/dev/pipeline/archived/TASK_139_cortex_v2_phase3_cache_prewarming.yaml +0 -65
  379. package/core/dev/pipeline/archived/TASK_146_unified_documentation.yaml +0 -141
  380. package/core/dev/pipeline/archived/TASK_147_pipeline_execution_rules.yaml +0 -76
  381. package/core/dev/pipeline/archived/TASK_148_update_claude_md.yaml +0 -77
  382. package/core/dev/pipeline/archived/TASK_149_fix_nextjs_mdx_serialization.yaml +0 -63
  383. package/core/dev/pipeline/archived/TASK_149_update_team_docs.yaml +0 -77
  384. package/core/dev/pipeline/archived/TASK_150_pipeline_workflow_guide.yaml +0 -82
  385. package/core/dev/pipeline/archived/TASK_164_fix_smart_context_switch.yaml +0 -49
  386. package/core/dev/pipeline/archived/TASK_165_ctags_symbol_index.yaml +0 -53
  387. package/core/dev/pipeline/archived/TASK_166_symbol_search_mcp_tool.yaml +0 -48
  388. package/core/dev/pipeline/archived/TASK_167_llm_module_summary.yaml +0 -55
  389. package/core/dev/pipeline/archived/TASK_168_map_reduce_context.yaml +0 -51
  390. package/core/dev/pipeline/archived/TASK_169_v2_integration_testing.yaml +0 -52
  391. package/core/dev/pipeline/backups/archive_2026-02-04T22-07-22/TASK_QUEUE_backup.json +0 -95
  392. package/core/dev/pipeline/docs/multi-agent-coordination.md +0 -446
  393. package/core/dev/pipeline/docs/overview.md +0 -406
  394. package/core/dev/pipeline/docs/task-management.md +0 -412
  395. package/core/dev/pipeline/docs/workflows.md +0 -32
  396. package/core/dev/pipeline/orchestrator/schemas/task_queue_schema.json +0 -58
  397. package/core/dev/pipeline/orchestrator/schemas/task_schema.json +0 -139
  398. package/core/dev/pipeline/plans/PLAN_task_cli_refactor.md +0 -281
  399. package/core/dev/pipeline/test_results/TASK_TEST_PARALLEL_002_result.txt +0 -27
  400. package/core/dev/plans/ANSUZ_SLIM_PLAN.md +0 -68
  401. package/core/dev/plans/CLI_FIRST_INSTALL_FLOW.md +0 -120
  402. package/core/dev/plans/FORMATION_RETIREMENT_PLAN.md +0 -313
  403. package/core/dev/plans/KUZU_REPLACEMENT_PLAN.md +0 -126
  404. package/core/dev/scripts/CRASH_DIAGNOSIS.md +0 -47
  405. package/core/dev/scripts/README.md +0 -142
  406. package/core/dev/scripts/RUN_ONCE.bat +0 -40
  407. package/core/dev/scripts/START_DEV_AGENT.bat +0 -63
  408. package/core/dev/scripts/START_MULTI_AGENT.bat +0 -80
  409. package/core/dev/scripts/dev_agent_scheduler.ps1 +0 -536
  410. package/core/dev/scripts/init_git.ps1 +0 -396
  411. package/core/dev/scripts/init_git.sh +0 -337
  412. package/core/dev/scripts/init_project.ps1 +0 -851
  413. package/core/dev/scripts/init_project.sh +0 -477
  414. package/core/dev/scripts/multi_agent_scheduler.ps1 +0 -2021
  415. package/core/dev/scripts/multi_agent_scheduler.sh +0 -1344
  416. package/core/dev/scripts/run_once.sh +0 -47
  417. package/core/dev/scripts/setup_rag.ps1 +0 -304
  418. package/core/dev/scripts/setup_rag.sh +0 -230
  419. package/core/dev/scripts/start_dev_agent.sh +0 -137
  420. package/core/dev/scripts/start_multi_agent.sh +0 -41
  421. package/core/dev/scripts/sync_task_queue.ps1 +0 -505
  422. package/core/dev/scripts/sync_task_queue.sh +0 -392
  423. package/core/dev/specs/agent-connect/PROTOCOL.md +0 -177
  424. package/core/dev/specs/agent-connect/SDK_GUIDE.md +0 -915
  425. package/core/dev/specs/agent-connect/examples/minimal-site/README.md +0 -137
  426. package/core/dev/specs/agent-connect/examples/minimal-site/package.json +0 -12
  427. package/core/dev/specs/agent-connect/examples/minimal-site/public/index.html +0 -116
  428. package/core/dev/specs/agent-connect/examples/minimal-site/public/install-redirect.js +0 -73
  429. package/core/dev/specs/agent-connect/examples/minimal-site/server.js +0 -516
  430. package/core/dev/specs/agent-connect/examples/minimal-site/test/smoke.test.mjs +0 -263
  431. package/core/dev/specs/agent-connect/history/DEFECT_REPORT_kenaz-agent-hub_2026-09-09_v0.4-empty-prompt-no-first-turn.md +0 -77
  432. package/core/dev/specs/agent-connect/history/DEFECT_REPORT_kenaz-agent-hub_2026-09-09_v0.4-prompt-mojibake.md +0 -90
  433. package/core/dev/specs/agent-connect/history/FEATURE_REQUEST_kenaz-agent-hub_2026-09-07.md +0 -61
  434. package/core/dev/specs/agent-connect/history/FEATURE_REQUEST_kenaz-agent-hub_2026-09-08_relay-v1-conformance.md +0 -76
  435. package/core/dev/specs/agent-connect/history/FEATURE_REQUEST_kenaz-agent-hub_2026-09-09_v0.4-session-channel.md +0 -87
  436. package/core/dev/specs/agent-connect/history/FLOWPIX_REPLY_agent-hub_2026-09-08_relay-v1-answers.md +0 -68
  437. package/core/dev/specs/agent-connect/history/FLOWPIX_bridge_CONTRACT.md +0 -642
  438. package/core/dev/specs/agent-connect/history/FLOWPIX_spikes_relay_spike_relay.mjs +0 -244
  439. package/core/dev/specs/agent-connect/history/KENAZ_RESPONSE_agent-hub_2026-09-07.md +0 -77
  440. package/core/dev/specs/agent-connect/history/KENAZ_RESPONSE_agent-hub_2026-09-08_direction-change-v0.3.md +0 -44
  441. package/core/dev/specs/agent-connect/history/KENAZ_RESPONSE_agent-hub_2026-09-08_relay-v1-answers-ack.md +0 -37
  442. package/core/dev/specs/agent-connect/history/KENAZ_RESPONSE_agent-hub_2026-09-08_relay-v1-conformance.md +0 -56
  443. package/core/dev/specs/agent-connect/history/KENAZ_RESPONSE_agent-hub_2026-09-09_annotations-install-coldstart.md +0 -44
  444. package/core/dev/specs/agent-connect/history/KENAZ_RESPONSE_agent-hub_2026-09-09_empty-prompt-first-turn.md +0 -56
  445. package/core/dev/specs/agent-connect/history/KENAZ_RESPONSE_agent-hub_2026-09-09_prompt-mojibake-fixed.md +0 -48
  446. package/core/dev/specs/agent-connect/history/KENAZ_RESPONSE_agent-hub_2026-09-09_session-channel.md +0 -57
  447. package/core/dev/specs/agent-connect/history/PROTOCOL_v0.3_snapshot.md +0 -379
  448. package/core/dev/specs/agent-connect/history/README.md +0 -47
  449. package/core/dev/specs/peer/CODEX_INTERACTIVE_PUSH.md +0 -65
  450. package/core/dev/specs/peer/CODEX_MANAGED_DAEMON.md +0 -54
  451. package/core/dev/specs/peer/CODEX_PEER_PULL_SPIKE.md +0 -54
  452. package/core/dev/specs/peer/MODS_SPIKE.md +0 -133
  453. package/core/dev/specs/peer/PER_PROJECT_ADDRESSING.md +0 -143
  454. package/core/dev/specs/peer/SWARM_PROTOCOLS.md +0 -256
  455. package/core/dev/specs/peer/codex-hook-shim-peer.test.js +0 -113
  456. package/core/dev/specs/peer/codex-push-launcher.test.js +0 -142
  457. package/core/dev/specs/peer/setup-codex-hooks.test.js +0 -60
  458. package/core/dev/specs/peer-ansuz/DELIVERY_SPIKE.md +0 -397
  459. package/core/dev/specs/peer-ansuz/DESIGN.md +0 -109
  460. package/core/dev/specs/peer-ansuz/spike/claude_poke.js +0 -129
  461. package/core/dev/specs/peer-ansuz/spike/claude_session_start_hook.js +0 -37
  462. package/core/dev/specs/peer-ansuz/spike/claude_settings_hook.json +0 -14
  463. package/core/dev/specs/peer-ansuz/spike/codex_appserver_client.js +0 -105
  464. package/core/dev/specs/peer-ansuz/spike/codex_appserver_query.js +0 -29
  465. package/core/dev/specs/peer-ansuz/spike/extract_timeline.js +0 -26
  466. package/core/dev/specs/synapse/SYMBOL_IDENTITY.md +0 -305
  467. package/core/dev/spikes/A4-cypher-varlen.md +0 -176
  468. package/core/dev/spikes/bloat-rounds.sh +0 -25
  469. package/core/dev/spikes/mods/clean-claude.js +0 -9
  470. package/core/dev/spikes/mods/drive-probe.js +0 -29
  471. package/core/dev/spikes/mods/e2e-peer.js +0 -71
  472. package/core/dev/spikes/mods/evidence/e2e-peer-control.json +0 -17
  473. package/core/dev/spikes/mods/evidence/e2e-peer-mod.json +0 -17
  474. package/core/dev/spikes/mods/evidence/probe-006a6e65-d807-4bc1-b648-fd7d1edfe0b4.jsonl +0 -4
  475. package/core/dev/spikes/mods/evidence/probe-cebdf1f7-f9c4-47a8-83cd-7c0786177404.jsonl +0 -12
  476. package/core/dev/spikes/mods/evidence/probe-eb21147d-10ce-4c32-93ed-37ca37d88d5a.jsonl +0 -11
  477. package/core/dev/spikes/mods/evidence/stream-cebdf1f7.jsonl +0 -18
  478. package/core/dev/spikes/mods/kenaz-mod-probe/.claude-plugin/plugin.json +0 -1
  479. package/core/dev/spikes/mods/kenaz-mod-probe/hooks/hooks.json +0 -1
  480. package/core/dev/spikes/mods/kenaz-mod-probe/hooks/register.ts +0 -65
  481. package/core/dev/spikes/mods/kenaz-mod-probe/tsconfig.json +0 -3
@@ -1,421 +0,0 @@
1
- [WORKTREE SUBAGENT MODE]
2
- 你已被 Ansuz 透過 Agent tool 的 worktree isolation 指派任務。規則:
3
- 1. 開始前先輸出一行摘要:「📋 {TASK_ID}: {你準備做什麼}」(一句話,不超過 30 字)。然後再動手。
4
- 2. 直接執行,不要提問。需求已經確認過了。
5
- 3. CLAUDE.md 已啟用 — 遵循其規則(此為互動式 Claude Code 環境)。
6
- 4. 完成後輸出結構化結果。
7
- 5. 遇到無法執行的問題,輸出錯誤描述後結束。
8
- 6. **Git 操作被允許且必要** — 你在隔離的 worktree 中執行,commits 落在 task branch,不影響用戶 branch:
9
- - **COMMIT FIRST(順序不可調換)**:改完程式碼就**立刻** `git add -A && git commit --no-verify -m "[{TASK_ID}] task completed"`,**不要等驗證通過再 commit**。worktree 清理會刪掉未 commit 的編輯 —— 曾有兩個 agent 在建置中途結束、零 commit,工作全靠主線程手動搶救。寧可 commit 三次也不要一次都沒有。
10
- - 禁止 git push 到遠端。不可切換 branch。
11
- 12. **⚠️ 你送出訊息就等於結束本次執行。** 你的最終訊息**就是**回傳值 —— 沒有「稍後回來接手」這回事。不要規劃「先讓出控制權、等背景工作完成再繼續」,那會直接結束你的執行並留下無人收拾的背景行程。
12
- 13. **禁止啟動預期超過數分鐘的建置或測試** —— cold Rust build(kuzu 的 CMake 可跑十幾分鐘)、完整測試套件都屬此類。原因是結構性的:Bash 前景呼叫上限 10 分鐘,超時會被砍;改用背景跑則你沒有同步工作可做,只能送出訊息(見規則 12),於是留下持有 target dir 鎖的孤兒行程,後續建置全部空等。
13
- - **正確做法**:改完程式碼 → commit(規則 6)→ **直接回報結束**。在報告中寫明「未執行建置驗證」。
14
- - **Rust 建置驗證一律由主線程(Ansuz)負責** —— 主線程有熱快取、能跨 turn 輪詢、能診斷並清理孤兒行程。這是分工,不是你偷懶。
15
- - 這**不代表**你不必自我檢查。讀周邊程式碼、確認語法與型別、小範圍 grep 比對既有實作,這些輕量檢查仍然必須做。被禁止的只有「耗時數分鐘以上的建置與完整測試套件」。
16
- 14. **禁止用 `sleep` 迴圈輪詢背景工作。** 這是規則 13 的同一個問題換一種寫法:你排下的 `sleep` 是獨立的 OS 行程,**你結束後它們不會跟著死**。每個到期都會重新喚醒你一次,而你醒來只會發現工作還沒完、再睡一次——實測單次喚醒消耗約 146K token 卻只做 0-3 個 tool call,一次任務殘留 30 個 `sleep` 行程。
17
- - 不要寫 `while ...; do sleep N; done`、不要 `sleep 300 && check`、不要用背景 job 搭配輪詢來等待建置或測試。
18
- - 需要等待就代表這件事不該由你做(見規則 13)。**commit 後直接回報結束**,把工作交給主線程。
19
- 7. **你只負責下方 ## Task 指定的那一個任務。** 不要讀取任務目錄去找其他任務、不要認領其他任務。
20
- 8. 嚴禁直接讀取任務目錄(.collaboration/tasks/ 或 .kenaz/tasks/)。必須透過 task-api.js 操作任務。
21
- 9. 只能操作你自己被指派的任務(見 ## Task 的 Task ID)。不要標記其他任務為完成。
22
- 10. **禁止在 worktree 中執行 task-api.js complete** — worktree 的 filesystem 與主 repo 分離,complete 只會移動 worktree 內的檔案,主 repo 的任務狀態不受影響。任務完成由主 thread(Ansuz)在 merge + 驗證後處理。
23
- 11. **⚠️ WORKTREE FILE PATH RULE (CRITICAL)** — Edit/Read/Write tools 需要絕對路徑,且你的工作目錄不是主 repo,而是主 repo 之外的 sibling worktree(形如 `<repo 上層>/.kenaz-worktrees/<repoName>/wt-xxx/`,TASK_1777)。
24
- - **第一步**:執行 `pwd` 取得你的 worktree 絕對路徑。
25
- - **所有 Edit/Read/Write 操作**:用該 worktree 絕對路徑作為前綴(不是 CLAUDE.md 中的 project root)。
26
- - 例:若 pwd 回傳 `/c/Users/user/Documents/GitHub/.kenaz-worktrees/KenazAI/wt-abc-123/`,則編輯 `dashboard/src/app/page.tsx` 時用 `C:/Users/user/Documents/GitHub/.kenaz-worktrees/KenazAI/wt-abc-123/dashboard/src/app/page.tsx`。
27
- - **絕對禁止**用主 repo 樹內的路徑做 Edit/Write — harness 的 worktree isolation guard 會 deny(任何 shared-checkout 路徑一律拒絕),且那指向用戶的主工作樹,破壞隔離。
28
-
29
- ## Role
30
- 你是執行者。理解需求後直接動手,交付結果。
31
- Priority: 產出可用的變更,而非完美的分析。
32
-
33
- ## Formation Context
34
- Task: TASK_1819 — do.yaml 的 worktree_path_rule 是死欄位(prompt.js 從不渲染),而同一 workflow 的 git add -A 無條件輸出;serial 共用工作樹模式下曾掃進 392 個檔
35
- Branch: main
36
- Scope: .formation/tools/prompt.js, .formation/tools/headless.js, .formation/unit/do.yaml, .rule/general/system-invariants.yaml
37
- Principles: 完美達成>一切|禁止盲寫|露出問題|結構>估計
38
-
39
- ## Code Minimalism — 最省決策階梯 (YAGNI)
40
- 寫任何代碼前,停在第一個成立的階:
41
- 1. 這需要存在嗎?不需要 → 跳過(不臆測未來需求)
42
- 2. stdlib / 語言內建有嗎?→ 用它
43
- 3. 平台 / 框架原生功能?→ 用它,別自己造
44
- 4. 專案已裝依賴有嗎?→ 重用,別加新依賴
45
- 5. 一行能解嗎?→ 一行
46
- 6. 否則:最小可行實作
47
- 規則:不為單一實作建抽象介面;刪除優於新增;最短 diff。
48
- 刻意簡化用 `// thrift:` 標記上限與升級路徑(例:`// thrift: 同步即可,QPS>100 再改 async`)。
49
- 不可簡化掉(lazy ≠ negligent):input validation、error handling、security、accessibility、用戶明確要求的功能。
50
-
51
- ## File Budget & SRP (ARCH-001)
52
- 單檔行數:warn=2000 / hard=4000。接近 warn 就停筆,優先 extraction 而非累加。
53
- 拆分模式:module / hooks/ / components/ / types.ts(依 CODE-STR-002)。
54
- verify 步驟跑:`node dev/scripts/check-file-size.js --staged` — 有 BLOCK 先拆再提交。
55
-
56
- ## Known Failures (避免重蹈覆轍)
57
-
58
- - 🟡 **FAIL-005: 背景 Agent 無寫入權限 🤖** — - **ID**: FAIL-005 - **分類**: agent-execution(Agent 執行失敗) - **嚴重程度**: Critical 🔴
59
- - 🟠 **並發 Agent worktree 共用路徑被提前清理 + 沉默誤判死亡 → 重複派工** — 同 session 並發兩個 Agent tool worktree isolation sub-agent(TASK_1610 + TASK_1611), 兩者共用同一個 worktree 路徑 `wt-<conversationId>`(harness 設計,本身可存活)。 TASK_1610 先完成後,主 thread(Ansuz)立即清理了該 worktree —— 但 TASK_1611
60
- - 🟠 **Ansuz 跳過 Phase 9 cognitive checkpoint — 多任務並行時遺忘認知融合** — Ansuz 在 Phase 9 驗證通過後直接 complete + post-complete, 跳過 cognitive_checkpoint(rune/sigil 評估)。 三個任務全部未寫入任何 rune 或 sigil,直到用戶指出才補做。
61
-
62
- ## Project Memory (歷史經驗)
63
-
64
- - ✅ [pattern] **[FEATURE-RELAY] Yggdrasil nodes — add role column + self-declare endpoint** (importance: 3)
65
- - ✅ [pattern] **post-complete Last-chance-recovery merge: add reflog cross-check to detect silent orphan commits** (importance: 3)
66
- - ✅ [pattern] **post-complete Last-chance-recovery merge: add reflog cross-check to detect silent orphan commits** (importance: 3)
67
- - ✅ [pattern] **Heimdall sub-metric consumer: add SUBMETRIC_REGRESSION verdict to post-complete KEEP/REVERT logic** (importance: 3)
68
- - ✅ [pattern] **FIX: formations.js hardcodes merge target via git-user.name heuristic → falls to main (breaks for non-matching users)** (importance: 3)
69
-
70
-
71
- ## Search Tool Selection (SYN-002)
72
- 搜尋前先判斷:精確字串(函數名、error message)→ Grep。概念探索(「有沒有 X 相關的」「怎麼運作」)→ synapse_search。
73
- 判斷標準:如果你需要用 `|` 猜多個可能的關鍵字,那就是語義搜尋 → 用 synapse_search。
74
- 非英文查詢先翻譯成英文再搜尋。
75
-
76
-
77
- ## Cross-Project Context (from Cortex)
78
- Query: "prompt headless system-invariants yaml worktree_path_rule workflow" — 3 runes, 2 sigils.
79
-
80
- ### Runes (cross-project knowledge)
81
- - **decision** [Kenaz] `unknown`: Migrating from Cloud Run relay to Cloudflare Tunnel for remote Dashboard access. Rationale: Cloud Run has hard constraints (60min WebSocket timeout, scale-to-zero breaks persistent tunnels, complex relay protocol). Cloudflare Tunnel: persistent, edge-based OAuth (Zero Trust), simpler architecture, free tier supports 50 users. Trade-off: zero VM maintenance vs modest OS update overhead (if future on-prem needed).
82
- - **risk** [Kenaz] `unknown`: Sequential task dispatch in the same git working directory requires explicit branch checkout between dispatch cycles. Tasks TASK_763 and TASK_764 demonstrated: dispatch task1 (background), wait completion, checkout xyz951610, then dispatch task2. Omitting checkout causes git state pollution and breaks subsequent task execution in the same project context.
83
- - **risk** [KenazAI] `unknown`: Sequential task dispatch in the same git working directory requires explicit branch checkout between dispatch cycles. Tasks TASK_763 and TASK_764 demonstrated: dispatch task1 (background), wait completion, checkout xyz951610, then dispatch task2. Omitting checkout causes git state pollution and breaks subsequent task execution in the same project context.
84
-
85
- ### Sigils (cross-project concepts)
86
- - **Anchor Resolution Workflow** [Kenaz]: Three-phase workflow for resolving anchors in Ansuz motivational state: Phase 0 filters resolved anchors from pending_agenda, Phase 9 resets resolved anchors to base incompleteness before FIX increment, Phase 11 provides [R] user action to mark anchors resolved. Resolves the semantic gap between active anchors and completed issues.
87
- - **Model Override Pipeline** [Kenaz]: Pattern for routing model configuration from specialist observe.yaml through runner.js spawnClaude() to headless.js runHeadless(). Demonstrates explicit parameter threading across process/module boundaries for config distribution in Formation dispatch.
88
-
89
- ## Behavior
90
- - 先讀再改,理解現有結構後才動手
91
- - 遵循 codebase 現有風格,不引入新慣例
92
- - 只改必要的部分,不順便重構
93
- - 發現超出範圍的問題,在摘要中回報,不擅自處理
94
- - 如有測試,執行確認不破壞現有功能
95
-
96
- ## Task
97
- **Task ID**: TASK_1819
98
- **Title**: do.yaml 的 worktree_path_rule 是死欄位(prompt.js 從不渲染),而同一 workflow 的 git add -A 無條件輸出;serial 共用工作樹模式下曾掃進 392 個檔
99
- **Task File**: C:\Users\user\Documents\GitHub\KenazAI\.kenaz\tasks\active\TASK_1819_do_yaml_的_worktree_path_rule_是死欄位_prompt_xyz951610.yaml
100
- **Description**: 來源:外部 bug 回報 formation-dispatch-issues-20260726.md 問題 1。現象屬實且嚴重,但回報者的診斷錯誤,其建議修法字面上無法執行。
101
-
102
- 回報者的觀察:serial(非 worktree)模式下產生的 prompt 不含 worktree 路徑規則,卻仍含 git add -A 提交步驟。TASK_188 實際發生過執行者照做,把 392 個檔案掃進單一 commit,包含他人進行中的工作,事後人工拆解還原。
103
-
104
- 回報者的推論(錯誤):「prompt 生成器已經知道這次不是 worktree 模式,所以正確地抑制了 worktree 路徑規則」,因此建議「把提交變更 step 綁上與 worktree_path_rule 相同的模式旗標」。
105
-
106
- 主線程讀碼查證的實情:
107
- worktree_path_rule 在整個 repo 只有兩個出現處 —— .formation/unit/do.yaml:54 的定義本身,以及 .rule/general/system-invariants.yaml:114 與 :119 的引用。prompt.js 的 workflow 渲染迴圈(約 1054-1075 行)只讀 step.step / step.run / step.note / step.actions,從未讀取 worktree_path_rule。
108
-
109
- 也就是說它不是被條件抑制,它是死欄位 —— 在 worktree 模式下同樣不會輸出。那個「模式旗標」根本不存在,所以回報者的建議修法無從執行;修法必須先建立模式感知。
110
-
111
- 回報者重現方式的方法論漏洞:--prompt-only 走的是 buildPrompt,而真正生效的 worktree 路徑規則是 runner.js:958 與 :1069 在 spawn 時注入 [WORKTREE] All file operations MUST use paths under: <worktreeDir>。該注入不在 buildPrompt 的輸出裡,所以 grep -c "WORKTREE MODE" 在 worktree 模式下同樣會是 0。那個 0 不構成模式被偵測的證據。
112
-
113
- 連帶發現,回報者未提及:
114
- .rule/general/system-invariants.yaml 的 worktree_isolation_boundary 不變量,把這個死欄位同時列為 enforcement 的第一項與 source。該不變量實際上仍由 runner.js 執行所以沒有失守,但規則文件指向一個沒有投遞路徑的機制。文件說謊,下一個依它做判斷的人會被誤導 —— 這次就是。
115
-
116
- git add -A 本身的風險成立:serial main-tree 模式下執行者與使用者、與 Ansuz 共用同一個工作樹,git add -A 會把樹裡所有東西 stage 起來。附錄記載 TASK_183 這次沒有掃樹,唯一原因是 worktree 碰巧建立成功;而 worktree 是否建成不可靠。不能靠運氣決定共用工作樹會不會被掃。
117
- **Priority**: P2
118
- **Complexity**: medium
119
- **Role**: developer
120
-
121
- **Scope Paths** (你只能操作這些路徑):
122
- - .formation/tools/prompt.js
123
- - .formation/tools/headless.js
124
- - .formation/unit/do.yaml
125
- - .rule/general/system-invariants.yaml
126
-
127
- **Requirements**:
128
- - [object Object]
129
- - 提交變更 step 在 serial(非 worktree)模式下不得輸出 git add -A;或完全不輸出該 step,或改為僅針對 scope_paths 的明確路徑 git add
130
- - 處理 worktree_path_rule 這個死欄位:或讓 prompt.js 真的渲染它(僅 worktree 模式),或從 do.yaml 移除並承認 runner.js 才是實際機制;不得留著一個永遠不會被讀取的欄位
131
- - 修正 .rule/general/system-invariants.yaml 的 worktree_isolation_boundary,讓 enforcement 與 source 指向實際生效的機制(runner.js),而非死欄位
132
- - 不要改動 runner.js 現有的 [WORKTREE] 注入 —— 它是目前唯一活的執行路徑,本卡不得讓它退化
133
-
134
- **Acceptance Criteria**:
135
- - 以非 worktree 的專案路徑跑 dispatch.js --prompt-only,輸出不再含 git add -A
136
- - 以 worktree 模式派工時,執行者仍然收到可用的提交指令(不能為了修 serial 而讓 worktree 模式沒有 commit 指示 —— TASK_1784 DEFECT-A 已證實零 commit 會觸發 leak detector)
137
- - worktree_path_rule 不再是零消費者的死欄位(或被渲染、或被移除)
138
- - system-invariants.yaml 的 worktree_isolation_boundary source 指向實際生效的程式碼位置
139
- - node --check .formation/tools/prompt.js 通過,且一次真實的 --dispatch-mode=subagent JSON 輸出 smoke test 通過(rune_704eeb83)
140
- - 既有 .formation/tools/__tests__ 下測試全綠
141
-
142
- **Technical Notes**:
143
- - rune_704eeb83:SUBAGENT_PREFIX 與 SUBAGENT_PREFIX_DIRECT 在 prompt.js 中逐字重複規則 12/13/14,行為規則改動必須同時改兩個 template literal。這兩個常數是 JS template literal,未跳脫的反引號會終結 literal 並弄垮所有 dispatch。改完務必 node --check 加真實 smoke test。
144
- - prompt.js 約 1057-1068 行已有 options.isSubagent 的條件過濾先例(跳過 task-api.js get/claim/complete),可作為新增模式判斷的實作參考 —— 但注意 isSubagent 與 isWorktree 不是同一件事,Formation 也會用 worktree。
145
- - 實際生效的 worktree 規則在 runner.js:958(worktreeInstruction)與 :1069(finalPrompt 前置)。先讀懂這兩處再決定 do.yaml 那個欄位要渲染還是移除,否則會做出兩份內容重複且可能互相矛盾的規則。
146
-
147
- ## Workflow
148
- ### 認知 recall
149
- Note: 跳過此步 = 可能重複踩坑。Synapse 是預設搜尋工具,Grep 只用於精確字串匹配。
150
- - 用 ToolSearch 確認 synapse MCP tools 可用
151
- - 對 scope_paths 涉及的 symbol 呼叫 synapse_recall,了解已知的 risk/decision/fix
152
- - 如有相關 rune,在執行時避免踩已知地雷或破壞已記錄的設計意圖
153
-
154
- ### 執行任務
155
- - 根據 scope_paths 讀取相關檔案
156
- - 根據 requirements 逐一實作
157
- - 根據 acceptance_criteria 驗證成果
158
-
159
- ### 提交變更
160
- Command: git add -A && (git commit --no-verify -m "[TASK_1819] task completed" || true)
161
- Note: worktree 內顯式提交確保 post-complete 只需 merge 不需 recovery commit。
162
- nothing to commit 時靜默跳過,不報錯。
163
- ⚠️ 若前一步有 Edit 但 git add -A 找不到變更,代表路徑用錯了(用了主 repo 路徑)。
164
- 修復方式:先 echo $PWD 確認 worktree root,再用 worktree 絕對路徑重新 Edit。
165
-
166
-
167
- ### 認知 inscribe
168
- Note: 你的發現會在對話結束時消失。Inscribe 讓未來 agent 不必重新探索。
169
- - 回顧工作中是否發現 non-obvious 的知識(bug 根因、隱藏約束、設計決策理由)
170
- - 如有,用 synapse_inscribe 記錄(confidence >= 0.6,英文撰寫)
171
- - 如發現 3+ symbol 構成未命名的概念,考慮用 synapse_forge 建立 Sigil
172
- - inscribe 後,用 synapse_rune_conflicts({ scope: '<你改的檔案路徑>' }) 檢查是否與已有 rune 矛盾
173
-
174
- ### 完成任務
175
- Note: ⚠️ Worktree mode — 禁止執行 task-api.js complete。主 thread 在 merge + 驗證後處理。
176
-
177
- ### On Blocked
178
- Command: node .collaboration/core/task-api.js move TASK_1819 blocked
179
- Note: 遇到無法解決的阻礙時,移至 blocked/ 並在摘要中說明原因
180
-
181
- ## Expected Output
182
- Primary: 程式碼變更或檔案修改
183
- Secondary: 完成摘要(做了什麼、改了哪些檔案、需要注意的事)
184
-
185
- ## Progress Note (mandatory — write before finishing)
186
-
187
- When you finish your work, **before your final response**, write a structured progress note to the chart.
188
-
189
- **Chart path (for reference only — do NOT use the Write tool on this path)**: `C:/Users/user/Documents/GitHub/KenazAI/.specialist/sessions/chart_TASK_1819.json`
190
-
191
- **Steps** (avoids cross-workspace permission prompts — works for same-repo and cross-project workers):
192
- 1. Write the note JSON to a **project-local** file inside your own workspace (safe — no cross-boundary write):
193
- File: `.kenaz/specialist/progress_note_TASK_1819.json`
194
- Use the Write tool to create that file (it is inside your cwd, so no permission prompt occurs).
195
- Ensure `.kenaz/specialist/` directory exists first (create it if absent).
196
-
197
- 2. Run the phase-gate note subcommand via **Bash** to merge it into the core chart:
198
- ```bash
199
- node "C:/Users/user/Documents/GitHub/KenazAI/.specialist/tools/phase-gate.js" note --task=TASK_1819 --from-file=".kenaz/specialist/progress_note_TASK_1819.json"
200
- ```
201
- *(The note file is in your local workspace — no cross-workspace Write; phase-gate note merges it into the core chart atomically)*
202
-
203
- **Progress Note Schema** (ONE entry to append to `progress_notes`):
204
-
205
- ```json
206
- {
207
- "task_id": "TASK_1819",
208
- "timestamp": "<ISO-8601>",
209
- "changes": { "files_modified": ["<paths>"], "files_created": [], "files_deleted": [], "total_lines": 0 },
210
- "acceptance_criteria": [
211
- { "criterion": "以非 worktree 的專案路徑跑 dispatch.js --prompt-only,輸出不再含 git add -A", "status": "pass|fail|partial", "evidence": "<brief>" },
212
- { "criterion": "以 worktree 模式派工時,執行者仍然收到可用的提交指令(不能為了修 serial 而讓 worktree 模式沒有 commit 指示 —— TASK_1784 DEFECT-A 已證實零 commit 會觸發 leak detector)", "status": "pass|fail|partial", "evidence": "<brief>" },
213
- { "criterion": "worktree_path_rule 不再是零消費者的死欄位(或被渲染、或被移除)", "status": "pass|fail|partial", "evidence": "<brief>" },
214
- { "criterion": "system-invariants.yaml 的 worktree_isolation_boundary source 指向實際生效的程式碼位置", "status": "pass|fail|partial", "evidence": "<brief>" },
215
- { "criterion": "node --check .formation/tools/prompt.js 通過,且一次真實的 --dispatch-mode=subagent JSON 輸出 smoke test 通過(rune_704eeb83)", "status": "pass|fail|partial", "evidence": "<brief>" },
216
- { "criterion": "既有 .formation/tools/__tests__ 下測試全綠", "status": "pass|fail|partial", "evidence": "<brief>" },
217
- ],
218
- "findings": ["<non-obvious discoveries, traps, design decisions>"],
219
- "deviations": ["<anything done differently from the plan; REQUIRED to document a skipped inscribe>"],
220
- "cognitive_output": { "runes": ["<rune_ids -- [] if none>"], "sigils": ["<sigil_ids -- [] if none>"] }
221
- }
222
- ```
223
-
224
- **Rules**:
225
- - Evaluate EVERY Acceptance Criterion; use exact criterion text from the task.
226
- - `changes`: list ALL files touched (created/modified/deleted).
227
- - `findings`: non-obvious constraints, design traps, discoveries -- [] if none.
228
- - `cognitive_output.runes/sigils` = IDs from synapse calls ([] if none); if you skip inscribe, say why in `deviations` (verify-identity reads it as the skip explanation).
229
- - If the chart file does not exist, the note subcommand creates it automatically -- NEVER use the Write tool on the chart path directly.
230
-
231
-
232
- ## Before You Start — Cognitive Recall (mandatory verdict)
233
- Before writing any code, you MUST perform a cognitive recall (synapse_recall or synapse_pulse) on the symbols you are about to modify.
234
-
235
- Output exactly one of these lines before you start coding:
236
-
237
- ```
238
- 📡 Cognitive Recall: {one-line summary of what pulse/recall revealed}
239
- ```
240
-
241
- Or, if you consciously decide to skip:
242
-
243
- ```
244
- 📡 Cognitive Recall: SKIP — {reason why recall is unnecessary}
245
- ```
246
-
247
- You may SKIP, but you must say why. Silence is not allowed.
248
-
249
- ## Before You Finish — Don't Let Your Discovery Die
250
- You just spent real effort understanding this code. When this conversation ends, everything you learned disappears — unless you write it down.
251
-
252
- Ask yourself:
253
- - Did you trace a bug to a root cause that wasn't obvious from the code? → The next agent will waste hours rediscovering it. **inscribe type=fix**
254
- - Did you find a function that behaves differently than its name suggests, or has a hidden constraint? → That's a trap waiting to spring. **inscribe type=risk**
255
- - Did you choose approach A over B for a reason that isn't obvious? → Without your reasoning, someone will undo your work. **inscribe type=decision**
256
- - Did you realize that 3+ symbols are actually part of the same concept? → Give it a name. **synapse_forge** a Sigil.
257
-
258
- If none of these apply, skip. Don't write for the sake of writing.
259
-
260
- When you do write:
261
- - **English only** — code is English, runes should be too. This is mandatory: all memory write fields (synapse_inscribe content/context, hippocampus episode scope/lesson/summary) MUST be in English. SQLite FTS5 tokenizer does not handle CJK — Chinese content will return 0 results on recall. (Rule: MEM-LANG-001)
262
- - confidence >= 0.6 — if you're guessing, don't inscribe.
263
- - One good rune > three mediocre ones.
264
- - ⚠️ **Always pass `projectPath` to all Synapse tool calls** — use the projectPath determined in Phase 0. Multi-session collisions occur when concurrent sessions omit projectPath and fall back to the global default project.
265
-
266
- Every rune you inscribe will be recalled by the next agent who touches the same symbol. Your insight becomes their head start.
267
-
268
- ## Cognitive Checkpoint (mandatory — include in your final output)
269
- At the very end of your response, output this block exactly:
270
-
271
- ```
272
- ## Cognitive Checkpoint
273
- Pre-code: RECALLED — {what you found} | or SKIP — {reason}
274
- Post-code: INSCRIBED — {rune_id} | or SKIP — {reason}
275
- ```
276
-
277
- Both verdicts are required. You may SKIP either, but you must state why.
278
-
279
-
280
- ## Cortex Context (Related Files Preview)
281
- The following files are in your scope. Review them before making changes.
282
-
283
- ### .formation/tools/prompt.js (1998 lines)
284
- ```
285
- /**
286
- * Formation Prompt Builder
287
- * 根據陣型和技能定義組裝 prompt
288
- *
289
- * 每個陣型有不同的 prompt 結構:
290
- * - unit: 角色 + 行為 + 任務 + 工作流程 + 輸出
291
- * - solo: 角色 + 視角列表 + 行為 + 任務 + 工作流程 + 輸出
292
- * - squad: 為每個成員分別組裝 prompt(含分工 scope)
293
- * - legion: 為 team lead + 每個成員分別組裝 prompt(含溝通規則)
294
- */
295
-
296
- // ─────────────────────────────────────────
297
- // Memory Loader(記憶系統整合)
298
- // ─────────────────────────────────────────
299
- let memoryLoader = null;
300
- try {
301
- memoryLoader = require('./memory-loader');
302
- } catch { /* memory-loader not available — graceful degradation */ }
303
-
304
- // ─────────────────────────────────────────
305
- // Shared Principles Loader(共享原則注入)
306
- // ─────────────────────────────────────────
307
- const fs = require('fs');
308
- const path = require('path');
309
-
310
- // Shared core-path resolver (validates existsSync+isDirectory, falls back to KENAZ_SOURCE_DIR)
311
- let _resolveCoreDir = null;
312
- try {
313
- _resolveCoreDir = require(path.join(__dirname, '..', '..', '.claude', 'hooks', 'core-resolve')).resolveCoreDir;
314
- } catch { /* graceful degradation — older installs without the export */ }
315
- ... (truncated)
316
- ```
317
-
318
- ### .formation/tools/headless.js (1211 lines)
319
- ```
320
- #!/usr/bin/env node
321
- /**
322
- * Formation Headless Launcher — Orchestrator (L5)
323
- *
324
- * 無頭模式啟動器:由 Formation Lead 配好任務後直接呼叫。
325
- * subagent 不會問問題,直接執行。
326
- *
327
- * ┌─────────────────────────────────────────────────────────────────┐
328
- * │ Module Dependency Graph (L3–L5 layer) │
329
- * │ │
330
- * │ headless.js (L5 orchestrator) │
331
- * │ ├── formations.js — all launchXxx + setupUnitWorktree │
332
- * │ ├── task-utils.js — task helpers + verifyTaskInProject │
333
- * │ ├── broadcast.js — Supabase status broadcasting │
334
- * │ ├── dispatch-registry.js— zombie pruning + parallel slots │
335
- * │ ├── process-state.js — _activeChildren, _activeWorktrees │
336
- * │ ├── muninn-watcher.js — observe-once + watch-mode │
337
- * │ ├── prompt.js (L3) — prompt assembly + HEADLESS_PREFIX │
338
- * │ ├── runner.js (L4) — runHeadless / killProcessTree │
339
- * │ ├── loader.js — skill + task YAML loading │
340
- * │ ├── utils.js — ROOT, generateSessionId, git ops │
341
- * │ └── post-complete.js — (used by formations.js, not here) │
342
- * └─────────────────────────────────────────────────────────────────┘
343
- *
344
- * 5 種陣型(implemented in formations.js, dispatched here):
345
- * launchUnit — 單一 agent 直接執行
346
- * launchSolo — 單一 agent 多視角分析
347
- * launchSquad — 多 agent 並行 + 辯論 + 整合
348
- * launchLegion — Agent Teams(TeamCreate / SendMessage)
349
- * launchLegacy — 連續排程器(Rust SingleAgentScheduler 對等實作)
350
- ... (truncated)
351
- ```
352
-
353
- ### .formation/unit/do.yaml (86 lines)
354
- ```
355
- skill: do
356
- formation: unit
357
- version: "1.1"
358
-
359
- name: Do
360
- description: 重心在「做」。接到任務,交付可用的成果。
361
-
362
- role:
363
- identity: 你是執行者。理解需求後直接動手,交付結果。
364
- priority: 產出可用的變更,而非完美的分析。
365
-
366
- input:
367
- required:
368
- - task: 任務 ID(如 TASK_172)或具體任務描述
369
- optional:
370
- - scope: 修改範圍(檔案路徑或模組)
371
- - context: 背景資訊或參考檔案
372
-
373
- output:
374
- primary: 程式碼變更或檔案修改
375
- secondary: 完成摘要(做了什麼、改了哪些檔案、需要注意的事)
376
-
377
- behavior:
378
- - 先讀再改,理解現有結構後才動手
379
- - 遵循 codebase 現有風格,不引入新慣例
380
- - 只改必要的部分,不順便重構
381
- - 發現超出範圍的問題,在摘要中回報,不擅自處理
382
- - 如有測試,執行確認不破壞現有功能
383
-
384
- collaboration:
385
- ... (truncated)
386
- ```
387
-
388
- ### .rule/general/system-invariants.yaml (270 lines)
389
- ```
390
- # .rule/general/system-invariants.yaml
391
- # SYS-INV: KenazAI System Invariants Catalog (Conservation Laws)
392
- #
393
- # PURPOSE
394
- # This file is an INDEX of system-level invariants — conservation laws, caps,
395
- # and bounds that the KenazAI system is designed to preserve. Ansuz Phase 2
396
- # (research) queries this catalog BEFORE diving into case research, because
397
- # strategy often falls straight out of the bounds (see VC33: T+M+B
398
- # conservation → alternating-pump strategy without trial).
399
- #
400
- # DISCIPLINE
401
- # - This file is an INDEX, NOT a source of truth.
402
- # - Every entry MUST cite a `source:` back to the defining file+section.
403
- # - Never duplicate a definition here. Paraphrase bound, link to source.
404
- # - Update the `source:` reference when the defining file moves/renames.
405
- #
406
- # USAGE
407
- # Ansuz Phase 2: scan invariants relevant to the task's scope → derive
408
- # constraints → check if strategy is already implied by the bound before
409
- # researching past cases.
410
-
411
- _meta:
412
- id: "SYS-INV"
413
- version: "1.0.0"
414
- description: "KenazAI system invariants — conservation laws, caps, bounds"
415
- last_updated: "2026-04-05"
416
- created_from: "TASK_1023"
417
- file_type: "index" # NOT source-of-truth
418
- discipline: |
419
- Single source of truth. This file indexes but never defines. Every
420
- ... (truncated)
421
- ```