briefloop 0.11.12__py3-none-any.whl

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 (424) hide show
  1. briefloop-0.11.12.dist-info/METADATA +473 -0
  2. briefloop-0.11.12.dist-info/RECORD +424 -0
  3. briefloop-0.11.12.dist-info/WHEEL +5 -0
  4. briefloop-0.11.12.dist-info/entry_points.txt +3 -0
  5. briefloop-0.11.12.dist-info/licenses/LICENSE +22 -0
  6. briefloop-0.11.12.dist-info/top_level.txt +1 -0
  7. multi_agent_brief/__init__.py +36 -0
  8. multi_agent_brief/analysis_blocks/__init__.py +11 -0
  9. multi_agent_brief/analysis_blocks/builder.py +206 -0
  10. multi_agent_brief/analysis_blocks/renderer.py +237 -0
  11. multi_agent_brief/analysis_blocks/schemas.py +52 -0
  12. multi_agent_brief/analysis_modules/__init__.py +8 -0
  13. multi_agent_brief/analysis_modules/base.py +87 -0
  14. multi_agent_brief/analysis_modules/market_competitor/__init__.py +68 -0
  15. multi_agent_brief/analysis_modules/market_competitor/auditor.py +290 -0
  16. multi_agent_brief/analysis_modules/market_competitor/config.py +187 -0
  17. multi_agent_brief/analysis_modules/market_competitor/event_builder.py +226 -0
  18. multi_agent_brief/analysis_modules/market_competitor/renderer.py +199 -0
  19. multi_agent_brief/analysis_modules/market_competitor/schemas.py +518 -0
  20. multi_agent_brief/analysis_modules/policy_regulatory/__init__.py +7 -0
  21. multi_agent_brief/analysis_modules/policy_regulatory/audit.py +195 -0
  22. multi_agent_brief/analysis_modules/policy_regulatory/module.py +387 -0
  23. multi_agent_brief/analysis_modules/policy_regulatory/schemas.py +129 -0
  24. multi_agent_brief/analysis_modules/registry.py +73 -0
  25. multi_agent_brief/audience/__init__.py +19 -0
  26. multi_agent_brief/audience/profiles.py +246 -0
  27. multi_agent_brief/audience_memory/__init__.py +23 -0
  28. multi_agent_brief/audience_memory/profile.py +358 -0
  29. multi_agent_brief/audit/__init__.py +36 -0
  30. multi_agent_brief/audit/case_applicability.py +181 -0
  31. multi_agent_brief/audit/deterministic.py +471 -0
  32. multi_agent_brief/audit/editorial_governance.py +404 -0
  33. multi_agent_brief/audit/final_quality.py +764 -0
  34. multi_agent_brief/audit/harness.py +242 -0
  35. multi_agent_brief/audit/interfaces.py +96 -0
  36. multi_agent_brief/audit/limitation_hygiene.py +238 -0
  37. multi_agent_brief/audit/proposal_boundary.py +34 -0
  38. multi_agent_brief/audit/redaction.py +27 -0
  39. multi_agent_brief/audit/rule_packs.py +96 -0
  40. multi_agent_brief/audit/semantic.py +435 -0
  41. multi_agent_brief/capabilities/__init__.py +22 -0
  42. multi_agent_brief/capabilities/catalog.py +215 -0
  43. multi_agent_brief/capabilities/detect.py +199 -0
  44. multi_agent_brief/capabilities/models.py +60 -0
  45. multi_agent_brief/capabilities/recommend.py +206 -0
  46. multi_agent_brief/cli/__init__.py +2 -0
  47. multi_agent_brief/cli/analysis_commands.py +140 -0
  48. multi_agent_brief/cli/approval_commands.py +107 -0
  49. multi_agent_brief/cli/audit_commands.py +59 -0
  50. multi_agent_brief/cli/capability_commands.py +548 -0
  51. multi_agent_brief/cli/claude_commands.py +159 -0
  52. multi_agent_brief/cli/competitors_commands.py +182 -0
  53. multi_agent_brief/cli/controls_commands.py +137 -0
  54. multi_agent_brief/cli/deliver_commands.py +942 -0
  55. multi_agent_brief/cli/eval_cases_commands.py +99 -0
  56. multi_agent_brief/cli/experiments_commands.py +395 -0
  57. multi_agent_brief/cli/feedback_commands.py +192 -0
  58. multi_agent_brief/cli/finalize_commands.py +153 -0
  59. multi_agent_brief/cli/gates_commands.py +174 -0
  60. multi_agent_brief/cli/hermes_commands.py +356 -0
  61. multi_agent_brief/cli/improve_commands.py +224 -0
  62. multi_agent_brief/cli/init_commands.py +564 -0
  63. multi_agent_brief/cli/init_wizard.py +1473 -0
  64. multi_agent_brief/cli/input_commands.py +237 -0
  65. multi_agent_brief/cli/main.py +288 -0
  66. multi_agent_brief/cli/onboard_commands.py +193 -0
  67. multi_agent_brief/cli/product_commands.py +1449 -0
  68. multi_agent_brief/cli/provenance_commands.py +100 -0
  69. multi_agent_brief/cli/release_commands.py +68 -0
  70. multi_agent_brief/cli/repair_commands.py +169 -0
  71. multi_agent_brief/cli/run_commands.py +292 -0
  72. multi_agent_brief/cli/runtime_commands.py +81 -0
  73. multi_agent_brief/cli/secrets_commands.py +232 -0
  74. multi_agent_brief/cli/semantic_support_commands.py +80 -0
  75. multi_agent_brief/cli/sources_commands.py +647 -0
  76. multi_agent_brief/cli/start_commands.py +8 -0
  77. multi_agent_brief/cli/state_commands.py +446 -0
  78. multi_agent_brief/cli/status_commands.py +26 -0
  79. multi_agent_brief/cli/workbuddy_commands.py +103 -0
  80. multi_agent_brief/configs/artifact_contracts.yaml +514 -0
  81. multi_agent_brief/configs/orchestrator_contract.yaml +181 -0
  82. multi_agent_brief/configs/policy_packs/default.yaml +65 -0
  83. multi_agent_brief/configs/policy_profiles/evidence_extract_default.yaml +58 -0
  84. multi_agent_brief/configs/policy_profiles/finance_default.yaml +44 -0
  85. multi_agent_brief/configs/policy_profiles/internet_default.yaml +44 -0
  86. multi_agent_brief/configs/policy_profiles/manufacturing_default.yaml +33 -0
  87. multi_agent_brief/configs/policy_profiles/solar_manufacturing_default.yaml +64 -0
  88. multi_agent_brief/configs/report_packs/evidence_extract.yaml +48 -0
  89. multi_agent_brief/configs/report_packs/management_monthly.yaml +36 -0
  90. multi_agent_brief/configs/report_packs/market_weekly.yaml +36 -0
  91. multi_agent_brief/configs/report_packs/solar_industry_periodic.yaml +50 -0
  92. multi_agent_brief/configs/report_templates/evidence_extract.yaml +55 -0
  93. multi_agent_brief/configs/report_templates/management_monthly.yaml +48 -0
  94. multi_agent_brief/configs/report_templates/market_weekly.yaml +49 -0
  95. multi_agent_brief/configs/report_templates/solar_industry_periodic.yaml +75 -0
  96. multi_agent_brief/configs/stage_specs.yaml +180 -0
  97. multi_agent_brief/contracts/__init__.py +41 -0
  98. multi_agent_brief/contracts/base.py +99 -0
  99. multi_agent_brief/contracts/errors.py +41 -0
  100. multi_agent_brief/contracts/migrations/__init__.py +5 -0
  101. multi_agent_brief/contracts/migrations/claim_v1_to_v2.py +33 -0
  102. multi_agent_brief/contracts/registry.py +159 -0
  103. multi_agent_brief/contracts/role_topology.py +25 -0
  104. multi_agent_brief/contracts/schemas/__init__.py +35 -0
  105. multi_agent_brief/contracts/schemas/analysis_pack.py +135 -0
  106. multi_agent_brief/contracts/schemas/atomic_claim_graph.py +304 -0
  107. multi_agent_brief/contracts/schemas/audit_report.py +80 -0
  108. multi_agent_brief/contracts/schemas/candidate_item.py +51 -0
  109. multi_agent_brief/contracts/schemas/claim.py +197 -0
  110. multi_agent_brief/contracts/schemas/claim_draft.py +386 -0
  111. multi_agent_brief/contracts/schemas/claim_support_matrix.py +334 -0
  112. multi_agent_brief/contracts/schemas/evidence_span_registry.py +270 -0
  113. multi_agent_brief/contracts/schemas/policy_profile.py +247 -0
  114. multi_agent_brief/contracts/schemas/report_spec.py +257 -0
  115. multi_agent_brief/contracts/schemas/semantic_assessment_report.py +480 -0
  116. multi_agent_brief/contracts/schemas/source_evidence_pack_manifest.py +233 -0
  117. multi_agent_brief/contracts/schemas/source_item.py +96 -0
  118. multi_agent_brief/contracts/semantic_assessment_status.py +12 -0
  119. multi_agent_brief/contracts/source_metadata.py +252 -0
  120. multi_agent_brief/contracts/target_contract.py +460 -0
  121. multi_agent_brief/contracts/validator.py +225 -0
  122. multi_agent_brief/controls/__init__.py +23 -0
  123. multi_agent_brief/controls/contract.py +106 -0
  124. multi_agent_brief/controls/switchboard.py +1076 -0
  125. multi_agent_brief/core/__init__.py +2 -0
  126. multi_agent_brief/core/citations.py +14 -0
  127. multi_agent_brief/core/claim_ledger.py +94 -0
  128. multi_agent_brief/core/config.py +191 -0
  129. multi_agent_brief/core/env.py +69 -0
  130. multi_agent_brief/core/previous.py +83 -0
  131. multi_agent_brief/core/schemas.py +181 -0
  132. multi_agent_brief/core/selection.py +189 -0
  133. multi_agent_brief/delivery/__init__.py +6 -0
  134. multi_agent_brief/delivery/base.py +36 -0
  135. multi_agent_brief/delivery/feishu.py +204 -0
  136. multi_agent_brief/delivery/gws.py +237 -0
  137. multi_agent_brief/evaluation_cases/__init__.py +15 -0
  138. multi_agent_brief/evaluation_cases/contract.py +429 -0
  139. multi_agent_brief/evaluation_cases/fixtures/cases/approved_guidance_materialized/workspace/config.yaml +18 -0
  140. multi_agent_brief/evaluation_cases/fixtures/cases/approved_guidance_materialized/workspace/improvement/ledger.jsonl +2 -0
  141. multi_agent_brief/evaluation_cases/fixtures/cases/approved_guidance_materialized/workspace/sources.yaml +2 -0
  142. multi_agent_brief/evaluation_cases/fixtures/cases/approved_guidance_materialized/workspace/user.md +4 -0
  143. multi_agent_brief/evaluation_cases/fixtures/cases/company_event_missing_latest_official_check/workspace/config.yaml +13 -0
  144. multi_agent_brief/evaluation_cases/fixtures/cases/company_event_missing_latest_official_check/workspace/sources.yaml +9 -0
  145. multi_agent_brief/evaluation_cases/fixtures/cases/company_event_missing_latest_official_check/workspace/user.md +4 -0
  146. multi_agent_brief/evaluation_cases/fixtures/cases/control_switchboard_selection_is_not_execution/workspace/config.yaml +12 -0
  147. multi_agent_brief/evaluation_cases/fixtures/cases/control_switchboard_selection_is_not_execution/workspace/sources.yaml +6 -0
  148. multi_agent_brief/evaluation_cases/fixtures/cases/control_switchboard_selection_is_not_execution/workspace/user.md +4 -0
  149. multi_agent_brief/evaluation_cases/fixtures/cases/feedback_triage_required/workspace/config.yaml +6 -0
  150. multi_agent_brief/evaluation_cases/fixtures/cases/feedback_triage_required/workspace/input/human_feedback.md +1 -0
  151. multi_agent_brief/evaluation_cases/fixtures/cases/feedback_triage_required/workspace/sources.yaml +2 -0
  152. multi_agent_brief/evaluation_cases/fixtures/cases/feedback_triage_required/workspace/user.md +3 -0
  153. multi_agent_brief/evaluation_cases/fixtures/cases/final_abstract_quality_warning_surface/workspace/config.yaml +8 -0
  154. multi_agent_brief/evaluation_cases/fixtures/cases/final_abstract_quality_warning_surface/workspace/output/brief.md +14 -0
  155. multi_agent_brief/evaluation_cases/fixtures/cases/final_abstract_quality_warning_surface/workspace/output/intermediate/audit_report.json +1 -0
  156. multi_agent_brief/evaluation_cases/fixtures/cases/final_abstract_quality_warning_surface/workspace/output/intermediate/audited_brief.md +5 -0
  157. multi_agent_brief/evaluation_cases/fixtures/cases/final_abstract_quality_warning_surface/workspace/output/intermediate/candidate_claims.json +1 -0
  158. multi_agent_brief/evaluation_cases/fixtures/cases/final_abstract_quality_warning_surface/workspace/output/intermediate/claim_ledger.json +1 -0
  159. multi_agent_brief/evaluation_cases/fixtures/cases/final_abstract_quality_warning_surface/workspace/output/intermediate/screened_candidates.json +1 -0
  160. multi_agent_brief/evaluation_cases/fixtures/cases/final_abstract_quality_warning_surface/workspace/sources.yaml +2 -0
  161. multi_agent_brief/evaluation_cases/fixtures/cases/final_abstract_quality_warning_surface/workspace/user.md +3 -0
  162. multi_agent_brief/evaluation_cases/fixtures/cases/formal_release_missing_human_approval/workspace/config.yaml +13 -0
  163. multi_agent_brief/evaluation_cases/fixtures/cases/formal_release_missing_human_approval/workspace/sources.yaml +9 -0
  164. multi_agent_brief/evaluation_cases/fixtures/cases/formal_release_missing_human_approval/workspace/user.md +4 -0
  165. multi_agent_brief/evaluation_cases/fixtures/cases/guidance_manifestation_not_observable/workspace/config.yaml +4 -0
  166. multi_agent_brief/evaluation_cases/fixtures/cases/guidance_manifestation_not_observable/workspace/sources.yaml +2 -0
  167. multi_agent_brief/evaluation_cases/fixtures/cases/guidance_manifestation_not_observable/workspace/user.md +3 -0
  168. multi_agent_brief/evaluation_cases/fixtures/cases/media_only_legal_policy_blocks_research_review/workspace/config.yaml +13 -0
  169. multi_agent_brief/evaluation_cases/fixtures/cases/media_only_legal_policy_blocks_research_review/workspace/sources.yaml +9 -0
  170. multi_agent_brief/evaluation_cases/fixtures/cases/media_only_legal_policy_blocks_research_review/workspace/user.md +4 -0
  171. multi_agent_brief/evaluation_cases/fixtures/cases/mixed_metric_scope_support_blocker/workspace/config.yaml +13 -0
  172. multi_agent_brief/evaluation_cases/fixtures/cases/mixed_metric_scope_support_blocker/workspace/sources.yaml +9 -0
  173. multi_agent_brief/evaluation_cases/fixtures/cases/mixed_metric_scope_support_blocker/workspace/user.md +5 -0
  174. multi_agent_brief/evaluation_cases/fixtures/cases/planned_blocking_issue_cannot_continue/workspace/config.yaml +6 -0
  175. multi_agent_brief/evaluation_cases/fixtures/cases/planned_blocking_issue_cannot_continue/workspace/output/intermediate/audited_brief.md +3 -0
  176. multi_agent_brief/evaluation_cases/fixtures/cases/planned_blocking_issue_cannot_continue/workspace/output/intermediate/candidate_claims.json +1 -0
  177. multi_agent_brief/evaluation_cases/fixtures/cases/planned_blocking_issue_cannot_continue/workspace/output/intermediate/claim_ledger.json +1 -0
  178. multi_agent_brief/evaluation_cases/fixtures/cases/planned_blocking_issue_cannot_continue/workspace/output/intermediate/feedback_issues.json +25 -0
  179. multi_agent_brief/evaluation_cases/fixtures/cases/planned_blocking_issue_cannot_continue/workspace/output/intermediate/repair_plan.json +27 -0
  180. multi_agent_brief/evaluation_cases/fixtures/cases/planned_blocking_issue_cannot_continue/workspace/output/intermediate/screened_candidates.json +1 -0
  181. multi_agent_brief/evaluation_cases/fixtures/cases/planned_blocking_issue_cannot_continue/workspace/sources.yaml +2 -0
  182. multi_agent_brief/evaluation_cases/fixtures/cases/planned_blocking_issue_cannot_continue/workspace/user.md +3 -0
  183. multi_agent_brief/evaluation_cases/fixtures/cases/provenance_projection_minimal/workspace/config.yaml +8 -0
  184. multi_agent_brief/evaluation_cases/fixtures/cases/provenance_projection_minimal/workspace/output/intermediate/audit_report.json +1 -0
  185. multi_agent_brief/evaluation_cases/fixtures/cases/provenance_projection_minimal/workspace/output/intermediate/audited_brief.md +3 -0
  186. multi_agent_brief/evaluation_cases/fixtures/cases/provenance_projection_minimal/workspace/output/intermediate/candidate_claims.json +1 -0
  187. multi_agent_brief/evaluation_cases/fixtures/cases/provenance_projection_minimal/workspace/output/intermediate/claim_ledger.json +11 -0
  188. multi_agent_brief/evaluation_cases/fixtures/cases/provenance_projection_minimal/workspace/output/intermediate/quality_gate_report.json +22 -0
  189. multi_agent_brief/evaluation_cases/fixtures/cases/provenance_projection_minimal/workspace/output/intermediate/screened_candidates.json +1 -0
  190. multi_agent_brief/evaluation_cases/fixtures/cases/provenance_projection_minimal/workspace/sources.yaml +2 -0
  191. multi_agent_brief/evaluation_cases/fixtures/cases/provenance_projection_minimal/workspace/user.md +3 -0
  192. multi_agent_brief/evaluation_cases/fixtures/cases/reader_facing_source_appendix/workspace/config.yaml +13 -0
  193. multi_agent_brief/evaluation_cases/fixtures/cases/reader_facing_source_appendix/workspace/output/intermediate/audit_report.json +1 -0
  194. multi_agent_brief/evaluation_cases/fixtures/cases/reader_facing_source_appendix/workspace/output/intermediate/audited_brief.md +5 -0
  195. multi_agent_brief/evaluation_cases/fixtures/cases/reader_facing_source_appendix/workspace/output/intermediate/candidate_claims.json +1 -0
  196. multi_agent_brief/evaluation_cases/fixtures/cases/reader_facing_source_appendix/workspace/output/intermediate/claim_ledger.json +40 -0
  197. multi_agent_brief/evaluation_cases/fixtures/cases/reader_facing_source_appendix/workspace/output/intermediate/screened_candidates.json +1 -0
  198. multi_agent_brief/evaluation_cases/fixtures/cases/reader_facing_source_appendix/workspace/sources.yaml +3 -0
  199. multi_agent_brief/evaluation_cases/fixtures/cases/reader_facing_source_appendix/workspace/user.md +3 -0
  200. multi_agent_brief/evaluation_cases/fixtures/cases/reader_facing_target_relevance/workspace/config.yaml +8 -0
  201. multi_agent_brief/evaluation_cases/fixtures/cases/reader_facing_target_relevance/workspace/output/brief.md +3 -0
  202. multi_agent_brief/evaluation_cases/fixtures/cases/reader_facing_target_relevance/workspace/output/intermediate/audit_report.json +1 -0
  203. multi_agent_brief/evaluation_cases/fixtures/cases/reader_facing_target_relevance/workspace/output/intermediate/audited_brief.md +3 -0
  204. multi_agent_brief/evaluation_cases/fixtures/cases/reader_facing_target_relevance/workspace/output/intermediate/candidate_claims.json +1 -0
  205. multi_agent_brief/evaluation_cases/fixtures/cases/reader_facing_target_relevance/workspace/output/intermediate/claim_ledger.json +13 -0
  206. multi_agent_brief/evaluation_cases/fixtures/cases/reader_facing_target_relevance/workspace/output/intermediate/screened_candidates.json +1 -0
  207. multi_agent_brief/evaluation_cases/fixtures/cases/reader_facing_target_relevance/workspace/sources.yaml +2 -0
  208. multi_agent_brief/evaluation_cases/fixtures/cases/reader_facing_target_relevance/workspace/user.md +3 -0
  209. multi_agent_brief/evaluation_cases/fixtures/cases/release_readiness_forged_event_blocker/workspace/config.yaml +13 -0
  210. multi_agent_brief/evaluation_cases/fixtures/cases/release_readiness_forged_event_blocker/workspace/output/intermediate/release_readiness_report.json +31 -0
  211. multi_agent_brief/evaluation_cases/fixtures/cases/release_readiness_forged_event_blocker/workspace/sources.yaml +9 -0
  212. multi_agent_brief/evaluation_cases/fixtures/cases/release_readiness_forged_event_blocker/workspace/user.md +4 -0
  213. multi_agent_brief/evaluation_cases/fixtures/cases/reverted_entry_removed_from_next_snapshot/workspace/config.yaml +18 -0
  214. multi_agent_brief/evaluation_cases/fixtures/cases/reverted_entry_removed_from_next_snapshot/workspace/improvement/ledger.jsonl +3 -0
  215. multi_agent_brief/evaluation_cases/fixtures/cases/reverted_entry_removed_from_next_snapshot/workspace/improvement/memory.md +3 -0
  216. multi_agent_brief/evaluation_cases/fixtures/cases/reverted_entry_removed_from_next_snapshot/workspace/output/intermediate/improvement_memory_snapshot.md +3 -0
  217. multi_agent_brief/evaluation_cases/fixtures/cases/reverted_entry_removed_from_next_snapshot/workspace/sources.yaml +2 -0
  218. multi_agent_brief/evaluation_cases/fixtures/cases/reverted_entry_removed_from_next_snapshot/workspace/user.md +4 -0
  219. multi_agent_brief/evaluation_cases/fixtures/cases/same_evidence_reader_quality_regression/workspace/config.yaml +12 -0
  220. multi_agent_brief/evaluation_cases/fixtures/cases/same_evidence_reader_quality_regression/workspace/input/sources/source-001.txt +1 -0
  221. multi_agent_brief/evaluation_cases/fixtures/cases/same_evidence_reader_quality_regression/workspace/output/brief.md +37 -0
  222. multi_agent_brief/evaluation_cases/fixtures/cases/same_evidence_reader_quality_regression/workspace/output/delivery/brief.md +37 -0
  223. multi_agent_brief/evaluation_cases/fixtures/cases/same_evidence_reader_quality_regression/workspace/output/intermediate/atomic_claim_graph.json +17 -0
  224. multi_agent_brief/evaluation_cases/fixtures/cases/same_evidence_reader_quality_regression/workspace/output/intermediate/audit_report.json +5 -0
  225. multi_agent_brief/evaluation_cases/fixtures/cases/same_evidence_reader_quality_regression/workspace/output/intermediate/audited_brief.md +37 -0
  226. multi_agent_brief/evaluation_cases/fixtures/cases/same_evidence_reader_quality_regression/workspace/output/intermediate/claim_ledger.json +20 -0
  227. multi_agent_brief/evaluation_cases/fixtures/cases/same_evidence_reader_quality_regression/workspace/output/intermediate/evidence_span_registry.json +20 -0
  228. multi_agent_brief/evaluation_cases/fixtures/cases/same_evidence_reader_quality_regression/workspace/output/intermediate/finalize_report.json +40 -0
  229. multi_agent_brief/evaluation_cases/fixtures/cases/same_evidence_reader_quality_regression/workspace/output/intermediate/gates/auditor_quality_gate_report.json +42 -0
  230. multi_agent_brief/evaluation_cases/fixtures/cases/same_evidence_reader_quality_regression/workspace/output/intermediate/gates/finalize_quality_gate_report.json +42 -0
  231. multi_agent_brief/evaluation_cases/fixtures/cases/same_evidence_reader_quality_regression/workspace/output/intermediate/screened_candidates.json +33 -0
  232. multi_agent_brief/evaluation_cases/fixtures/cases/same_evidence_reader_quality_regression/workspace/output/source_appendix.md +12 -0
  233. multi_agent_brief/evaluation_cases/fixtures/cases/same_evidence_reader_quality_regression/workspace/output/source_appendix_trace.md +10 -0
  234. multi_agent_brief/evaluation_cases/fixtures/cases/same_evidence_reader_quality_regression/workspace/report_spec.yaml +24 -0
  235. multi_agent_brief/evaluation_cases/fixtures/cases/same_evidence_reader_quality_regression/workspace/sources.yaml +4 -0
  236. multi_agent_brief/evaluation_cases/fixtures/cases/same_evidence_reader_quality_regression/workspace/user.md +3 -0
  237. multi_agent_brief/evaluation_cases/fixtures/cases/source_evidence_pack_blocks_non_evidence_file/workspace/config.yaml +13 -0
  238. multi_agent_brief/evaluation_cases/fixtures/cases/source_evidence_pack_blocks_non_evidence_file/workspace/input/sources/README.md +4 -0
  239. multi_agent_brief/evaluation_cases/fixtures/cases/source_evidence_pack_blocks_non_evidence_file/workspace/output/intermediate/source_evidence_pack_manifest.json +26 -0
  240. multi_agent_brief/evaluation_cases/fixtures/cases/source_evidence_pack_blocks_non_evidence_file/workspace/sources.yaml +9 -0
  241. multi_agent_brief/evaluation_cases/fixtures/cases/source_evidence_pack_blocks_non_evidence_file/workspace/user.md +4 -0
  242. multi_agent_brief/evaluation_cases/fixtures/cases/stale_current_claim/workspace/config.yaml +9 -0
  243. multi_agent_brief/evaluation_cases/fixtures/cases/stale_current_claim/workspace/output/intermediate/audit_report.json +1 -0
  244. multi_agent_brief/evaluation_cases/fixtures/cases/stale_current_claim/workspace/output/intermediate/audited_brief.md +3 -0
  245. multi_agent_brief/evaluation_cases/fixtures/cases/stale_current_claim/workspace/output/intermediate/candidate_claims.json +1 -0
  246. multi_agent_brief/evaluation_cases/fixtures/cases/stale_current_claim/workspace/output/intermediate/claim_ledger.json +13 -0
  247. multi_agent_brief/evaluation_cases/fixtures/cases/stale_current_claim/workspace/output/intermediate/screened_candidates.json +1 -0
  248. multi_agent_brief/evaluation_cases/fixtures/cases/stale_current_claim/workspace/sources.yaml +2 -0
  249. multi_agent_brief/evaluation_cases/fixtures/cases/stale_current_claim/workspace/user.md +3 -0
  250. multi_agent_brief/evaluation_cases/fixtures/cases/third_party_price_snapshot_formal_block/workspace/config.yaml +13 -0
  251. multi_agent_brief/evaluation_cases/fixtures/cases/third_party_price_snapshot_formal_block/workspace/sources.yaml +9 -0
  252. multi_agent_brief/evaluation_cases/fixtures/cases/third_party_price_snapshot_formal_block/workspace/user.md +4 -0
  253. multi_agent_brief/evaluation_cases/fixtures/cases/trajectory_retry_budget_exhausted/workspace/config.yaml +4 -0
  254. multi_agent_brief/evaluation_cases/fixtures/cases/trajectory_retry_budget_exhausted/workspace/sources.yaml +2 -0
  255. multi_agent_brief/evaluation_cases/fixtures/cases/trajectory_retry_budget_exhausted/workspace/user.md +3 -0
  256. multi_agent_brief/evaluation_cases/fixtures/cases/unapproved_entry_not_materialized/workspace/config.yaml +18 -0
  257. multi_agent_brief/evaluation_cases/fixtures/cases/unapproved_entry_not_materialized/workspace/improvement/ledger.jsonl +1 -0
  258. multi_agent_brief/evaluation_cases/fixtures/cases/unapproved_entry_not_materialized/workspace/sources.yaml +2 -0
  259. multi_agent_brief/evaluation_cases/fixtures/cases/unapproved_entry_not_materialized/workspace/user.md +4 -0
  260. multi_agent_brief/evaluation_cases/fixtures/cases/unauthorized_institution_branding_blocks_release/workspace/config.yaml +18 -0
  261. multi_agent_brief/evaluation_cases/fixtures/cases/unauthorized_institution_branding_blocks_release/workspace/sources.yaml +9 -0
  262. multi_agent_brief/evaluation_cases/fixtures/cases/unauthorized_institution_branding_blocks_release/workspace/user.md +5 -0
  263. multi_agent_brief/evaluation_cases/fixtures/cases/unsupported_material_fact/workspace/config.yaml +8 -0
  264. multi_agent_brief/evaluation_cases/fixtures/cases/unsupported_material_fact/workspace/output/intermediate/audit_report.json +1 -0
  265. multi_agent_brief/evaluation_cases/fixtures/cases/unsupported_material_fact/workspace/output/intermediate/audited_brief.md +8 -0
  266. multi_agent_brief/evaluation_cases/fixtures/cases/unsupported_material_fact/workspace/output/intermediate/candidate_claims.json +1 -0
  267. multi_agent_brief/evaluation_cases/fixtures/cases/unsupported_material_fact/workspace/output/intermediate/claim_ledger.json +1 -0
  268. multi_agent_brief/evaluation_cases/fixtures/cases/unsupported_material_fact/workspace/output/intermediate/screened_candidates.json +1 -0
  269. multi_agent_brief/evaluation_cases/fixtures/cases/unsupported_material_fact/workspace/sources.yaml +2 -0
  270. multi_agent_brief/evaluation_cases/fixtures/cases/unsupported_material_fact/workspace/user.md +3 -0
  271. multi_agent_brief/evaluation_cases/fixtures/manifest.yaml +861 -0
  272. multi_agent_brief/evaluation_cases/fixtures.py +20 -0
  273. multi_agent_brief/evaluation_cases/runner.py +1603 -0
  274. multi_agent_brief/experiments/__init__.py +45 -0
  275. multi_agent_brief/experiments/experiment_080.py +5835 -0
  276. multi_agent_brief/experiments/schemas.py +63 -0
  277. multi_agent_brief/experiments/target_contract.py +10 -0
  278. multi_agent_brief/feedback/__init__.py +17 -0
  279. multi_agent_brief/feedback/feedback_contract.py +482 -0
  280. multi_agent_brief/feedback/feedback_state.py +898 -0
  281. multi_agent_brief/hermes/__init__.py +25 -0
  282. multi_agent_brief/hermes/adapter.py +832 -0
  283. multi_agent_brief/improvement/__init__.py +83 -0
  284. multi_agent_brief/improvement/contract.py +1114 -0
  285. multi_agent_brief/improvement/memory.py +451 -0
  286. multi_agent_brief/improvement/product_definition.py +228 -0
  287. multi_agent_brief/improvement/state.py +961 -0
  288. multi_agent_brief/inputs/__init__.py +2 -0
  289. multi_agent_brief/inputs/classifier.py +322 -0
  290. multi_agent_brief/inputs/contracts.py +59 -0
  291. multi_agent_brief/inputs/extractor.py +310 -0
  292. multi_agent_brief/install/__init__.py +2 -0
  293. multi_agent_brief/install/writer.py +97 -0
  294. multi_agent_brief/onboarding/__init__.py +11 -0
  295. multi_agent_brief/onboarding/io.py +103 -0
  296. multi_agent_brief/onboarding/mapper.py +484 -0
  297. multi_agent_brief/onboarding/schema.py +46 -0
  298. multi_agent_brief/orchestrator/__init__.py +2 -0
  299. multi_agent_brief/orchestrator/fact_layer_import.py +352 -0
  300. multi_agent_brief/orchestrator/handoff.py +2209 -0
  301. multi_agent_brief/orchestrator/role_topology.py +42 -0
  302. multi_agent_brief/orchestrator/run_archive.py +888 -0
  303. multi_agent_brief/orchestrator/run_integrity.py +346 -0
  304. multi_agent_brief/orchestrator/runtime_state/__init__.py +70 -0
  305. multi_agent_brief/orchestrator/runtime_state/_io.py +167 -0
  306. multi_agent_brief/orchestrator/runtime_state/_transactions.py +298 -0
  307. multi_agent_brief/orchestrator/runtime_state/artifact_registry.py +1825 -0
  308. multi_agent_brief/orchestrator/runtime_state/atomic_claim_graph.py +96 -0
  309. multi_agent_brief/orchestrator/runtime_state/claim_ledger_freeze.py +510 -0
  310. multi_agent_brief/orchestrator/runtime_state/claim_metadata_enrichment.py +836 -0
  311. multi_agent_brief/orchestrator/runtime_state/claim_support_matrix.py +582 -0
  312. multi_agent_brief/orchestrator/runtime_state/completion_gates.py +672 -0
  313. multi_agent_brief/orchestrator/runtime_state/contracts_loader.py +66 -0
  314. multi_agent_brief/orchestrator/runtime_state/decisions.py +239 -0
  315. multi_agent_brief/orchestrator/runtime_state/errors.py +61 -0
  316. multi_agent_brief/orchestrator/runtime_state/event_log.py +256 -0
  317. multi_agent_brief/orchestrator/runtime_state/evidence_span_registry.py +233 -0
  318. multi_agent_brief/orchestrator/runtime_state/fact_layer.py +755 -0
  319. multi_agent_brief/orchestrator/runtime_state/identity.py +90 -0
  320. multi_agent_brief/orchestrator/runtime_state/lifecycle.py +675 -0
  321. multi_agent_brief/orchestrator/runtime_state/manifest.py +82 -0
  322. multi_agent_brief/orchestrator/runtime_state/operations.py +224 -0
  323. multi_agent_brief/orchestrator/runtime_state/paths.py +38 -0
  324. multi_agent_brief/orchestrator/runtime_state/repair.py +984 -0
  325. multi_agent_brief/orchestrator/runtime_state/safety_surfaces.py +147 -0
  326. multi_agent_brief/orchestrator/runtime_state/semantic_assessment_report.py +692 -0
  327. multi_agent_brief/orchestrator/runtime_state/semantic_support_acceptance.py +683 -0
  328. multi_agent_brief/orchestrator/runtime_state/source_evidence_pack.py +131 -0
  329. multi_agent_brief/orchestrator/runtime_state/stage_completion.py +1320 -0
  330. multi_agent_brief/orchestrator/runtime_state/trajectory.py +200 -0
  331. multi_agent_brief/orchestrator/runtime_state/workflow.py +350 -0
  332. multi_agent_brief/orchestrator/source_evidence.py +43 -0
  333. multi_agent_brief/orchestrator/timing.py +410 -0
  334. multi_agent_brief/orchestrator_contract.py +96 -0
  335. multi_agent_brief/outputs/__init__.py +2 -0
  336. multi_agent_brief/outputs/atomic_reader_projection.py +288 -0
  337. multi_agent_brief/outputs/docx.py +32 -0
  338. multi_agent_brief/outputs/finalize.py +1036 -0
  339. multi_agent_brief/outputs/ib_docx.py +983 -0
  340. multi_agent_brief/outputs/naming.py +38 -0
  341. multi_agent_brief/outputs/pdf.py +20 -0
  342. multi_agent_brief/outputs/reader_final_gate.py +509 -0
  343. multi_agent_brief/outputs/reader_projection.py +397 -0
  344. multi_agent_brief/outputs/source_appendix.py +753 -0
  345. multi_agent_brief/outputs/templates/__init__.py +112 -0
  346. multi_agent_brief/product/__init__.py +49 -0
  347. multi_agent_brief/product/bundle_projection.py +686 -0
  348. multi_agent_brief/product/citation_profile.py +145 -0
  349. multi_agent_brief/product/guidance_manifestation.py +421 -0
  350. multi_agent_brief/product/materiality_selection.py +472 -0
  351. multi_agent_brief/product/policy_gate_adapter.py +116 -0
  352. multi_agent_brief/product/policy_profile.py +39 -0
  353. multi_agent_brief/product/policy_projection.py +161 -0
  354. multi_agent_brief/product/policy_registry.py +83 -0
  355. multi_agent_brief/product/policy_resolver.py +225 -0
  356. multi_agent_brief/product/quality_closeout.py +188 -0
  357. multi_agent_brief/product/quality_panel.py +2217 -0
  358. multi_agent_brief/product/release_approval.py +1034 -0
  359. multi_agent_brief/product/report_pack.py +130 -0
  360. multi_agent_brief/product/report_pack_aliases.py +68 -0
  361. multi_agent_brief/product/report_registry.py +101 -0
  362. multi_agent_brief/product/report_spec.py +181 -0
  363. multi_agent_brief/product/support_wording.py +525 -0
  364. multi_agent_brief/product/template_conformance.py +516 -0
  365. multi_agent_brief/product/template_projection.py +123 -0
  366. multi_agent_brief/product/template_registry.py +244 -0
  367. multi_agent_brief/product/template_render_plan.py +315 -0
  368. multi_agent_brief/product/template_renderer.py +224 -0
  369. multi_agent_brief/product/trajectory_regulation.py +441 -0
  370. multi_agent_brief/provenance/__init__.py +5 -0
  371. multi_agent_brief/provenance/builder.py +841 -0
  372. multi_agent_brief/provenance/contract.py +21 -0
  373. multi_agent_brief/provenance/io.py +144 -0
  374. multi_agent_brief/provenance/model.py +110 -0
  375. multi_agent_brief/provenance/references.py +43 -0
  376. multi_agent_brief/provenance/validator.py +135 -0
  377. multi_agent_brief/quality_gates/__init__.py +19 -0
  378. multi_agent_brief/quality_gates/contract.py +581 -0
  379. multi_agent_brief/quality_gates/state.py +2498 -0
  380. multi_agent_brief/repair/__init__.py +5 -0
  381. multi_agent_brief/repair/router.py +842 -0
  382. multi_agent_brief/runtime_assets.py +431 -0
  383. multi_agent_brief/sources/__init__.py +16 -0
  384. multi_agent_brief/sources/api_filings.py +236 -0
  385. multi_agent_brief/sources/api_news.py +174 -0
  386. multi_agent_brief/sources/base.py +142 -0
  387. multi_agent_brief/sources/cached_package.py +119 -0
  388. multi_agent_brief/sources/cli_provider.py +263 -0
  389. multi_agent_brief/sources/coverage.py +336 -0
  390. multi_agent_brief/sources/decider.py +756 -0
  391. multi_agent_brief/sources/doctor.py +373 -0
  392. multi_agent_brief/sources/evidence_pack.py +364 -0
  393. multi_agent_brief/sources/feishu_provider.py +326 -0
  394. multi_agent_brief/sources/filing_resolver.py +400 -0
  395. multi_agent_brief/sources/industry_packs.py +130 -0
  396. multi_agent_brief/sources/join.py +206 -0
  397. multi_agent_brief/sources/local_signal.py +81 -0
  398. multi_agent_brief/sources/local_signal_planner.py +636 -0
  399. multi_agent_brief/sources/manual.py +259 -0
  400. multi_agent_brief/sources/mcp_provider.py +309 -0
  401. multi_agent_brief/sources/mineru_provider.py +601 -0
  402. multi_agent_brief/sources/normalizer.py +95 -0
  403. multi_agent_brief/sources/opencli_provider.py +282 -0
  404. multi_agent_brief/sources/planner.py +178 -0
  405. multi_agent_brief/sources/registry.py +367 -0
  406. multi_agent_brief/sources/rss.py +190 -0
  407. multi_agent_brief/sources/search_backends/__init__.py +31 -0
  408. multi_agent_brief/sources/search_backends/base.py +51 -0
  409. multi_agent_brief/sources/search_backends/brave.py +192 -0
  410. multi_agent_brief/sources/search_backends/capabilities.py +94 -0
  411. multi_agent_brief/sources/search_backends/exa.py +180 -0
  412. multi_agent_brief/sources/search_backends/firecrawl.py +164 -0
  413. multi_agent_brief/sources/search_backends/serper.py +241 -0
  414. multi_agent_brief/sources/search_backends/tavily.py +124 -0
  415. multi_agent_brief/sources/sourcehub.py +505 -0
  416. multi_agent_brief/sources/web_search.py +267 -0
  417. multi_agent_brief/status.py +966 -0
  418. multi_agent_brief/tools/__init__.py +3 -0
  419. multi_agent_brief/tools/draft_cleanup.py +198 -0
  420. multi_agent_brief/workbuddy/__init__.py +1 -0
  421. multi_agent_brief/workbuddy/diagnose.py +569 -0
  422. multi_agent_brief/workbuddy/skill_pack.py +309 -0
  423. multi_agent_brief/workspace/__init__.py +1 -0
  424. multi_agent_brief/workspace/init_profile.py +45 -0
@@ -0,0 +1,99 @@
1
+ """Evaluation-case CLI commands."""
2
+
3
+ from __future__ import annotations
4
+
5
+ import argparse
6
+ import json
7
+ from typing import Any
8
+
9
+ from multi_agent_brief.evaluation_cases.contract import EvaluationCaseContractError
10
+ from multi_agent_brief.evaluation_cases.runner import (
11
+ EvaluationCaseRunError,
12
+ list_evaluation_cases,
13
+ run_evaluation_cases,
14
+ validate_evaluation_cases,
15
+ )
16
+
17
+
18
+ def register(subparsers: argparse._SubParsersAction) -> None:
19
+ parser = subparsers.add_parser(
20
+ "eval-cases",
21
+ help="Run packaged public-safe control-surface evaluation cases.",
22
+ )
23
+ actions = parser.add_subparsers(dest="eval_cases_action", required=True)
24
+
25
+ list_parser = actions.add_parser("list", help="List available evaluation cases.")
26
+ list_parser.add_argument("--cases-dir", help="Custom evaluation cases directory.")
27
+ list_parser.add_argument("--json", action="store_true", help="Emit machine-readable JSON.")
28
+
29
+ validate_parser = actions.add_parser("validate", help="Validate evaluation case fixtures.")
30
+ validate_parser.add_argument("--cases-dir", help="Custom evaluation cases directory.")
31
+ validate_parser.add_argument("--json", action="store_true", help="Emit machine-readable JSON.")
32
+
33
+ run_parser = actions.add_parser("run", help="Run evaluation cases.")
34
+ run_parser.add_argument("--cases-dir", help="Custom evaluation cases directory.")
35
+ run_parser.add_argument("--case-id", "--case", dest="case_id", help="Run one case id.")
36
+ run_parser.add_argument("--repo-workdir", help="Repository or packaged contract base.")
37
+ run_parser.add_argument(
38
+ "--keep-workspaces",
39
+ action="store_true",
40
+ help="Copy temporary case workspaces into .mabw-eval-cases for debugging.",
41
+ )
42
+ run_parser.add_argument("--json", action="store_true", help="Emit machine-readable JSON.")
43
+
44
+
45
+ def handle(args: argparse.Namespace) -> int:
46
+ try:
47
+ if args.eval_cases_action == "list":
48
+ result = list_evaluation_cases(cases_dir=getattr(args, "cases_dir", None))
49
+ _print_result("eval-cases list", result, as_json=getattr(args, "json", False))
50
+ return 0
51
+
52
+ if args.eval_cases_action == "validate":
53
+ result = validate_evaluation_cases(cases_dir=getattr(args, "cases_dir", None))
54
+ _print_result("eval-cases validate", result, as_json=getattr(args, "json", False))
55
+ return 0 if result.get("ok") else 1
56
+
57
+ if args.eval_cases_action == "run":
58
+ result = run_evaluation_cases(
59
+ cases_dir=getattr(args, "cases_dir", None),
60
+ case_id=getattr(args, "case_id", None),
61
+ repo_workdir=getattr(args, "repo_workdir", None),
62
+ keep_workspaces=getattr(args, "keep_workspaces", False),
63
+ )
64
+ _print_result("eval-cases run", result, as_json=getattr(args, "json", False))
65
+ return 0 if result.get("ok") else 1
66
+ except (EvaluationCaseContractError, EvaluationCaseRunError, ValueError) as exc:
67
+ payload = exc.to_dict() if hasattr(exc, "to_dict") else {
68
+ "ok": False,
69
+ "error": str(exc),
70
+ "details": getattr(exc, "details", {}),
71
+ }
72
+ _print_result("eval-cases error", payload, as_json=getattr(args, "json", False))
73
+ return 1
74
+
75
+ return 1
76
+
77
+
78
+ def _print_result(label: str, result: dict[str, Any], *, as_json: bool) -> None:
79
+ if as_json:
80
+ print(json.dumps(result, ensure_ascii=False, indent=2, sort_keys=True))
81
+ return
82
+ if "error" in result:
83
+ print(f"[{label}] {result.get('error')}")
84
+ for error in result.get("errors") or (result.get("details") or {}).get("errors") or []:
85
+ print(f" - {error}")
86
+ return
87
+ print(f"[{label}] ok: {result.get('ok')}")
88
+ if "case_count" in result:
89
+ print(f"[{label}] cases: {result.get('case_count')}")
90
+ if "passed_count" in result:
91
+ print(f"[{label}] passed: {result.get('passed_count')}")
92
+ print(f"[{label}] failed: {result.get('failed_count')}")
93
+ for error in result.get("errors") or []:
94
+ print(f" - {error}")
95
+ for case in result.get("cases") or []:
96
+ if isinstance(case, dict):
97
+ print(f" - {case.get('case_id')} ({case.get('case_type')})")
98
+ else:
99
+ print(f" - {case}")
@@ -0,0 +1,395 @@
1
+ """Experiment harness CLI commands."""
2
+
3
+ from __future__ import annotations
4
+
5
+ import argparse
6
+ import json
7
+ from typing import Any
8
+
9
+ from multi_agent_brief.experiments import (
10
+ Experiment080Error,
11
+ export_blind_pack,
12
+ import_assessment,
13
+ register_run_record,
14
+ scaffold_condition,
15
+ score_run_record,
16
+ summarize_case,
17
+ validate_case_dir,
18
+ )
19
+
20
+
21
+ def register(subparsers: argparse._SubParsersAction) -> None:
22
+ parser = subparsers.add_parser(
23
+ "experiments",
24
+ help="Validate experimental harness metadata without running workflow stages.",
25
+ )
26
+ experiments_sub = parser.add_subparsers(dest="experiments_action", required=True)
27
+
28
+ exp080 = experiments_sub.add_parser(
29
+ "080",
30
+ help="MABW-080 approved-guidance manifestation experiment tools.",
31
+ )
32
+ exp080_sub = exp080.add_subparsers(dest="experiment_080_action", required=True)
33
+
34
+ validate = exp080_sub.add_parser(
35
+ "validate-case",
36
+ help="Read-only validation for an MABW-080 case directory.",
37
+ )
38
+ validate.add_argument("case_dir", help="Path to experiments/080/cases/<case_id>.")
39
+ validate.add_argument("--json", action="store_true", help="Emit machine-readable JSON.")
40
+
41
+ register_run = exp080_sub.add_parser(
42
+ "register-run",
43
+ help="Register a completed workspace run into an MABW-080 case.",
44
+ )
45
+ register_run.add_argument("--case", required=True, dest="case_dir", help="Path to experiments/080/cases/<case_id>.")
46
+ register_run.add_argument(
47
+ "--condition",
48
+ required=True,
49
+ choices=("baseline", "memory", "prompt_only"),
50
+ help="080 condition for this run.",
51
+ )
52
+ register_run.add_argument("--workspace", required=True, help="Completed MABW workspace to register.")
53
+ register_run.add_argument("--output", required=True, help="Path to write run_record.json.")
54
+ register_run.add_argument(
55
+ "--repo-workdir",
56
+ help="Optional explicit MABW source checkout for git commit provenance. Defaults to case_manifest.repo_commit.",
57
+ )
58
+ register_run.add_argument("--json", action="store_true", help="Emit machine-readable JSON.")
59
+
60
+ score_run = exp080_sub.add_parser(
61
+ "score-run",
62
+ help="Build a deterministic MABW-080 scorecard draft from a registered run.",
63
+ )
64
+ score_run.add_argument("--case", required=True, dest="case_dir", help="Path to experiments/080/cases/<case_id>.")
65
+ score_run.add_argument("--run-record", required=True, help="Path to run_record.json.")
66
+ score_run.add_argument("--output", required=True, help="Path to write scorecard.json.")
67
+ score_run.add_argument("--json", action="store_true", help="Emit machine-readable JSON.")
68
+
69
+ import_assessment_parser = exp080_sub.add_parser(
70
+ "import-assessment",
71
+ help="Import external guidance-manifestation assessment into an MABW-080 scorecard.",
72
+ )
73
+ import_assessment_parser.add_argument("--scorecard", help="Path to scorecard.json.")
74
+ import_assessment_parser.add_argument("--assessment", required=True, help="Path to assessment.json.")
75
+ import_assessment_parser.add_argument("--output", required=True, help="Path to write assessed scorecard.json.")
76
+ import_assessment_parser.add_argument(
77
+ "--blind-pack",
78
+ help="Optional blind_pack.json for hash-bound condition-blind assessment import.",
79
+ )
80
+ import_assessment_parser.add_argument(
81
+ "--reveal-mapping",
82
+ help="Optional reveal_mapping.json that maps blind item IDs back to scorecards after hash verification.",
83
+ )
84
+ import_assessment_parser.add_argument("--json", action="store_true", help="Emit machine-readable JSON.")
85
+
86
+ blind_pack = exp080_sub.add_parser(
87
+ "export-blind-pack",
88
+ help="Export a condition-blind, hash-bound assessment pack from auditable scorecards.",
89
+ )
90
+ blind_pack.add_argument("--case", required=True, dest="case_dir", help="Path to experiments/080/cases/<case_id>.")
91
+ blind_pack.add_argument(
92
+ "--scorecard",
93
+ required=True,
94
+ action="append",
95
+ dest="scorecards",
96
+ help="Scorecard JSON path to include. Pass once per condition.",
97
+ )
98
+ blind_pack.add_argument("--output", required=True, help="Directory to write blind_pack.json and reveal_mapping.json.")
99
+ blind_pack.add_argument("--seed", help="Optional deterministic shuffle seed for repeatable exports.")
100
+ blind_pack.add_argument("--json", action="store_true", help="Emit machine-readable JSON.")
101
+
102
+ summarize = exp080_sub.add_parser(
103
+ "summarize",
104
+ help="Summarize deterministic MABW-080 scorecards for a case.",
105
+ )
106
+ summarize.add_argument("--case", required=True, dest="case_dir", help="Path to experiments/080/cases/<case_id>.")
107
+ summarize.add_argument(
108
+ "--scorecard",
109
+ action="append",
110
+ dest="scorecards",
111
+ default=[],
112
+ help="Additional scorecard JSON path to include. May be passed multiple times.",
113
+ )
114
+ summarize.add_argument("--output", help="Optional path to write case_summary.json.")
115
+ summarize.add_argument("--json", action="store_true", help="Emit machine-readable JSON.")
116
+
117
+ scaffold = exp080_sub.add_parser(
118
+ "scaffold-condition",
119
+ help="Prepare one initialized MABW-080 condition workspace with deterministic fast-rerun import.",
120
+ )
121
+ scaffold.add_argument("--case", required=True, dest="case_dir", help="Path to experiments/080/cases/<case_id>.")
122
+ scaffold.add_argument(
123
+ "--condition",
124
+ required=True,
125
+ choices=("baseline", "memory", "prompt_only"),
126
+ help="080 condition to scaffold.",
127
+ )
128
+ scaffold.add_argument(
129
+ "--workspace",
130
+ required=True,
131
+ help=(
132
+ "Initialized condition workspace to import into. Must already contain "
133
+ "config.yaml, sources.yaml, user.md, and audience_profile.md."
134
+ ),
135
+ )
136
+ scaffold.add_argument(
137
+ "--archive",
138
+ help="Optional run archive manifest or archive directory. Defaults to frozen_fact_layer.source_archive_path.",
139
+ )
140
+ scaffold.add_argument("--runtime", default="hermes", help="Runtime value to record in imported runtime state.")
141
+ scaffold.add_argument("--repo-workdir", help="Optional MABW source checkout for packaged config resolution.")
142
+ scaffold.add_argument("--json", action="store_true", help="Emit machine-readable JSON.")
143
+
144
+
145
+ def handle(args: argparse.Namespace) -> int:
146
+ if args.experiments_action != "080":
147
+ return 1
148
+ if args.experiment_080_action == "validate-case":
149
+ payload = validate_case_dir(args.case_dir)
150
+ if getattr(args, "json", False):
151
+ print(json.dumps(payload, ensure_ascii=False, indent=2, sort_keys=True))
152
+ else:
153
+ _print_validate_case(payload)
154
+ return 0 if payload.get("ok") else 1
155
+ if args.experiment_080_action == "score-run":
156
+ try:
157
+ payload = score_run_record(
158
+ case_dir=args.case_dir,
159
+ run_record=args.run_record,
160
+ output=args.output,
161
+ )
162
+ except Experiment080Error as exc:
163
+ payload = exc.to_dict()
164
+ if getattr(args, "json", False):
165
+ print(json.dumps(payload, ensure_ascii=False, indent=2, sort_keys=True))
166
+ else:
167
+ print(f"[experiments 080 score-run] ok: False")
168
+ details = payload.get("details") if isinstance(payload.get("details"), dict) else {}
169
+ code = details.get("code")
170
+ suffix = f" ({code})" if code else ""
171
+ print(f" - {payload.get('error')}{suffix}")
172
+ return 1
173
+ if getattr(args, "json", False):
174
+ print(json.dumps(payload, ensure_ascii=False, indent=2, sort_keys=True))
175
+ else:
176
+ _print_score_run(payload)
177
+ return 0
178
+ if args.experiment_080_action == "import-assessment":
179
+ try:
180
+ payload = import_assessment(
181
+ scorecard=args.scorecard,
182
+ assessment=args.assessment,
183
+ output=args.output,
184
+ blind_pack=args.blind_pack,
185
+ reveal_mapping=args.reveal_mapping,
186
+ )
187
+ except Experiment080Error as exc:
188
+ payload = exc.to_dict()
189
+ if getattr(args, "json", False):
190
+ print(json.dumps(payload, ensure_ascii=False, indent=2, sort_keys=True))
191
+ else:
192
+ print(f"[experiments 080 import-assessment] ok: False")
193
+ details = payload.get("details") if isinstance(payload.get("details"), dict) else {}
194
+ code = details.get("code")
195
+ suffix = f" ({code})" if code else ""
196
+ print(f" - {payload.get('error')}{suffix}")
197
+ return 1
198
+ if getattr(args, "json", False):
199
+ print(json.dumps(payload, ensure_ascii=False, indent=2, sort_keys=True))
200
+ else:
201
+ _print_import_assessment(payload)
202
+ return 0
203
+ if args.experiment_080_action == "export-blind-pack":
204
+ try:
205
+ payload = export_blind_pack(
206
+ case_dir=args.case_dir,
207
+ scorecards=args.scorecards,
208
+ output=args.output,
209
+ seed=args.seed,
210
+ )
211
+ except Experiment080Error as exc:
212
+ payload = exc.to_dict()
213
+ if getattr(args, "json", False):
214
+ print(json.dumps(payload, ensure_ascii=False, indent=2, sort_keys=True))
215
+ else:
216
+ print(f"[experiments 080 export-blind-pack] ok: False")
217
+ details = payload.get("details") if isinstance(payload.get("details"), dict) else {}
218
+ code = details.get("code")
219
+ suffix = f" ({code})" if code else ""
220
+ print(f" - {payload.get('error')}{suffix}")
221
+ return 1
222
+ if getattr(args, "json", False):
223
+ print(json.dumps(payload, ensure_ascii=False, indent=2, sort_keys=True))
224
+ else:
225
+ _print_export_blind_pack(payload)
226
+ return 0
227
+ if args.experiment_080_action == "summarize":
228
+ try:
229
+ payload = summarize_case(
230
+ case_dir=args.case_dir,
231
+ output=args.output,
232
+ scorecards=args.scorecards,
233
+ )
234
+ except Experiment080Error as exc:
235
+ payload = exc.to_dict()
236
+ if getattr(args, "json", False):
237
+ print(json.dumps(payload, ensure_ascii=False, indent=2, sort_keys=True))
238
+ else:
239
+ print(f"[experiments 080 summarize] ok: False")
240
+ details = payload.get("details") if isinstance(payload.get("details"), dict) else {}
241
+ code = details.get("code")
242
+ suffix = f" ({code})" if code else ""
243
+ print(f" - {payload.get('error')}{suffix}")
244
+ return 1
245
+ if getattr(args, "json", False):
246
+ print(json.dumps(payload, ensure_ascii=False, indent=2, sort_keys=True))
247
+ else:
248
+ _print_summarize(payload)
249
+ return 0
250
+ if args.experiment_080_action == "scaffold-condition":
251
+ try:
252
+ payload = scaffold_condition(
253
+ case_dir=args.case_dir,
254
+ condition=args.condition,
255
+ workspace=args.workspace,
256
+ archive=args.archive,
257
+ runtime=args.runtime,
258
+ repo_workdir=args.repo_workdir,
259
+ )
260
+ except Experiment080Error as exc:
261
+ payload = exc.to_dict()
262
+ if getattr(args, "json", False):
263
+ print(json.dumps(payload, ensure_ascii=False, indent=2, sort_keys=True))
264
+ else:
265
+ print(f"[experiments 080 scaffold-condition] ok: False")
266
+ details = payload.get("details") if isinstance(payload.get("details"), dict) else {}
267
+ code = details.get("code")
268
+ suffix = f" ({code})" if code else ""
269
+ print(f" - {payload.get('error')}{suffix}")
270
+ return 1
271
+ if getattr(args, "json", False):
272
+ print(json.dumps(payload, ensure_ascii=False, indent=2, sort_keys=True))
273
+ else:
274
+ _print_scaffold_condition(payload)
275
+ return 0
276
+ if args.experiment_080_action != "register-run":
277
+ return 1
278
+ try:
279
+ payload = register_run_record(
280
+ case_dir=args.case_dir,
281
+ condition=args.condition,
282
+ workspace=args.workspace,
283
+ output=args.output,
284
+ repo_workdir=args.repo_workdir,
285
+ )
286
+ except Experiment080Error as exc:
287
+ payload = exc.to_dict()
288
+ if getattr(args, "json", False):
289
+ print(json.dumps(payload, ensure_ascii=False, indent=2, sort_keys=True))
290
+ else:
291
+ print(f"[experiments 080 register-run] ok: False")
292
+ details = payload.get("details") if isinstance(payload.get("details"), dict) else {}
293
+ code = details.get("code")
294
+ suffix = f" ({code})" if code else ""
295
+ print(f" - {payload.get('error')}{suffix}")
296
+ return 1
297
+ if getattr(args, "json", False):
298
+ print(json.dumps(payload, ensure_ascii=False, indent=2, sort_keys=True))
299
+ else:
300
+ _print_register_run(payload)
301
+ return 0
302
+
303
+
304
+ def _print_validate_case(payload: dict[str, Any]) -> None:
305
+ print(f"[experiments 080 validate-case] ok: {payload.get('ok')}")
306
+ if payload.get("case_id"):
307
+ print(f"[experiments 080 validate-case] case_id: {payload.get('case_id')}")
308
+ conditions = payload.get("conditions") or []
309
+ if conditions:
310
+ print(f"[experiments 080 validate-case] conditions: {', '.join(conditions)}")
311
+ for error in payload.get("errors") or []:
312
+ location = f" ({error.get('path')})" if error.get("path") else ""
313
+ print(f" - {error.get('code')}: {error.get('message')}{location}")
314
+ for warning in payload.get("warnings") or []:
315
+ location = f" ({warning.get('path')})" if warning.get("path") else ""
316
+ print(f" - warning {warning.get('code')}: {warning.get('message')}{location}")
317
+
318
+
319
+ def _print_register_run(payload: dict[str, Any]) -> None:
320
+ print(f"[experiments 080 register-run] ok: {payload.get('ok')}")
321
+ print(f"[experiments 080 register-run] case_id: {payload.get('case_id')}")
322
+ print(f"[experiments 080 register-run] condition: {payload.get('condition')}")
323
+ print(f"[experiments 080 register-run] run_id: {payload.get('run_id')}")
324
+ print(f"[experiments 080 register-run] output: {payload.get('output')}")
325
+
326
+
327
+ def _print_score_run(payload: dict[str, Any]) -> None:
328
+ print(f"[experiments 080 score-run] ok: {payload.get('ok')}")
329
+ print(f"[experiments 080 score-run] case_id: {payload.get('case_id')}")
330
+ print(f"[experiments 080 score-run] condition: {payload.get('condition')}")
331
+ print(f"[experiments 080 score-run] run_id: {payload.get('run_id')}")
332
+ print(f"[experiments 080 score-run] validity_class: {payload.get('validity_class')}")
333
+ print(f"[experiments 080 score-run] assessment_status: {payload.get('assessment_status')}")
334
+ print(f"[experiments 080 score-run] output: {payload.get('output')}")
335
+
336
+
337
+ def _print_import_assessment(payload: dict[str, Any]) -> None:
338
+ print(f"[experiments 080 import-assessment] ok: {payload.get('ok')}")
339
+ print(f"[experiments 080 import-assessment] case_id: {payload.get('case_id')}")
340
+ print(f"[experiments 080 import-assessment] condition: {payload.get('condition')}")
341
+ print(f"[experiments 080 import-assessment] run_id: {payload.get('run_id')}")
342
+ print(f"[experiments 080 import-assessment] validity_class: {payload.get('validity_class')}")
343
+ print(f"[experiments 080 import-assessment] assessment_status: {payload.get('assessment_status')}")
344
+ print(f"[experiments 080 import-assessment] output: {payload.get('output')}")
345
+
346
+
347
+ def _print_export_blind_pack(payload: dict[str, Any]) -> None:
348
+ print(f"[experiments 080 export-blind-pack] ok: {payload.get('ok')}")
349
+ print(f"[experiments 080 export-blind-pack] case_id: {payload.get('case_id')}")
350
+ print(f"[experiments 080 export-blind-pack] assessment_target: {payload.get('assessment_target')}")
351
+ print(f"[experiments 080 export-blind-pack] blind_item_count: {payload.get('blind_item_count')}")
352
+ print(f"[experiments 080 export-blind-pack] blind_pack: {payload.get('blind_pack')}")
353
+ print(f"[experiments 080 export-blind-pack] reveal_mapping: {payload.get('reveal_mapping')}")
354
+
355
+
356
+ def _print_summarize(payload: dict[str, Any]) -> None:
357
+ print(f"[experiments 080 summarize] ok: {payload.get('ok')}")
358
+ print(f"[experiments 080 summarize] case_id: {payload.get('case_id')}")
359
+ print(f"[experiments 080 summarize] scorecard_count: {payload.get('scorecard_count')}")
360
+ summary = payload.get("summary") if isinstance(payload.get("summary"), dict) else {}
361
+ run_counts = summary.get("run_counts") if isinstance(summary.get("run_counts"), dict) else {}
362
+ validity_counts = (
363
+ run_counts.get("validity_class_counts")
364
+ if isinstance(run_counts.get("validity_class_counts"), dict)
365
+ else {}
366
+ )
367
+ if validity_counts:
368
+ rendered = ", ".join(f"{key}={validity_counts[key]}" for key in sorted(validity_counts))
369
+ print(f"[experiments 080 summarize] validity: {rendered}")
370
+ manifestation = summary.get("manifestation") if isinstance(summary.get("manifestation"), dict) else {}
371
+ if manifestation:
372
+ print(
373
+ "[experiments 080 summarize] manifestation: "
374
+ f"score_2={manifestation.get('score_2_manifested_count', 0)}, "
375
+ f"score_3_overapplication={manifestation.get('score_3_overapplication_count', 0)}"
376
+ )
377
+ output = payload.get("output")
378
+ if output:
379
+ print(f"[experiments 080 summarize] output: {output}")
380
+
381
+
382
+ def _print_scaffold_condition(payload: dict[str, Any]) -> None:
383
+ print(f"[experiments 080 scaffold-condition] ok: {payload.get('ok')}")
384
+ print(f"[experiments 080 scaffold-condition] case_id: {payload.get('case_id')}")
385
+ print(f"[experiments 080 scaffold-condition] condition: {payload.get('condition')}")
386
+ print(f"[experiments 080 scaffold-condition] workspace: {payload.get('workspace')}")
387
+ print(f"[experiments 080 scaffold-condition] metadata: {payload.get('metadata_path')}")
388
+ print(f"[experiments 080 scaffold-condition] instructions: {payload.get('operator_instructions_path')}")
389
+ fact_import = payload.get("fact_layer_import") if isinstance(payload.get("fact_layer_import"), dict) else {}
390
+ if fact_import:
391
+ print(f"[experiments 080 scaffold-condition] source_run_id: {fact_import.get('source_run_id')}")
392
+ stages = fact_import.get("satisfied_stage_ids") if isinstance(fact_import.get("satisfied_stage_ids"), list) else []
393
+ if stages:
394
+ print(f"[experiments 080 scaffold-condition] imported_stages: {', '.join(str(stage) for stage in stages)}")
395
+ print(f"[experiments 080 scaffold-condition] next: {payload.get('next_command')}")