Commit Graph
478 Commits
Author SHA1 Message Date
robbond 4687226bd8 test(experiment): repair relationship discovery result handling 2026-08-19 16:14:50 +01:00
robbond 8fb284c374 test(experiment): checkpoint fragment relationship discovery apparatus 2026-08-19 15:43:06 +01:00
robbond 8c52939c02 test(experiment): checkpoint derived focused current-view result 2026-08-19 15:34:41 +01:00
robbond 644108db71 test(experiment): checkpoint derived focused current-view apparatus 2026-08-19 15:27:14 +01:00
robbond 0b0d5594fe test(experiment): checkpoint granular answer fragment result 2026-08-19 14:41:57 +01:00
robbond fbeaf01f90 docs: archive verified historical experiment families 2026-08-19 14:25:43 +01:00
robbond e6d0327641 docs: archive historical Confidence Engine evidence 2026-08-19 12:07:17 +01:00
robbond a12f9555af docs: clarify Confidence Engine context authority 2026-08-19 11:49:30 +01:00
robbond 5b43c1b8f9 docs: preserve Confidence Engine methodology continuity 2026-08-19 10:46:05 +01:00
robbond e1b54e4073 test(experiment): checkpoint granular answer fragment apparatus 2026-08-19 10:14:46 +01:00
robbond 6ed3415220 test(experiment): checkpoint three-turn separated reasoning result 2026-08-19 09:51:31 +01:00
robbond 98889039c2 test(experiment): checkpoint three-turn separated reasoning apparatus 2026-08-19 09:35:48 +01:00
robbond 9c715161b0 test(experiment): checkpoint separated reasoning layers result 2026-08-19 09:15:25 +01:00
robbond 56de4a7ef3 test(experiment): checkpoint separated reasoning layers apparatus 2026-08-19 08:53:33 +01:00
robbond b20707c447 test(experiment): checkpoint focused context boundary result 2026-08-19 08:33:41 +01:00
robbond 6ed4d60029 test(experiment): checkpoint focused context boundary apparatus 2026-08-19 07:59:41 +01:00
robbond 153bbee85e test(experiment): checkpoint two-turn focused refinement result 2026-08-19 07:53:26 +01:00
robbond 8520f2195d test(experiment): expose two-turn live refinement route 2026-08-19 07:44:55 +01:00
robbond ebcf1d9306 test(experiment): checkpoint two-turn focused refinement apparatus 2026-08-19 07:35:32 +01:00
robbond dafc020f66 feat(experiment): checkpoint one-turn focused investigation UI 2026-08-19 07:07:10 +01:00
robbond 7add85d8d2 feat(experiment): checkpoint focused investigation boundaries 2026-08-19 05:41:32 +01:00
robbond c0b963973f test(experiment): checkpoint focused vs global result 2026-08-19 05:15:25 +01:00
robbond 913dfec507 test(experiment): checkpoint comparison observability 2026-08-18 19:28:30 +01:00
robbond 952cb442b5 test(experiment): checkpoint focused vs global comparison apparatus 2026-08-18 18:34:08 +01:00
robbond 2f6c90b027 test(experiment): checkpoint focused answer deconstruction 2026-08-18 18:25:35 +01:00
robbond 648e1c7a29 test(experiment): checkpoint explicit-node formulation 2026-08-18 17:29:07 +01:00
robbond fd98cda8ba feat(experiment): checkpoint RTO question lifecycle 2026-08-18 16:38:15 +01:00
robbond 6b25100f9a feat(experiment): checkpoint RTO open-question workspace 2026-08-18 15:25:27 +01:00
robbond db5016c138 feat(experiment): checkpoint RTO case workspace lifecycle 2026-08-18 14:59:52 +01:00
robbond 4a34dcc361 test(experiment): ground RTO apparatus in real fixture 2026-08-18 12:39:19 +01:00
robbond 25a88c5fc3 feat: multi-thread experimental apparatus (RTO.A1)
Add fixture-only apparatus for representing multiple concurrent open
investigation items within a fixed case context.

New scenario 'multi-thread' exposes:
- A fixed central situation statement and case summary (product-launch
  timing decision, drawn from existing pre-anchored-product-launch
  data)
- Three open investigation items — none compulsory: enterprise customer
  signing probability, competitor timing, financial viability comparison
- One engine recommendation (mt-ent-customer-signing, ordered first)
- User selection of any item; chosen item becomes visually primary while
  others remain visible as context
- Experimental state isolated in _experimental / _experimentalState —
  never aliases production graph fields
2026-08-18 10:39:16 +01:00
robbond 8339b6849a docs: checkpoint return to Confidence Engine origin confidence-engine-return-to-origin 2026-08-18 08:33:05 +01:00
robbond 55b7551739 test(harness): preserve null-question start captures 2026-08-18 07:11:27 +01:00
robbond 5d0ce0ddd3 experiment: compare model and deterministic investigation selection 2026-08-18 07:00:39 +01:00
robbond 600b07d820 test(harness): support gated live investigation continuation 2026-08-18 06:48:40 +01:00
robbond 7dd4a956fb experiment: validate live financial investigation progression 2026-08-18 06:32:40 +01:00
robbond a52f0345a1 experiment: validate live question-rejection ownership 2026-08-17 18:25:40 +01:00
robbond 7685a4f2af test(evidence): preserve live product-launch journey captures 2026-08-17 18:08:47 +01:00
robbond 8117f3d307 docs: record current reasoning checkpoint 2026-08-17 17:58:54 +01:00
robbond 772ae495c6 fix(reasoning): preserve investigation ownership across selection and question rejection 2026-08-17 17:58:45 +01:00
robbond d908f3746d test(e2e): preserve manually recorded investigation journey 2026-08-17 13:48:56 +01:00
robbond 6ca8381b99 fix(reasoning): correct insufficient-observation comparability state 2026-08-17 09:32:21 +01:00
robbond ade445e453 fix(reasoning): reconcile evidence and preserve deterministic continuation 2026-08-17 08:06:08 +01:00
robbond f2f495d5c7 fix(ui): preserve investigation workspace across no-question states 2026-08-17 08:06:01 +01:00
robbond 0cd68f40a5 docs: record playwright selector apparatus repair 2026-08-15 13:56:06 +01:00
robbond 2561b5d720 test(e2e): repair investigation textarea selectors 2026-08-15 13:55:59 +01:00
robbond a599922d9f experiment: confirm live explicit sufficiency closure 2026-08-15 12:43:56 +01:00
robbond abc01b181f experiment: confirm live confirmation-gated state b path 2026-08-15 12:27:08 +01:00
robbond 357be25de5 docs: record confirmation-gated closure enforcement 2026-08-15 11:35:02 +01:00
robbond b181c3ea75 fix(reasoning): enforce confirmation-gated decision closure
- reconcileDecisionClosureOwnership normaliser between reconciliation and validation (Boundary B)
- Strips terminal parent updates without explicit user confirmation; preserves all other proposal work
- Strips parent from resolvedUnknownNodeIds bookkeeping on no-confirmation strip
- Restores reconciler-forced resolved→unknown for synthetic updates too
- Prevents hybrid unknown+value states by nulling newValue in all stripping paths
- No-op update created when reconciler synthesized the entry to prevent downstream errors

Prompt:
- Rule #143 rewritten from evidence-sufficiency to explicit-confirmation gate
- Directs model to use possibleInference for directional conclusions when confirmation absent

Regression preservation:
- 60B.43 lifecycle invariant restored via explicit confirmation phrases in fixture answers
- 60B.49 reconciliation auto-add invariant restored under confirmed closure flow
- Test apparatus fixed: structuralActionRequired required with userSupportedMeaning (validator constraint)

New coverage:
- 10 tests for all 60B.79/80 coverage requirements
- 5 prompt alignment tests for Rule #143
2026-08-15 11:34:39 +01:00