Commit Graph
230 Commits
Author SHA1 Message Date
robbond 556acfb156 feat(confidence-engine): render INVESTIGATING cue on Open Question cards with focused history
- ThreadContributionsBadge (rendered per-node on OpenQuestionsPanel
  cards and Done-for-now cards) now shows an amber INVESTIGATING
  indicator when the node has matching contributions via targetNodeId
  identity match.
- UNCLEAR and INVESTIGATING cues coexist independently on the same
  card — UNCLEAR is epistemic state, INVESTIGATING is activity cue.
- Deterministic test suite added: focused-investigation-history (11
  tests) covering identity matching, zero-contrib edge cases,
  multiple-contrib coalescing, done-for-now retention, and uncoupling
  from UNCLEAR state.
- All 57 tests pass.
2026-08-28 11:25:40 +01:00
robbond f1bd91faf8 feat(confidence-engine): promote focused learning on done 2026-08-28 10:48:45 +01:00
robbond e221bd3bf8 feat(confidence-engine): isolate finding-informed understanding 2026-08-28 08:16:37 +01:00
robbond 166ee91698 feat(confidence-engine): persist canonical investigation state 2026-08-27 16:21:41 +01:00
robbond bc35e05253 refactor(confidence-engine): migrate scenario persistence to storage provider 2026-08-27 15:44:58 +01:00
robbond ba956eeb3a refactor(confidence-engine): add investigation storage provider 2026-08-27 15:24:38 +01:00
robbond 22e1d7484b feat(confidence-engine): support finding corrections 2026-08-27 13:43:23 +01:00
robbond 5c926154cd feat(confidence-engine): support not-relevant findings 2026-08-27 12:08:11 +01:00
robbond 7858650334 feat(confidence-engine): expose correlated findings to focused presentation 2026-08-27 09:23:51 +01:00
robbond ca7d8e5384 feat(confidence-engine): correlate focused result with contribution 2026-08-27 08:37:23 +01:00
robbond 061ea364b3 feat(confidence-engine): derive findings from focused contributions 2026-08-27 06:44:07 +01:00
robbond abeb3fcb03 feat(confidence-engine): add focused investigation overlay workspace 2026-08-26 19:22:54 +01:00
robbond 3235c35cf0 feat(confidence-engine): add focused finding handoff plumbing 2026-08-26 16:07:21 +01:00
robbond cb707c0192 test(confidence-engine): capture tentative mapping regression 2026-08-26 14:06:51 +01:00
robbond fdb173d0e9 feat(confidence-engine): anchor focused frontier to investigation relevance 2026-08-26 12:16:41 +01:00
robbond cfd463d8b3 test(confidence-engine): capture structural frontier priority regression 2026-08-26 12:10:07 +01:00
robbond fd02be0f29 fix(confidence-engine): render focused investigation in current presentation 2026-08-26 11:52:18 +01:00
robbond 6288ef1031 fix(confidence-engine): keep focused investigation in current presentation 2026-08-26 11:30:59 +01:00
robbond 81dda77392 fix(confidence-engine): reopen completed focused investigation 2026-08-26 10:20:45 +01:00
robbond 42a7e82d88 feat(confidence-engine): tighten focused relationship attribution 2026-08-26 07:56:27 +01:00
robbond 3ca37b0918 test(confidence-engine): checkpoint focused deconstruction regression cases 2026-08-26 07:34:22 +01:00
robbond 112739b8e5 feat(confidence-engine): checkpoint focused deconstruction reasoning 2026-08-25 15:10:09 +01:00
robbond 9d670822a3 feat(confidence-engine): preserve focused deconstruction semantic fidelity 2026-08-24 10:11:06 +01:00
robbond 2c108df5a9 checkpoint: preserve latest live run graph output json 2026-08-23 19:56:07 +01:00
robbond c134b5cb04 feat(confidence-engine): stabilize investigation workspace with semantic decomposition and deterministic presentation anchors 2026-08-23 16:59:55 +01:00
robbond 01c57788ee feat(confidence-engine): stabilize user-directed investigation flow
Intentional changes in this checkpoint:
- Deconstruct route: use body.targetNodeId (client identity) over raw.model-invented ID
- ThreadContributionsBadge: compact per-thread contribution indicator with expandable history
- Reopen continuation: resume from accumulated contributions instead of reformulating
- showEvidenceLimit gate: hide evidence-limit card during active investigation paths
- Evidence-limit visibility correction in rendering pipeline
- Section ordering: assumptions and connections after 'Still unclear' in focused result
- Prompt v0.3: preserve user-stated alternatives as separate unknowns; no count inflation
- 3 durable regression tests (target identity, contribution persistence, reopen state)
- evidence-limit card visibility gate test suite

Temporary residue removed:
- test-analysis.mjs (scratch diagnostic)
- 5 diagnostic console.log blocks from reasoning-workspace.jsx
2026-08-23 12:05:51 +01:00
robbond 517d780e2c checkpoint: preserve semantic decomposition investigation state 2026-08-22 08:21:29 +01:00
robbond 68be2344c6 fix(rto): persist focused contributions immediately after deconstruct success
The successful focused deconstruct calls onFocusedContribution which
updates parent state, but never persisted the new collection to
sessionStorage. This meant an immediate reload would lose the
contribution.

Fix: add a useEffect in ReasoningWorkspace that watches the
focusedContributions prop for changes and saves via the existing
saveSession mechanism. A ref guard prevents double-save alongside the
existing updateStatus-success effect.
2026-08-21 18:33:20 +01:00
robbond fce68a050f feat(ui): RTO.31 ownership of focused contributions flows to scenario form
- Add focusedContributions state + appendFocusedContribution callback in ScenarioForm
- Contributions persist through session lifecycle (save/restore/restart)
- Pass onFocusedContribution and focusedContributions to ReasoningWorkspace
- Call onFocusedContribution on successful deconstruct with full result shape
- Test: contribution sequence, field preservation, same/different target coexistence
2026-08-21 18:03:49 +01:00
robbond 41afd9b49f checkpoint: preserve reflection and response-contract work 2026-08-21 14:29:39 +01:00
robbond 412551c968 test(ui): restore deconstruction before question choice 2026-08-20 15:58:23 +01:00
robbond 65ced2e406 test(ui): make initial branch selection user owned 2026-08-20 14:11:37 +01:00
robbond 9fb9735c6e test(experiment): checkpoint semantic relationship inference result 2026-08-19 19:14:46 +01:00
robbond e1a18e27e7 test(experiment): checkpoint relationship negative-control result 2026-08-19 17:27:52 +01:00
robbond c97f07ba65 test(experiment): checkpoint fragment relationship discovery result 2026-08-19 16:59:22 +01:00
robbond 8c52939c02 test(experiment): checkpoint derived focused current-view result 2026-08-19 15:34:41 +01:00
robbond 0b0d5594fe test(experiment): checkpoint granular answer fragment result 2026-08-19 14:41:57 +01:00
robbond 6ed3415220 test(experiment): checkpoint three-turn separated reasoning result 2026-08-19 09:51:31 +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 153bbee85e test(experiment): checkpoint two-turn focused refinement result 2026-08-19 07:53:26 +01:00
robbond ebcf1d9306 test(experiment): checkpoint two-turn focused refinement apparatus 2026-08-19 07:35:32 +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 4a34dcc361 test(experiment): ground RTO apparatus in real fixture 2026-08-18 12:39:19 +01:00