Commit Graph
22 Commits
Author SHA1 Message Date
robbond ede5d54e36 fix(confidence-engine): v0.59c-layout — stack freshness beneath View report
Replace flex-row View report + status with flex-col stack so the
freshness label sits below the button and no longer floats between
actions on the Portfolio.
2026-09-03 15:50:52 +01:00
robbond f06138de32 feat(confidence-engine): v0.59b-c — report freshness on Report page + Portfolio
v0.59b — Report page freshness UI:
- Shows Current / Update available beside the generated report
- Manual Update report action with duplicate prevention guard
- Explanation copy about investigation changes since generation
- Persists generatedFromRevision during update flow

v0.59c — Portfolio Report freshness state:
- Surfaces Current / Update available alongside existing View report link
- Derives solely from revision provenance (zero model calls)
- No Update report action on Portfolio (manual update owned by Report page)
- Neither state shown when no Report exists
- Updated makeSnapshot with investigationRevision for realistic test data
2026-09-03 14:41:02 +01:00
robbond 99b3d26817 feat(confidence-engine): v0.59a — correct Investigation revision provenance
Semantic revision tracking ensures every meaningful persisted
Investigation change advances investigationRevision exactly once,
while Report generation records (but does not advance) the current
revision as generatedFromRevision for provenance integrity.

Corrections:
- updateFindingDisposition: add setInvestigationRevision(+1) for
  semantic transitions (eligible→not_relevant, restore)
- updateFindingProposition: add no-op guard + setInvestigationRevision(+1)
- onRestart/ContinueLaterBanner/reset button: add setInvestigationRevision(0)
- onSituationGraphChange (Re-open seam): already had revision +1 in dirty impl

Established behaviour preserved:
- Re-open via reopenResolvedUnknown → onSituationGraphChange → revision +1
- Empty Done via handleDoneForNowPromotion → revision +1
- Report generation records generatedFromRevision, advances by 0
- Autosave passes revision but does not increment it
- clearInvestigation() ownership intact

Tests: targeted Vitest suite (17 tests) covering all provenance boundaries.

Durable rule documented in current-handoff.md §v0.59a.
2026-09-03 13:39:40 +01:00
robbond 7db28c8611 feat(confidence-engine): generate investigation report on demand 2026-09-03 09:18:29 +01:00
robbond 99b75dca4e feat(confidence-engine): confirm destructive investigation restart 2026-09-03 07:36:43 +01:00
robbond 0da7b63e30 refine(confidence-engine): clarify portfolio investigation actions 2026-09-03 07:01:18 +01:00
robbond 32e1b01767 feat(confidence-engine): separate investigation report routes 2026-09-03 06:39:35 +01:00
robbond 83818c0c71 feat(confidence-engine): add investigation overview synthesis seam 2026-09-02 14:34:32 +01:00
robbond 043ba5f264 feat(confidence-engine): clarify understanding during Done refresh 2026-09-02 07:53:45 +01:00
robbond 8432ed45d4 fix(confidence-engine): keep episode reasoning server-side 2026-09-01 11:24:48 +01:00
robbond 8e941b0c7b fix(confidence-engine): resolve synthesis model configuration 2026-08-31 07:32:04 +01:00
robbond ff1119b4d5 feat(confidence-engine): establish current understanding synthesis seam 2026-08-30 18:48:38 +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 7add85d8d2 feat(experiment): checkpoint focused investigation boundaries 2026-08-19 05:41:32 +01:00
robbond 236d14f86c experiment: widen investigation canvas 2026-08-05 11:33:18 +01:00
robbond 7bc1c93486 feat: evolve investigation into guided conversation 2026-08-03 17:01:04 +01:00
robbond 0dd15345e4 fix: make active reasoning state visible 2026-08-03 16:09:04 +01:00
robbond ed32d585bb feat: add user-focused reasoning workspace 2026-08-03 15:18:35 +01:00
robbond a948910ba8 feat: add situation graph update API route 2026-08-02 08:32:18 +01:00
robbond 3c1362d8a1 feat: add initial situation graph orchestration 2026-08-02 06:52:26 +01:00
robbond d72c7c5465 chore: establish clean v0.2 baseline
Include only the working reconstruction prototype with Ollama integration:
- double-wrapping fix (lib/llm/provider.js)
- explicit v0.2 JSON output schema (prompts/reconstruct-v0.2.md)
- Zod validation layer (lib/reconstruction/schema.js)
- shared core analysis path (lib/analysis.js)
- prompt versioning infrastructure (lib/reconstruction/prompt.js)
- provider abstraction
- functioning Ollama provider path
- updated API route with centralized analysis
- UI components displaying v0.2 data and validation errors
- .gitignore rules for generated evaluation artifacts

Exclude: evaluator experiments, diagnostic tests, debug scripts,
generated artifacts, comparison findings, test data tied to evaluator.
2026-08-01 14:45:06 +01:00
robbond a2f9e472ea chore: preserve initial reconstruction prototype 2026-07-31 18:51:38 +01:00