robbond
607a2d4a58
fix: ensure loading overlay renders during analyse
2026-08-05 09:51:17 +01:00
robbond
553bdb1bdd
fix: allow loading render before awaiting (prevent React batching)
2026-08-05 09:16:56 +01:00
robbond
61210c1200
fix: localise update reasoning state
2026-08-05 08:36:18 +01:00
robbond
6d11c1d503
fix: unify reasoning mode across submissions
2026-08-05 08:27:22 +01:00
robbond
c4f5744c30
feat: Phase 2-5 UX enhancements — recovery cards, session persistence, summary panel, contract backlog
...
Phase 2: Recovery state components (ProviderUnavailableCard,
MalformedResponseCard, UnexpectedStateCard, ContinueLaterBanner) with
automatic error detection for provider/network/malformed/unexpected states.
Phase 3: Session persistence via sessionStorage — save after each
successful turn, restore on mount, clear on restart/reset. Continuelater banner shown when session is restored.
Phase 4: InvestigationSummaryPanel component displaying current status,
understanding summary, questions answered/remaining, investigation timestamps.
Phase 5: docs/reasoning-contract-backlog.md documenting all mocked
fields (60+ rows across 7 categories) with feature/UI need/mock/desired
output/stage/notes columns.
Also: wired onRestart through ReasoningWorkspace → ScenarioForm, fixed
getErrorType scope issues, removed broken window.__restartInvestigation.
2026-08-05 06:48:59 +01:00
robbond
9e0fca8f53
fix: preserve plain-language current understanding
2026-08-04 18:43:50 +01:00
robbond
f703fdc842
fix: clarify terminal investigation states
2026-08-04 18:10:06 +01:00
robbond
ae615c4343
feat: make the workspace tldr first
2026-08-04 17:39:30 +01:00
robbond
97a4847770
feat: add mock investigation mode for UI development
...
- lib/mocks/confidence-engine/mock-client.js: self-contained ESM interceptor with 6 inline turn fixtures, no external deps or require() calls
- components/scenario-form.jsx: MOCK_ENABLED compile-time boolean, useMockGlobals() hook injects window.__MOCK_* globals at runtime, ternary dispatch to mockFetch
- .env.example: NEXT_PUBLIC_CONFIDENCE_ENGINE_MOCKS, MOCK_DELAY, MOCK_SCENARIO env vars
- docs/v0.7-ui-mock-mode.md: setup, scenarios (default/complete/error), architecture, safety rules, fixture schema
2026-08-04 13:56:15 +01:00
robbond
7c07ce195d
Revert "feat: allow earlier evidence to be revised"
...
This reverts commit 13b14fd01a
2026-08-04 13:10:09 +01:00
robbond
13b14fd01a
feat: allow earlier evidence to be revised
2026-08-03 20:00:13 +01:00
robbond
f5cbf4b629
fix: preserve conversation after update
2026-08-03 19:23:06 +01:00
robbond
3a83944006
fix: set update loading state before request
2026-08-03 19:01:04 +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
72ef175971
feat: surface new unknowns after graph updates
2026-08-02 10:30:59 +01:00
robbond
a9bce79658
feat: add one-turn situation graph update UI
2026-08-02 09:43:42 +01:00
robbond
575b8fd971
feat: connect UI to situation graph start flow
2026-08-02 07:21:40 +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
robbond