robbond
6e4db76807
fix: align mock responses with real UI contract
2026-08-04 14:11:59 +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
fe6a9925cb
fix: stabilise multi-turn question progression
2026-08-03 13:55:39 +01:00
robbond
34c25fcb43
fix: reselect after reasoning pattern filtering
2026-08-03 12:39:01 +01:00
robbond
c27320984c
feat: enforce reasoning pattern consistency
2026-08-03 12:10:57 +01:00
robbond
3e2edd2edc
fix: continue question selection after graph updates
2026-08-03 11:28:49 +01:00
robbond
b00928d6fb
feat: introduce reasoning pattern selection
2026-08-03 10:25:26 +01:00
robbond
42d4da3496
feat: decompose non-answerable unknowns
2026-08-03 09:53:28 +01:00
robbond
db994d7764
fix: make graph-backed questions authoritative
2026-08-03 09:13:52 +01:00
robbond
ef04b9e494
fix: normalise reported claim evidence kind
2026-08-03 08:50:37 +01:00
robbond
3c0f7f5a45
feat: enforce one-concept questions
2026-08-03 08:40:39 +01:00
robbond
b2ffc54964
feat: evaluate deterministic cross-branch corroboration
2026-08-03 07:19:20 +01:00
robbond
1d64144e01
feat: separate confidence from reasoning completeness
2026-08-03 07:05:20 +01:00
robbond
49765e95a0
feat: propagate child resolution through reasoning graph
2026-08-03 06:52:52 +01:00
robbond
d52690cf2b
feat: decompose composite unknowns before questioning
2026-08-03 06:32:12 +01:00
robbond
0723c2f49a
feat: decompose composite unknowns before questioning
2026-08-02 19:24:38 +01:00
robbond
b1c633ba5c
feat: back next questions with explicit graph unknowns
2026-08-02 19:03:07 +01:00
robbond
25a989450c
feat: advance reasoning after comparability is resolved
2026-08-02 17:06:34 +01:00
robbond
7d408701b5
fix: defer relationship classification until comparability is established
2026-08-02 16:48:10 +01:00
robbond
c97f5f7303
feat: classify observation relationships after comparability
2026-08-02 16:40:24 +01:00
robbond
0c7558d31f
feat: introduce comparability assessment before contradiction reasoning
2026-08-02 16:28:11 +01:00
robbond
51ce356218
fix: handle unjustified unknown selection ties
2026-08-02 16:09:00 +01:00
robbond
586802950d
feat: explain deterministic unknown selection
2026-08-02 15:27:00 +01:00
robbond
5ef9710293
Implemented Investigation Strategy
2026-08-02 15:10:49 +01:00
robbond
781d6a462f
test: generalise question priority across decisions
2026-08-02 13:02:49 +01:00
robbond
48ce66dddb
feat: formulate follow-up questions from graph context
2026-08-02 12:47:34 +01:00
robbond
4affadab4b
fix: link emergent unknowns to answer-derived graph nodes
2026-08-02 12:17:49 +01:00
robbond
392564ed61
feat: prioritise follow-up questions by information value
2026-08-02 11:11:55 +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
cb77f955ed
feat: apply validated graph update proposals
2026-08-02 08:24:56 +01:00
robbond
f3cdfce0b0
feat: add graph update proposal orchestration
2026-08-02 08:15:54 +01:00
robbond
b38a6a9f2e
feat: define graph update proposal contract
2026-08-02 08:00:37 +01:00
robbond
02a6ecd0da
fix: normalise compatible live reconstruction responses
2026-08-02 07:50:02 +01:00
robbond
0ccc03c111
feat: add situation graph foundation
2026-08-02 06:59:23 +01:00
robbond
3c1362d8a1
feat: add initial situation graph orchestration
2026-08-02 06:52:26 +01:00
robbond
79ea2f6824
feat: add v0.3 normalised comparison reasoning
...
Add explicit reasoning guidance for normalising counts by exposure/denominator,
distinguishing total count from rate, and avoiding correlation-as-causation errors.
Changes:
- prompts/reconstruct-v0.3.md: new prompt with normalisation discipline
- lib/reconstruction/prompt.js: v0.3 loader + env var override support
- lib/analysis.js: defer DEFAULT_PROMPT_VERSION to prompt module (defaults to v0.3)
- PROMPT_VERSIONS extended to [v0.1, v0.2, v0.3]
- tests/v03-reasoning.test.js: 34 focused tests covering prompt loading, schema validation, guidance completeness, and target scenario fixture
- playwright.config.js + tests/smoke.test.js: minimal UI smoke test for browser rendering
- package.json: add @playwright/test as devDependency
Default switches to v0.3; v0.2 selectable via promptVersion or RECONSTRUCTION_PROMPT_VERSION env var.
2026-08-01 15:39:30 +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