- Add reconstruct-v0.5-d-deconstruct-no21.md prompt (removes rule 21)
from original deconstruct-first prompt: 'Do not create artificial
uncertainties to increase their number.'
- Extend start-case-experiment-helper.cjs with --condition D and
--treatment no21 CLI flags for treatment selector apparatus
- Add programmatic treatment validation (rejects invalid treatments
cross-condition, validates only 'no21' is a valid treatment value)
- Condition D output uses freeformText field instead of reconstruction
JSON — avoids production JSON schema enforcement on freeform text
- Mock double supports freeform mode: returns deterministic raw text
instead of structured importantUnknowns when isFreeform=true
- Add 23 targeted tests: J (Condition D prompt selection),
J.1 (treatment validation), J.2 (prompt isolation verification)
- Fix existing B.1 assertions to use matchObject for execution field
Adds experimental apparatus for testing whether removing the question field
from importantUnknowns in reconstruction output improves semantic fidelity.
New files:
- lib/reconstruction/schema-variant.js (conditionB schema + production passthrough)
- prompts/reconstruct-v0.5-b-noreq.md (alt prompt, identical line count to prod)
Changed files:
- lib/graph/orchestrator.js (pass generationSchema through dependencies)
- lib/analysis.js (accept opts.generationSchema fallback to original schema)
- scripts/start-case-experiment-helper.cjs (--condition B/A flag support)
- tests/scripts/start-case-experiment-helper.test.js (8 new deterministic tests)
43 targeted deterministic tests PASS. Production callers use original prompt/schema unchanged.
No live model calls. No full suite evidence available.
Co-Authored-By: Claude Code <noreply@anthropic.com>
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
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.
robbond
