test(confidence-engine): add current understanding synthesis experiment helper

Co-Authored-By: Claude Code <noreply@anthropic.com>
2026-10-08 09:49:09 +01:00
parent 279b9a2a67
commit dd875b5535
3 changed files with 482 additions and 0 deletions
@@ -0,0 +1,54 @@
+# CU Synthesis Experiment Apparatus — Iteration 3
+
+## Purpose
+
+Deterministic experiment helper for invoking the production `synthesizeCurrentUnderstanding()` function with fixed local input fixtures, without live model calls.
+
+## Files
+
+| File | Role |
+|------|------|
+| `scripts/current-understanding-experiment-helper.cjs` | Standalone helper (CJS + dynamic import ESM) |
+| `tests/graph/current-understanding-experiment-helper.test.js` | Deterministic verification (14 tests, 0 live calls) |
+
+## Usage
+
+### Helper (CLI)
+
+```bash
+node scripts/current-understanding-experiment-helper.cjs --file fixtures/cu-synthesis.json
+```
+
+Fixture contract: `{ situationGraph: object, findings: array }`
+
+### Test
+
+```bash
+npx vitest run tests/graph/current-understanding-experiment-helper.test.js --environment=node
+```
+
+## Existing Mechanics Reused
+
+- Dynamic `import()` seam from CJS to ESM (proven in `scripts/overview-experiment-helper.cjs` line 64)
+- Environment loading via `@next/env` `loadEnvConfig` (proven in both existing helpers)
+- `.env.local` ownership of `OLLAMA_BASE_URL` and `OLLAMA_MODEL` preserved — helper reads from `process.env`, never writes
+- Deterministic inline test double provider pattern (mirrors `makeFakeProvider` in `tests/graph/current-understanding-synthesis.test.js`)
+
+## Production Entry Point
+
+`synthesizeCurrentUnderstanding()` from `lib/graph/current-understanding-synthesis.js`
+
+Input contract: `{ situationGraph: object, findings: array }`
+Optional deps: `{ provider: object, modelName: string }`
+
+Output: `{ currentUnderstanding: string }`
+
+## Verification Results
+
+All 14 deterministic tests PASS. Zero live model calls. The following invariants verified:
+- Fixed compatible input reaches `synthesizeCurrentUnderstanding()`
+- Expected structured output `{ currentUnderstanding }` captured
+- Prompt includes revised Rule 2 boundary text ("Do not introduce or describe open questions...")
+- Exactly one synthesis invocation per run
+- Input fixture is not mutated (deep clone + compare)
+- No persistence/Supabase/DB operations