fix(confidence-engine): supply synthesis output schema

2026-09-07 13:44:57 +01:00
parent 3f2e2e05ae
commit 7548a6af59
3 changed files with 19 additions and 2 deletions
@@ -41,7 +41,8 @@ If YES, the next live experiment is one timed/costed OpenAI UI investigation mea
 - Current deterministic final-fetch schema remains internally valid, yet the live rejection contradicts it. `CONFIDENCE_ENGINE_EXPERIMENT_TRACE_OPENAI_SCHEMA=1` now emits one safe, server-side structural summary immediately before the OpenAI fetch—no prompt, answer, request body, secret, or model output.
 - The focused-deconstruction route now emits complementary safe server diagnostics for start, provider success/failure, focused validation, and end status; the OpenAI schema trace remains provider-owned. No user content or secrets are logged.
 - Canonical focused relationship items are now strict `{ from, to, type }`: all required non-empty strings, free-text `type`, and no `rationale`; `relationships` remains required and may be `[]`. Schema, prompt field names, and validator align; the stale rationale-bearing test fixture was corrected.
- Focused and provider deterministic suites pass; the OpenAI projector is unchanged. Zero live calls occurred. Next evidence boundary: live provider compatibility of this same canonical focused contract.
+- Live Terra focused deconstruction now passes through the real UI, but the following Current Understanding synthesis exposed a separate caller/schema mismatch: its prompt and validator require `{ currentUnderstanding }` while the provider received the default initial-reconstruction schema.
+- Synthesis now supplies its own output schema as provider argument three; provider implementation is unchanged. Synthesis and provider deterministic suites pass with zero live calls. Next boundary: one isolated live synthesis request using the already captured situationGraph and findings payload.

 ## Repository checkpoint