robbond/confidence-engine
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(confidence-engine): enforce openai strict object invariants

Browse Source
This commit is contained in:
robbond
2026-09-07 12:22:03 +01:00
parent e289f0be1f
commit 0d27d4935b
3 changed files with 31 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/current-handoff.md
+2 -1
View File
@@ -37,7 +37,8 @@ If YES, the next live experiment is one timed/costed OpenAI UI investigation mea
- The OpenAI provider now honors a caller-supplied structured-output schema, applying its existing strict-schema transport projection; absent an alternate schema, initial reconstruction retains its existing strict schema and transport normalization.
- The next live run exposed incomplete recursive strict projection: OpenAI rejected `relationships.items` because it lacked `additionalProperties: false`. The projector now recognizes every `type: "object"` node, including property-less objects in array items, and recursively enforces strict object schemas while preserving initial-reconstruction optionality/nullability behavior.
- This deterministically fixes the focused-deconstruction transport failures. Provider and focused-route suites pass with zero live calls.
- The latest Terra request then exposed an inconsistent root `properties`/`required` contract. The projector now derives `required` after projection from the surviving property keys, and recursive tests verify `properties`, `required`, and `additionalProperties` consistency. Property-less object strictness and initial-reconstruction transport behavior remain preserved.
- Provider and focused-route suites pass with zero live calls.
- Next boundary: retry one fresh real Playwright-driven OpenAI/Terra investigation; do not reuse the failed focused-deconstruction attempt.
## Repository checkpoint