review-result-schema-is-normalized
IN premise
Every result dict returned by `parse_review_response` is guaranteed to have exactly six keys (`id`, `valid`, `sufficient`, `necessary`, `unnecessary_antecedents`, `comment`) regardless of what the LLM returned, via normalization with safe defaults.
Summary
The review system's response parser always produces a consistent, predictable structure with six fields, even if the LLM returns incomplete or malformed output. This means downstream code can safely access any of those fields without checking for missing keys, simplifying error handling throughout the review pipeline.
Dependents
These beliefs depend on this one:
- review-output-is-uniform-and-fail-safe — Review response parsing defaults missing fields to passing, accepts only JSON arrays as valid input, and normalizes every result to a guaranteed six-key schema — producing uniform fail-safe structured output regardless of LLM response quality.
Details
| Source | entries/2026/05/05/reasons_lib-review.md |