review-parse-requires-json-array
IN premise
`parse_review_response` only accepts JSON arrays; a bare JSON object `{...}` is treated as unparseable and returns an empty list — the LLM must return a list even for single-item reviews.
Summary
The review parser is strict about its expected format: if the LLM returns a single review finding as a JSON object instead of wrapping it in an array, the parser silently discards it and reports zero findings. This means any prompt that asks the LLM to produce review output must explicitly instruct it to always return a JSON array, even when there is only one item to report.
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/tests-test_review.md |