fix(meta_analyzer): parse stringified findings array from LLM

[matt-appno]

Problem

MetaAnalyzerResult has a field_validator that repairs overall_assessment when an LLM returns it as a JSON string (mode="before" → json.loads), but there is no equivalent validator for the top-level findings array.

Some models/endpoints — reproducibly Claude Sonnet via an OpenAI-compatible gateway (SKILLSPECTOR_PROVIDER=openai pointed at a router) — return findings as a stringified JSON array rather than a real list. This fails Pydantic's list_type validation and crashes the scan:

Error: 1 validation error for MetaAnalyzerResult
findings
  Input should be a valid array [type=list_type, input_value='[\n  {\n    "pattern_id"...', input_type=str]

The process exits with code 2 and no report is written, even though all per-file analyzers ran successfully. I hit this on multiple real scans (a skill and an MCP-server repo).

Fix

Add a mirrored field_validator("findings", mode="before") that json.loads a string payload, falling back to an empty list on parse failure or a non-list result — exactly matching the existing _parse_stringified_assessment behavior for overall_assessment.

Tests

New TestMetaAnalyzerResultFindingsValidator in tests/nodes/test_llm_analyzer_base.py covering:

• stringified JSON array → parsed into MetaAnalyzerFinding objects
• native list → unchanged
• invalid string → []
• non-list JSON (e.g. an object) → []

Full file suite passes (83 passed); ruff check / ruff format clean.

🤖 Generated with Claude Code