mirror of
https://github.com/dograh-hq/dograh.git
synced 2026-06-13 08:15:21 +02:00
6ae9ba5d9e
parse_llm_json is explicitly designed to return a list when the model emits a
top-level JSON array (it has a dedicated test for that). The QA analyzers then
call parsed.get("tags", ...) directly on the result. When parsed is a list,
that raises AttributeError, which is NOT caught by the surrounding
except (json.JSONDecodeError, ValueError) — so a single stray array response
from the QA model crashed the entire QA analysis run instead of degrading to
empty results.
The live variable-extraction path already guards this exact case with an
isinstance(..., dict) check; mirror it in both QA analysis call sites
(_run_qa_analysis per-node and _run_whole_call_qa_analysis fallback) so a
non-dict parse result coerces to {} and the run produces empty defaults.
Adds a regression test that drives the whole-call analyzer with an array
response and asserts empty results rather than a crash.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
|
||
|---|---|---|
| .. | ||
| __init__.py | ||
| analysis.py | ||
| conversation.py | ||
| llm_config.py | ||
| metrics.py | ||
| node_summary.py | ||
| tracing.py | ||