Files
graphify/tests
rajarshidattapy bce2c9b3d3 fix(llm): recover JSON from reasoning-first model replies (#2882)
Reasoning-first models think out loud, fence the answer, or both, so the reply is not a
bare JSON object and the strict parse dropped the whole chunk. Try the whole reply first
(unchanged fast path), then each balanced-brace candidate, preferring braces that carry
the extraction keys so narration braces do not shadow the answer; a shape restatement
that carries the keys but no content is kept only as a last resort.
2026-08-20 15:44:56 +01:00
..