Macky
9df2938557
fix(llm): log raw provider output on JSON failure, raise judge budget to 6000
- complete_json(): log model/max_tokens + raw provider text (1500 cap) when
json.loads fails, so a truncated judge reply is diagnosable from the log
- complete()/complete_conversation(): log reasoning_content head on empty
content (hidden reasoning starves the shared max_tokens cap)
- simulator.judge(): max_tokens 2000 -> 6000 (server accepts 8000)
- tests: pin judge budget; new test_llm_failure_logging.py pins the logging
(autouse fixture restores app.llm logger disabled by alembic fileConfig)
547 passed. Incident #4 (500 char 125).
2026-10-02 22:30:28 +07:00
..
2026-10-02 22:30:28 +07:00
2026-08-16 02:41:10 +07:00
2026-08-25 20:37:54 +07:00
2026-10-02 12:53:59 +07:00
2026-08-09 09:51:27 +07:00
2026-10-02 22:30:28 +07:00
2026-10-01 15:19:46 +07:00
2026-08-21 12:28:22 +07:00
2026-08-20 10:57:04 +07:00
2026-08-16 02:41:10 +07:00
2026-08-09 09:48:55 +07:00