MiroFish Fix Bot 4cb20ff011 fix(backend): resolve 500 on ontology generation + Zep source_targets limit ... - llm_client: SSE-aware streaming calls, empty-content retry, and bulletproof truncated-JSON recovery (handles unterminated strings, trailing comma/colon, BOM) so a truncated LLM response no longer 500s - ontology_generator: raise max_tokens 4096->16384 (JSON was being truncated) and cap edge source_targets to 10 (Zep API limit) to fix 400 'source_targets cannot contain more than 10 items' - graph: log the real exception on 500 for easier diagnosis - frontend api: surface the backend's actual error message instead of just 'status code 500'		2026-07-10 15:24:29 +00:00
..
__init__.py	Implement Report Agent for automated report generation and interaction	2025-12-09 15:10:55 +08:00
graph.py	fix(backend): resolve 500 on ontology generation + Zep source_targets limit	2026-07-10 15:24:29 +00:00
report.py	fix(i18n): pass locale to background threads via thread-local storage	2026-04-01 16:55:51 +08:00
simulation.py	fix(i18n): replace hardcoded Chinese stage names in simulation prepare SSE	2026-04-01 17:31:00 +08:00
streaming.py	feat: Add performance optimizations for MiroFish simulation	2026-07-09 01:20:39 +00:00