- 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' |
||
|---|---|---|
| .. | ||
| app | ||
| scripts | ||
| pyproject.toml | ||
| requirements.txt | ||
| run.py | ||
| uv.lock | ||