LLMs sometimes fabricate <tool_result> blocks inside their own responses, polluting the message history with invented data that subsequent iterations treat as authoritative. This adds _strip_fake_tool_results() which removes any such blocks before the assistant response is appended to history. |
||
|---|---|---|
| .. | ||
| app | ||
| scripts | ||
| pyproject.toml | ||
| requirements.txt | ||
| run.py | ||
| uv.lock | ||