adb151fbe6
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. |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| graph_builder.py | ||
| oasis_profile_generator.py | ||
| ontology_generator.py | ||
| report_agent.py | ||
| simulation_config_generator.py | ||
| simulation_ipc.py | ||
| simulation_manager.py | ||
| simulation_runner.py | ||
| text_processor.py | ||
| zep_entity_reader.py | ||
| zep_graph_memory_updater.py | ||
| zep_tools.py | ||