1d96b09875
When the LLM generates a <tool_call> block followed by a self-generated <tool_result> block in the same response, the fake result must be stripped before appending to message history. The real tool result will be injected separately by the system. This fixes a React Hallucination bug where models could fabricate tool results that didn't actually come from tool invocations. |
||
|---|---|---|
| .. | ||
| __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 | ||