mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-04-25 00:16:23 +02:00
Introduce an agent orchestrator service that supports three execution patterns (ReAct, plan-then-execute, supervisor) with LLM-based meta-routing to select the appropriate pattern and task type per request. Update the agent schema to support orchestration fields (correlation, sub-agents, plan steps) and remove legacy response fields (answer, thought, observation). |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| conftest.py | ||
| test_agent_service_non_streaming.py | ||
| test_agent_step_arguments.py | ||
| test_conversation_state.py | ||
| test_mcp_tool_auth.py | ||
| test_react_processor.py | ||
| test_reasoning_engine.py | ||
| test_tool_coordination.py | ||
| test_tool_filter.py | ||
| test_tool_service.py | ||
| test_tool_service_lifecycle.py | ||