Skip to content

orchestrator

diapason.agents.orchestrator

OrchestratorAgent — multi-turn agent with tool-calling loop.

Supports two modes:

  • function_calling (default): Uses OpenAI-format tool definitions and parses tool_calls from the engine response.
  • structured: Uses a THOUGHT/TOOL/INPUT/FINAL_ANSWER text format (like ReAct) with a canonical system prompt from the orchestrator prompt registry. This is the format used by the SFT/GRPO training pipelines, making the Orchestrator a distinctive trainable agent type.

OrchestratorAgent

Bases: ToolUsingAgent

Multi-turn agent that routes between tools and the LLM.

Implements a tool-calling loop: 1. Send messages with tool definitions to the engine. 2. If the response contains tool_calls, execute them and loop. 3. If no tool_calls, return the final answer. 4. Stop after max_turns iterations.

In structured mode the agent instead uses a THOUGHT: / TOOL: / INPUT: / FINAL_ANSWER: text protocol identical to the format used by the orchestrator SFT/GRPO training pipelines.