Router Delegate#

Source: examples/patterns/router_delegate.py

Introduction#

RouteLLM motivates specialized route selection, AutoGen demonstrates multi-agent delegation patterns, and Human-AI collaboration by design frames why explicit routing supports accountable coordination. This example shows intent-based routing across direct and multi-step agents using a shared runtime surface.

Technical Implementation#

  1. Configure Tracer with JSONL + console output so each run emits machine-readable traces and lifecycle logs.

  2. Build the runtime surface (public APIs only) and execute RouterDelegatePattern.run(...) with a fixed request_id.

  3. Configure and invoke Toolbox integrations (core/script/MCP/callable) before assembling the final payload.

  4. Print a compact JSON payload including trace_info for deterministic tests and docs examples.

        flowchart LR
    A["Input prompt or scenario"] --> B["main(): runtime wiring"]
    B --> C["RouterDelegatePattern.run(...)"]
    C --> D["router delegates to specialized agent surfaces"]
    C --> E["Tracer JSONL + console events"]
    D --> F["ExecutionResult/payload"]
    E --> F
    F --> G["Printed JSON output"]
    
 1from __future__ import annotations
 2
 3import json
 4from pathlib import Path
 5
 6import design_research_agents as drag
 7
 8_EXAMPLE_LLAMA_CLIENT_KWARGS = {
 9    "model": "Qwen_Qwen3-4B-Instruct-2507-Q4_K_M.gguf",
10    "hf_model_repo_id": "bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF",
11    "api_model": "qwen3-4b-instruct-2507-q4km",
12    "context_window": 8192,
13    "startup_timeout_seconds": 240.0,
14    "request_timeout_seconds": 240.0,
15}
16
17
18def main() -> None:
19    """Route one design prompt to the best delegate and print summary."""
20    # Fixed request id keeps traces and docs output deterministic across runs.
21    request_id = "example-workflow-router-delegate-design-001"
22    tracer = drag.Tracer(
23        enabled=True,
24        trace_dir=Path("artifacts/examples/traces"),
25        enable_jsonl=True,
26        enable_console=True,
27    )
28    # Run the router/delegate pattern using public runtime surfaces. Using this with statement will automatically
29    # shut down the managed client and tool runtime when the example is done.
30    with drag.Toolbox() as tool_runtime, drag.LlamaCppServerLLMClient(**_EXAMPLE_LLAMA_CLIENT_KWARGS) as llm_client:
31        direct_llm_agent = drag.DirectLLMCall(llm_client=llm_client, tracer=tracer)
32        json_tool_agent = drag.MultiStepAgent(
33            mode="json",
34            llm_client=llm_client,
35            tool_runtime=tool_runtime,
36            max_steps=3,
37            allowed_tools=("text.word_count",),
38            tracer=tracer,
39        )
40
41        workflow = drag.RouterDelegatePattern(
42            llm_client=llm_client,
43            tool_runtime=tool_runtime,
44            alternatives={
45                "direct_llm_agent": direct_llm_agent,
46                "json_tool_agent": json_tool_agent,
47            },
48            alternative_descriptions={
49                "direct_llm_agent": "Use for concise textual design summaries with no runtime tools.",
50                "json_tool_agent": ("Use for design requests needing runtime text analysis or tool calls."),
51            },
52            tracer=tracer,
53        )
54
55        result = workflow.run(
56            prompt=(
57                "Count the words in the phrase 'modular field service workflow' using the "
58                "appropriate delegate and return only the word_count."
59            ),
60            request_id=request_id,
61        )
62
63    # Print the results
64    summary = result.summary()
65    print(json.dumps(summary, ensure_ascii=True, indent=2, sort_keys=True))
66
67
68if __name__ == "__main__":
69    main()

Expected Results#

Run Command

PYTHONPATH=src python3 examples/patterns/router_delegate.py

Example output shape (values vary by run):

{
  "success": true,
  "final_output": "<example-specific payload>",
  "terminated_reason": "<string-or-null>",
  "error": null,
  "trace": {
    "request_id": "<request-id>",
    "trace_dir": "artifacts/examples/traces",
    "trace_path": "artifacts/examples/traces/run_<timestamp>_<request_id>.jsonl"
  }
}

References#