Plan Execute#
Source: examples/patterns/plan_execute.py
Introduction#
Plan-and-Solve and ReAct both separate planning from execution to reduce reasoning drift, while AutoGen shows how these roles can be modularized across components. This example encodes planner-executor separation with tool-backed execution and deterministic trace artifacts.
Technical Implementation#
Configure
Tracerwith JSONL + console output so each run emits machine-readable traces and lifecycle logs.Build the runtime surface (public APIs only) and execute
PlanExecutePattern.run(...)with a fixedrequest_id.Configure and invoke
Toolboxintegrations (core/script/MCP/callable) before assembling the final payload.Print a compact JSON payload including
trace_infofor deterministic tests and docs examples.
flowchart LR
A["Input prompt or scenario"] --> B["main(): runtime wiring"]
B --> C["PlanExecutePattern.run(...)"]
C --> D["Planner and executor phases share tool/runtime state"]
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 """Run planner-executor orchestration with tracing."""
20 # Fixed request ids keep trace paths and sample output stable for docs/tests.
21 request_id = "example-workflow-plan-execute-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 planner/executor pattern using public runtime surfaces. Using this with statement will
29 # automatically 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 executor_delegate = drag.MultiStepAgent(
32 mode="json",
33 llm_client=llm_client,
34 tool_runtime=tool_runtime,
35 max_steps=3,
36 allowed_tools=("text.word_count",),
37 tracer=tracer,
38 )
39 workflow = drag.PlanExecutePattern(
40 llm_client=llm_client,
41 tool_runtime=tool_runtime,
42 executor_delegate=executor_delegate,
43 max_iterations=1,
44 tracer=tracer,
45 )
46 result = workflow.run(
47 prompt=(
48 "Create and execute a one-step plan that uses text.word_count to count the words "
49 "in the phrase 'design system research workflow', then return only word_count."
50 ),
51 request_id=request_id,
52 )
53
54 # Print the results
55 summary = result.summary()
56 print(json.dumps(summary, ensure_ascii=True, indent=2, sort_keys=True))
57
58
59if __name__ == "__main__":
60 main()
Expected Results#
Run Command
PYTHONPATH=src python3 examples/patterns/plan_execute.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"
}
}