_build_commands() — langchain Function Reference
Architecture documentation for the _build_commands() function in factory.py from the langchain codebase.
Entity Profile
Dependency Diagram
graph TD 75a07fc9_a1f8_f785_227c_5009d6f748b3["_build_commands()"] fd7a28b1_3772_169b_6524_1342f35143b1["factory.py"] 75a07fc9_a1f8_f785_227c_5009d6f748b3 -->|defined in| fd7a28b1_3772_169b_6524_1342f35143b1 f4b66c38_651c_807a_caca_41f73fbbe516["create_agent()"] f4b66c38_651c_807a_caca_41f73fbbe516 -->|calls| 75a07fc9_a1f8_f785_227c_5009d6f748b3 style 75a07fc9_a1f8_f785_227c_5009d6f748b3 fill:#6366f1,stroke:#818cf8,color:#fff
Relationship Graph
Source Code
libs/langchain_v1/langchain/agents/factory.py lines 162–201
def _build_commands(
model_response: ModelResponse,
middleware_commands: list[Command[Any]] | None = None,
) -> list[Command[Any]]:
"""Build a list of Commands from a model response and middleware commands.
The first Command contains the model response state (messages and optional
structured_response). Middleware commands are appended as-is.
Args:
model_response: The model response containing messages and optional
structured output.
middleware_commands: Commands accumulated from middleware layers during
composition (inner-first ordering).
Returns:
List of ``Command`` objects ready to be returned from a model node.
"""
state: dict[str, Any] = {"messages": model_response.result}
if model_response.structured_response is not None:
state["structured_response"] = model_response.structured_response
for cmd in middleware_commands or []:
if cmd.goto:
msg = (
"Command goto is not yet supported in wrap_model_call middleware. "
"Use the jump_to state field with before_model/after_model hooks instead."
)
raise NotImplementedError(msg)
if cmd.resume:
msg = "Command resume is not yet supported in wrap_model_call middleware."
raise NotImplementedError(msg)
if cmd.graph:
msg = "Command graph is not yet supported in wrap_model_call middleware."
raise NotImplementedError(msg)
commands: list[Command[Any]] = [Command(update=state)]
commands.extend(middleware_commands or [])
return commands
Domain
Subdomains
Called By
Source
Frequently Asked Questions
What does _build_commands() do?
_build_commands() is a function in the langchain codebase, defined in libs/langchain_v1/langchain/agents/factory.py.
Where is _build_commands() defined?
_build_commands() is defined in libs/langchain_v1/langchain/agents/factory.py at line 162.
What calls _build_commands()?
_build_commands() is called by 1 function(s): create_agent.
Analyze Your Own Codebase
Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.
Try Supermodel Free