langgraph_agent_toolkit.agents.blueprints.deep_agent.agent module

Build a Deep Agent with thread-scoped virtual files and optional MCP tools.

langgraph_agent_toolkit.agents.blueprints.deep_agent.agent.create_model()[source][source]

Select the model at worker startup without changing shared settings.

Return type:

BaseChatModel

langgraph_agent_toolkit.agents.blueprints.deep_agent.agent.build_graph(extra_tools=(), *, model=None, subagents=None, interrupt_on=None, backend=None, offload_binary_content=False, store=None, permissions=None, skills=None, memory=None, tool_selection=None, selector_model=None, extra_middleware=())[source][source]

Create a graph for the service or an embedded application.

The service assigns its configured checkpointer after MCP discovery. The default backend keeps virtual files in that conversation. It does not open host files, create a shell, or configure a cross-thread memory store. Custom tools and compiled subagents retain their operator-defined access. An injected backend retains its operator-defined access and storage scope. Binary offloading requires external storage at /blobs/. The operator must keep that storage available for checkpoint restoration. Earlier checkpoints can still contain the original media. Checkpoint deletion does not delete external blobs. The caller manages the lifecycle of an injected store. Pass store when binary content uses a StoreBackend. Permissions apply to built-in file tools. They do not restrict custom tools. Skills and memory paths refer to trusted files in the configured backend. Async subagents require a separate Agent Protocol server.

Parameters:

  • extra_tools (Sequence[BaseTool])

  • model (BaseChatModel | None)

  • subagents (Sequence[SubAgent | CompiledSubAgent | AsyncSubAgent] | None)

  • interrupt_on (dict[str, bool | InterruptOnConfig] | None)

  • backend (BackendProtocol | None)

  • offload_binary_content (bool)

  • store (BaseStore | None)

  • permissions (list[FilesystemPermission] | None)

  • skills (list[str] | None)

  • memory (list[str] | None)

  • tool_selection (ToolSelectionConfig | None)

  • selector_model (BaseChatModel | None)

  • extra_middleware (Sequence[AgentMiddleware])

Return type:

CompiledStateGraph