Interface ReactAgent<StructuredResponseFormat, StateSchema, ContextSchema, TMiddleware>

options

graph

• get graph(): AgentGraph<
      StateSchema,
      StructuredResponseFormat,
      ContextSchema,
      TMiddleware,
  >

  Get the compiled StateGraph.

  Returns AgentGraph<StateSchema, StructuredResponseFormat, ContextSchema, TMiddleware>

drawMermaid

• drawMermaid(
      params?: {
          backgroundColor?: string;
          curveStyle?: string;
          nodeColors?: Record<string, string>;
          withStyles?: boolean;
          wrapLabelNWords?: number;
      },
  ): Promise<any>

  Draw the graph as a Mermaid string.

  Parameters

  • Optionalparams: {
        backgroundColor?: string;
        curveStyle?: string;
        nodeColors?: Record<string, string>;
        withStyles?: boolean;
        wrapLabelNWords?: number;
    }

    Parameters for the drawMermaid method.

    • OptionalbackgroundColor?: string

      The background color of the graph.

    • OptionalcurveStyle?: string

      The style of the graph's curves.

    • OptionalnodeColors?: Record<string, string>

      The colors of the graph's nodes.

    • OptionalwithStyles?: boolean

      Whether to include styles in the graph.

    • OptionalwrapLabelNWords?: number

      The maximum number of words to wrap in a node's label.

  Returns Promise<any>

  Mermaid string

drawMermaidPng

• drawMermaidPng(
      params?: {
          backgroundColor?: string;
          curveStyle?: string;
          nodeColors?: Record<string, string>;
          withStyles?: boolean;
          wrapLabelNWords?: number;
      },
  ): Promise<Uint8Array<any>>

  Visualize the graph as a PNG image.

  Parameters

  • Optionalparams: {
        backgroundColor?: string;
        curveStyle?: string;
        nodeColors?: Record<string, string>;
        withStyles?: boolean;
        wrapLabelNWords?: number;
    }

    Parameters for the drawMermaidPng method.

    • OptionalbackgroundColor?: string

      The background color of the graph.

    • OptionalcurveStyle?: string

      The style of the graph's curves.

    • OptionalnodeColors?: Record<string, string>

      The colors of the graph's nodes.

    • OptionalwithStyles?: boolean

      Whether to include styles in the graph.

    • OptionalwrapLabelNWords?: number

      The maximum number of words to wrap in a node's label.

  Returns Promise<Uint8Array<any>>

  PNG image as a buffer

invoke

• invoke(
      state: any,
      config?: InvokeConfiguration<
          InferContextInput<ContextSchema> & InferMiddlewareContextInputs<
              TMiddleware,
          >,
      >,
  ): Promise<any>

  Executes the agent with the given state and returns the final state after all processing.

  This method runs the agent's entire workflow synchronously, including:

  • Processing the input messages through any configured middleware
  • Calling the language model to generate responses
  • Executing any tool calls made by the model
  • Running all middleware hooks (beforeModel, afterModel, etc.)

  Parameters

  • state: any

    The initial state for the agent execution. Can be:

    • An object containing messages array and any middleware-specific state properties
    • A Command object for more advanced control flow
  • Optionalconfig: InvokeConfiguration<
        InferContextInput<ContextSchema> & InferMiddlewareContextInputs<
            TMiddleware,
        >,
    >

    Optional runtime configuration including:

    • context

      The context for the agent execution.

    • configurable

      LangGraph configuration options like thread_id, run_id, etc.

    • store

      The store for the agent execution for persisting state, see more in Memory storage.

    • signal

      An optional AbortSignal for the agent execution.

    • recursionLimit

      The recursion limit for the agent execution.

  Returns Promise<any>

  A Promise that resolves to the final agent state after execution completes. The returned state includes: - a messages property containing an array with all messages (input, AI responses, tool calls/results) - a structuredResponse property containing the structured response (if configured) - all state values defined in the middleware

  Example

  const agent = new ReactAgent({
    llm: myModel,
    tools: [calculator, webSearch],
    responseFormat: z.object({
      weather: z.string(),
    }),
  });
  
  const result = await agent.invoke({
    messages: [{ role: "human", content: "What's the weather in Paris?" }]
  });
  
  console.log(result.structuredResponse.weather); // outputs: "It's sunny and 75°F."
  Copy

stream

• stream<
      TStreamMode extends undefined
      | StreamMode
      | StreamMode[],
      TEncoding extends undefined | "text/event-stream",
  >(
      state: any,
      config?: StreamConfiguration<
          InferContextInput<ContextSchema> & InferMiddlewareContextInputs<
              TMiddleware,
          >,
          TStreamMode,
          TEncoding,
      >,
  ): Promise<
      IterableReadableStream<
          StreamOutputMap<
              TStreamMode,
              false,
              any,
              any,
              string,
              unknown,
              unknown,
              TEncoding,
          >,
      >,
  >

  Executes the agent with streaming, returning an async iterable of state updates as they occur.

  This method runs the agent's workflow similar to invoke, but instead of waiting for completion, it streams high-level state updates in real-time. This allows you to:

  • Display intermediate results to users as they're generated
  • Monitor the agent's progress through each step
  • React to state changes as nodes complete

  For more granular event-level streaming (like individual LLM tokens), use streamEvents instead.

  Type Parameters

  • TStreamMode extends undefined | StreamMode | StreamMode[]
  • TEncoding extends undefined | "text/event-stream"

  Parameters

  • state: any

    The initial state for the agent execution. Can be:

    • An object containing messages array and any middleware-specific state properties
    • A Command object for more advanced control flow
  • Optionalconfig: StreamConfiguration<
        InferContextInput<ContextSchema> & InferMiddlewareContextInputs<
            TMiddleware,
        >,
        TStreamMode,
        TEncoding,
    >

    Optional runtime configuration including:

    • context

      The context for the agent execution.

    • configurable

      LangGraph configuration options like thread_id, run_id, etc.

    • store

      The store for the agent execution for persisting state, see more in Memory storage.

    • signal

      An optional AbortSignal for the agent execution.

    • streamMode

      The streaming mode for the agent execution, see more in Supported stream modes.

    • recursionLimit

      The recursion limit for the agent execution.

  Returns Promise<
      IterableReadableStream<
          StreamOutputMap<
              TStreamMode,
              false,
              any,
              any,
              string,
              unknown,
              unknown,
              TEncoding,
          >,
      >,
  >

  A Promise that resolves to an IterableReadableStream of state updates. Each update contains the current state after a node completes.

  Example

  const agent = new ReactAgent({
    llm: myModel,
    tools: [calculator, webSearch]
  });
  
  const stream = await agent.stream({
    messages: [{ role: "human", content: "What's 2+2 and the weather in NYC?" }]
  });
  
  for await (const chunk of stream) {
    console.log(chunk); // State update from each node
  }
  Copy