import * as _langchain_langgraph0 from "@langchain/langgraph";
import { AnnotationRoot, CompiledStateGraph, StateGraph } from "@langchain/langgraph";
import { AgentNameMode, CreateReactAgentParams, withAgentName } from "@langchain/langgraph/prebuilt";
import * as _langchain_core_messages0 from "@langchain/core/messages";
import { DynamicTool, StructuredToolInterface } from "@langchain/core/tools";
import { LanguageModelLike } from "@langchain/core/language_models/base";
import { RunnableToolLike } from "@langchain/core/runnables";
import { InteropZodType } from "@langchain/core/utils/types";
import { RemoteGraph } from "@langchain/langgraph/remote";

//#region src/supervisor.d.ts
type OutputMode = "full_history" | "last_message";
/** @inline */
type CreateSupervisorParams<AnnotationRootT extends AnnotationRoot<any>, StructuredResponseFormat extends Record<string, any> = Record<string, any>> = {
  /**
   * List of agents to manage.
   * Accepts compiled graphs from both `createReactAgent` (`@langchain/langgraph`)
   * and `createAgent` (`langchain`) via `.graph`.
   */
  agents: (CompiledStateGraph<AnnotationRootT["State"], AnnotationRootT["Update"], string, AnnotationRootT["spec"], AnnotationRootT["spec"]> | CompiledStateGraph<any, any, string, any, any> | RemoteGraph)[];
  /**
   * Language model to use for the supervisor
   */
  llm: LanguageModelLike;
  /**
   * Tools to use for the supervisor
   */
  tools?: (StructuredToolInterface | RunnableToolLike | DynamicTool)[];
  /**
   * An optional prompt for the supervisor. Can be one of:
   * - `string`: This is converted to a SystemMessage and added to the beginning of the list of messages in state["messages"]
   * - `SystemMessage`: this is added to the beginning of the list of messages in state["messages"]
   * - `Function`: This function should take in full graph state and the output is then passed to the language model
   * - `Runnable`: This runnable should take in full graph state and the output is then passed to the language model
   */
  prompt?: CreateReactAgentParams["prompt"];
  /**
   * An optional schema for the final supervisor output.
   *
   * If provided, output will be formatted to match the given schema and returned in the 'structuredResponse' state key.
   * If not provided, `structuredResponse` will not be present in the output state.
   *
   * Can be passed in as:
   *   - Zod schema
   *   - JSON schema
   *   - { prompt, schema }, where schema is one of the above.
   *        The prompt will be used together with the model that is being used to generate the structured response.
   *
   * @remarks
   * **Important**: `responseFormat` requires the model to support `.withStructuredOutput()`.
   *
   * **Note**: The graph will make a separate call to the LLM to generate the structured response after the agent loop is finished.
   * This is not the only strategy to get structured responses, see more options in [this guide](https://langchain-ai.github.io/langgraph/how-tos/react-agent-structured-output/).
   */
  responseFormat?: InteropZodType<StructuredResponseFormat> | {
    prompt: string;
    schema: InteropZodType<StructuredResponseFormat> | Record<string, unknown>;
  } | Record<string, unknown>;
  /**
   * State schema to use for the supervisor graph
   */
  stateSchema?: AnnotationRootT;
  /**
   * Context schema to use for the supervisor graph
   */
  contextSchema?: AnnotationRootT;
  /**
   * Mode for adding managed agents' outputs to the message history in the multi-agent workflow.
   * Can be one of:
   * - `"full_history"`: add the entire agent message history
   * - `"last_message"`: add only the last message (default)
   */
  outputMode?: OutputMode;
  /**
   * Whether to add the supervisor-to-agent handoff messages (the supervisor
   * `AIMessage` containing the handoff tool call and the handoff `ToolMessage`)
   * to the message history forwarded to the expert agent. If `false`, those
   * handoff bookkeeping messages are omitted from the expert agent's message
   * history. This is useful for providers that strictly validate tool-call
   * message sequences. Defaults to `true`.
   */
  addHandoffMessages?: boolean;
  /**
   * Whether to add a pair of (AIMessage, ToolMessage) to the message history
   * when returning control to the supervisor to indicate that a handoff has occurred
   * Defaults to the value of `addHandoffMessages`.
   */
  addHandoffBackMessages?: boolean;
  /**
   * Name of the supervisor node
   */
  supervisorName?: string;
  /**
   * Use to specify how to expose the agent name to the underlying supervisor LLM.
   * - `undefined`: Relies on the LLM provider using the name attribute on the AI message. Currently, only OpenAI supports this.
   * - `"inline"`: Add the agent name directly into the content field of the AI message using XML-style tags.
   *   Example: "How can I help you" -> "<name>agent_name</name><content>How can I help you?</content>"
   */
  includeAgentName?: AgentNameMode;
  /**
   * An optional node to add before the LLM node in the supervisor agent (i.e., the node that calls the LLM).
   * Useful for managing long message histories (e.g., message trimming, summarization, etc.).
   *
   * Pre-model hook must be a callable or a runnable that takes in current graph state and returns a state update in the form of:
   * ```javascript
   * {
   *   messages: [new RemoveMessage({ id: REMOVE_ALL_MESSAGES }), ...],
   *   llmInputMessages: [...]
   *   ...
   * }
   * ```
   * **Important**: At least one of `messages` or `llmInputMessages` MUST be provided and will be used as an input to the `agent` node.
   * The rest of the keys will be added to the graph state.
   *
   *
   * **Warning**: If you are returning `messages` in the pre-model hook, you should OVERWRITE the `messages` key by doing the following:
   * ```javascript
   * { messages: [new RemoveMessage({ id: REMOVE_ALL_MESSAGES }), ...newMessages], ... }
   * ```
   */
  preModelHook?: CreateReactAgentParams<AnnotationRootT, StructuredResponseFormat>["preModelHook"];
  /**
   * An optional node to add after the LLM node in the supervisor agent (i.e., the node that calls the LLM).
   * Useful for implementing human-in-the-loop, guardrails, validation, or other post-processing.
   * Post-model hook must be a callable or a runnable that takes in current graph state and returns a state update.
   */
  postModelHook?: CreateReactAgentParams<AnnotationRootT, StructuredResponseFormat>["postModelHook"];
};
/**
 * Create a multi-agent supervisor.
 *
 * @param params Parameters for the supervisor.
 * @returns The supervisor graph.
 */
declare const createSupervisor: <AnnotationRootT extends AnnotationRoot<any> = AnnotationRoot<{
  messages: _langchain_langgraph0.BaseChannel<_langchain_core_messages0.BaseMessage<_langchain_core_messages0.MessageStructure<_langchain_core_messages0.MessageToolSet>, _langchain_core_messages0.MessageType>[], _langchain_langgraph0.OverwriteValue<_langchain_core_messages0.BaseMessage<_langchain_core_messages0.MessageStructure<_langchain_core_messages0.MessageToolSet>, _langchain_core_messages0.MessageType>[]> | _langchain_langgraph0.Messages, unknown>;
}>, StructuredResponseFormat extends Record<string, any> = Record<string, any>>({
  agents,
  llm,
  tools,
  prompt,
  responseFormat,
  stateSchema,
  contextSchema,
  outputMode,
  addHandoffMessages,
  addHandoffBackMessages,
  supervisorName,
  includeAgentName,
  preModelHook,
  postModelHook
}: CreateSupervisorParams<AnnotationRootT, StructuredResponseFormat>) => StateGraph<AnnotationRootT["spec"], AnnotationRootT["State"], AnnotationRootT["Update"], string, AnnotationRootT["spec"], AnnotationRootT["spec"], _langchain_langgraph0.StateDefinition, unknown, unknown, unknown>;
//#endregion
export { type AgentNameMode, CreateSupervisorParams, type OutputMode, createSupervisor, withAgentName };
//# sourceMappingURL=supervisor.d.ts.map