@plust/datasleuth - v0.2.0
    Preparing search index...

    Interface OrchestrateOptions

    Options for the orchestration step

    interface OrchestrateOptions {
        model: LanguageModelV1;
        searchProvider?: any;
        tools?: Record<string, ResearchStep>;
        customPrompt?: string;
        maxIterations?: number;
        exitCriteria?: (state: ResearchState) => boolean | Promise<boolean>;
        includeInResults?: boolean;
        continueOnError?: boolean;
        toolSelectorFn?: (
            state: ResearchState,
            availableTools: string[],
        ) => Promise<{ toolName: string; reasoning: string }>;
        retry?: { maxRetries?: number; baseDelay?: number };
    }
    Index

    Properties

    model: LanguageModelV1

    LLM model to use for orchestration (from the AI library)

    searchProvider?: any

    Default search provider to use for search-dependent steps

    tools?: Record<string, ResearchStep>

    Map of tool names to step functions that can be used by the agent

    customPrompt?: string

    Custom prompt for the orchestration agent

    maxIterations?: number

    Maximum number of iterations

    exitCriteria?: (state: ResearchState) => boolean | Promise<boolean>

    Optional function that determines when to exit orchestration

    includeInResults?: boolean

    Whether to include the orchestration results in the final output

    continueOnError?: boolean

    Whether to continue if a tool execution fails

    toolSelectorFn?: (
        state: ResearchState,
        availableTools: string[],
    ) => Promise<{ toolName: string; reasoning: string }>

    Custom tool selection function (if provided, uses this instead of LLM)

    retry?: { maxRetries?: number; baseDelay?: number }

    Retry configuration

    Type declaration

    • OptionalmaxRetries?: number

      Maximum number of retries

    • OptionalbaseDelay?: number

      Base delay between retries in ms