Chatoyant - v0.9.0
    Preparing search index...

    Interface GenerateWithToolsOptions

    Combined options for generation with tools.

    interface GenerateWithToolsOptions {
        provider?: ProviderId;
        timeout?: number;
        retries?: number;
        localBaseUrl?: string;
        localApiKey?: string;
        localTimeout?: number;
        temperature?: number;
        creativity?: CreativityLevel;
        maxTokens?: number;
        topP?: number;
        stop?: string | string[];
        frequencyPenalty?: number;
        presencePenalty?: number;
        reasoning?: ReasoningLevel;
        webSearch?: boolean;
        cache?: boolean;
        extra?: Record<string, unknown>;
        maxIterations?: number;
        toolTimeout?: number;
        onToolError?: "respond" | "throw";
        onToolCallStart?: (calls: ToolCall[]) => void;
        onToolCallComplete?: (results: ToolResult[]) => void;
    }

    Hierarchy (View Summary)

    Index

    Properties

    provider? timeout? retries? localBaseUrl? localApiKey? localTimeout? temperature? creativity? maxTokens? topP? stop? frequencyPenalty? presencePenalty? reasoning? webSearch? cache? extra? maxIterations? toolTimeout? onToolError? onToolCallStart? onToolCallComplete?

    Properties

    provider?: ProviderId

    Override the provider (auto-detected from model by default).

    timeout?: number

    Request timeout in milliseconds.

    120000
    retries?: number

    Number of retries on failure.

    3
    localBaseUrl?: string

    Base URL for the local provider. Overrides the LOCAL_BASE_URL environment variable. Required when using provider: 'local' without LOCAL_BASE_URL set.

    'http://127.0.0.1:11434/v1'  // Ollama

    'http://127.0.0.1:8765/v1'   // mlx-lm / omlx
    localApiKey?: string

    API key for the local provider. Overrides the LOCAL_API_KEY environment variable. Defaults to "local" for servers that don't validate keys.

    localTimeout?: number

    Request timeout in ms for the local provider. Defaults to 60 000 ms. Increase for slow or large local models.

    temperature?: number

    Sampling temperature (0-2). Lower = more deterministic, higher = more creative. undefined = provider default.

    Can also use semantic presets via creativity option.

    creativity?: CreativityLevel

    Semantic creativity level. Alternative to raw temperature values.

    • 'precise': Temperature 0 (deterministic)
    • 'balanced': Temperature 0.7 (default)
    • 'creative': Temperature 1.0
    • 'wild': Temperature 1.5

    If both temperature and creativity are set, temperature takes precedence.

    maxTokens?: number

    Maximum tokens to generate. undefined = provider default.

    topP?: number

    Top-p (nucleus) sampling. undefined = provider default.

    stop?: string | string[]

    Stop sequences.

    frequencyPenalty?: number

    Frequency penalty (-2 to 2).

    presencePenalty?: number

    Presence penalty (-2 to 2).

    reasoning?: ReasoningLevel

    Unified reasoning level across providers. Maps automatically to provider-specific implementations:

    • 'off': No reasoning (OpenAI: none, Anthropic: no thinking, xAI: *-non-reasoning)
    • 'low': Light reasoning (OpenAI: low, Anthropic: 2048 tokens)
    • 'medium': Moderate reasoning (OpenAI: medium, Anthropic: 8192 tokens)
    • 'high': Deep reasoning (OpenAI: high, Anthropic: 32768 tokens, xAI: *-reasoning)

    Note: Not all models support reasoning. For unsupported models, this is ignored.

    webSearch?: boolean

    Enable web search (xAI only). Ignored for other providers.

    cache?: boolean

    Enable prompt caching (Anthropic only). Marks the system prompt for caching.

    extra?: Record<string, unknown>

    Arbitrary additional options passed to the provider. Use for bleeding-edge features not yet in the typed interface.

    maxIterations?: number

    Maximum tool call iterations before stopping.

    5
    toolTimeout?: number

    Timeout for each tool execution in milliseconds.

    10000
    onToolError?: "respond" | "throw"

    How to handle tool execution errors.

    • 'respond': Send error back to model (default)
    • 'throw': Throw immediately
    'respond'
    onToolCallStart?: (calls: ToolCall[]) => void

    Callback fired when the model issues tool calls, before execution begins. Useful for showing tool activity indicators in UIs.

    onToolCallComplete?: (results: ToolResult[]) => void

    Callback fired after all tool calls in an iteration have been executed. Receives the results (including success/failure status) for each call.

    Settings

    Member Visibility

    On This Page

    Properties