import type { AssistantMessageEventStream } from "./utils/event-stream.js";
export type { AssistantMessageEventStream } from "./utils/event-stream.js";
export type KnownApi = "openai-completions" | "mistral-conversations" | "openai-responses" | "azure-openai-responses" | "openai-codex-responses" | "anthropic-messages" | "bedrock-converse-stream" | "google-generative-ai" | "google-gemini-cli" | "google-vertex";
export type Api = KnownApi | (string & {});
export type KnownProvider = "amazon-bedrock" | "anthropic" | "google" | "google-gemini-cli" | "google-antigravity" | "google-vertex" | "openai" | "azure-openai-responses" | "openai-codex" | "github-copilot" | "xai" | "groq" | "cerebras" | "openrouter" | "vercel-ai-gateway" | "mistral" | "minimax" | "minimax-cn" | "huggingface" | "opencode" | "opencode-go" | "kimi-coding" | "kimi-coding-oauth";
export type Provider = KnownProvider | string;
export type ThinkingLevel = "minimal" | "low" | "medium" | "high" | "xhigh" | "max";
/** Token budgets for each thinking level (token-based providers only) */
export interface ThinkingBudgets {
    minimal?: number;
    low?: number;
    medium?: number;
    high?: number;
}
export type CacheRetention = "none" | "short" | "long";
export type Transport = "sse" | "websocket" | "auto";
/** Explicit credential transport for providers that support multiple auth schemes. */
export type AuthMode = "api-key" | "bearer";
export interface StreamOptions {
    temperature?: number;
    maxTokens?: number;
    signal?: AbortSignal;
    apiKey?: string;
    /**
     * Preferred transport for providers that support multiple transports.
     * Providers that do not support this option ignore it.
     */
    transport?: Transport;
    /**
     * Prompt cache retention preference. Providers map this to their supported values.
     * Default: "short".
     */
    cacheRetention?: CacheRetention;
    /**
     * Optional session identifier for providers that support session-based caching.
     * Providers can use this to enable prompt caching, request routing, or other
     * session-aware features. Ignored by providers that don't support it.
     */
    sessionId?: string;
    /**
     * Optional callback for inspecting or replacing provider payloads before sending.
     * Return undefined to keep the payload unchanged.
     */
    onPayload?: (payload: unknown, model: Model<Api>) => unknown | undefined | Promise<unknown | undefined>;
    /**
     * Optional custom HTTP headers to include in API requests.
     * Merged with provider defaults; can override default headers.
     * Not supported by all providers (e.g., AWS Bedrock uses SDK auth).
     */
    headers?: Record<string, string>;
    /**
     * Maximum delay in milliseconds to wait for a retry when the server requests a long wait.
     * If the server's requested delay exceeds this value, the request fails immediately
     * with an error containing the requested delay, allowing higher-level retry logic
     * to handle it with user visibility.
     * Default: 60000 (60 seconds). Set to 0 to disable the cap.
     */
    maxRetryDelayMs?: number;
    /**
     * Optional metadata to include in API requests.
     * Providers extract the fields they understand and ignore the rest.
     * For example, Anthropic uses `user_id` for abuse tracking and rate limiting.
     */
    metadata?: Record<string, unknown>;
    /**
     * Optional callback for non-fatal warnings during streaming (e.g. malformed JSON chunks).
     * Called by providers when errors are caught but don't terminate the stream.
     * The session layer wires this to surface warnings in the conversation.
     */
    onWarning?: (code: string, message: string) => void;
}
export type ProviderStreamOptions = StreamOptions & Record<string, unknown>;
export interface SimpleStreamOptions extends StreamOptions {
    reasoning?: ThinkingLevel;
    /** Custom token budgets for thinking levels (token-based providers only) */
    thinkingBudgets?: ThinkingBudgets;
    /**
     * Controls how thinking content is returned by providers that support it.
     * "summarized": return summarized thinking text. "omitted": return empty thinking
     * with only an encrypted signature (lower latency, nothing to display).
     * Only honored by adaptive-thinking Anthropic/Bedrock Claude models; ignored elsewhere.
     * When unset, the provider default applies (Opus 4.7+ default to "omitted").
     */
    thinkingDisplay?: "summarized" | "omitted";
}
export type StreamFunction<TApi extends Api = Api, TOptions extends StreamOptions = StreamOptions> = (model: Model<TApi>, context: Context, options?: TOptions) => AssistantMessageEventStream;
export interface TextSignatureV1 {
    v: 1;
    id: string;
    phase?: "commentary" | "final_answer";
}
export interface TextContent {
    type: "text";
    text: string;
    textSignature?: string;
}
export interface ThinkingContent {
    type: "thinking";
    thinking: string;
    thinkingSignature?: string;
    /** When true, the thinking content was redacted by safety filters. The opaque
     *  encrypted payload is stored in `thinkingSignature` so it can be passed back
     *  to the API for multi-turn continuity. */
    redacted?: boolean;
}
export interface ImageContent {
    type: "image";
    data: string;
    mimeType: string;
}
export interface ToolCall {
    type: "toolCall";
    id: string;
    name: string;
    arguments: Record<string, any>;
    thoughtSignature?: string;
}
export interface Usage {
    input: number;
    output: number;
    cacheRead: number;
    cacheWrite: number;
    totalTokens: number;
    cost: {
        input: number;
        output: number;
        cacheRead: number;
        cacheWrite: number;
        total: number;
    };
}
export type StopReason = "stop" | "length" | "toolUse" | "error" | "aborted";
export interface UserMessage {
    role: "user";
    content: string | (TextContent | ImageContent)[];
    timestamp: number;
}
export interface AssistantMessage {
    role: "assistant";
    content: (TextContent | ThinkingContent | ToolCall)[];
    api: Api;
    provider: Provider;
    model: string;
    responseId?: string;
    usage: Usage;
    stopReason: StopReason;
    errorMessage?: string;
    timestamp: number;
    durationMs?: number;
}
export interface ToolResultMessage<TDetails = any> {
    role: "toolResult";
    toolCallId: string;
    toolName: string;
    content: (TextContent | ImageContent)[];
    details?: TDetails;
    isError: boolean;
    timestamp: number;
}
export type Message = UserMessage | AssistantMessage | ToolResultMessage;
import type { TSchema } from "@sinclair/typebox";
export interface Tool<TParameters extends TSchema = TSchema> {
    name: string;
    description: string;
    parameters: TParameters;
}
export interface Context {
    systemPrompt?: string;
    messages: Message[];
    tools?: Tool[];
}
/**
 * Event protocol for AssistantMessageEventStream.
 *
 * Streams should emit `start` before partial updates, then terminate with either:
 * - `done` carrying the final successful AssistantMessage, or
 * - `error` carrying the final AssistantMessage with stopReason "error" or "aborted"
 *   and errorMessage.
 */
export type AssistantMessageEvent = {
    type: "start";
    partial: AssistantMessage;
} | {
    type: "text_start";
    contentIndex: number;
    partial: AssistantMessage;
} | {
    type: "text_delta";
    contentIndex: number;
    delta: string;
    partial: AssistantMessage;
} | {
    type: "text_end";
    contentIndex: number;
    content: string;
    partial: AssistantMessage;
} | {
    type: "thinking_start";
    contentIndex: number;
    partial: AssistantMessage;
} | {
    type: "thinking_delta";
    contentIndex: number;
    delta: string;
    partial: AssistantMessage;
} | {
    type: "thinking_end";
    contentIndex: number;
    content: string;
    partial: AssistantMessage;
} | {
    type: "toolcall_start";
    contentIndex: number;
    partial: AssistantMessage;
} | {
    type: "toolcall_delta";
    contentIndex: number;
    delta: string;
    partial: AssistantMessage;
} | {
    type: "toolcall_end";
    contentIndex: number;
    toolCall: ToolCall;
    partial: AssistantMessage;
} | {
    type: "done";
    reason: Extract<StopReason, "stop" | "length" | "toolUse">;
    message: AssistantMessage;
} | {
    type: "error";
    reason: Extract<StopReason, "aborted" | "error">;
    error: AssistantMessage;
};
/**
 * Compatibility settings for OpenAI-compatible completions APIs.
 * Use this to override URL-based auto-detection for custom providers.
 */
export interface OpenAICompletionsCompat {
    /** Whether the provider supports the `store` field. Default: auto-detected from URL. */
    supportsStore?: boolean;
    /** Whether the provider supports the `developer` role (vs `system`). Default: auto-detected from URL. */
    supportsDeveloperRole?: boolean;
    /** Whether the provider supports `reasoning_effort`. Default: auto-detected from URL. */
    supportsReasoningEffort?: boolean;
    /** Optional mapping from dreb reasoning levels to provider/model-specific `reasoning_effort` values. */
    reasoningEffortMap?: Partial<Record<ThinkingLevel, string>>;
    /** Whether the provider supports `stream_options: { include_usage: true }` for token usage in streaming responses. Default: true. */
    supportsUsageInStreaming?: boolean;
    /** Which field to use for max tokens. Default: auto-detected from URL. */
    maxTokensField?: "max_completion_tokens" | "max_tokens";
    /** Whether tool results require the `name` field. Default: auto-detected from URL. */
    requiresToolResultName?: boolean;
    /** Whether a user message after tool results requires an assistant message in between. Default: auto-detected from URL. */
    requiresAssistantAfterToolResult?: boolean;
    /** Whether thinking blocks must be converted to text blocks with <thinking> delimiters. Default: auto-detected from URL. */
    requiresThinkingAsText?: boolean;
    /** Format for reasoning/thinking parameter. "openai" uses reasoning_effort, "openrouter" uses reasoning: { effort }, "zai" uses top-level enable_thinking: boolean, "qwen" uses top-level enable_thinking: boolean, "qwen-chat-template" uses chat_template_kwargs.enable_thinking plus a top-level mapped reasoning_effort (Qwen3.8+ models default-map dreb levels onto the native low/medium/xhigh tiers), and "kimi" uses nested thinking: { type, effort? } plus prompt_cache_key. Default: "openai". */
    thinkingFormat?: "openai" | "openrouter" | "zai" | "qwen" | "qwen-chat-template" | "kimi";
    /** OpenRouter-specific routing preferences. Only used when baseUrl points to OpenRouter. */
    openRouterRouting?: OpenRouterRouting;
    /** Vercel AI Gateway routing preferences. Only used when baseUrl points to Vercel AI Gateway. */
    vercelGatewayRouting?: VercelGatewayRouting;
    /** Whether the provider supports the `strict` field in tool definitions. Default: true. */
    supportsStrictMode?: boolean;
}
/** Compatibility settings for OpenAI Responses APIs. */
export interface OpenAIResponsesCompat {
}
/**
 * OpenRouter provider routing preferences.
 * Controls which upstream providers OpenRouter routes requests to.
 * @see https://openrouter.ai/docs/provider-routing
 */
export interface OpenRouterRouting {
    /** List of provider slugs to exclusively use for this request (e.g., ["amazon-bedrock", "anthropic"]). */
    only?: string[];
    /** List of provider slugs to try in order (e.g., ["anthropic", "openai"]). */
    order?: string[];
}
/**
 * Vercel AI Gateway routing preferences.
 * Controls which upstream providers the gateway routes requests to.
 * @see https://vercel.com/docs/ai-gateway/models-and-providers/provider-options
 */
export interface VercelGatewayRouting {
    /** List of provider slugs to exclusively use for this request (e.g., ["bedrock", "anthropic"]). */
    only?: string[];
    /** List of provider slugs to try in order (e.g., ["anthropic", "openai"]). */
    order?: string[];
}
export interface Model<TApi extends Api> {
    id: string;
    name: string;
    api: TApi;
    provider: Provider;
    baseUrl: string;
    reasoning: boolean;
    input: ("text" | "image")[];
    cost: {
        input: number;
        output: number;
        cacheRead: number;
        cacheWrite: number;
    };
    contextWindow: number;
    maxTokens: number;
    headers?: Record<string, string>;
    /**
     * Model identifier sent to the API when it differs from the registry id.
     * Used by context-tiered models such as Kimi K3, where dreb exposes a
     * single user-facing model (`k3`) but sends the cheaper 256k variant
     * (`k3-256k`) on the wire until the session context outgrows it.
     */
    wireModelId?: string;
    /** Explicit auth transport. When unset, the provider's default and token heuristics apply. */
    authMode?: AuthMode;
    /** Compatibility overrides for OpenAI-compatible APIs. If not set, auto-detected from baseUrl. */
    compat?: TApi extends "openai-completions" ? OpenAICompletionsCompat : TApi extends "openai-responses" ? OpenAIResponsesCompat : never;
}
//# sourceMappingURL=types.d.ts.map