import { z } from 'zod';
/**
 * How a GR00T embodiment is named when selecting one: a tag string, its
 * numeric `cat_id` (0..31), or an object carrying either plus an optional
 * camera-count override. Mirrors the addon's `VlaEmbodimentSelector`.
 *
 * On the load path (`config.embodiment`) an object naming neither `tag` nor
 * `catId` is allowed — the GGUF's default embodiment is used, with only the
 * `numCameras` override applied.
 */
export declare const vlaEmbodimentSelectorSchema: z.ZodUnion<readonly [z.ZodString, z.ZodNumber, z.ZodObject<{
    tag: z.ZodOptional<z.ZodString>;
    catId: z.ZodOptional<z.ZodNumber>;
    numCameras: z.ZodOptional<z.ZodNumber>;
}, z.core.$strip>]>;
export type VlaEmbodimentSelector = z.input<typeof vlaEmbodimentSelectorSchema>;
/**
 * The selector shape `vlaSetEmbodiment` accepts: a switch must name an
 * embodiment, so the neither-tag-nor-catId object form is rejected here
 * (matching the addon's `setEmbodiment` validation).
 */
export declare const vlaEmbodimentSelectionSchema: z.ZodUnion<readonly [z.ZodString, z.ZodNumber, z.ZodObject<{
    tag: z.ZodOptional<z.ZodString>;
    catId: z.ZodOptional<z.ZodNumber>;
    numCameras: z.ZodOptional<z.ZodNumber>;
}, z.core.$strip>]>;
/**
 * The static type matching `vlaEmbodimentSelectionSchema`. Hand-written
 * because zod refinements don't narrow the inferred type — `z.input` of the
 * schema would still allow the load-path-only `{ numCameras }` / `{}`
 * spellings that the switch schema rejects at runtime. The `never` fields
 * encode "exactly one of tag / catId" structurally.
 */
export type VlaEmbodimentSelection = string | number | {
    tag: string;
    catId?: never;
    numCameras?: number;
} | {
    catId: number;
    tag?: never;
    numCameras?: number;
};
export declare const vlaConfigSchema: z.ZodObject<{
    backend: z.ZodOptional<z.ZodArray<z.ZodEnum<{
        cpu: "cpu";
        auto: "auto";
        cuda: "cuda";
        vulkan: "vulkan";
        metal: "metal";
        opencl: "opencl";
        hip: "hip";
        rocm: "rocm";
        sycl: "sycl";
    }>>>;
    verbosity: z.ZodOptional<z.ZodNumber>;
    embodiment: z.ZodOptional<z.ZodUnion<readonly [z.ZodString, z.ZodNumber, z.ZodObject<{
        tag: z.ZodOptional<z.ZodString>;
        catId: z.ZodOptional<z.ZodNumber>;
        numCameras: z.ZodOptional<z.ZodNumber>;
    }, z.core.$strip>]>>;
}, z.core.$strip>;
export type VlaConfig = z.input<typeof vlaConfigSchema>;
export declare const vlaHparamsSchema: z.ZodObject<{
    chunkSize: z.ZodNumber;
    actionDim: z.ZodNumber;
    maxActionDim: z.ZodNumber;
    maxStateDim: z.ZodNumber;
    tokenizerMaxLength: z.ZodNumber;
    visionImageSize: z.ZodNumber;
    numCameras: z.ZodOptional<z.ZodNumber>;
    stateInputMode: z.ZodOptional<z.ZodEnum<{
        discrete: "discrete";
        continuous: "continuous";
    }>>;
    imageInputMode: z.ZodOptional<z.ZodEnum<{
        pixels: "pixels";
        patches: "patches";
    }>>;
    imagePatchElems: z.ZodOptional<z.ZodNumber>;
    selectedEmbodimentTag: z.ZodOptional<z.ZodString>;
    selectedEmbodimentCatId: z.ZodOptional<z.ZodNumber>;
}, z.core.$strip>;
export type VlaHparams = z.infer<typeof vlaHparamsSchema>;
export declare const vlaStatsSchema: z.ZodObject<{
    vision_ms: z.ZodOptional<z.ZodNumber>;
    prefill_compute_ms: z.ZodOptional<z.ZodNumber>;
    prefill_total_ms: z.ZodOptional<z.ZodNumber>;
    smollm2_compute_ms: z.ZodOptional<z.ZodNumber>;
    smollm2_total_ms: z.ZodOptional<z.ZodNumber>;
    ode_ms: z.ZodOptional<z.ZodNumber>;
    total_ms: z.ZodOptional<z.ZodNumber>;
    backendDevice: z.ZodOptional<z.ZodNumber>;
}, z.core.$strip>;
export type VlaStats = z.infer<typeof vlaStatsSchema>;
export declare const vlaRunRequestSchema: z.ZodObject<{
    type: z.ZodLiteral<"vlaRun">;
    modelId: z.ZodString;
    images: z.ZodArray<z.ZodString>;
    imgWidth: z.ZodNumber;
    imgHeight: z.ZodNumber;
    state: z.ZodString;
    tokens: z.ZodString;
    mask: z.ZodString;
    noise: z.ZodOptional<z.ZodString>;
}, z.core.$strip>;
export type VlaRunRequest = z.input<typeof vlaRunRequestSchema>;
export declare const vlaRunResponseSchema: z.ZodObject<{
    actions: z.ZodString;
    actionDim: z.ZodNumber;
    chunkSize: z.ZodNumber;
    stats: z.ZodOptional<z.ZodObject<{
        vision_ms: z.ZodOptional<z.ZodNumber>;
        prefill_compute_ms: z.ZodOptional<z.ZodNumber>;
        prefill_total_ms: z.ZodOptional<z.ZodNumber>;
        smollm2_compute_ms: z.ZodOptional<z.ZodNumber>;
        smollm2_total_ms: z.ZodOptional<z.ZodNumber>;
        ode_ms: z.ZodOptional<z.ZodNumber>;
        total_ms: z.ZodOptional<z.ZodNumber>;
        backendDevice: z.ZodOptional<z.ZodNumber>;
    }, z.core.$strip>>;
}, z.core.$strip>;
export type VlaRunResponse = z.infer<typeof vlaRunResponseSchema>;
export declare const vlaHparamsRequestSchema: z.ZodObject<{
    type: z.ZodLiteral<"vlaHparams">;
    modelId: z.ZodString;
}, z.core.$strip>;
export type VlaHparamsRequest = z.input<typeof vlaHparamsRequestSchema>;
export declare const vlaHparamsResponseSchema: z.ZodObject<{
    hparams: z.ZodObject<{
        chunkSize: z.ZodNumber;
        actionDim: z.ZodNumber;
        maxActionDim: z.ZodNumber;
        maxStateDim: z.ZodNumber;
        tokenizerMaxLength: z.ZodNumber;
        visionImageSize: z.ZodNumber;
        numCameras: z.ZodOptional<z.ZodNumber>;
        stateInputMode: z.ZodOptional<z.ZodEnum<{
            discrete: "discrete";
            continuous: "continuous";
        }>>;
        imageInputMode: z.ZodOptional<z.ZodEnum<{
            pixels: "pixels";
            patches: "patches";
        }>>;
        imagePatchElems: z.ZodOptional<z.ZodNumber>;
        selectedEmbodimentTag: z.ZodOptional<z.ZodString>;
        selectedEmbodimentCatId: z.ZodOptional<z.ZodNumber>;
    }, z.core.$strip>;
    backendName: z.ZodNullable<z.ZodString>;
}, z.core.$strip>;
export type VlaHparamsResponse = z.infer<typeof vlaHparamsResponseSchema>;
export declare const vlaSetEmbodimentRequestSchema: z.ZodObject<{
    type: z.ZodLiteral<"vlaSetEmbodiment">;
    modelId: z.ZodString;
    embodiment: z.ZodUnion<readonly [z.ZodString, z.ZodNumber, z.ZodObject<{
        tag: z.ZodOptional<z.ZodString>;
        catId: z.ZodOptional<z.ZodNumber>;
        numCameras: z.ZodOptional<z.ZodNumber>;
    }, z.core.$strip>]>;
}, z.core.$strip>;
export type VlaSetEmbodimentRequest = z.input<typeof vlaSetEmbodimentRequestSchema>;
export declare const vlaSetEmbodimentResponseSchema: z.ZodObject<{
    hparams: z.ZodObject<{
        chunkSize: z.ZodNumber;
        actionDim: z.ZodNumber;
        maxActionDim: z.ZodNumber;
        maxStateDim: z.ZodNumber;
        tokenizerMaxLength: z.ZodNumber;
        visionImageSize: z.ZodNumber;
        numCameras: z.ZodOptional<z.ZodNumber>;
        stateInputMode: z.ZodOptional<z.ZodEnum<{
            discrete: "discrete";
            continuous: "continuous";
        }>>;
        imageInputMode: z.ZodOptional<z.ZodEnum<{
            pixels: "pixels";
            patches: "patches";
        }>>;
        imagePatchElems: z.ZodOptional<z.ZodNumber>;
        selectedEmbodimentTag: z.ZodOptional<z.ZodString>;
        selectedEmbodimentCatId: z.ZodOptional<z.ZodNumber>;
    }, z.core.$strip>;
}, z.core.$strip>;
export type VlaSetEmbodimentResponse = z.infer<typeof vlaSetEmbodimentResponseSchema>;
export interface VlaClientRunParams {
    modelId: string;
    images: Float32Array[];
    imgWidth: number;
    imgHeight: number;
    state: Float32Array;
    tokens: Int32Array;
    mask: Uint8Array;
    noise?: Float32Array;
}
export interface VlaClientRunResult {
    actions: Float32Array;
    actionDim: number;
    chunkSize: number;
    stats?: VlaStats;
}