import {z} from 'zod'

export type V1GroqConfig = {temperature?: number | undefined};

export type V1TranscribeConfigAudioEncoding = 'AUDIO_ENCODING_UNSPECIFIED' | 'AUTO_DETECT' | 'LINEAR16' | 'MP3' | 'OGG_OPUS' | 'FLAC';

export type V1VoiceProfileConfig = {enableVoiceProfile: boolean, topN?: number | undefined};

export type V1InworldSttV1Config = {minEndOfTurnSilenceWhenConfident?: number | undefined, vadThreshold?: number | undefined};

export type V1TranscribeConfig = {groqConfig: V1GroqConfig, modelId: string, audioEncoding: V1TranscribeConfigAudioEncoding, language?: string | undefined, sampleRateHertz?: number | undefined, numberOfChannels?: number | undefined, inactivityTimeoutSeconds?: number | undefined, endOfTurnConfidenceThreshold?: number | undefined, prompts?: Array<string> | undefined, includeWordTimestamps?: boolean | undefined, enableSpeakerDiarization?: boolean | undefined, voiceProfileConfig?: V1VoiceProfileConfig | undefined} | {inworldSttV1Config: V1InworldSttV1Config, modelId: string, audioEncoding: V1TranscribeConfigAudioEncoding, language?: string | undefined, sampleRateHertz?: number | undefined, numberOfChannels?: number | undefined, inactivityTimeoutSeconds?: number | undefined, endOfTurnConfidenceThreshold?: number | undefined, prompts?: Array<string> | undefined, includeWordTimestamps?: boolean | undefined, enableSpeakerDiarization?: boolean | undefined, voiceProfileConfig?: V1VoiceProfileConfig | undefined} | {modelId: string, audioEncoding: V1TranscribeConfigAudioEncoding, language?: string | undefined, sampleRateHertz?: number | undefined, numberOfChannels?: number | undefined, inactivityTimeoutSeconds?: number | undefined, endOfTurnConfidenceThreshold?: number | undefined, prompts?: Array<string> | undefined, includeWordTimestamps?: boolean | undefined, enableSpeakerDiarization?: boolean | undefined, voiceProfileConfig?: V1VoiceProfileConfig | undefined};

export type Sttv1AudioContent = {content: string};

export type V1TranscribeSpeechRequest = {transcribeConfig: V1TranscribeConfig, audioData: Sttv1AudioContent};

export type CreateApiSttV1TranscribeArgs = {body: V1TranscribeSpeechRequest};

export type CreateApiSttV1TranscribeOptions = {baseUrl?: string | undefined, inworldBasic?: string | undefined, fetch?: typeof fetch | undefined};

export const transcriptionWordTimestamp = z.object({word: z.string().optional(), confidence: z.number().optional(), startTimeMs: z.number().int().optional(), endTimeMs: z.number().int().optional(), speaker: z.number().int().optional()});

export const v1Transcription = z.object({transcript: z.string().optional(), isFinal: z.boolean().optional(), wordTimestamps: z.array(transcriptionWordTimestamp).optional()});

export const inworldsttv1Usage = z.object({transcribedAudioMs: z.number().int().optional(), modelId: z.string().optional()});

export const v1TranscribeSpeechResponse = z.object({transcription: v1Transcription.optional(), usage: inworldsttv1Usage.optional()});

export const validateResponse = async <Output>(
  schema: {
    readonly '~standard': {
      readonly validate: (value: unknown) => ({ readonly value: Output; readonly issues?: undefined } | { readonly issues: ReadonlyArray<{ readonly message: string; readonly path?: ReadonlyArray<PropertyKey | { readonly key: PropertyKey }> | undefined }> }) | Promise<{ readonly value: Output; readonly issues?: undefined } | { readonly issues: ReadonlyArray<{ readonly message: string; readonly path?: ReadonlyArray<PropertyKey | { readonly key: PropertyKey }> | undefined }> }>
    }
  },
  value: unknown
): Promise<Output> => {
  const result = await schema['~standard'].validate(value)

  if (result.issues !== undefined) {
    const detail = result.issues
      .map(({ message, path }) =>
        path?.length
          ? `${path.map((segment) => String(typeof segment === 'object' ? segment.key : segment)).join('.')}: ${message}`
          : message
      )
      .join('; ')

    throw new Error(`Response does not match the schema: ${detail}`, { cause: { issues: result.issues } })
  }

  return result.value
};

/**
 * Get Speech-to-Text transcription synchronously
 * 
 * POST /stt/v1/transcribe
 */
export const createApiSttV1Transcribe = async (args: CreateApiSttV1TranscribeArgs, options?: CreateApiSttV1TranscribeOptions) => {
const {baseUrl = "https://api.inworld.ai", fetch: fetchFn = fetch, inworldBasic} = options ?? {}

const query = new URLSearchParams()
const headers = new Headers()
headers.set('content-type', "application/json")
headers.set('accept', "application/json")

if (inworldBasic !== undefined) headers.set("Authorization", inworldBasic)

const url = `${baseUrl.replace(/\/+$/, '')}/stt/v1/transcribe${query.size > 0 ? `?${query}` : ''}`

const res = await fetchFn(url, {method: "POST", headers, body: JSON.stringify(args.body)})

if (!res.ok) throw new Error(`Request failed with status ${res.status}`, {cause: {status: res.status, body: await res.text()}})

return validateResponse(v1TranscribeSpeechResponse, await res.json())
};