Voice

import { CopilotKit } from "@copilotkit/react-core/v2";
import { VoiceChat } from "./voice-chat";

export default function VoiceDemoPage() {
  return (
    <CopilotKit
      runtimeUrl="/api/copilotkit-voice"
      agent="voice-demo"
      useSingleEndpoint={false}
      // The dev-only `<cpk-web-inspector>` overlay (auto-enabled on
      // localhost via shouldShowDevConsole) intercepts pointer events
      // on top of the voice sample-audio button, so dev/D5 probe runs
      // can't click it through Playwright. Production isn't localhost
      // so the inspector never mounts there — voice is D5 in prod and
      // D4 locally for this reason alone. Disable explicitly here so
      // the demo behaves the same in both environments.
      enableInspector={false}
    >
      <VoiceChat />
    </CopilotKit>
  );
}

export function SampleAudioButton({
  onTranscribed,
  sampleText,
}: SampleAudioButtonProps) {
  return (
    <button
      type="button"
      data-testid="voice-sample-audio-button"
      onClick={() => onTranscribed(sampleText)}
      title={`Inserts: "${sampleText}"`}
      className="inline-flex w-fit items-center gap-2 rounded-md border border-black/10 bg-white px-3 py-1.5 text-xs font-medium hover:bg-black/5 dark:border-white/10 dark:bg-black/30 dark:hover:bg-white/10"
    >
      <span aria-hidden>🎙</span>
      <span>Try a sample audio</span>
    </button>
  );
}

import type { NextRequest } from "next/server";
import {
  CopilotRuntime,
  TranscriptionService,
  createCopilotRuntimeHandler,
} from "@copilotkit/runtime/v2";
import type { TranscribeFileOptions } from "@copilotkit/runtime/v2";
import { LangGraphAgent } from "@copilotkit/runtime/langgraph";
import { TranscriptionServiceOpenAI } from "@copilotkit/voice";
import OpenAI from "openai";

const LANGGRAPH_URL =
  process.env.LANGGRAPH_DEPLOYMENT_URL || "http://localhost:8123";

const voiceDemoAgent = new LangGraphAgent({
  deploymentUrl: LANGGRAPH_URL,
  graphId: "sample_agent",
});

/**
 * Transcription service wrapper that reports a clean, typed auth error when
 * OPENAI_API_KEY is not configured. When the key is present we delegate to
 * the real OpenAI-backed service; any upstream Whisper error keeps its
 * natural categorization.
 *
 * Note: We pin `baseURL` to real OpenAI (or `OPENAI_TRANSCRIPTION_BASE_URL`
 * when explicitly set) instead of falling through to `OPENAI_BASE_URL`. In
 * local docker / Railway preview environments `OPENAI_BASE_URL` points at
 * aimock so LLM completions stay deterministic, but aimock has a catchall
 * `endpoint: "transcription"` fixture that would otherwise intercept every
 * real mic recording and return the canned "What is the weather in Tokyo?"
 * phrase regardless of what the user actually said. The sample-audio button
 * is the deterministic affordance (synchronous text injection); the mic is
 * the only path that should exercise real Whisper.
 */
class GuardedOpenAITranscriptionService extends TranscriptionService {
  private delegate: TranscriptionServiceOpenAI | null;

  constructor() {
    super();
    const apiKey = process.env.OPENAI_API_KEY;
    const baseURL =
      process.env.OPENAI_TRANSCRIPTION_BASE_URL ?? "https://api.openai.com/v1";
    this.delegate = apiKey
      ? new TranscriptionServiceOpenAI({
          openai: new OpenAI({ apiKey, baseURL }),
        })
      : null;
  }

  async transcribeFile(options: TranscribeFileOptions): Promise<string> {
    if (!this.delegate) {
      // "api key" substring → handleTranscribe maps to AUTH_FAILED → 401.
      throw new Error(
        "OPENAI_API_KEY not configured for this deployment (api key missing). " +
          "Set OPENAI_API_KEY to enable voice transcription.",
      );
    }
    return this.delegate.transcribeFile(options);
  }
}

// Cache the runtime + handler across invocations so the transcription service
// is constructed once per Node process instead of per request. The guarded
// service reads OPENAI_API_KEY lazily in its transcribeFile call path, so
// deferring construction past module load is not required for cold-start
// safety under missing-key conditions.
let cachedHandler: ((req: Request) => Promise<Response>) | null = null;
function getHandler(): (req: Request) => Promise<Response> {
  if (cachedHandler) return cachedHandler;

  const runtime = new CopilotRuntime({
    // @ts-ignore -- Published CopilotRuntime agents type wraps Record in
    // MaybePromise<NonEmptyRecord<...>> which rejects plain Records; fixed in
    // source, pending release.
    agents: {
      // The page mounts <CopilotKit agent="voice-demo">; resolve that to
      // the neutral sample_agent graph.
      "voice-demo": voiceDemoAgent,
      // useAgent() with no args defaults to "default"; alias so any internal
      // default-agent lookups resolve against the same graph.
      default: voiceDemoAgent,
    },
    transcriptionService: new GuardedOpenAITranscriptionService(),
  });

  cachedHandler = createCopilotRuntimeHandler({
    runtime,
    basePath: "/api/copilotkit-voice",
  });
  return cachedHandler;
}

// Next.js App Router bindings. This file lives at
// `src/app/api/copilotkit-voice/[[...slug]]/route.ts` — the catchall slug
// pattern forwards every sub-path (`/info`, `/agent/:id/run`,
// `/transcribe`, ...) to the V2 handler so its URL router can dispatch.
export const POST = (req: NextRequest) => getHandler()(req);
export const GET = (req: NextRequest) => getHandler()(req);
export const PUT = (req: NextRequest) => getHandler()(req);
export const DELETE = (req: NextRequest) => getHandler()(req);

import type { NextRequest } from "next/server";
import {
  CopilotRuntime,
  TranscriptionService,
  createCopilotRuntimeHandler,
} from "@copilotkit/runtime/v2";
import type { TranscribeFileOptions } from "@copilotkit/runtime/v2";
import { LangGraphAgent } from "@copilotkit/runtime/langgraph";
import { TranscriptionServiceOpenAI } from "@copilotkit/voice";
import OpenAI from "openai";

const LANGGRAPH_URL =
  process.env.LANGGRAPH_DEPLOYMENT_URL || "http://localhost:8123";

const voiceDemoAgent = new LangGraphAgent({
  deploymentUrl: LANGGRAPH_URL,
  graphId: "sample_agent",
});

/**
 * Transcription service wrapper that reports a clean, typed auth error when
 * OPENAI_API_KEY is not configured. When the key is present we delegate to
 * the real OpenAI-backed service; any upstream Whisper error keeps its
 * natural categorization.
 *
 * Note: We pin `baseURL` to real OpenAI (or `OPENAI_TRANSCRIPTION_BASE_URL`
 * when explicitly set) instead of falling through to `OPENAI_BASE_URL`. In
 * local docker / Railway preview environments `OPENAI_BASE_URL` points at
 * aimock so LLM completions stay deterministic, but aimock has a catchall
 * `endpoint: "transcription"` fixture that would otherwise intercept every
 * real mic recording and return the canned "What is the weather in Tokyo?"
 * phrase regardless of what the user actually said. The sample-audio button
 * is the deterministic affordance (synchronous text injection); the mic is
 * the only path that should exercise real Whisper.
 */
class GuardedOpenAITranscriptionService extends TranscriptionService {
  private delegate: TranscriptionServiceOpenAI | null;

  constructor() {
    super();
    const apiKey = process.env.OPENAI_API_KEY;
    const baseURL =
      process.env.OPENAI_TRANSCRIPTION_BASE_URL ?? "https://api.openai.com/v1";
    this.delegate = apiKey
      ? new TranscriptionServiceOpenAI({
          openai: new OpenAI({ apiKey, baseURL }),
        })
      : null;
  }

  async transcribeFile(options: TranscribeFileOptions): Promise<string> {
    if (!this.delegate) {
      // "api key" substring → handleTranscribe maps to AUTH_FAILED → 401.
      throw new Error(
        "OPENAI_API_KEY not configured for this deployment (api key missing). " +
          "Set OPENAI_API_KEY to enable voice transcription.",
      );
    }
    return this.delegate.transcribeFile(options);
  }
}