B.Tech-Project-III/thirdeye/meet_extension/content.js

/**
 * ThirdEye Meet Recorder — Content Script
 * Injected into meet.google.com pages.
 * Uses Web Speech API (Chrome built-in) for live transcription.
 * Buffers transcript and POSTs chunks to ThirdEye backend every CHUNK_INTERVAL_MS.
 */

const CHUNK_INTERVAL_MS = 30000; // Send a chunk every 30 seconds
const MAX_BUFFER_CHARS = 8000;   // ~2000 tokens — safe for LLM processing

let recognition = null;
let isRecording = false;
let transcriptBuffer = "";
let meetingId = null;
let backendUrl = "http://localhost:8000";
let ingestSecret = "thirdeye_meet_secret_change_me";
let groupId = "meet_sessions";
let chunkTimer = null;
let chunkCount = 0;

// --- Helpers ---

function getMeetingId() {
  // Extract meeting code from URL: meet.google.com/abc-defg-hij
  const match = window.location.pathname.match(/\/([a-z]{3}-[a-z]{4}-[a-z]{3})/i);
  if (match) return match[1];
  // Fallback: use timestamp-based ID
  return `meet_${Date.now()}`;
}

function getParticipantName() {
  // Try to find the user's own name from the Meet DOM
  const nameEl = document.querySelector('[data-self-name]');
  if (nameEl) return nameEl.getAttribute('data-self-name');
  const profileEl = document.querySelector('img[data-iml]');
  if (profileEl && profileEl.alt) return profileEl.alt;
  return "Unknown";
}

// --- Transport ---

async function sendChunkToBackend(text, isFinal = false) {
  if (!text || text.trim().length < 10) return; // Don't send near-empty chunks

  const payload = {
    meeting_id: meetingId,
    group_id: groupId,
    chunk_index: chunkCount++,
    text: text.trim(),
    speaker: getParticipantName(),
    timestamp: new Date().toISOString(),
    is_final: isFinal,
  };

  try {
    const res = await fetch(`${backendUrl}/api/meet/ingest`, {
      method: "POST",
      headers: {
        "Content-Type": "application/json",
        "X-ThirdEye-Secret": ingestSecret,
      },
      body: JSON.stringify(payload),
    });

    if (!res.ok) {
      console.warn(`[ThirdEye] Backend rejected chunk: ${res.status}`);
    } else {
      console.log(`[ThirdEye] Chunk ${payload.chunk_index} sent (${text.length} chars)`);
      chrome.runtime.sendMessage({
        type: "CHUNK_SENT",
        chunkIndex: payload.chunk_index,
        charCount: text.length,
        meetingId: meetingId,
      });
    }
  } catch (err) {
    console.warn(`[ThirdEye] Failed to send chunk: ${err.message}`);
    // Buffer is NOT cleared on failure — next flush will include this text
    transcriptBuffer = text + "\n" + transcriptBuffer;
  }
}

// --- Periodic flush ---

function flushBuffer() {
  if (transcriptBuffer.trim().length > 0) {
    sendChunkToBackend(transcriptBuffer);
    transcriptBuffer = "";
  }
}

function startChunkTimer() {
  if (chunkTimer) clearInterval(chunkTimer);
  chunkTimer = setInterval(flushBuffer, CHUNK_INTERVAL_MS);
}

function stopChunkTimer() {
  if (chunkTimer) {
    clearInterval(chunkTimer);
    chunkTimer = null;
  }
}

// --- Web Speech API ---

function initSpeechRecognition() {
  const SpeechRecognition = window.SpeechRecognition || window.webkitSpeechRecognition;

  if (!SpeechRecognition) {
    console.error("[ThirdEye] Web Speech API not available in this browser.");
    chrome.runtime.sendMessage({ type: "ERROR", message: "Web Speech API not supported." });
    return null;
  }

  const rec = new SpeechRecognition();
  rec.continuous = true;       // Don't stop after first pause
  rec.interimResults = true;   // Get partial results while speaking
  rec.lang = "en-US";          // Change if needed
  rec.maxAlternatives = 1;

  rec.onstart = () => {
    console.log("[ThirdEye] Speech recognition started.");
    chrome.runtime.sendMessage({ type: "STATUS", status: "recording", meetingId });
  };

  rec.onresult = (event) => {
    let newText = "";
    for (let i = event.resultIndex; i < event.results.length; i++) {
      const result = event.results[i];
      if (result.isFinal) {
        newText += result[0].transcript + " ";
      }
      // We only accumulate FINAL results to avoid duplicates from interim results
    }

    if (newText.trim()) {
      transcriptBuffer += newText;
      // Guard: if buffer is getting huge, flush early
      if (transcriptBuffer.length > MAX_BUFFER_CHARS) {
        flushBuffer();
      }
    }
  };

  rec.onerror = (event) => {
    console.warn(`[ThirdEye] Speech recognition error: ${event.error}`);
    if (event.error === "not-allowed") {
      chrome.runtime.sendMessage({
        type: "ERROR",
        message: "Microphone permission denied. Allow mic access in Chrome settings.",
      });
    } else if (event.error !== "no-speech") {
      // Restart on non-fatal errors
      setTimeout(() => { if (isRecording) rec.start(); }, 1000);
    }
  };

  rec.onend = () => {
    console.log("[ThirdEye] Speech recognition ended.");
    if (isRecording) {
      // Auto-restart: Chrome's Web Speech API stops after ~60s of silence
      setTimeout(() => { if (isRecording) rec.start(); }, 250);
    }
  };

  return rec;
}

// --- Public controls (called from popup via chrome.tabs.sendMessage) ---

async function startRecording(config = {}) {
  if (isRecording) return;

  // Load config from storage or use provided values
  const stored = await chrome.storage.sync.get(["backendUrl", "ingestSecret", "groupId"]);
  backendUrl = config.backendUrl || stored.backendUrl || "http://localhost:8000";
  ingestSecret = config.ingestSecret || stored.ingestSecret || "thirdeye_meet_secret_change_me";
  groupId = config.groupId || stored.groupId || "meet_sessions";

  meetingId = getMeetingId();
  chunkCount = 0;
  transcriptBuffer = "";
  isRecording = true;

  recognition = initSpeechRecognition();
  if (!recognition) {
    isRecording = false;
    return;
  }

  recognition.start();
  startChunkTimer();

  // Notify backend that a new meeting has started
  try {
    await fetch(`${backendUrl}/api/meet/start`, {
      method: "POST",
      headers: {
        "Content-Type": "application/json",
        "X-ThirdEye-Secret": ingestSecret,
      },
      body: JSON.stringify({
        meeting_id: meetingId,
        group_id: groupId,
        started_at: new Date().toISOString(),
        speaker: getParticipantName(),
      }),
    });
  } catch (err) {
    console.warn("[ThirdEye] Could not notify backend of meeting start:", err.message);
  }
}

async function stopRecording() {
  if (!isRecording) return;

  isRecording = false;
  stopChunkTimer();

  if (recognition) {
    recognition.stop();
    recognition = null;
  }

  // Send the final buffered chunk marked as final
  await sendChunkToBackend(transcriptBuffer, true);
  transcriptBuffer = "";

  chrome.runtime.sendMessage({ type: "STATUS", status: "stopped", meetingId });
  console.log("[ThirdEye] Recording stopped.");
}

// --- Message listener (from popup) ---

chrome.runtime.onMessage.addListener((msg, sender, sendResponse) => {
  if (msg.type === "START_RECORDING") {
    startRecording(msg.config || {}).then(() => sendResponse({ ok: true }));
    return true; // async
  }
  if (msg.type === "STOP_RECORDING") {
    stopRecording().then(() => sendResponse({ ok: true }));
    return true;
  }
  if (msg.type === "GET_STATUS") {
    sendResponse({
      isRecording,
      meetingId,
      bufferLength: transcriptBuffer.length,
      chunkCount,
    });
    return true;
  }
});

console.log("[ThirdEye] Content script loaded on", window.location.href);