feat: Gemini SDK upgrade + VideoPack schema alignment

apps/web/package.json

@@ -9,6 +9,7 @@
     "lint": "next lint"
   },
   "dependencies": {
+    "@google/genai": "^1.43.0",
     "@google/generative-ai": "^0.24.1",
     "@stripe/stripe-js": "^2.0.0",
     "@supabase/supabase-js": "^2.39.0",

apps/web/src/app/api/extract-events/route.ts

@@ -1,5 +1,5 @@
 import OpenAI from 'openai';
-import { GoogleGenerativeAI } from '@google/generative-ai';
+import { GoogleGenAI, Type } from '@google/genai';
 import { NextResponse } from 'next/server';
 
 let _openai: OpenAI | null = null;
@@ -8,13 +8,13 @@ function getOpenAI() {
   return _openai;
 }
 
-let _gemini: GoogleGenerativeAI | null = null;
+let _gemini: GoogleGenAI | null = null;
 function getGemini() {
-  if (!_gemini) _gemini = new GoogleGenerativeAI(process.env.GEMINI_API_KEY || '');
+  if (!_gemini) _gemini = new GoogleGenAI({ apiKey: process.env.GEMINI_API_KEY || '' });
   return _gemini;
 }
 
-// JSON Schema for structured extraction via Responses API
+// JSON Schema for structured extraction via OpenAI Responses API
 const extractionSchema = {
   type: 'object' as const,
   properties: {
@@ -54,6 +54,43 @@ const extractionSchema = {
   additionalProperties: false,
 };
 
+// Gemini responseSchema using @google/genai Type system
+const geminiResponseSchema = {
+  type: Type.OBJECT,
+  properties: {
+    events: {
+      type: Type.ARRAY,
+      items: {
+        type: Type.OBJECT,
+        properties: {
+          type: { type: Type.STRING, enum: ['action', 'topic', 'insight', 'tool', 'resource'] },
+          title: { type: Type.STRING },
+          description: { type: Type.STRING },
+          timestamp: { type: Type.STRING, nullable: true },
+          priority: { type: Type.STRING, enum: ['high', 'medium', 'low'] },
+        },
+        required: ['type', 'title', 'description', 'priority'],
+      },
+    },
+    actions: {
+      type: Type.ARRAY,
+      items: {
+        type: Type.OBJECT,
+        properties: {
+          title: { type: Type.STRING },
+          description: { type: Type.STRING },
+          category: { type: Type.STRING, enum: ['setup', 'build', 'deploy', 'learn', 'research', 'configure'] },
+          estimatedMinutes: { type: Type.NUMBER, nullable: true },
+        },
+        required: ['title', 'description', 'category'],
+      },
+    },
+    summary: { type: Type.STRING },
+    topics: { type: Type.ARRAY, items: { type: Type.STRING } },
+  },
+  required: ['events', 'actions', 'summary', 'topics'],
+};
+
 const SYSTEM_PROMPT = `You are an expert content analyst. Extract structured data from video transcripts.
 Be specific and practical — no vague or generic items.
 For events: classify type (action/topic/insight/tool/resource) and priority (high/medium/low).
@@ -94,15 +131,18 @@ async function extractWithOpenAI(trimmed: string, videoTitle?: string, videoUrl?
 }
 
 async function extractWithGemini(trimmed: string, videoTitle?: string, videoUrl?: string) {
-  const model = getGemini().getGenerativeModel({
+  const ai = getGemini();
+  const response = await ai.models.generateContent({
     model: 'gemini-2.0-flash',
-    generationConfig: {
-      responseMimeType: 'application/json',
+    contents: `${SYSTEM_PROMPT}\n\n${buildUserPrompt(trimmed, videoTitle, videoUrl)}`,
+    config: {
       temperature: 0.3,
+      responseMimeType: 'application/json',
+      responseSchema: geminiResponseSchema,
+      tools: [{ googleSearch: {} }],
     },
   });
-  const result = await model.generateContent(`${SYSTEM_PROMPT}\n\n${buildUserPrompt(trimmed, videoTitle, videoUrl)}`);
-  const text = result.response.text();
+  const text = response.text ?? '';
   return JSON.parse(text);
 }
 

apps/web/src/app/api/transcribe/route.ts

@@ -1,5 +1,5 @@
 import OpenAI from 'openai';
-import { GoogleGenerativeAI } from '@google/generative-ai';
+import { GoogleGenAI } from '@google/genai';
 import { NextResponse } from 'next/server';
 
 let _openai: OpenAI | null = null;
@@ -8,9 +8,9 @@ function getOpenAI() {
   return _openai;
 }
 
-let _gemini: GoogleGenerativeAI | null = null;
+let _gemini: GoogleGenAI | null = null;
 function getGemini() {
-  if (!_gemini) _gemini = new GoogleGenerativeAI(process.env.GEMINI_API_KEY || '');
+  if (!_gemini) _gemini = new GoogleGenAI({ apiKey: process.env.GEMINI_API_KEY || '' });
   return _gemini;
 }
 
@@ -121,32 +121,76 @@ Be thorough — capture all key points, quotes, and technical details.`,
       }
     }
 
-    // Strategy 3: Gemini fallback (when OpenAI unavailable)
+    // Strategy 3: Gemini with direct YouTube URL processing + Google Search grounding
     if (url && !audioUrl && process.env.GEMINI_API_KEY) {
       try {
-        const model = getGemini().getGenerativeModel({
+        const ai = getGemini();
+        const result = await ai.models.generateContent({
           model: 'gemini-2.0-flash',
-          generationConfig: { temperature: 0.2 },
+          contents: [
+            {
+              role: 'user',
+              parts: [
+                {
+                  fileData: {
+                    mimeType: 'video/*',
+                    fileUri: url,
+                  },
+                },
+                {
+                  text: 'Provide a complete, detailed transcript of this video. ' +
+                    'Include all spoken content verbatim. ' +
+                    'Include timestamps where possible in [MM:SS] format. ' +
+                    'Be thorough and comprehensive — capture every key point, quote, and technical detail.',
+                },
+              ],
+            },
+          ],
+          config: {
+            temperature: 0.2,
+            tools: [{ googleSearch: {} }],
+          },
         });
-
-        const result = await model.generateContent(
-          `You are a video content transcription assistant. ` +
-          `For the following YouTube video URL, provide a detailed transcript or content summary. ` +
-          `Include all key points, technical details, quotes, and actionable insights. ` +
-          `Be thorough and comprehensive.\n\nVideo URL: ${url}`
-        );
-        const text = result.response.text();
+        const text = result.text ?? '';
 
         if (text.length > 100) {
           return NextResponse.json({
             success: true,
             transcript: text,
-            source: 'gemini',
+            source: 'gemini-video',
             wordCount: text.split(/\s+/).length,
           });
         }
       } catch (e) {
-        console.warn('Gemini transcript fallback failed:', e);
+        console.warn('Gemini video URL processing failed, trying text fallback:', e);
+
+        // Fallback: text-based Gemini with Google Search grounding
+        try {
+          const ai = getGemini();
+          const result = await ai.models.generateContent({
+            model: 'gemini-2.0-flash',
+            contents: `You are a video content transcription assistant. ` +
+              `For the following YouTube video URL, provide a detailed transcript or content summary. ` +
+              `Include all key points, technical details, quotes, and actionable insights. ` +
+              `Be thorough and comprehensive.\n\nVideo URL: ${url}`,
+            config: {
+              temperature: 0.2,
+              tools: [{ googleSearch: {} }],
+            },
+          });
+          const text = result.text ?? '';
+
+          if (text.length > 100) {
+            return NextResponse.json({
+              success: true,
+              transcript: text,
+              source: 'gemini',
+              wordCount: text.split(/\s+/).length,
+            });
+          }
+        } catch (e2) {
+          console.warn('Gemini text fallback also failed:', e2);
+        }
       }
     }