Feature: Podcast Generator Implementation

.gitignore

@@ -0,0 +1,45 @@
+# See https://help.github.com/articles/ignoring-files/ for more about ignoring files.
+
+# dependencies
+/node_modules
+/.pnp
+.pnp.*
+.yarn/*
+!.yarn/patches
+!.yarn/plugins
+!.yarn/releases
+!.yarn/versions
+
+# testing
+/coverage
+
+# next.js
+/.next/
+/out/
+
+# production
+/build
+
+# misc
+.DS_Store
+*.pem
+
+# debug
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+.pnpm-debug.log*
+
+# env files (can opt-in for committing if needed)
+.env*
+
+# vercel
+.vercel
+
+# typescript
+*.tsbuildinfo
+next-env.d.ts
+node_modules
+
+/src/generated/prisma
+*.db

IMPLEMENTATION_PLAN.md

@@ -0,0 +1,50 @@
+# Implementation Plan - Podcast Generator
+
+## Phase 0: Git Setup
+- [x] Check if the current directory is an initialized git repository.
+- [x] If it is, create and checkout a new feature branch named `podcast-generator`.
+
+## Phase 1: Environment & Project Setup
+- [x] Initialize a new Next.js project with TypeScript, Tailwind CSS, and App Router.
+- [x] Install backend dependencies: `prisma`, `@prisma/client` (or `better-sqlite3`), `rss-parser`, `fluent-ffmpeg`, `@google/generative-ai` (Gemini SDK), `@google-cloud/text-to-speech`.
+- [x] Install frontend dependencies: `lucide-react` (for icons), `axios` or use `fetch`.
+- [x] Configure Environment Variables (`.env.local`): `GOOGLE_AI_API_KEY`, `GOOGLE_APPLICATION_CREDENTIALS`, `DATABASE_URL`.
+- [x] Verify `ffmpeg` installation on the local machine.
+
+## Phase 2: Database & Data Access
+- [x] Initialize Prisma with SQLite provider (`npx prisma init --datasource-provider sqlite`).
+- [x] Define `Feed` model in `prisma/schema.prisma` (id, url, title, createdAt).
+- [x] Define `Podcast` model in `prisma/schema.prisma` (id, title, filePath, duration, createdAt, summary).
+- [x] Run migration to create the SQLite database (`npx prisma migrate dev --name init`).
+- [x] Create a `db.ts` lib file to export the singleton Prisma client instance.
+
+## Phase 3: Backend Services (Core Logic)
+- [x] **RSS Service**: Create `lib/services/rss.ts`. Implement `fetchLatestArticles(feeds)` using `rss-parser`. Filter articles from the last 24 hours.
+- [x] **AI Service (Summarization)**: Create `lib/services/gemini.ts`. Implement `generatePodcastScript(articles)` using the Gemini API. Construct the prompt as specified in the Tech Spec.
+- [x] **TTS Service (Synthesis)**: Create `lib/services/tts.ts`. Implement `synthesizeSpeech(text)` using Google Cloud TTS (Chirp model). Handle text chunking if necessary.
+- [x] **Audio Service (Processing)**: Create `lib/services/audio.ts`. Implement `concatAudioSegments(segments, outputPath)` using `fluent-ffmpeg` to merge Intro + Body + Outro.
+
+## Phase 4: API Routes
+- [x] **Feed Endpoints**: Create `app/api/feeds/route.ts` and `app/api/feeds/[id]/route.ts`. Implement GET (list), POST (add & validate), DELETE (remove).
+- [x] **Podcast Endpoints**: Create `app/api/podcasts/route.ts`. Implement GET (list history).
+- [x] **Generation Endpoint**: Create `app/api/podcasts/generate/route.ts`. Implement POST. This should orchestrate the full pipeline: Fetch RSS -> Summarize -> TTS -> Concat -> Save to DB -> Return Result.
+
+## Phase 5: Frontend - UI Components
+- [x] **Layout & Hero**: Update `app/page.tsx` with a responsive layout. Add the Hero section with the "Robot agent reading news" image (placeholder or generated).
+- [x] **Feed Manager Component**: Create `components/FeedManager.tsx`. Implement a form to add URLs and a list to display/delete current feeds. Connect to `/api/feeds`.
+- [x] **Podcast History & Player**: Create `components/PodcastPlayer.tsx`. Display a list of generated podcasts. When selected, play the audio file using the standard `<audio>` tag. Connect to `/api/podcasts`.
+- [x] **Generate Button**: Create a prominent "Generate Podcast" button in `app/page.tsx`. Connect to `/api/podcasts/generate` and handle loading states (this might take a while to process).
+
+## Phase 6: Integration & Polish
+- [x] Verify the full flow: Add Feed -> Generate -> Wait -> Play Audio.
+- [x] Add basic error handling (invalid RSS, API failures).
+- [x] Refine the Prompt engineering for Gemini to ensure the script sounds natural.
+- [x] Ensure the generated audio files are accessible publicly (saved in `public/podcasts` or served via a static route).
+
+## Phase 7: Completion & Version Control
+- [x] Verify application functionality.
+- [x] Create a `README.md` file explaining the application functions, how to interact with them, the architecture, file breakdown and how to run and test it locally.
+- [x] Add all changes to the repository (`git add .`).
+- [x] Commit the changes (`git commit -m "Complete implementation of Podcast Generator"`).
+- [x] Push the feature branch to the remote repository, creating a branch with the same name in the remote repository, using the Gemini CLI github MCP server.
+- [x] Open a pull request for the feature branch using the Gemini CLI github MCP server, leave it open for review, don't merge it.

README.md

@@ -1,94 +1,55 @@
-# Spec-Driven Development w Gemini CLI
-
-This repo has some basic assets to experiment **Spec-Driven Development** using the Gemini CLI. You will act as a developer going from a raw Functional Specification to a deployed Pull Request in a single session.
-
-## Assets
-
-* `.gemini/commands/`: Contains configuration files for custom commands (`techspec`, `plan`, `build`).
-* `GEMINI.md`: Contains project rules and guidelines.
-* `.github/workflows`: Contains CI workflow.
-* **No application code**.
+# Podcast Generator
+
+A Next.js application that generates personalized audio news podcasts from RSS feeds using Google Gemini for summarization and Google Cloud Chirp for high-quality text-to-speech.
+
+## Features
+
+- **RSS Feed Management**: Add and remove RSS feeds.
+- **AI Summarization**: Automatically fetches and summarizes the latest articles from your feeds using Gemini 1.5 Flash.
+- **Audio Generation**: Converts summaries into natural-sounding speech using Google's Chirp models.
+- **Podcast Player**: Listen to your generated daily briefings directly in the app.
+
+## Architecture
+
+- **Frontend**: Next.js (App Router), Tailwind CSS.
+- **Backend**: Next.js API Routes.
+- **Database**: SQLite (via Prisma & Better-SQLite3).
+- **AI Services**: Google Gemini API, Google Cloud Text-to-Speech.
+- **Audio Processing**: fluent-ffmpeg.
+
+## Setup
+
+1.  **Clone the repository**.
+2.  **Install dependencies**:
+    ```bash
+    npm install
+    ```
+3.  **Environment Variables**:
+    Create a `.env.local` file with the following:
+    ```env
+    GOOGLE_AI_API_KEY=your_gemini_api_key
+    GOOGLE_APPLICATION_CREDENTIALS=path/to/your/google_cloud_credentials.json
+    DATABASE_URL="file:./dev.db"
+    ```
+4.  **Database Migration**:
+    ```bash
+    npx prisma migrate dev --name init
+    ```
+5.  **Run Development Server**:
+    ```bash
+    npm run dev
+    ```
 
 ## Requirements
 
-The `GEMINI.md` configuration and custom commands require the following extensions:
-* **Google Workspace**
-* **Nano Banana**
-* **GitHub**
-
----
-
-## Step 1: The Architect Phase (/techspec)
-
-**Goal:** Transform a Functional Spec (Google Doc) into a Technical Spec (Google Doc).
-
-1. **Command:**
-   ```
-   /techspec "Name of your functional specs doc" "Your desired technology stack and requirements"
-   ```
-
-2. **What Happens:**
-    * The agent searches your Drive for the doc.
-    * It reads the requirements.
-    * It generates a **Technical Specification** including Data Models, API Routes, and Architecture based on your inputs.
-    * **Output:** It creates a *new* Google Doc titled "Technical Specification - Application name" and gives you the link.
-
----
-
-## Step 2: The Planning Phase (/plan)
-
-**Goal:** Break the Technical Spec down into an atomic Implementation Plan.
-
-1. **Command:**
-   ```
-   /plan "Name of your Tech spec doc"
-   ```
-   *(Use the exact name of the doc generated in Step 1)*
-
-2. **What Happens:**
-    * The agent reads the Tech Spec.
-    * It creates a local file `IMPLEMENTATION_PLAN.md`.
-    * It breaks the project into phases (e.g., Setup, Backend, Frontend, Polish).
-    * It defines the Git strategy.
-
----
-
-## Step 3: The Build Phase (/build)
-
-**Goal:** Execute the plan and write the code.
-
-1. **Command:**
-   ```
-   /build IMPLEMENTATION_PLAN.md "Name of your Tech spec doc"
-   ```
-
-2. **What Happens (Iterative):**
-    * **Execution:** The agent iterates through the plan, initializing the project structure and writing the application code.
-    * **Visuals:** It generates necessary visual assets (images, icons) as defined in the spec.
-    * **Progress:** It updates `IMPLEMENTATION_PLAN.md` as tasks are completed.
-
----
-
-## Step 4: Final Delivery
-
-**Goal:** Push the code and open a Pull Request.
-
-1. **Action:**
-   The `/build` command's final phase usually covers this, or you can manually instruct the agent to finalize the project.
-
-2. **What Happens:**
-    * The agent runs final checks (linting/formatting).
-    * It creates a `README.md` for the new application.
-    * It commits all changes.
-    * It pushes the feature branch to GitHub.
-    * It uses the GitHub extension to **Open a Pull Request**.
-
----
+- Node.js 18+
+- ffmpeg installed on the system.
+- Google Cloud Project with Vertex AI / Gemini API and Text-to-Speech API enabled.
 
-## Summary of Commands
+## Usage
 
-| Step | Command | Input | Output |
-| :--- | :--- | :--- | :--- |
-| **1. Spec** | `/techspec` | Functional Doc (Drive) | Tech Spec (Drive) |
-| **2. Plan** | `/plan` | Tech Spec (Drive) | `IMPLEMENTATION_PLAN.md` |
-| **3. Build** | `/build` | Plan + Tech Spec | Code, Assets, App |
+1.  Open `http://localhost:3000`.
+2.  Add RSS feed URLs (e.g., `https://rss.nytimes.com/services/xml/rss/nyt/HomePage.xml`).
+3.  Click "Generate New Episode".
+4.  Wait for the process to complete (this can take a minute).
+5.  Play the generated episode from the list.

eslint.config.mjs

@@ -0,0 +1,18 @@
+import { defineConfig, globalIgnores } from "eslint/config";
+import nextVitals from "eslint-config-next/core-web-vitals";
+import nextTs from "eslint-config-next/typescript";
+
+const eslintConfig = defineConfig([
+  ...nextVitals,
+  ...nextTs,
+  // Override default ignores of eslint-config-next.
+  globalIgnores([
+    // Default ignores of eslint-config-next:
+    ".next/**",
+    "out/**",
+    "build/**",
+    "next-env.d.ts",
+  ]),
+]);
+
+export default eslintConfig;