Podcast Generator Implementation

GEMINI.md

@@ -14,65 +14,8 @@ When executing an implementation plan, after a phase is completed, ask the user
 
 If asked to use icons or pictures in your app (for example hero images or background images) generate them with the Nano Banana extension 
 
-## SQLAlchemy Database interactions coding guidelines
-
-When using SQLAlchemy with Python and Flask, all database models and queries must adhere to the modern **SQLAlchemy 2.0** style. The legacy query API from `Flask-SQLAlchemy` (`Model.query`) is forbidden.
-
-### 1. Model Definition
-
-Models must be defined using `sqlalchemy.orm.Mapped` and `sqlalchemy.orm.mapped_column` with type annotations.
-
-**Bad (Legacy Style):**
-```python
-class User(db.Model):
-    id = db.Column(db.Integer, primary_key=True)
-    email = db.Column(db.String(40), unique=True, nullable=False)
-```
-
-**Good (Modern SQLAlchemy 2.0 Style):**
-```python
-import sqlalchemy as sa
-import sqlalchemy.orm as so
-
-class User(db.Model):
-    id: so.Mapped[int] = so.mapped_column(primary_key=True)
-    email: so.Mapped[str] = so.mapped_column(sa.String(40), unique=True)
-```
-
-### 2. Database Queries
-
-All queries must be constructed using the `sqlalchemy.select()` function. Do not use the `Model.query` object.
-
-**Bad (Legacy `Model.query`):**
-```python
-# Get by primary key
-user = User.query.get(1)
-
-# Filter and get first
-user = User.query.filter_by(email="test@example.com").first()
-
-# Get all
-users = User.query.all()
-```
-
-**Good (Modern `select()` construct):**
-```python
-import sqlalchemy as sa
-
-# Get by primary key
-user = db.session.get(User, 1)
-
-# Filter and get first
-stmt = sa.select(User).where(User.email == "test@example.com")
-user = db.session.scalars(stmt).first()
-
-# Get all
-stmt = sa.select(User)
-users = db.session.scalars(stmt).all()
-```
-
-
-
 
+For guide on interacting with Gemini API follow the instructions in:
+@gemini-styleguide.md
 
 

IMPLEMENTATION_PLAN.md

@@ -0,0 +1,58 @@
+# 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: Project Initialization & Configuration
+- [x] Initialize a new Next.js project with Tailwind CSS (`npx create-next-app@latest podcast-generator --typescript --tailwind --eslint`).
+- [x] Install project dependencies: `npm install google-genai rss-parser uuid`.
+- [x] Create a `.env.local` file for environment variables (`GOOGLE_API_KEY`, `PROJECT_ID`).
+- [x] Generate a Hero Image ("Robot Agent in TV Studio") using the Nano Banana extension and save it to `public/hero-image.png`.
+- [x] Verify the application runs locally (`npm run dev`).
+
+## Phase 2: Data Layer & API - Feeds
+- [x] Create a utility module `lib/store.ts` to handle reading/writing to a local JSON file (`data/db.json`) for data persistence. Define the `Feed` and `Podcast` interfaces here.
+- [x] Implement the API route `GET /api/feeds` to retrieve the list of stored feeds.
+- [x] Implement the API route `POST /api/feeds` to add a new feed. This must use `rss-parser` to validate the URL and fetch the feed title before saving.
+- [x] Implement the API route `DELETE /api/feeds` to remove a feed by ID.
+- [x] Verify API endpoints using `curl` or a tool like Postman.
+
+## Phase 3: Frontend - Layout & Feed Manager
+- [x] Update `app/layout.tsx` and `app/page.tsx` to implement the basic two-column layout. Include the Hero Image at the top.
+- [x] Create a `components/FeedManager.tsx` component. This should include:
+    - An input form to add a new RSS feed URL.
+    - A list displaying currently added feeds with a "Remove" button.
+- [x] Connect `FeedManager` to the `/api/feeds` endpoints to fetch, add, and delete feeds dynamically.
+- [x] Verify the Feed Manager UI works correctly (adding valid/invalid URLs, removing feeds).
+
+## Phase 4: API - Podcast Generation Logic
+- [x] Create the `POST /api/podcasts/generate` endpoint. This should:
+    - Accept a request to start generation.
+    - Create a new "PENDING" podcast record in the DB.
+    - Trigger the generation process asynchronously (or simulate async if Vercel limits apply, but for local use, normal async is fine).
+    - Return the `podcastId`.
+- [x] Implement the "Fetch & Filter" logic: Fetch articles from all stored feeds and filter for those published in the last 24 hours.
+- [x] Implement the "Summarization" service: Use `google-genai` (`gemini-2.5-flash`) to summarize each article into a short script segment.
+- [x] Implement the "Script Compilation" logic: specific Intro + Summaries + Outro.
+- [x] Implement the "Audio Synthesis" service: Use `google-genai` (or specific TTS endpoint if `google-genai` audio generation is distinct) to convert the full script to speech. Save the resulting audio buffer to `public/podcasts/[id].mp3`.
+- [x] Update the podcast record in `data/db.json` to "COMPLETED" with the path and duration.
+- [x] Implement `GET /api/podcasts` to list all generated podcasts.
+- [x] Implement `GET /api/podcasts/[id]` to return the status of a specific generation job.
+
+## Phase 5: Frontend - Podcast Player & History
+- [x] Create a `components/PodcastGenerator.tsx` component with a "Generate Podcast" button.
+    - It should call `/api/podcasts/generate`.
+    - It should display a loading state (spinner) while polling `/api/podcasts/[id]` until status is "COMPLETED".
+- [x] Create a `components/PodcastList.tsx` component to display the history of generated podcasts.
+- [x] Create/Integrate an `AudioPlayer` component (standard HTML5 `<audio>` tag styled with Tailwind) to play the generated files.
+- [x] Integrate these components into the main page layout.
+- [x] Verify the full flow: Add Feed -> Generate -> Wait -> Play Audio.
+
+## Phase 6: 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.

gemini-styleguide.md

@@ -0,0 +1,107 @@
+# GoogleCloudPlatform/generative-ai Style Guide
+
+The current year is 2025.
+
+## Markdown Style (For `.md` files and `.ipynb` Markdown Cells)
+
+- Use single backticks ( ` ` ) to format inline code elements, such as variable names, function names, enum names, and brief code snippets.
+- Add documentation links to the appropriate Vertex AI pages when describing product features. e.g. https://cloud.google.com/vertex-ai/generative-ai/docs
+  - Do not reference documentation from the Gemini Developer API, e.g. https://ai.google.dev/ unless there is not a suitable page in the Vertex AI documentation.
+
+---
+
+The Author block in Notebooks and Markdown should be in a format like this:
+
+For one author:
+
+| Author |
+| --- |
+| [Firstname Lastname](https://github.com/username) |
+
+For multiple authors
+
+| Authors |
+| --- |
+| [Firstname Lastname](https://github.com/username) |
+| [Firstname Lastname](https://github.com/username) |
+
+## Code Requirements
+
+- Don't include hard-coded Google Cloud project IDs, always use a placeholder like `[your-project-id]`
+
+**Correct**
+
+```py
+PROJECT_ID = "[your-project-id]"
+```
+
+***Incorrect**
+
+```py
+PROJECT_ID = "actual-projectid-1234"
+```
+
+## Golden Rule: Use the Correct and Current SDK
+
+Always use the Google Gen AI SDK to call the Gemini models, which became the
+standard library for all Gemini API interactions as of 2025. Do not use legacy
+libraries and SDKs. 3rd party integrations like LangGraph, LlamaIndex, LiteLLM are okay.
+
+- **Library Name:** Google Gen AI SDK
+- **Python Package:** `google-genai`
+- **Legacy Library**: (`google-generativeai`) is deprecated.
+
+**Installation:**
+
+- **Incorrect:** `pip install google-generativeai`
+- **Incorrect:** `pip install google-ai-generativelanguage`
+- **Correct:** `pip install google-genai`
+
+**APIs and Usage:**
+
+- **Incorrect:** `import google.generativeai as genai`-> **Correct:** `from
+    google import genai`
+- **Incorrect:** `from google.ai import generativelanguage_v1`  ->
+    **Correct:** `from google import genai`
+- **Incorrect:** `from google.generativeai` -> **Correct:** `from google
+    import genai`
+- **Incorrect:** `from google.generativeai import types` -> **Correct:** `from
+    google.genai import types`
+- **Incorrect:** `import google.generativeai as genai` -> **Correct:** `from
+    google import genai`
+- **Incorrect:** `genai.configure(api_key=...)` -> **Correct:** `client =
+    genai.Client(api_key="...")`
+- **Incorrect:** `model = genai.GenerativeModel(...)`
+- **Incorrect:** `model.generate_content(...)` -> **Correct:**
+    `client.models.generate_content(...)`
+- **Incorrect:** `response = model.generate_content(..., stream=True)` ->
+    **Correct:** `client.models.generate_content_stream(...)`
+- **Incorrect:** `genai.GenerationConfig(...)` -> **Correct:**
+    `types.GenerateContentConfig(...)`
+- **Incorrect:** `safety_settings={...}` -> **Correct:** Use `safety_settings`
+    inside a `GenerateContentConfig` object.
+- **Incorrect:** `from google.api_core.exceptions import GoogleAPIError` ->
+    **Correct:** `from google.genai.errors import APIError`
+- **Incorrect:** `types.ResponseModality.TEXT`
+
+## Models
+
+- By default, use the following models when using `google-genai`:
+  - **General Text & Multimodal Tasks:** `gemini-2.5-flash`
+  - **Coding and Complex Reasoning Tasks:** `gemini-2.5-pro`
+  - **Latency-sensitive operations:** `gemini-2.5-flash-lite`
+  - **Image Generation Tasks:** `imagen-4.0-fast-generate-001`,
+        `imagen-4.0-generate-001` or `imagen-4.0-ultra-generate-001`
+  - **Image Editing Tasks:** `gemini-2.5-flash-image-preview`
+  - **Video Generation Tasks:** `veo-3.0-fast-generate-preview` or
+        `veo-3.0-generate-preview`.
+
+- It is also acceptable to use following models if explicitly requested by the
+    user:
+  - **Gemini 2.0 Series**: `gemini-2.0-flash-lite`, `gemini-2.0-flash`, `gemini-2.0-pro`
+
+- Do not use the following deprecated models (or their variants like
+    `gemini-1.5-flash-latest`):
+  - **Prohibited:** `gemini-1.5-flash`
+  - **Prohibited:** `gemini-1.5-pro`
+  - **Prohibited:** `gemini-pro`

podcast-generator/.gitignore

@@ -0,0 +1,41 @@
+# 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