# Project export: FeedCast This document was generated by HackStack to give an AI agent context about a hackathon project. Sections are labeled with their provenance; content marked as truncated was cut to keep this document small. ## Project metadata - Hackathon: Cal Hacks 12.0 - Tagline: Conversational AI generated news podcast personalized to your interest and needs - Devpost: https://devpost.com/software/feedcast - GitHub: https://github.com/metahdev/feedcast - Video: https://www.youtube.com/embed/I3DDfRpzzFk?enablejsapi=1&hl=en_US&rel=0&start=&version=3&wmode=transparent - Team: 1 GitHub contributor(s) — metahdev (5 commits) ## Devpost submission (written by the team) ### Inspiration Every day, we’re flooded with articles, videos, and news, but it’s hard to keep up without getting overwhelmed. We built FeedCast to turn that chaos into clarity: personalized, bite-sized audio summaries that let you stay informed while you’re on the go. Whether you’re commuting, walking to class, or grabbing coffee, FeedCast turns downtime into learning. What It Does FeedCast creates your own AI-generated news podcast — tailored to your interests. It curates trending stories, summarizes them into natural-sounding audio, and delivers them through an intuitive iOS app with real-time voice interaction. Users can interact with the podcast information, ask follow ups and clarifying questions. How We Built It We built a full-stack iOS app powered by a FastAPI backend. The iOS app uses SwiftUI for the interface and LiveKit for real-time voice chat. On the backend, we integrated Claude AI for script generation and fact-checking, OpenAI for conversation handling, and automated audio synthesis. Supabase manages authentication, database storage, and audio hosting. Our agent system orchestrates personalized content generation using prompt engineering for high-quality, engaging results. Challenges We Ran Into Getting LiveKit working smoothly for real-time audio was tougher than expected — a lot of debugging went into stable streaming. We initially tried FetchAI for the agent system but pivoted to a custom Claude-based pipeline for better control and content quality. Balancing personalization, accuracy, and natural flow in long-form AI speech took several prompt-engineering iterations. Accomplishments We’re Proud Of Built seamless real-time AI voice interaction with LiveKit Created an end-to-end system from user preferences → curated content → audio generation Designed synchronized text transcripts that follow along with playback Achieved natural, coherent AI-generated podcast segments through prompt refinement What We Learned We deepened our understanding of prompt engineering, real-time audio streaming, and multi-agent orchestration. We also learned how to integrate AI systems with a robust FastAPI backend and SwiftUI front end. What’s Next We plan to expand beyond news — adding educational content, research topics, and custom themes. The goal is to utilize this project as a way to make small quick actions based on your personal goals from adding a to do list to writing emails. ## README (from the GitHub repository) No README available. ## Detected evidence (automated analysis) Indexed codebase: 173 recognized source files, 915 KB. - Anthropic (technology) — detected in the code - FastAPI (technology) — detected in the code - OpenAI (technology) — detected in the code - Python (language) — detected in the code - SQL (language) — detected in the code - Supabase (technology) — detected in the code - Swift (language) — detected in the code - AI coding agent: Claude Code — evidence: config files committed to the repository - AI coding agent: Codex — evidence: config files committed to the repository ## Codebase structure (from repository index) ### Files (120 of 276) ``` .gitignore ARCHITECTURE.md backend/API_USAGE_NEWS_PODCAST.md backend/check_episodes_schema.py backend/check_topic_schema.py backend/clean_agent/__init__.py backend/clean_agent/.env.example backend/clean_agent/agent_core.py backend/clean_agent/app.py backend/clean_agent/README_CLEAN.md backend/clean_agent/services/__init__.py backend/clean_agent/services/claude_service.py backend/clean_agent/services/memory_service.py backend/clean_agent/services/search_adapter.py backend/clean_agent/services/supabase_client.py backend/clean_agent/tests/__init__.py backend/clean_agent/tests/test_clean_agent.py backend/CLEANUP_SUMMARY.md backend/DEBUG_SUMMARY.md backend/generate_podcast_example.py backend/HOW_TO_GENERATE_PODCAST.md backend/IMPLEMENTATION_COMPLETE.md backend/main.py backend/podcast_generation/__init__.py backend/podcast_generation/claude_service.py backend/podcast_generation/fact_checker.py backend/podcast_generation/generator.py backend/podcast_generation/types.py backend/podcast_output.log backend/QUICK_START.md backend/REFACTORING_PODCASTS_TO_EPISODES.md backend/REQUIRED_MIGRATIONS.sql backend/routers/podcast_router.py backend/test_db_connectivity.py backend/test_db_schema_quick.py backend/test_full_end_to_end.py backend/test_output.log backend/test_real_user_episode.py CHANGES_SUMMARY.md DARK_MODE_FIXES.md feedcast-livekit/.github/workflows/ci.yaml feedcast-livekit/.gitignore feedcast-livekit/.swift-version feedcast-livekit/.swiftformat feedcast-livekit/BroadcastExtension/BroadcastExtension.entitlements feedcast-livekit/BroadcastExtension/Info.plist feedcast-livekit/BroadcastExtension/SampleHandler.swift feedcast-livekit/feedcast-agent/.dockerignore feedcast-livekit/feedcast-agent/.env.example feedcast-livekit/feedcast-agent/.github/workflows/ruff.yml feedcast-livekit/feedcast-agent/.github/workflows/template-check.yml feedcast-livekit/feedcast-agent/.github/workflows/tests.yml feedcast-livekit/feedcast-agent/.gitignore feedcast-livekit/feedcast-agent/AGENTS.md feedcast-livekit/feedcast-agent/CLAUDE.md feedcast-livekit/feedcast-agent/DEPLOY_INSTRUCTIONS.md feedcast-livekit/feedcast-agent/DEPLOY_NOW.md feedcast-livekit/feedcast-agent/Dockerfile feedcast-livekit/feedcast-agent/GEMINI.md feedcast-livekit/feedcast-agent/livekit.toml feedcast-livekit/feedcast-agent/pyproject.toml feedcast-livekit/feedcast-agent/README.md feedcast-livekit/feedcast-agent/src/__init__.py feedcast-livekit/feedcast-agent/src/agent.py feedcast-livekit/feedcast-agent/TEST_AGENT.md feedcast-livekit/feedcast-agent/tests/test_agent.py feedcast-livekit/feedcast-agent/uv.lock feedcast-livekit/feedcast-sandbox/.github/workflows/ci.yaml feedcast-livekit/feedcast-sandbox/.gitignore feedcast-livekit/feedcast-sandbox/.swift-version feedcast-livekit/feedcast-sandbox/.swiftformat feedcast-livekit/feedcast-sandbox/BroadcastExtension/BroadcastExtension.entitlements feedcast-livekit/feedcast-sandbox/BroadcastExtension/Info.plist feedcast-livekit/feedcast-sandbox/BroadcastExtension/SampleHandler.swift feedcast-livekit/feedcast-sandbox/README.md feedcast-livekit/feedcast-sandbox/VoiceAgent/App/AppView.swift feedcast-livekit/feedcast-sandbox/VoiceAgent/App/AppViewModel.swift feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/AppIcon.appiconset/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/AppIcon.solidimagestack/Back.solidimagestacklayer/Content.imageset/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/AppIcon.solidimagestack/Back.solidimagestacklayer/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/AppIcon.solidimagestack/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/AppIcon.solidimagestack/Front.solidimagestacklayer/Content.imageset/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/AppIcon.solidimagestack/Front.solidimagestacklayer/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/Colors/bg1.colorset/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/Colors/bg2.colorset/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/Colors/bg3.colorset/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/Colors/bgAccent.colorset/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/Colors/bgModerate.colorset/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/Colors/bgSerious.colorset/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/Colors/bgSuccess.colorset/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/Colors/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/Colors/fg0.colorset/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/Colors/fg1.colorset/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/Colors/fg2.colorset/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/Colors/fg3.colorset/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/Colors/fg4.colorset/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/Colors/fgAccent.colorset/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/Colors/fgModerate.colorset/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/Colors/fgSerious.colorset/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/Colors/fgSuccess.colorset/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/Colors/separator1.colorset/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/Colors/separator2.colorset/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/Colors/separatorAccent.colorset/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/Colors/separatorModerate.colorset/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/Colors/separatorSerious.colorset/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/Colors/separatorSuccess.colorset/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Assets.xcassets/Contents.json feedcast-livekit/feedcast-sandbox/VoiceAgent/Auth/TokenService.swift feedcast-livekit/feedcast-sandbox/VoiceAgent/Chat/ChatViewModel.swift feedcast-livekit/feedcast-sandbox/VoiceAgent/Chat/Message.swift feedcast-livekit/feedcast-sandbox/VoiceAgent/Chat/Receive/MessageReceiver.swift feedcast-livekit/feedcast-sandbox/VoiceAgent/Chat/Receive/TranscriptionDelegateReceiver.swift feedcast-livekit/feedcast-sandbox/VoiceAgent/Chat/Receive/TranscriptionStreamReceiver.swift feedcast-livekit/feedcast-sandbox/VoiceAgent/Chat/Send/LocalMessageSender.swift feedcast-livekit/feedcast-sandbox/VoiceAgent/Chat/Send/MessageSender.swift feedcast-livekit/feedcast-sandbox/VoiceAgent/Chat/View/ChatTextInputView.swift feedcast-livekit/feedcast-sandbox/VoiceAgent/Chat/View/ChatView.swift feedcast-livekit/feedcast-sandbox/VoiceAgent/ControlBar/ControlBar.swift feedcast-livekit/feedcast-sandbox/VoiceAgent/ControlBar/Devices/AudioDeviceSelector.swift feedcast-livekit/feedcast-sandbox/VoiceAgent/ControlBar/Devices/VideoDeviceSelector.swift [156 more files omitted for size] ``` ### Dependencies - feedcast-livekit/feedcast-agent/pyproject.toml: livekit-agents[silero,turn-detector]@~=1.2, livekit-plugins-noise-cancellation@~=0.2, python-dotenv - requirements.txt: aiohttp@>=3.8.0, anthropic@>=0.7.0, backoff@>=2.2.0, fastapi@>=0.100.0, google-api-python-client@>=2.100.0, httpx@==0.25.0, numpy@>=1.24.0, openai@>=1.0.0, pydantic@>=2.0.0, python-dotenv@>=1.0.0, requests@>=2.31.0, sentence-transformers@>=2.2.0, supabase@>=2.0.0, uagents@>=0.4.0, uvicorn@>=0.23.0 ### Recent commits (newest first) - backend working but server not up - fish integrated - Merge branch 'main' of github.com:metahdev/feedcast - merge - a livekit integration, podcast generation - 🧠 PACoS Brain: Complete system with hybrid intent classification - Remove .env file and add .gitignore for security - 1-query live_search implemented - feet ## Key source files (fetched from GitHub, selected and truncated for size) ### SWIFT_COMPILATION_FIX.md ```markdown # Swift Compilation Fixes ## Errors Fixed ### 1. ✅ Invalid redeclaration of 'TranscriptSegment' **Problem:** `TranscriptSegment` was defined in multiple files: - `OpenAIService.swift` (original definition) - `VoiceChatView.swift` (duplicate definition) **Solution:** - Removed duplicate definition from VoiceChatView.swift - Use `OpenAIService.TranscriptSegment` to reference the struct ### 2. ✅ Cannot find 'PublishDataOptions' in scope **Problem:** `PublishDataOptions` doesn't exist in LiveKit Swift SDK **Solution:** Changed from: ```swift try await room?.localParticipant.publish(data: transcriptJSON, options: PublishDataOptions( reliable: true, topic: "podcast_transcript" )) ``` To: ```swift try await room?.localParticipant.publish(data: transcriptJSON, reliable: true, topic: "podcast_transcript") ``` ### 3. ✅ Type of expression is ambiguous without a type annotation **Problem:** Swift couldn't infer types in the data channel code **Solution:** Added explicit type annotations: ```swift // Before let transcriptMessage = [ "type": "podcast_transcript", "segments": transcriptSegments.map { segment in [ "startTime": segment.startTime, "endTime": segment.endTime, "text": segment.text ] } ] as [String: Any] // After let transcriptMessage: [String: Any] = [ "type": "podcast_transcript", "segments": transcriptSegments.map { segment -> [String: Any] in return [ "startTime": segment.startTime, "endTime": segment.endTime, "text": segment.text ] } ] ``` ## Changes Made ### VoiceChatView.swift 1. **Line 480, 522:** Changed `TranscriptSegment` to `OpenAIService.TranscriptSegment` 2. **Line 525-534:** Added explicit type annotations to fix ambiguity 3. **Line 537:** Fixed data publishing API call 4. **Line 791:** Removed duplicate `TranscriptSegment` struct definition ## Result ✅ All compilation errors resolved ✅ No linter warnings ✅ Code properly references OpenAIService.TranscriptSegment ✅ Data channel publishing uses correct LiveKit API ## File Modified - `feedcast/Views/VoiceChatView.swift` ``` ### TODO.md ```markdown # Feedcast - Development TODO List ## ✅ Completed - [x] Create all data models - [x] Build service layer with dummy data - [x] Create ViewModels for state management - [x] Build Library view with grid layout - [x] Build Player view with integrated chat - [x] Build Interests management view - [x] Create comprehensive documentation - [x] Add Supabase client and configuration - [x] Integrate Supabase authentication - [x] Create beautiful onboarding flow (5 pages) - [x] Add sign up / sign in functionality - [x] Update app entry point with auth flow ## 🚧 In Progress - [ ] Install Supabase Swift SDK via SPM (MANUAL STEP - see SUPABASE_SETUP.md) - [ ] Configure Config.swift with real Supabase credentials (MANUAL STEP) - [ ] Run SQL in Supabase dashboard (MANUAL STEP) ## 📋 Pending (Post-Supabase Setup) ### Backend Integration - [ ] Update PodcastService to save podcasts to Supabase - [ ] Update ChatService to persist messages to Supabase - [ ] Add password reset functionality - [ ] Add email verification handling - [ ] Implement user profile editing ### FetchAI Integration - [ ] Set up FetchAI agent configuration - [ ] Implement podcast content generation - [ ] Implement intelligent chat responses - [ ] Add context-aware conversation handling - [ ] Implement cross-conversation learning ### LiveKit Integration - [ ] Set up LiveKit server/room - [ ] Integrate audio streaming service - [ ] Replace simulated playback with real audio - [ ] Add background audio support - [ ] Implement audio buffering ### UI/UX Enhancements - [ ] Add loading states throughout app - [ ] Add error handling UI - [ ] Add pull-to-refresh everywhere - [ ] Add empty states - [ ] Add haptic feedback - [ ] Add animations and transitions - [ ] Add dark mode support (if needed) ### Features - [ ] Implement daily podcast generation scheduling - [ ] Add podcast sharing functionality - [ ] Add podcast discovery/recommendations - [ ] Add playback history - [ ] Add offline mode - [ ] Add push notifications for daily podcasts ### Testing - [ ] Add unit tests for ViewModels - [ ] Add integration tests for services - [ ] Add UI tests for critical flows - [ ] Test authentication edge cases - [ ] Test onboarding flow completely ### Polish - [ ] Add app icon - [ ] Add launch screen - [ ] Add custom podcast cover generation - [ ] Add sound effects - [ ] Optimize performance - [ ] Add analytics ## 🎯 Immediate Next Steps (After Manual Setup) 1. **First:** Follow SUPABASE_SETUP.md to: - Add Supabase SDK - Run SQL - Configure credentials 2. **Test:** Run app and verify: - Onboarding flow works - Can create account - Can sign in - Data persists in Supabase - Interests are saved 3. **Then:** Continue with PodcastService integration ## 📝 Notes - **Onboarding is complete and beautiful!** - 5 pages with smooth UX - **Auth is fully integrated** - Sign up, sign in, data persistence - **Demo mode works** - App gracefully handles missing Supabase config - **Security i [truncated — 743 more characters] ``` ### requirements.txt ``` # PACoS Brain Dependencies uagents>=0.4.0 pydantic>=2.0.0 anthropic>=0.7.0 google-api-python-client>=2.100.0 python-dotenv>=1.0.0 requests>=2.31.0 aiohttp>=3.8.0 sentence-transformers>=2.2.0 numpy>=1.24.0 openai>=1.0.0 supabase>=2.0.0 httpx==0.25.0 backoff>=2.2.0 fastapi>=0.100.0 uvicorn>=0.23.0 ``` ### feedcast-livekit/feedcast-agent/pyproject.toml ``` [build-system] requires = ["setuptools>=61.0", "wheel"] build-backend = "setuptools.build_meta" [project] name = "agent-starter-python" version = "1.0.0" description = "Simple voice AI assistant built with LiveKit Agents for Python" requires-python = ">=3.9" dependencies = [ "livekit-agents[silero,turn-detector]~=1.2", "livekit-plugins-noise-cancellation~=0.2", "python-dotenv", ] [dependency-groups] dev = [ "pytest", "pytest-asyncio", "ruff", ] [tool.setuptools.packages.find] where = ["src"] [tool.setuptools.package-dir] "" = "src" [tool.pytest.ini_options] asyncio_mode = "auto" asyncio_default_fixture_loop_scope = "function" [tool.ruff] line-length = 88 target-version = "py39" [tool.ruff.lint] select = ["E", "F", "W", "I", "N", "B", "A", "C4", "UP", "SIM", "RUF"] ignore = ["E501"] # Line too long (handled by formatter) [tool.ruff.format] quote-style = "double" indent-style = "space" ``` ### feedcast-livekit/feedcast-agent/Dockerfile ``` # syntax=docker/dockerfile:1 # Use the official UV Python base image with Python 3.13 on Debian Bookworm # UV is a fast Python package manager that provides better performance than pip # We use the slim variant to keep the image size smaller while still having essential tools ARG PYTHON_VERSION=3.13 FROM ghcr.io/astral-sh/uv:python${PYTHON_VERSION}-bookworm-slim AS base # Keeps Python from buffering stdout and stderr to avoid situations where # the application crashes without emitting any logs due to buffering. ENV PYTHONUNBUFFERED=1 # Create a non-privileged user that the app will run under. # See https://docs.docker.com/develop/develop-images/dockerfile_best-practices/#user ARG UID=10001 RUN adduser \ --disabled-password \ --gecos "" \ --home "/app" \ --shell "/sbin/nologin" \ --uid "${UID}" \ appuser # Install build dependencies required for Python packages with native extensions # gcc: C compiler needed for building Python packages with C extensions # python3-dev: Python development headers needed for compilation # We clean up the apt cache after installation to keep the image size down RUN apt-get update && apt-get install -y \ gcc \ g++ \ python3-dev \ && rm -rf /var/lib/apt/lists/* # Create a new directory for our application code # And set it as the working directory WORKDIR /app # Copy just the dependency files first, for more efficient layer caching COPY pyproject.toml uv.lock ./ RUN mkdir -p src # Install Python dependencies using UV's lock file # --locked ensures we use exact versions from uv.lock for reproducible builds # This creates a virtual environment and installs all dependencies # Ensure your uv.lock file is checked in for consistency across environments RUN uv sync --locked # Copy all remaining application files into the container # This includes source code, configuration files, and dependency specifications # (Excludes files specified in .dockerignore) COPY . . # Change ownership of all app files to the non-privileged user # This ensures the application can read/write files as needed RUN chown -R appuser:appuser /app # Switch to the non-privileged user for all subsequent operations # This improves security by not running as root USER appuser # Pre-download any ML models or files the agent needs # This ensures the container is ready to run immediately without downloading # dependencies at runtime, which improves startup time and reliability RUN uv run src/agent.py download-files # Run the application using UV # UV will activate the virtual environment and run the agent. # The "start" command tells the worker to connect to LiveKit and begin waiting for jobs. CMD ["uv", "run", "src/agent.py", "start"] ``` ### backend/main.py ```python r""" Main FastAPI application for the Feedcast podcast generation system. Integrates all services and provides comprehensive API endpoints. """ import os import logging from typing import Dict, Any from fastapi import FastAPI, HTTPException from fastapi.middleware.cors import CORSMiddleware from fastapi.responses import JSONResponse import uvicorn from dotenv import load_dotenv # Load environment variables load_dotenv() # Import services from clean_agent.agent_core import CleanAgent from podcast_generation.clean_agent_integration import init_podcast_routes from routers.podcast_router import router as podcast_router from podcast_generation.claude_service import ClaudePodcastService from podcast_generation.fact_checker import FactChecker from podcast_generation.generator import PodcastGenerator from clean_agent.services.supabase_client import SupabaseClient # Configure logging logging.basicConfig(level=logging.INFO) logger = logging.getLogger(__name__) # Create FastAPI app app = FastAPI( title="Feedcast Podcast Generation API", description="AI-powered podcast generation system with fact-checking and personalization", version="1.0.0", docs_url="/docs", redoc_url="/redoc" ) # Configure CORS app.add_middleware( CORSMiddleware, allow_origins=["*"], # Configure appropriately for production allow_credentials=True, allow_methods=["*"], allow_headers=["*"], ) # Global service instances agent = None claude_service = None fact_checker = None podcast_generator = None supabase_client = None @app.on_event("startup") async def startup_event(): """Initialize services on startup.""" global agent, claude_service, fact_checker, podcast_generator, supabase_client logger.info("Starting up Feedcast Podcast Generation API...") try: # Initialize Clean Agent logger.info("Initializing Clean Agent...") agent = CleanAgent() # Verify Anthropic API key anthropic_key = os.getenv("ANTHROPIC_API_KEY") if not anthropic_key: logger.error("ANTHROPIC_API_KEY environment variable not set") raise HTTPException(status_code=500, detail="Anthropic API key not configured") # Initialize Supabase client logger.info("Initializing Supabase client...") try: supabase_client_instance = SupabaseClient() if not supabase_client_instance.is_connected(): logger.warning("Supabase connection failed - running in limited mode") supabase_client = None else: supabase_client = supabase_client_instance.client except Exception as e: logger.warning(f"Supabase initialization failed: {e} - running in limited mode") supabase_client = None # Initialize Claude service logger.info("Initializing Claude service...") claude_service = ClaudePodcastService(api_key=anthropic_key) # Initialize Fact Checker logger.info("Initializing Fact Checker...") fact_checker = FactChecker(claude_service) # Initialize Podcast Generator logger.info("Initializing Podcast Generator...") podcast_generator = PodcastGenerator(supabase_client, claude_service, fact_checker) logger.info("All services initialized successfully!") except Exception as e: logger.error(f"Failed to initialize services: {str(e)}") raise HTTPException(status_code=500, detail=f"Service initialization failed: {str(e)}") @app.on_event("shutdown") async def shutdown_event(): """Cleanup on shutdown.""" global claude_service logger.info("Shutting down Feedcast Podcast Generation API...") if claude_service: try: await claude_service.close() except Exception as e: logger.warning(f"Error closing Claude service: {e}") # Global exception handler @app.exception_handler(Exception) async def global_exception_handler(request, exc): """Global exception handler for unhandled errors.""" logger.error(f"Unhandled exception: {str(exc)}") return JSONResponse( status_code=500, content={"detail": "Internal server error", "error": str(exc)} ) # Add existing routes @app.get("/") async def root(): """Root endpoint.""" return { "message": "Feedcast Podcast Generation API", "version": "1.0.0", "services": { "clean_agent": "active", "podcast_generation": "active", "claude_service": "active", "fact_checker": "active" } } @app.post("/chat") async def chat(message: str): """Process a chat message.""" if not agent: raise HTTPException(status_code=500, detail="Clean Agent not initialized") try: response = await agent.process_message(message) return {"response": response} except Exception as e: logger.error(f"Chat processing error: {str(e)}") return {"error": str(e)} # Enhanced health check endpoint @app.get("/health") async def health_check(): """Comprehensive health check for all services.""" health_status = { "status": "healthy", "timestamp": "2024-01-01T00:00:00Z", # Will be updated below "services": {} } try: from datetime import datetime health_status["timestamp"] = datetime.utcnow().isoformat() # Check Clean Agent health_status["services"]["clean_agent"] = { "status": "healthy" if agent else "unhealthy", "message": "Clean Agent initialized" if agent else "Clean Agent not initialized" } # Check Supabase connection if supabase_client: try: # Test database connection result = supabase_client.table("users").select("id").limit(1).execute() health_status["serv [truncated — 4136 more characters] ``` ### backend/clean_agent/app.py ```python """ FastAPI application for the clean agent with podcast generation capabilities. """ import os import logging from typing import Dict, Any from fastapi import FastAPI, HTTPException from fastapi.middleware.cors import CORSMiddleware import uvicorn from dotenv import load_dotenv # Load environment variables load_dotenv() import sys import os sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) from agent_core import CleanAgent from podcast_generation.clean_agent_integration import init_podcast_routes from routers.podcast_router import router as podcast_router from podcast_generation.claude_service import ClaudePodcastService from podcast_generation.fact_checker import FactChecker from podcast_generation.generator import PodcastGenerator from clean_agent.services.supabase_client import SupabaseClient # Configure logging logging.basicConfig(level=logging.INFO) logger = logging.getLogger(__name__) # Create FastAPI app app = FastAPI( title="Feedcast Clean Agent API", description="AI-powered clean agent with podcast generation capabilities", version="1.0.0" ) # Configure CORS app.add_middleware( CORSMiddleware, allow_origins=["*"], # Adjust in production allow_credentials=True, allow_methods=["*"], allow_headers=["*"], ) # Global service instances agent = None claude_service = None fact_checker = None podcast_generator = None supabase_client = None @app.on_event("startup") async def startup_event(): """Initialize services on startup.""" global agent, claude_service, fact_checker, podcast_generator, supabase_client logger.info("Starting up Feedcast Clean Agent API...") try: # Initialize Clean Agent logger.info("Initializing Clean Agent...") agent = CleanAgent() # Verify Anthropic API key anthropic_key = os.getenv("ANTHROPIC_API_KEY") if not anthropic_key: logger.error("ANTHROPIC_API_KEY environment variable not set") raise HTTPException(status_code=500, detail="Anthropic API key not configured") # Initialize Supabase client logger.info("Initializing Supabase client...") try: supabase_client_instance = SupabaseClient() if not supabase_client_instance.is_connected(): logger.warning("Supabase connection failed - running in limited mode") supabase_client = None else: supabase_client = supabase_client_instance.client except Exception as e: logger.warning(f"Supabase initialization failed: {e} - running in limited mode") supabase_client = None # Initialize Claude service logger.info("Initializing Claude service...") claude_service = ClaudePodcastService(api_key=anthropic_key) # Initialize Fact Checker logger.info("Initializing Fact Checker...") fact_checker = FactChecker(claude_service) # Initialize Podcast Generator logger.info("Initializing Podcast Generator...") podcast_generator = PodcastGenerator(supabase_client, claude_service, fact_checker) logger.info("All services initialized successfully!") except Exception as e: logger.error(f"Failed to initialize services: {str(e)}") raise HTTPException(status_code=500, detail=f"Service initialization failed: {str(e)}") @app.on_event("shutdown") async def shutdown_event(): """Cleanup on shutdown.""" global claude_service logger.info("Shutting down Feedcast Clean Agent API...") if claude_service: try: await claude_service.close() except Exception as e: logger.warning(f"Error closing Claude service: {e}") # Add existing routes @app.get("/") async def root(): """Root endpoint.""" return { "message": "Feedcast Clean Agent API", "version": "1.0.0", "services": { "clean_agent": "active", "podcast_generation": "active", "claude_service": "active", "fact_checker": "active" } } @app.post("/chat") async def chat(message: str): """Process a chat message.""" if not agent: raise HTTPException(status_code=500, detail="Clean Agent not initialized") try: response = await agent.process_message(message) return {"response": response} except Exception as e: logger.error(f"Chat processing error: {str(e)}") return {"error": str(e)} # Enhanced health check endpoint @app.get("/health") async def health_check(): """Comprehensive health check for all services.""" health_status = { "status": "healthy", "timestamp": "2024-01-01T00:00:00Z", # Will be updated below "services": {} } try: from datetime import datetime health_status["timestamp"] = datetime.utcnow().isoformat() # Check Clean Agent health_status["services"]["clean_agent"] = { "status": "healthy" if agent else "unhealthy", "message": "Clean Agent initialized" if agent else "Clean Agent not initialized" } # Check Supabase connection if supabase_client: try: # Test database connection result = await supabase_client.table("users").select("id").limit(1).execute() health_status["services"]["supabase"] = { "status": "healthy", "message": "Database connection successful", "tables_accessible": True } except Exception as e: health_status["services"]["supabase"] = { "status": "unhealthy", "message": f"Database connection failed: {str(e)}", "tables_accessible": False } else: [truncated — 3575 more characters] ``` ### ONBOARDED_MIGRATION.sql ```sql -- Migration: Add onboarded column to users table -- Purpose: Track whether user has completed onboarding process -- Date: 2025-10-26 -- Add onboarded column to users table (defaults to false for new users) ALTER TABLE users ADD COLUMN IF NOT EXISTS onboarded BOOLEAN DEFAULT FALSE NOT NULL; -- Optional: If you want to mark existing users as already onboarded -- Uncomment the following line if needed: -- UPDATE users SET onboarded = TRUE WHERE created_at < NOW(); -- Verify the column was added SELECT column_name, data_type, column_default FROM information_schema.columns WHERE table_name = 'users' AND column_name = 'onboarded'; ``` ### SUPABASE_TRANSCRIPT_MIGRATION.sql ```sql -- Migration: Add transcript column to episodes table -- This is optional - transcripts are stored in memory for now -- Run this in Supabase SQL Editor if you want to store transcripts in the database -- Add transcript column to episodes table ALTER TABLE episodes ADD COLUMN IF NOT EXISTS transcript JSONB; -- Add comment to document the column COMMENT ON COLUMN episodes.transcript IS 'JSON array of timestamped transcript segments for synchronized playback'; -- Create an index for better query performance if searching transcripts CREATE INDEX IF NOT EXISTS idx_episodes_transcript ON episodes USING GIN (transcript); -- Verify the migration SELECT column_name, data_type, is_nullable FROM information_schema.columns WHERE table_name = 'episodes' AND column_name = 'transcript'; -- Example transcript structure: -- [ -- { -- "text": "Welcome to the podcast...", -- "startTime": 0.0, -- "endTime": 3.5 -- }, -- { -- "text": "Today we're discussing...", -- "startTime": 3.5, -- "endTime": 7.2 -- } -- ] ``` ### SUPABASE_MIGRATION.sql ```sql -- Migration: Add user profile fields and news sources -- Run this in Supabase SQL Editor to add new fields to existing database -- Add new columns to users table ALTER TABLE users ADD COLUMN IF NOT EXISTS country TEXT, ADD COLUMN IF NOT EXISTS age INTEGER, ADD COLUMN IF NOT EXISTS gender TEXT, ADD COLUMN IF NOT EXISTS occupation TEXT, ADD COLUMN IF NOT EXISTS news_sources TEXT[] DEFAULT '{}'; -- Add comments to document the columns COMMENT ON COLUMN users.country IS 'User''s country of residence'; COMMENT ON COLUMN users.age IS 'User''s age'; COMMENT ON COLUMN users.gender IS 'User''s gender identity'; COMMENT ON COLUMN users.occupation IS 'User''s occupation or job title'; COMMENT ON COLUMN users.news_sources IS 'Array of news sources the user follows (e.g., BBC, CNN, NYT)'; -- Note: RLS policies remain the same - users can only access their own data -- No changes needed to existing policies -- Verify the migration SELECT column_name, data_type, is_nullable FROM information_schema.columns WHERE table_name = 'users' AND column_name IN ('country', 'age', 'gender', 'occupation', 'news_sources'); ``` [162 more indexed source files omitted to keep this export small. The full file list is in the Codebase structure section above.]