feat: migrate to Gradio SDK deployment for HF Spaces

- Update README.md YAML frontmatter for Gradio SDK 5.49.1
- Add HF Spaces deployment files (requirements.txt, packages.txt)
- Add production logging suppression for cleaner HF Spaces logs
- Update documentation to show all 3 ML foundation models
- Add MCP client configuration section with HF Space URL
- Correct ensemble predictor to Chronos-Bolt + TTM + N-HiTS

README.md

@@ -3,11 +3,15 @@ title: Portfolio Intelligence Platform
 emoji: 📊
 colorFrom: blue
 colorTo: purple
-sdk: docker
+sdk: gradio
+sdk_version: 5.49.1
+python_version: "3.12"
 app_file: app.py
 pinned: false
 license: mit
 short_description: AI portfolio analysis with multi-agent MCP orchestration
+suggested_hardware: cpu-upgrade
+startup_duration_timeout: 30m
 tags:
   - building-mcp-track-enterprise
   - building-mcp-track-customer
@@ -89,11 +93,11 @@ This architecture demonstrates that **agentic systems can be both transparent an
 
 - **9 MCP Servers**: Yahoo Finance, FMP, Trading-MCP, FRED, Portfolio Optimiser, Risk Analyser, Ensemble Predictor, News Sentiment, Feature Extraction
 - **Advanced Risk Metrics**: VaR, CVaR, Monte Carlo simulation, Sharpe ratio, Information Ratio, Calmar Ratio, Ulcer Index, GARCH volatility forecasting
-- **ML Forecasting**: Amazon Chronos foundation model + ensemble methods for 30/90-day price predictions
+- **ML Forecasting**: Ensemble of 3 foundation models (Chronos-Bolt, TTM, N-HiTS) for 30-day price predictions
 - **Quantitative Models**: Hierarchical Risk Parity (HRP), Black-Litterman, Mean-Variance optimisation
 - **Real-time Visualisations**: Interactive Plotly charts for allocations, risk, performance, correlations
 
-### 🎯 Four Workflow Modes
+### 🎯 Four Workflow Tasks
 
 1. **Analyse Portfolio**: Comprehensive analysis with visualisations, risk metrics, and AI recommendations
 2. **Build Portfolio**: Goal-based portfolio construction using ReAct agent with dynamic tool selection
@@ -156,8 +160,8 @@ This architecture demonstrates that **agentic systems can be both transparent an
 │  Phase 2.5: ML Predictions                                                  │
 │  ┌────────────────────────────────────────────────────────────┐            │
 │  │  Ensemble Predictor MCP                                     │            │
-│  │  Chronos foundation model + statistical baselines          │            │
-│  │  30/90-day price forecasts with confidence intervals       │            │
+│  │  3 Foundation Models: Chronos-Bolt + TTM + N-HiTS          │            │
+│  │  30-day price forecasts with confidence intervals          │            │
 │  └────────────────────────────────────────────────────────────┘            │
 └──────────────────────────────────┬──────────────────────────────────────────┘
                                    │
@@ -184,6 +188,30 @@ This architecture demonstrates that **agentic systems can be both transparent an
 
 ### MCP Server Integration
 
+The platform exposes **22 MCP tools** via Gradio's native MCP server at `/gradio_api/mcp/`. These tools are organised into namespaced categories:
+
+| Category | Tools | Purpose |
+|----------|-------|---------|
+| **market_*** | 10 tools | Quotes, historical data, fundamentals, financials, economic data |
+| **technical_*** | 5 tools | Indicators, feature extraction, normalisation, selection |
+| **portfolio_*** | 3 tools | HRP, Black-Litterman, Mean-Variance optimisation |
+| **risk_*** | 2 tools | VaR/CVaR analysis, GARCH volatility forecasting |
+| **ml_*** | 1 tool | Ensemble forecasting (Chronos-Bolt + statistical models) |
+| **sentiment_*** | 1 tool | News sentiment analysis |
+
+**MCP Client Configuration:**
+```json
+{
+  "mcpServers": {
+    "portfolio-intelligence": {
+      "url": "https://mcp-1st-birthday-finance-portfolio-intelligence-platform.hf.space/gradio_api/mcp/"
+    }
+  }
+}
+```
+
+#### Backend MCP Servers
+
 | MCP Server | Purpose | Data Provided | API Provider |
 |------------|---------|---------------|--------------|
 | **Yahoo Finance** | Market data | Real-time quotes, historical prices, dividends | yfinance |
@@ -192,7 +220,7 @@ This architecture demonstrates that **agentic systems can be both transparent an
 | **FRED** | Economic data | GDP, unemployment, Fed funds rate | Federal Reserve |
 | **Portfolio Optimiser** | Allocation | HRP, Black-Litterman, Mean-Variance weights | PyPortfolioOpt |
 | **Risk Analyser** | Risk metrics | VaR, CVaR, Sharpe, Sortino, max drawdown | riskfolio-lib |
-| **Ensemble Predictor** | ML forecasts | 30/90-day price predictions with confidence | Chronos-Bolt |
+| **Ensemble Predictor** | ML forecasts | 30-day price predictions with confidence | Chronos-Bolt + TTM + N-HiTS |
 | **News Sentiment** | Sentiment analysis | VADER sentiment scores on recent news | VADER + Finnhub |
 | **Feature Extraction** | ML features | Technical and fundamental feature vectors | Internal |
 
@@ -227,12 +255,13 @@ This architecture demonstrates that **agentic systems can be both transparent an
 - QuantStats
 
 **ML & Forecasting**
-- Amazon Chronos-Bolt
-- NeuralForecast
+- Amazon Chronos-Bolt (9M params)
+- IBM Tiny Time Mixers (TTM)
+- Nixtla N-HiTS
 - scikit-learn
 
 **Infrastructure**
-- FastMCP 2.13.0
+- FastMCP 2.9.1 + Native Gradio MCP
 - Supabase PostgreSQL
 - Redis (Upstash) with in-memory fallback
 
@@ -244,13 +273,40 @@ This architecture demonstrates that **agentic systems can be both transparent an
 
 ## 🚀 Installation
 
-### Prerequisites
+### Deployment Options
+
+The platform supports two deployment methods:
+
+| Method | Use Case | SDK | Configuration |
+|--------|----------|-----|---------------|
+| **Hugging Face Spaces** | Production hosting | Gradio SDK 5.49.1 | `requirements.txt` + `packages.txt` |
+| **Local Development** | Development & testing | uv + pyproject.toml | `uv sync` |
+
+### Option 1: Hugging Face Spaces (Recommended)
+
+The easiest way to deploy is via Hugging Face Spaces with the Gradio SDK:
+
+1. Fork this repository to your Hugging Face account
+2. Add your API keys as Space Secrets (Settings → Variables and secrets)
+3. The Space will automatically build and deploy
+
+**Required Secrets:**
+- `ANTHROPIC_API_KEY` - Claude API access
+
+**Optional Secrets:**
+- `ELEVENLABS_API_KEY` - Audio narration
+- `FMP_API_KEY` - Financial data
+- `SUPABASE_URL`, `SUPABASE_KEY` - Database
+
+### Option 2: Local Development
+
+#### Prerequisites
 
 - **Python 3.12+** ([Download](https://www.python.org/downloads/))
 - **uv package manager** ([Install](https://github.com/astral-sh/uv))
 - **Anthropic API Key** ([Get Key](https://console.anthropic.com/))
 
-### Quick Start
+#### Quick Start
 
 ```bash
 # 1. Clone the repository
@@ -269,6 +325,7 @@ uv run python app.py
 
 # 5. Open your browser
 # Navigate to http://localhost:7860
+# MCP endpoint at http://localhost:7860/gradio_api/mcp/
 ```
 
 ### Environment Configuration
@@ -447,80 +504,81 @@ LINK 5
 ```
 Portfolio-Intelligence-Platform/
 │
-├── app.py                          # Main Gradio interface (4,800+ lines)
+├── app.py                          # Main Gradio interface (~4,950 lines)
 │
 ├── backend/
 │   ├── agents/
-│   │   ├── base_agent.py           # Base agent class
+│   │   ├── council/
+│   │   │   └── advisory_council.py # Bull/bear debate system
+│   │   ├── base_agent.py           # Base agent class with PydanticAI
 │   │   ├── workflow.py             # LangGraph 5-phase workflow
 │   │   ├── workflow_router.py      # Workflow routing logic
 │   │   ├── react_agent.py          # ReAct portfolio builder
 │   │   ├── portfolio_analyst.py    # LLM synthesis agent
-│   │   ├── personas.py             # Investor persona prompts
-│   │   ├── rehearsal.py            # Change simulation engine
-│   │   └── council/
-│   │       └── advisory_council.py # Bull/bear debate system
+│   │   ├── personas.py             # Investor personas (Buffett, Wood, Dalio)
+│   │   └── rehearsal.py            # Change simulation engine
 │   │
-│   ├── audio/                      # Audio generation
+│   ├── audio/
 │   │   └── tts_service.py          # ElevenLabs TTS integration
 │   │
 │   ├── mcp_servers/                # 9 MCP server implementations
-│   │   ├── yahoo_finance_mcp.py    # Market data
-│   │   ├── fmp_mcp.py              # Fundamentals
+│   │   ├── yahoo_finance_mcp.py    # Market data (yfinance)
+│   │   ├── fmp_mcp.py              # Fundamentals (FMP API)
 │   │   ├── trading_mcp.py          # Technical indicators
-│   │   ├── fred_mcp.py             # Economic data
-│   │   ├── portfolio_optimizer_mcp.py  # Optimisation
-│   │   ├── risk_analyzer_mcp.py    # Risk metrics
-│   │   ├── ensemble_predictor_mcp.py   # ML forecasting
-│   │   ├── news_sentiment_mcp.py   # Sentiment analysis
-│   │   └── feature_extraction_mcp.py   # Feature engineering
+│   │   ├── fred_mcp.py             # Economic data (FRED API)
+│   │   ├── portfolio_optimizer_mcp.py  # HRP, Black-Litterman, Mean-Variance
+│   │   ├── risk_analyzer_mcp.py    # VaR, CVaR, GARCH, risk metrics
+│   │   ├── ensemble_predictor_mcp.py   # Chronos-Bolt + TTM + N-HiTS
+│   │   ├── news_sentiment_mcp.py   # VADER sentiment (Finnhub)
+│   │   └── feature_extraction_mcp.py   # Technical/fundamental features
 │   │
 │   ├── models/
 │   │   ├── agent_state.py          # LangGraph state with reducers
 │   │   └── portfolio.py            # Pydantic data models
 │   │
-│   ├── data_providers/             # Data provider abstractions
+│   ├── data_providers/
 │   │   ├── base.py                 # Base provider interface
 │   │   ├── factory.py              # Provider factory pattern
 │   │   ├── yfinance_provider.py    # Yahoo Finance implementation
 │   │   └── fmp_provider.py         # FMP implementation
 │   │
-│   ├── visualizations/             # Plotly chart generators
-│   │   └── plotly_charts.py        # All visualisation logic
+│   ├── visualizations/
+│   │   └── plotly_charts.py        # Interactive Plotly charts
 │   │
-│   ├── caching/                    # Distributed caching
-│   │   ├── redis_cache.py          # Redis implementation
+│   ├── caching/
+│   │   ├── redis_cache.py          # Redis/Upstash implementation
 │   │   ├── decorators.py           # Cache decorators
 │   │   └── factory.py              # Cache factory
 │   │
-│   ├── rate_limiting/              # Tiered rate limiting
+│   ├── rate_limiting/
 │   │   ├── fixed_window.py         # Fixed window algorithm
 │   │   └── limiter.py              # Rate limiter interface
 │   │
-│   ├── stress_testing/             # Portfolio stress testing
-│   │   ├── scenarios.py            # Market scenarios
-│   │   ├── simulator.py            # Simulation engine
+│   ├── stress_testing/
+│   │   ├── scenarios.py            # Market stress scenarios
+│   │   ├── simulator.py            # Monte Carlo simulation
 │   │   └── visualizations.py       # Stress test charts
 │   │
-│   ├── tax/                        # Tax optimisation
+│   ├── tax/
 │   │   ├── calculator.py           # Tax calculations
-│   │   ├── optimizer.py            # Loss harvesting strategies
+│   │   ├── optimizer.py            # Tax-loss harvesting
 │   │   ├── interface.py            # Tax interfaces
 │   │   ├── models.py               # Tax data models
 │   │   └── tests/                  # Tax calculation tests
 │   │
-│   ├── monitoring/                 # Observability
+│   ├── monitoring/
 │   │   └── sentry.py               # Sentry error tracking
 │   │
-│   ├── utils/                      # Utility functions
-│   │   ├── serialisation.py        # Data serialisation
+│   ├── utils/
+│   │   ├── serialisation.py        # JSON/Decimal serialisation
 │   │   └── uuid_generator.py       # UUID generation
 │   │
-│   ├── mcp_router.py               # MCP orchestration
+│   ├── mcp_tools.py                # Unified MCP tools (22 namespaced functions)
+│   ├── mcp_router.py               # MCP orchestration (compatibility layer)
 │   ├── auth.py                     # Supabase authentication
 │   ├── database.py                 # PostgreSQL client
 │   ├── config.py                   # Configuration management
-│   ├── export.py                   # Portfolio export utilities
+│   ├── export.py                   # PDF/CSV export utilities
 │   └── theme.py                    # UI theme configuration
 │
 ├── database/
@@ -532,13 +590,16 @@ Portfolio-Intelligence-Platform/
 │   ├── test_advisory_council.py    # Advisory council tests
 │   ├── test_integration.py         # Integration tests
 │   ├── test_mcp_servers.py         # MCP server tests
+│   ├── test_mcp_tools.py           # MCP tools tests
 │   ├── test_p1_features.py         # P1 feature tests
 │   ├── test_rehearsal.py           # Rehearsal engine tests
 │   └── test_single_asset_portfolio.py  # Single asset tests
 │
-├── Dockerfile                      # Container configuration
-├── pyproject.toml                  # uv dependencies
+├── pyproject.toml                  # uv dependencies (local development)
+├── requirements.txt                # pip dependencies (HF Spaces)
+├── packages.txt                    # System dependencies (HF Spaces)
 ├── uv.lock                         # Locked dependencies
+├── Dockerfile                      # Docker deployment (optional)
 └── README.md                       # This file
 ```
 

app.py

@@ -27,6 +27,19 @@ from dotenv import load_dotenv
 # Load environment variables first
 load_dotenv()
 
+# Configure logging for production (suppress verbose output on HF Spaces)
+# Check if running on HF Spaces (SPACE_ID is set automatically)
+if os.environ.get("SPACE_ID"):
+    # Suppress verbose logging in production
+    logging.getLogger("gradio").setLevel(logging.WARNING)
+    logging.getLogger("gradio_client").setLevel(logging.WARNING)
+    logging.getLogger("httpx").setLevel(logging.WARNING)
+    logging.getLogger("uvicorn").setLevel(logging.WARNING)
+    logging.getLogger("uvicorn.access").setLevel(logging.WARNING)
+    # Disable telemetry
+    os.environ["GRADIO_ANALYTICS_ENABLED"] = "False"
+    os.environ["HF_HUB_DISABLE_TELEMETRY"] = "true"
+
 # Initialise Sentry monitoring early (before other imports that might raise errors)
 from backend.monitoring import initialise_sentry
 initialise_sentry()
@@ -4925,10 +4938,13 @@ Please try again with different parameters.
 
 if __name__ == "__main__":
     demo = create_interface()
+    # Suppress console output on HF Spaces for cleaner logs
+    is_hf_space = os.environ.get("SPACE_ID") is not None
     demo.queue().launch(
         server_name="0.0.0.0",
         server_port=7860,
         share=False,
+        quiet=is_hf_space,  # Suppress verbose output on HF Spaces
         mcp_server=True,  # Native MCP server at /gradio_api/mcp/
         allowed_paths=["/tmp"]  # Allow serving export files from temp directory
     )

packages.txt

@@ -0,0 +1,9 @@
+# System dependencies for HF Spaces Gradio SDK
+# Pre-installed: ffmpeg, cmake, libsm6, libsndfile1
+
+# Build tools for compiled packages
+build-essential
+libffi-dev
+
+# For SSL/TLS support
+libssl-dev

requirements.txt

@@ -0,0 +1,79 @@
+# Portfolio Intelligence Platform - HF Spaces Gradio SDK Dependencies
+# Note: gradio is pre-installed via sdk_version, DO NOT include here
+
+# AI Framework
+pydantic-ai-slim[anthropic]==1.18.0
+anthropic>=0.39.0
+instructor>=1.6.4
+
+# Agent Orchestration
+langgraph>=0.1.0
+langchain-anthropic>=0.1.0
+langchain-core>=0.2.0
+
+# MCP Framework (compatible with gradio[mcp] mcp==1.10.1)
+fastmcp==2.9.1
+
+# Backend
+fastapi>=0.104.0
+uvicorn[standard]>=0.24.0
+pydantic>=2.5.0
+
+# Database (using binary to avoid libpq-dev requirement)
+supabase>=2.9.0
+psycopg2-binary>=2.9.9
+
+# Caching & Rate Limiting
+redis>=5.0.0
+upstash-redis>=0.15.0
+orjson>=3.10.0
+
+# Quantitative Finance
+pyportfolioopt>=1.5.6
+riskfolio-lib>=7.0.0
+arch>=8.0.0
+quantstats>=0.0.77
+
+# Data & Analysis
+pandas>=2.2.3
+numpy>=2.0.0
+yfinance>=0.2.40
+scipy>=1.11.0
+matplotlib>=3.8.0
+plotly>=5.18.0
+
+# Export & Reporting
+reportlab>=4.0.0
+pypdf>=3.17.0
+
+# Feature Engineering
+pandas-ta>=0.3.14b
+PyWavelets>=1.4.1
+scikit-learn>=1.3.0
+
+# ML Models
+torch>=2.0.0
+xgboost>=3.1.0
+chronos-forecasting>=1.0.0
+
+# Deep Learning Time Series
+granite-tsfm>=0.2.22
+neuralforecast>=3.1.0
+
+# Utilities
+python-dotenv>=1.0.0
+httpx>=0.25.0
+tenacity>=8.2.0
+python-dateutil>=2.8.0
+
+# Sentiment Analysis
+vaderSentiment>=3.3.2
+
+# Text-to-Speech
+elevenlabs>=1.0.0
+
+# Monitoring
+sentry-sdk[fastapi]>=2.0.0,<3.0.0
+
+# Financial Data
+fmp-data>=1.0.2