Address PR review feedback from Gemini Code Assist

Fixes:
- Remove duplicate get_running_analyses function (critical)
- Fix N+1 query in get_pipeline_summary_for_date with batch queries (high)
- Add thread-safety warning comment for running_analyses dict (high)
- Remove package-lock.json from .gitignore and track it (high)
- Config param in memory.py kept for backward compatibility (documented)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

.env.example

@@ -0,0 +1,2 @@
+ALPHA_VANTAGE_API_KEY=alpha_vantage_api_key_placeholder
+OPENAI_API_KEY=openai_api_key_placeholder

.gitignore

@@ -1,8 +1,17 @@
+.venv
+results
 env/
 __pycache__/
 .DS_Store
 *.csv
-src/
+/src/
 eval_results/
 eval_data/
 *.egg-info/
+.env
+
+# Node.js
+node_modules/
+
+# Frontend dev artifacts
+.frontend-dev/

.python-version

@@ -0,0 +1 @@
+3.10

README.md

@@ -11,6 +11,18 @@
   <a href="https://github.com/TauricResearch/" target="_blank"><img alt="Community" src="https://img.shields.io/badge/Join_GitHub_Community-TauricResearch-14C290?logo=discourse"/></a>
 </div>
 
+<div align="center">
+  <!-- Keep these links. Translations will automatically update with the README. -->
+  <a href="https://www.readme-i18n.com/TauricResearch/TradingAgents?lang=de">Deutsch</a> | 
+  <a href="https://www.readme-i18n.com/TauricResearch/TradingAgents?lang=es">Español</a> | 
+  <a href="https://www.readme-i18n.com/TauricResearch/TradingAgents?lang=fr">français</a> | 
+  <a href="https://www.readme-i18n.com/TauricResearch/TradingAgents?lang=ja">日本語</a> | 
+  <a href="https://www.readme-i18n.com/TauricResearch/TradingAgents?lang=ko">한국어</a> | 
+  <a href="https://www.readme-i18n.com/TauricResearch/TradingAgents?lang=pt">Português</a> | 
+  <a href="https://www.readme-i18n.com/TauricResearch/TradingAgents?lang=ru">Русский</a> | 
+  <a href="https://www.readme-i18n.com/TauricResearch/TradingAgents?lang=zh">中文</a>
+</div>
+
 ---
 
 # TradingAgents: Multi-Agents LLM Financial Trading Framework 
@@ -19,6 +31,16 @@
 >
 > So we decided to fully open-source the framework. Looking forward to building impactful projects with you!
 
+<div align="center">
+<a href="https://www.star-history.com/#TauricResearch/TradingAgents&Date">
+ <picture>
+   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=TauricResearch/TradingAgents&type=Date&theme=dark" />
+   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=TauricResearch/TradingAgents&type=Date" />
+   <img alt="TradingAgents Star History" src="https://api.star-history.com/svg?repos=TauricResearch/TradingAgents&type=Date" style="width: 80%; height: auto;" />
+ </picture>
+</a>
+</div>
+
 <div align="center">
 
 🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https://www.youtube.com/watch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)
@@ -58,7 +80,7 @@ Our framework decomposes complex trading tasks into specialized roles. This ensu
 - Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.
 
 <p align="center">
-  <img src="assets/risk.png" width="70%" style="display: inline-block; margin: 0 2%;">
+  <img src="assets/trader.png" width="70%" style="display: inline-block; margin: 0 2%;">
 </p>
 
 ### Risk Management and Portfolio Manager
@@ -66,7 +88,7 @@ Our framework decomposes complex trading tasks into specialized roles. This ensu
 - The Portfolio Manager approves/rejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.
 
 <p align="center">
-  <img src="assets/trader.png" width="70%" style="display: inline-block; margin: 0 2%;">
+  <img src="assets/risk.png" width="70%" style="display: inline-block; margin: 0 2%;">
 </p>
 
 ## Installation and CLI
@@ -92,16 +114,21 @@ pip install -r requirements.txt
 
 ### Required APIs
 
-You will also need the FinnHub API and EODHD API for financial data. All of our code is implemented with the free tier.
-```bash
-export FINNHUB_API_KEY=$YOUR_FINNHUB_API_KEY
-```
+You will need the OpenAI API for all the agents, and [Alpha Vantage API](https://www.alphavantage.co/support/#api-key) for fundamental and news data (default configuration).
 
-You will need the OpenAI API for all the agents.
 ```bash
 export OPENAI_API_KEY=$YOUR_OPENAI_API_KEY
+export ALPHA_VANTAGE_API_KEY=$YOUR_ALPHA_VANTAGE_API_KEY
 ```
 
+Alternatively, you can create a `.env` file in the project root with your API keys (see `.env.example` for reference):
+```bash
+cp .env.example .env
+# Edit .env with your actual API keys
+```
+
+**Note:** We are happy to partner with Alpha Vantage to provide robust API support for TradingAgents. You can get a free AlphaVantage API [here](https://www.alphavantage.co/support/#api-key), TradingAgents-sourced requests also have increased rate limits to 60 requests per minute with no daily limits. Typically the quota is sufficient for performing complex tasks with TradingAgents thanks to Alpha Vantage’s open-source support program. If you prefer to use OpenAI for these data sources instead, you can modify the data vendor settings in `tradingagents/default_config.py`.
+
 ### CLI Usage
 
 You can also try out the CLI directly by running:
@@ -124,6 +151,143 @@ An interface will appear showing results as they load, letting you track the age
   <img src="assets/cli/cli_transaction.png" width="100%" style="display: inline-block; margin: 0 2%;">
 </p>
 
+---
+
+## 🌐 Nifty50 AI Trading Dashboard (Web Frontend)
+
+A modern, feature-rich web dashboard for TradingAgents, specifically built for **Indian Nifty 50 stocks**. This dashboard provides a complete visual interface for AI-powered stock analysis with full transparency into the multi-agent decision process.
+
+### 🚀 Quick Start
+
+```bash
+# Start the backend server
+cd frontend/backend
+pip install -r requirements.txt
+python server.py  # Runs on http://localhost:8001
+
+# Start the frontend (in a new terminal)
+cd frontend
+npm install
+npm run dev  # Runs on http://localhost:5173
+```
+
+### ✨ Key Features
+
+#### Dashboard - AI Recommendations at a Glance
+View all 50 Nifty stocks with AI recommendations, top picks, stocks to avoid, and one-click bulk analysis.
+
+<p align="center">
+  <img src="frontend/docs/screenshots/01-dashboard.png" width="100%" style="display: inline-block;">
+</p>
+
+#### 🌙 Dark Mode Support
+Full dark mode with automatic system theme detection for comfortable viewing.
+
+<p align="center">
+  <img src="frontend/docs/screenshots/08-dashboard-dark-mode.png" width="100%" style="display: inline-block;">
+</p>
+
+#### ⚙️ Configurable Settings Panel
+Configure your AI analysis directly from the browser:
+- **LLM Provider**: Claude Subscription or Anthropic API
+- **Model Selection**: Choose Deep Think (Opus) and Quick Think (Sonnet/Haiku) models
+- **API Key Management**: Securely stored in browser localStorage
+- **Debate Rounds**: Adjust thoroughness (1-5 rounds)
+
+<p align="center">
+  <img src="frontend/docs/screenshots/02-settings-modal.png" width="60%" style="display: inline-block;">
+</p>
+
+#### 📊 Stock Detail View
+Detailed analysis for each stock with interactive price charts, recommendation history, and AI analysis summaries.
+
+<p align="center">
+  <img src="frontend/docs/screenshots/03-stock-detail-overview.png" width="100%" style="display: inline-block;">
+</p>
+
+#### 🔬 Analysis Pipeline Visualization
+See exactly how the AI reached its decision with a 9-step pipeline showing:
+- Data collection progress
+- Individual agent reports (Market, News, Social Media, Fundamentals)
+- Real-time status tracking
+
+<p align="center">
+  <img src="frontend/docs/screenshots/04-analysis-pipeline.png" width="100%" style="display: inline-block;">
+</p>
+
+#### 💬 Investment Debates (Bull vs Bear)
+Watch AI agents debate investment decisions with full transparency:
+- **Bull Analyst**: Makes the case for buying
+- **Bear Analyst**: Presents risks and concerns
+- **Research Manager**: Weighs both sides and decides
+
+<p align="center">
+  <img src="frontend/docs/screenshots/05-debates-tab.png" width="100%" style="display: inline-block;">
+</p>
+
+<details>
+<summary><b>📜 View Full Debate Example (Click to expand)</b></summary>
+<p align="center">
+  <img src="frontend/docs/screenshots/06-investment-debate-expanded.png" width="100%" style="display: inline-block;">
+</p>
+</details>
+
+#### 📈 Historical Analysis & Backtesting
+Track AI performance over time with comprehensive analytics:
+- Prediction accuracy metrics (Buy/Sell/Hold)
+- Risk metrics (Sharpe ratio, max drawdown, win rate)
+- Portfolio simulator with customizable starting amounts
+- AI Strategy vs Nifty50 Index comparison
+
+<p align="center">
+  <img src="frontend/docs/screenshots/10-history-page.png" width="100%" style="display: inline-block;">
+</p>
+
+#### 📚 How It Works
+Educational content explaining the multi-agent AI system and decision process.
+
+<p align="center">
+  <img src="frontend/docs/screenshots/09-how-it-works.png" width="100%" style="display: inline-block;">
+</p>
+
+### 🛠️ Frontend Tech Stack
+
+| Technology | Purpose |
+|------------|---------|
+| React 18 + TypeScript | Core framework |
+| Vite | Build tool & dev server |
+| Tailwind CSS | Styling with dark mode |
+| Recharts | Interactive charts |
+| Lucide React | Icons |
+| FastAPI (Python) | Backend API |
+| SQLite | Data persistence |
+
+### 📁 Frontend Project Structure
+
+```
+frontend/
+├── src/
+│   ├── components/
+│   │   ├── pipeline/          # Pipeline visualization
+│   │   ├── SettingsModal.tsx  # Settings UI
+│   │   └── Header.tsx
+│   ├── contexts/
+│   │   └── SettingsContext.tsx
+│   ├── pages/
+│   │   ├── Dashboard.tsx
+│   │   ├── StockDetail.tsx
+│   │   ├── History.tsx
+│   │   └── About.tsx
+│   └── services/
+│       └── api.ts
+├── backend/
+│   ├── server.py
+│   └── database.py
+└── docs/screenshots/
+```
+
+---
+
 ## TradingAgents Package
 
 ### Implementation Details
@@ -136,8 +300,9 @@ To use TradingAgents inside your code, you can import the `tradingagents` module
 
 ```python
 from tradingagents.graph.trading_graph import TradingAgentsGraph
+from tradingagents.default_config import DEFAULT_CONFIG
 
-ta = TradingAgentsGraph(debug=True, config=config)
+ta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())
 
 # forward propagate
 _, decision = ta.propagate("NVDA", "2024-05-10")
@@ -155,7 +320,14 @@ config = DEFAULT_CONFIG.copy()
 config["deep_think_llm"] = "gpt-4.1-nano"  # Use a different model
 config["quick_think_llm"] = "gpt-4.1-nano"  # Use a different model
 config["max_debate_rounds"] = 1  # Increase debate rounds
-config["online_tools"] = True # Use online tools or cached data
+
+# Configure data vendors (default uses yfinance and Alpha Vantage)
+config["data_vendors"] = {
+    "core_stock_apis": "yfinance",           # Options: yfinance, alpha_vantage, local
+    "technical_indicators": "yfinance",      # Options: yfinance, alpha_vantage, local
+    "fundamental_data": "alpha_vantage",     # Options: openai, alpha_vantage, local
+    "news_data": "alpha_vantage",            # Options: openai, alpha_vantage, google, local
+}
 
 # Initialize with custom config
 ta = TradingAgentsGraph(debug=True, config=config)
@@ -165,7 +337,7 @@ _, decision = ta.propagate("NVDA", "2024-05-10")
 print(decision)
 ```
 
-> For `online_tools`, we recommend enabling them for experimentation, as they provide access to real-time data. The agents' offline tools rely on cached data from our **Tauric TradingDB**, a curated dataset we use for backtesting. We're currently in the process of refining this dataset, and we plan to release it soon alongside our upcoming projects. Stay tuned!
+> The default configuration uses yfinance for stock price and technical data, and Alpha Vantage for fundamental and news data. For production use or if you encounter rate limits, consider upgrading to [Alpha Vantage Premium](https://www.alphavantage.co/premium/) for more stable and reliable data access. For offline experimentation, there's a local data vendor option that uses our **Tauric TradingDB**, a curated dataset for backtesting, though this is still in development. We're currently refining this dataset and plan to release it soon alongside our upcoming projects. Stay tuned!
 
 You can view the full list of configurations in `tradingagents/default_config.py`.
 

cli/main.py

@@ -1,7 +1,13 @@
 from typing import Optional
 import datetime
 import typer
+from pathlib import Path
+from functools import wraps
 from rich.console import Console
+from dotenv import load_dotenv
+
+# Load environment variables from .env file
+load_dotenv()
 from rich.panel import Panel
 from rich.spinner import Spinner
 from rich.live import Live
@@ -20,6 +26,7 @@ from rich.rule import Rule
 
 from tradingagents.graph.trading_graph import TradingAgentsGraph
 from tradingagents.default_config import DEFAULT_CONFIG
+from tradingagents.dataflows.markets import is_nifty_50_stock, NIFTY_50_STOCKS
 from cli.models import AnalystType
 from cli.utils import *
 
@@ -97,7 +104,7 @@ class MessageBuffer:
             if content is not None:
                 latest_section = section
                 latest_content = content
-
+               
         if latest_section and latest_content:
             # Format the current section for display
             section_titles = {
@@ -295,10 +302,27 @@ def update_display(layout, spinner_text=None):
 
     # Add regular messages
     for timestamp, msg_type, content in message_buffer.messages:
+        # Convert content to string if it's not already
+        content_str = content
+        if isinstance(content, list):
+            # Handle list of content blocks (Anthropic format)
+            text_parts = []
+            for item in content:
+                if isinstance(item, dict):
+                    if item.get('type') == 'text':
+                        text_parts.append(item.get('text', ''))
+                    elif item.get('type') == 'tool_use':
+                        text_parts.append(f"[Tool: {item.get('name', 'unknown')}]")
+                else:
+                    text_parts.append(str(item))
+            content_str = ' '.join(text_parts)
+        elif not isinstance(content_str, str):
+            content_str = str(content)
+            
         # Truncate message content if too long
-        if isinstance(content, str) and len(content) > 200:
-            content = content[:197] + "..."
-        all_messages.append((timestamp, msg_type, content))
+        if len(content_str) > 200:
+            content_str = content_str[:197] + "..."
+        all_messages.append((timestamp, msg_type, content_str))
 
     # Sort by timestamp
     all_messages.sort(key=lambda x: x[0])
@@ -406,29 +430,42 @@ def get_user_selections():
             box_content += f"\n[dim]Default: {default}[/dim]"
         return Panel(box_content, border_style="blue", padding=(1, 2))
 
-    # Step 1: Ticker symbol
+    # Step 1: Market selection
     console.print(
         create_question_box(
-            "Step 1: Ticker Symbol", "Enter the ticker symbol to analyze", "SPY"
+            "Step 1: Market Selection", "Select the market for your analysis"
         )
     )
-    selected_ticker = get_ticker()
+    selected_market = select_market()
 
-    # Step 2: Analysis date
+    # Show Nifty 50 stocks if Indian market is selected
+    if selected_market == "india_nse":
+        show_nifty_50_stocks()
+
+    # Step 2: Ticker symbol
+    console.print(
+        create_question_box(
+            "Step 2: Ticker Symbol", "Enter the ticker symbol to analyze",
+            "RELIANCE" if selected_market == "india_nse" else "SPY"
+        )
+    )
+    selected_ticker = get_ticker_with_market_hint(selected_market)
+
+    # Step 3: Analysis date
     default_date = datetime.datetime.now().strftime("%Y-%m-%d")
     console.print(
         create_question_box(
-            "Step 2: Analysis Date",
+            "Step 3: Analysis Date",
             "Enter the analysis date (YYYY-MM-DD)",
             default_date,
         )
     )
     analysis_date = get_analysis_date()
 
-    # Step 3: Select analysts
+    # Step 4: Select analysts
     console.print(
         create_question_box(
-            "Step 3: Analysts Team", "Select your LLM analyst agents for the analysis"
+            "Step 4: Analysts Team", "Select your LLM analyst agents for the analysis"
         )
     )
     selected_analysts = select_analysts()
@@ -436,30 +473,41 @@ def get_user_selections():
         f"[green]Selected analysts:[/green] {', '.join(analyst.value for analyst in selected_analysts)}"
     )
 
-    # Step 4: Research depth
+    # Step 5: Research depth
     console.print(
         create_question_box(
-            "Step 4: Research Depth", "Select your research depth level"
+            "Step 5: Research Depth", "Select your research depth level"
         )
     )
     selected_research_depth = select_research_depth()
 
-    # Step 5: Thinking agents
+    # Step 6: OpenAI backend
     console.print(
         create_question_box(
-            "Step 5: Thinking Agents", "Select your thinking agents for analysis"
+            "Step 6: LLM Provider", "Select which service to talk to"
         )
     )
-    selected_shallow_thinker = select_shallow_thinking_agent()
-    selected_deep_thinker = select_deep_thinking_agent()
+    selected_llm_provider, backend_url = select_llm_provider()
+
+    # Step 7: Thinking agents
+    console.print(
+        create_question_box(
+            "Step 7: Thinking Agents", "Select your thinking agents for analysis"
+        )
+    )
+    selected_shallow_thinker = select_shallow_thinking_agent(selected_llm_provider)
+    selected_deep_thinker = select_deep_thinking_agent(selected_llm_provider)
 
     return {
         "ticker": selected_ticker,
         "analysis_date": analysis_date,
         "analysts": selected_analysts,
         "research_depth": selected_research_depth,
+        "llm_provider": selected_llm_provider.lower(),
+        "backend_url": backend_url,
         "shallow_thinker": selected_shallow_thinker,
         "deep_thinker": selected_deep_thinker,
+        "market": selected_market,
     }
 
 
@@ -683,6 +731,24 @@ def update_research_team_status(status):
     for agent in research_team:
         message_buffer.update_agent_status(agent, status)
 
+def extract_content_string(content):
+    """Extract string content from various message formats."""
+    if isinstance(content, str):
+        return content
+    elif isinstance(content, list):
+        # Handle Anthropic's list format
+        text_parts = []
+        for item in content:
+            if isinstance(item, dict):
+                if item.get('type') == 'text':
+                    text_parts.append(item.get('text', ''))
+                elif item.get('type') == 'tool_use':
+                    text_parts.append(f"[Tool: {item.get('name', 'unknown')}]")
+            else:
+                text_parts.append(str(item))
+        return ' '.join(text_parts)
+    else:
+        return str(content)
 
 def run_analysis():
     # First get all user selections
@@ -694,12 +760,68 @@ def run_analysis():
     config["max_risk_discuss_rounds"] = selections["research_depth"]
     config["quick_think_llm"] = selections["shallow_thinker"]
     config["deep_think_llm"] = selections["deep_thinker"]
+    config["backend_url"] = selections["backend_url"]
+    config["llm_provider"] = selections["llm_provider"].lower()
+    config["market"] = selections["market"]
+
+    # Display market info for NSE stocks
+    if is_nifty_50_stock(selections["ticker"]):
+        company_name = NIFTY_50_STOCKS.get(selections["ticker"].replace(".NS", ""), "")
+        console.print(f"[cyan]Analyzing NSE stock:[/cyan] {selections['ticker']} - {company_name}")
+        console.print("[dim]Using jugaad-data for NSE stock data, yfinance for fundamentals[/dim]")
 
     # Initialize the graph
     graph = TradingAgentsGraph(
         [analyst.value for analyst in selections["analysts"]], config=config, debug=True
     )
 
+    # Create result directory
+    results_dir = Path(config["results_dir"]) / selections["ticker"] / selections["analysis_date"]
+    results_dir.mkdir(parents=True, exist_ok=True)
+    report_dir = results_dir / "reports"
+    report_dir.mkdir(parents=True, exist_ok=True)
+    log_file = results_dir / "message_tool.log"
+    log_file.touch(exist_ok=True)
+
+    def save_message_decorator(obj, func_name):
+        func = getattr(obj, func_name)
+        @wraps(func)
+        def wrapper(*args, **kwargs):
+            func(*args, **kwargs)
+            timestamp, message_type, content = obj.messages[-1]
+            content = content.replace("\n", " ")  # Replace newlines with spaces
+            with open(log_file, "a") as f:
+                f.write(f"{timestamp} [{message_type}] {content}\n")
+        return wrapper
+    
+    def save_tool_call_decorator(obj, func_name):
+        func = getattr(obj, func_name)
+        @wraps(func)
+        def wrapper(*args, **kwargs):
+            func(*args, **kwargs)
+            timestamp, tool_name, args = obj.tool_calls[-1]
+            args_str = ", ".join(f"{k}={v}" for k, v in args.items())
+            with open(log_file, "a") as f:
+                f.write(f"{timestamp} [Tool Call] {tool_name}({args_str})\n")
+        return wrapper
+
+    def save_report_section_decorator(obj, func_name):
+        func = getattr(obj, func_name)
+        @wraps(func)
+        def wrapper(section_name, content):
+            func(section_name, content)
+            if section_name in obj.report_sections and obj.report_sections[section_name] is not None:
+                content = obj.report_sections[section_name]
+                if content:
+                    file_name = f"{section_name}.md"
+                    with open(report_dir / file_name, "w") as f:
+                        f.write(content)
+        return wrapper
+
+    message_buffer.add_message = save_message_decorator(message_buffer, "add_message")
+    message_buffer.add_tool_call = save_tool_call_decorator(message_buffer, "add_tool_call")
+    message_buffer.update_report_section = save_report_section_decorator(message_buffer, "update_report_section")
+
     # Now start the display layout
     layout = create_layout()
 
@@ -708,10 +830,17 @@ def run_analysis():
         update_display(layout)
 
         # Add initial messages
-        message_buffer.add_message("System", f"Selected ticker: {selections['ticker']}")
+        ticker_info = selections['ticker']
+        if is_nifty_50_stock(selections['ticker']):
+            company_name = NIFTY_50_STOCKS.get(selections['ticker'].replace(".NS", ""), "")
+            ticker_info = f"{selections['ticker']} ({company_name}) [NSE]"
+        message_buffer.add_message("System", f"Selected ticker: {ticker_info}")
         message_buffer.add_message(
             "System", f"Analysis date: {selections['analysis_date']}"
         )
+        message_buffer.add_message(
+            "System", f"Market: {selections['market'].upper()}"
+        )
         message_buffer.add_message(
             "System",
             f"Selected analysts: {', '.join(analyst.value for analyst in selections['analysts'])}",
@@ -754,14 +883,14 @@ def run_analysis():
 
                 # Extract message content and type
                 if hasattr(last_message, "content"):
-                    content = last_message.content
+                    content = extract_content_string(last_message.content)  # Use the helper function
                     msg_type = "Reasoning"
                 else:
                     content = str(last_message)
                     msg_type = "System"
 
                 # Add message to buffer
-                message_buffer.add_message(msg_type, content)
+                message_buffer.add_message(msg_type, content)                
 
                 # If it's a tool call, add it to tool calls
                 if hasattr(last_message, "tool_calls"):

cli/utils.py

@@ -1,7 +1,13 @@
 import questionary
 from typing import List, Optional, Tuple, Dict
+from rich.console import Console
+from rich.table import Table
+from rich import box
 
 from cli.models import AnalystType
+from tradingagents.dataflows.markets import NIFTY_50_STOCKS, is_nifty_50_stock
+
+console = Console()
 
 ANALYST_ORDER = [
     ("Market Analyst", AnalystType.MARKET),
@@ -122,22 +128,44 @@ def select_research_depth() -> int:
     return choice
 
 
-def select_shallow_thinking_agent() -> str:
+def select_shallow_thinking_agent(provider) -> str:
     """Select shallow thinking llm engine using an interactive selection."""
 
     # Define shallow thinking llm engine options with their corresponding model names
-    SHALLOW_AGENT_OPTIONS = [
-        ("GPT-4o-mini - Fast and efficient for quick tasks", "gpt-4o-mini"),
-        ("GPT-4.1-nano - Ultra-lightweight model for basic operations", "gpt-4.1-nano"),
-        ("GPT-4.1-mini - Compact model with good performance", "gpt-4.1-mini"),
-        ("GPT-4o - Standard model with solid capabilities", "gpt-4o"),
-    ]
+    SHALLOW_AGENT_OPTIONS = {
+        "openai": [
+            ("GPT-4o-mini - Fast and efficient for quick tasks", "gpt-4o-mini"),
+            ("GPT-4.1-nano - Ultra-lightweight model for basic operations", "gpt-4.1-nano"),
+            ("GPT-4.1-mini - Compact model with good performance", "gpt-4.1-mini"),
+            ("GPT-4o - Standard model with solid capabilities", "gpt-4o"),
+        ],
+        "anthropic": [
+            ("Claude Haiku 3.5 - Fast inference and standard capabilities", "claude-3-5-haiku-latest"),
+            ("Claude Sonnet 3.5 - Highly capable standard model", "claude-3-5-sonnet-latest"),
+            ("Claude Sonnet 3.7 - Exceptional hybrid reasoning and agentic capabilities", "claude-3-7-sonnet-latest"),
+            ("Claude Sonnet 4 - High performance and excellent reasoning", "claude-sonnet-4-0"),
+        ],
+        "google": [
+            ("Gemini 2.0 Flash-Lite - Cost efficiency and low latency", "gemini-2.0-flash-lite"),
+            ("Gemini 2.0 Flash - Next generation features, speed, and thinking", "gemini-2.0-flash"),
+            ("Gemini 2.5 Flash - Adaptive thinking, cost efficiency", "gemini-2.5-flash-preview-05-20"),
+        ],
+        "openrouter": [
+            ("Meta: Llama 4 Scout", "meta-llama/llama-4-scout:free"),
+            ("Meta: Llama 3.3 8B Instruct - A lightweight and ultra-fast variant of Llama 3.3 70B", "meta-llama/llama-3.3-8b-instruct:free"),
+            ("google/gemini-2.0-flash-exp:free - Gemini Flash 2.0 offers a significantly faster time to first token", "google/gemini-2.0-flash-exp:free"),
+        ],
+        "ollama": [
+            ("llama3.1 local", "llama3.1"),
+            ("llama3.2 local", "llama3.2"),
+        ]
+    }
 
     choice = questionary.select(
         "Select Your [Quick-Thinking LLM Engine]:",
         choices=[
             questionary.Choice(display, value=value)
-            for display, value in SHALLOW_AGENT_OPTIONS
+            for display, value in SHALLOW_AGENT_OPTIONS[provider.lower()]
         ],
         instruction="\n- Use arrow keys to navigate\n- Press Enter to select",
         style=questionary.Style(
@@ -158,25 +186,48 @@ def select_shallow_thinking_agent() -> str:
     return choice
 
 
-def select_deep_thinking_agent() -> str:
+def select_deep_thinking_agent(provider) -> str:
     """Select deep thinking llm engine using an interactive selection."""
 
     # Define deep thinking llm engine options with their corresponding model names
-    DEEP_AGENT_OPTIONS = [
-        ("GPT-4.1-nano - Ultra-lightweight model for basic operations", "gpt-4.1-nano"),
-        ("GPT-4.1-mini - Compact model with good performance", "gpt-4.1-mini"),
-        ("GPT-4o - Standard model with solid capabilities", "gpt-4o"),
-        ("o4-mini - Specialized reasoning model (compact)", "o4-mini"),
-        ("o3-mini - Advanced reasoning model (lightweight)", "o3-mini"),
-        ("o3 - Full advanced reasoning model", "o3"),
-        ("o1 - Premier reasoning and problem-solving model", "o1"),
-    ]
-
+    DEEP_AGENT_OPTIONS = {
+        "openai": [
+            ("GPT-4.1-nano - Ultra-lightweight model for basic operations", "gpt-4.1-nano"),
+            ("GPT-4.1-mini - Compact model with good performance", "gpt-4.1-mini"),
+            ("GPT-4o - Standard model with solid capabilities", "gpt-4o"),
+            ("o4-mini - Specialized reasoning model (compact)", "o4-mini"),
+            ("o3-mini - Advanced reasoning model (lightweight)", "o3-mini"),
+            ("o3 - Full advanced reasoning model", "o3"),
+            ("o1 - Premier reasoning and problem-solving model", "o1"),
+        ],
+        "anthropic": [
+            ("Claude Haiku 3.5 - Fast inference and standard capabilities", "claude-3-5-haiku-latest"),
+            ("Claude Sonnet 3.5 - Highly capable standard model", "claude-3-5-sonnet-latest"),
+            ("Claude Sonnet 3.7 - Exceptional hybrid reasoning and agentic capabilities", "claude-3-7-sonnet-latest"),
+            ("Claude Sonnet 4 - High performance and excellent reasoning", "claude-sonnet-4-0"),
+            ("Claude Opus 4 - Most powerful Anthropic model", "	claude-opus-4-0"),
+        ],
+        "google": [
+            ("Gemini 2.0 Flash-Lite - Cost efficiency and low latency", "gemini-2.0-flash-lite"),
+            ("Gemini 2.0 Flash - Next generation features, speed, and thinking", "gemini-2.0-flash"),
+            ("Gemini 2.5 Flash - Adaptive thinking, cost efficiency", "gemini-2.5-flash-preview-05-20"),
+            ("Gemini 2.5 Pro", "gemini-2.5-pro-preview-06-05"),
+        ],
+        "openrouter": [
+            ("DeepSeek V3 - a 685B-parameter, mixture-of-experts model", "deepseek/deepseek-chat-v3-0324:free"),
+            ("Deepseek - latest iteration of the flagship chat model family from the DeepSeek team.", "deepseek/deepseek-chat-v3-0324:free"),
+        ],
+        "ollama": [
+            ("llama3.1 local", "llama3.1"),
+            ("qwen3", "qwen3"),
+        ]
+    }
+    
     choice = questionary.select(
         "Select Your [Deep-Thinking LLM Engine]:",
         choices=[
             questionary.Choice(display, value=value)
-            for display, value in DEEP_AGENT_OPTIONS
+            for display, value in DEEP_AGENT_OPTIONS[provider.lower()]
         ],
         instruction="\n- Use arrow keys to navigate\n- Press Enter to select",
         style=questionary.Style(
@@ -193,3 +244,151 @@ def select_deep_thinking_agent() -> str:
         exit(1)
 
     return choice
+
+def select_llm_provider() -> tuple[str, str]:
+    """Select the OpenAI api url using interactive selection."""
+    # Define OpenAI api options with their corresponding endpoints
+    BASE_URLS = [
+        ("OpenAI", "https://api.openai.com/v1"),
+        ("Anthropic", "https://api.anthropic.com/"),
+        ("Google", "https://generativelanguage.googleapis.com/v1"),
+        ("Openrouter", "https://openrouter.ai/api/v1"),
+        ("Ollama", "http://localhost:11434/v1"),        
+    ]
+    
+    choice = questionary.select(
+        "Select your LLM Provider:",
+        choices=[
+            questionary.Choice(display, value=(display, value))
+            for display, value in BASE_URLS
+        ],
+        instruction="\n- Use arrow keys to navigate\n- Press Enter to select",
+        style=questionary.Style(
+            [
+                ("selected", "fg:magenta noinherit"),
+                ("highlighted", "fg:magenta noinherit"),
+                ("pointer", "fg:magenta noinherit"),
+            ]
+        ),
+    ).ask()
+    
+    if choice is None:
+        console.print("\n[red]no OpenAI backend selected. Exiting...[/red]")
+        exit(1)
+    
+    display_name, url = choice
+    print(f"You selected: {display_name}\tURL: {url}")
+
+    return display_name, url
+
+
+def select_market() -> str:
+    """Select market using an interactive selection."""
+
+    MARKET_OPTIONS = [
+        ("Auto-detect (Recommended)", "auto"),
+        ("US Markets (NYSE, NASDAQ)", "us"),
+        ("Indian NSE (Nifty 50)", "india_nse"),
+    ]
+
+    choice = questionary.select(
+        "Select Your [Market]:",
+        choices=[
+            questionary.Choice(display, value=value)
+            for display, value in MARKET_OPTIONS
+        ],
+        instruction="\n- Use arrow keys to navigate\n- Press Enter to select",
+        style=questionary.Style(
+            [
+                ("selected", "fg:cyan noinherit"),
+                ("highlighted", "fg:cyan noinherit"),
+                ("pointer", "fg:cyan noinherit"),
+            ]
+        ),
+    ).ask()
+
+    if choice is None:
+        console.print("\n[red]No market selected. Exiting...[/red]")
+        exit(1)
+
+    return choice
+
+
+def display_nifty_50_stocks():
+    """Display the list of Nifty 50 stocks in a formatted table."""
+    table = Table(
+        title="Nifty 50 Stocks",
+        box=box.ROUNDED,
+        show_header=True,
+        header_style="bold cyan",
+    )
+
+    table.add_column("Symbol", style="green", width=15)
+    table.add_column("Company Name", style="white", width=45)
+
+    # Sort stocks alphabetically
+    sorted_stocks = sorted(NIFTY_50_STOCKS.items())
+
+    for symbol, company_name in sorted_stocks:
+        table.add_row(symbol, company_name)
+
+    console.print(table)
+    console.print()
+
+
+def show_nifty_50_stocks() -> bool:
+    """Ask user if they want to see Nifty 50 stocks list."""
+    show = questionary.confirm(
+        "Would you like to see the list of Nifty 50 stocks?",
+        default=False,
+        style=questionary.Style(
+            [
+                ("selected", "fg:cyan noinherit"),
+                ("highlighted", "fg:cyan noinherit"),
+            ]
+        ),
+    ).ask()
+
+    if show:
+        display_nifty_50_stocks()
+
+    return show
+
+
+def get_ticker_with_market_hint(market: str) -> str:
+    """Get ticker symbol with market-specific hints."""
+    if market == "india_nse":
+        hint = "Enter NSE symbol (e.g., RELIANCE, TCS, INFY)"
+        default = "RELIANCE"
+    elif market == "us":
+        hint = "Enter US ticker symbol (e.g., AAPL, GOOGL, MSFT)"
+        default = "SPY"
+    else:
+        hint = "Enter ticker symbol (auto-detects market)"
+        default = "SPY"
+
+    ticker = questionary.text(
+        hint + ":",
+        default=default,
+        validate=lambda x: len(x.strip()) > 0 or "Please enter a valid ticker symbol.",
+        style=questionary.Style(
+            [
+                ("text", "fg:green"),
+                ("highlighted", "noinherit"),
+            ]
+        ),
+    ).ask()
+
+    if not ticker:
+        console.print("\n[red]No ticker symbol provided. Exiting...[/red]")
+        exit(1)
+
+    ticker = ticker.strip().upper()
+
+    # Provide feedback for NSE stocks
+    if is_nifty_50_stock(ticker):
+        company_name = NIFTY_50_STOCKS.get(ticker.replace(".NS", ""), "")
+        if company_name:
+            console.print(f"[green]Detected NSE stock:[/green] {ticker} - {company_name}")
+
+    return ticker

frontend/.gitignore

@@ -0,0 +1,24 @@
+# Logs
+logs
+*.log
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+pnpm-debug.log*
+lerna-debug.log*
+
+node_modules
+dist
+dist-ssr
+*.local
+
+# Editor directories and files
+.vscode/*
+!.vscode/extensions.json
+.idea
+.DS_Store
+*.suo
+*.ntvs*
+*.njsproj
+*.sln
+*.sw?

frontend/README.md

@@ -0,0 +1,210 @@
+# Nifty50 AI Trading Dashboard
+
+A modern, feature-rich frontend for the TradingAgents multi-agent AI stock analysis system. This dashboard provides real-time AI-powered recommendations for all 50 stocks in the Nifty 50 index, with full visibility into the analysis pipeline, agent reports, and debate processes.
+
+## Features Overview
+
+### Dashboard - Main View
+The main dashboard displays AI recommendations for all 50 Nifty stocks with:
+- **Summary Statistics**: Quick view of Buy/Hold/Sell distribution
+- **Top Picks**: Highlighted stocks with the strongest buy signals
+- **Stocks to Avoid**: High-confidence sell recommendations
+- **Analyze All**: One-click bulk analysis of all stocks
+- **Filter & Search**: Filter by recommendation type or search by symbol
+
+![Dashboard](docs/screenshots/01-dashboard.png)
+
+### Dark Mode Support
+Full dark mode support with automatic system theme detection:
+
+![Dashboard Dark Mode](docs/screenshots/08-dashboard-dark-mode.png)
+
+### Settings Panel
+Configure the AI analysis system directly from the browser:
+- **LLM Provider Selection**: Choose between Claude Subscription or Anthropic API
+- **API Key Management**: Securely store API keys in browser localStorage
+- **Model Selection**: Configure Deep Think (Opus) and Quick Think (Sonnet/Haiku) models
+- **Analysis Settings**: Adjust max debate rounds for thoroughness vs speed
+
+![Settings Modal](docs/screenshots/02-settings-modal.png)
+
+### Stock Detail View
+Detailed analysis view for individual stocks with:
+- **Price Chart**: Interactive price history with buy/sell/hold signal markers
+- **Recommendation Details**: Decision, confidence level, and risk assessment
+- **Recommendation History**: Historical AI decisions for the stock
+- **AI Analysis Summary**: Expandable detailed analysis sections
+
+![Stock Detail Overview](docs/screenshots/03-stock-detail-overview.png)
+
+### Analysis Pipeline Visualization
+See exactly how the AI reached its decision with the full analysis pipeline:
+- **9-Step Pipeline**: Track progress through data collection, analysis, debates, and final decision
+- **Agent Reports**: View individual reports from Market, News, Social Media, and Fundamentals analysts
+- **Real-time Status**: See which steps are completed, running, or pending
+
+![Analysis Pipeline](docs/screenshots/04-analysis-pipeline.png)
+
+### Investment Debates
+The AI uses a debate system where Bull and Bear analysts argue their cases:
+- **Bull vs Bear**: Opposing viewpoints with detailed arguments
+- **Research Manager Decision**: Final judgment weighing both sides
+- **Full Debate History**: Complete transcript of the debate rounds
+
+![Debates Tab](docs/screenshots/05-debates-tab.png)
+
+#### Expanded Debate View
+Full debate content with Bull and Bear arguments:
+
+![Investment Debate Expanded](docs/screenshots/06-investment-debate-expanded.png)
+
+### Data Sources Tracking
+View all raw data sources used for analysis:
+- **Source Types**: Market data, news, fundamentals, social media
+- **Fetch Status**: Success/failure indicators for each data source
+- **Data Preview**: Expandable view of fetched data
+
+![Data Sources Tab](docs/screenshots/07-data-sources-tab.png)
+
+### How It Works Page
+Educational content explaining the multi-agent AI system:
+- **Multi-Agent Architecture**: Overview of the specialized AI agents
+- **Analysis Process**: Step-by-step breakdown of the pipeline
+- **Agent Profiles**: Details about each analyst type
+- **Debate Process**: Explanation of how consensus is reached
+
+![How It Works](docs/screenshots/09-how-it-works.png)
+
+### Historical Analysis & Backtesting
+Track AI performance over time with comprehensive analytics:
+- **Prediction Accuracy**: Overall and per-recommendation-type accuracy
+- **Accuracy Trend**: Visualize accuracy over time
+- **Risk Metrics**: Sharpe ratio, max drawdown, win rate
+- **Portfolio Simulator**: Test different investment amounts
+- **AI vs Nifty50**: Compare AI strategy performance against the index
+- **Return Distribution**: Histogram of next-day returns
+
+![History Page](docs/screenshots/10-history-page.png)
+
+## Tech Stack
+
+- **Frontend**: React 18 + TypeScript + Vite
+- **Styling**: Tailwind CSS with dark mode support
+- **Charts**: Recharts for interactive visualizations
+- **Icons**: Lucide React
+- **State Management**: React Context API
+- **Backend**: FastAPI (Python) with SQLite database
+
+## Getting Started
+
+### Prerequisites
+- Node.js 18+
+- Python 3.10+
+- npm or yarn
+
+### Installation
+
+1. **Install frontend dependencies:**
+```bash
+cd frontend
+npm install
+```
+
+2. **Install backend dependencies:**
+```bash
+cd frontend/backend
+pip install -r requirements.txt
+```
+
+### Running the Application
+
+1. **Start the backend server:**
+```bash
+cd frontend/backend
+python server.py
+```
+The backend runs on `http://localhost:8001`
+
+2. **Start the frontend development server:**
+```bash
+cd frontend
+npm run dev
+```
+The frontend runs on `http://localhost:5173`
+
+## Project Structure
+
+```
+frontend/
+├── src/
+│   ├── components/
+│   │   ├── pipeline/          # Pipeline visualization components
+│   │   │   ├── PipelineOverview.tsx
+│   │   │   ├── AgentReportCard.tsx
+│   │   │   ├── DebateViewer.tsx
+│   │   │   ├── RiskDebateViewer.tsx
+│   │   │   └── DataSourcesPanel.tsx
+│   │   ├── Header.tsx
+│   │   ├── SettingsModal.tsx
+│   │   └── ...
+│   ├── contexts/
+│   │   └── SettingsContext.tsx  # Settings state management
+│   ├── pages/
+│   │   ├── Dashboard.tsx
+│   │   ├── StockDetail.tsx
+│   │   ├── History.tsx
+│   │   └── About.tsx
+│   ├── services/
+│   │   └── api.ts              # API client
+│   ├── types/
+│   │   └── pipeline.ts         # TypeScript types for pipeline data
+│   └── App.tsx
+├── backend/
+│   ├── server.py               # FastAPI server
+│   ├── database.py             # SQLite database operations
+│   └── recommendations.db      # SQLite database
+└── docs/
+    └── screenshots/            # Feature screenshots
+```
+
+## API Endpoints
+
+### Recommendations
+- `GET /recommendations/{date}` - Get all recommendations for a date
+- `GET /recommendations/{date}/{symbol}` - Get recommendation for a specific stock
+- `POST /recommendations` - Save new recommendations
+
+### Pipeline Data
+- `GET /recommendations/{date}/{symbol}/pipeline` - Get full pipeline data
+- `GET /recommendations/{date}/{symbol}/agents` - Get agent reports
+- `GET /recommendations/{date}/{symbol}/debates` - Get debate history
+- `GET /recommendations/{date}/{symbol}/data-sources` - Get data source logs
+
+### Analysis
+- `POST /analyze/{symbol}` - Run analysis for a single stock
+- `POST /analyze-bulk` - Run analysis for multiple stocks
+
+## Configuration
+
+Settings are stored in browser localStorage and include:
+- `deepThinkModel`: Model for complex analysis (opus/sonnet/haiku)
+- `quickThinkModel`: Model for fast operations (opus/sonnet/haiku)
+- `provider`: LLM provider (claude_subscription/anthropic_api)
+- `anthropicApiKey`: API key for Anthropic API provider
+- `maxDebateRounds`: Number of debate rounds (1-5)
+
+## Contributing
+
+1. Fork the repository
+2. Create a feature branch
+3. Make your changes
+4. Run tests and linting
+5. Submit a pull request
+
+## License
+
+This project is part of the TradingAgents research project.
+
+## Disclaimer
+
+AI-generated recommendations are for educational and informational purposes only. These do not constitute financial advice. Always conduct your own research and consult with a qualified financial advisor before making investment decisions.

frontend/backend/database.py

@@ -0,0 +1,702 @@
+"""SQLite database module for storing stock recommendations."""
+import sqlite3
+import json
+from pathlib import Path
+from datetime import datetime
+from typing import Optional
+
+DB_PATH = Path(__file__).parent / "recommendations.db"
+
+
+def get_connection():
+    """Get SQLite database connection."""
+    conn = sqlite3.connect(DB_PATH)
+    conn.row_factory = sqlite3.Row
+    return conn
+
+
+def init_db():
+    """Initialize the database with required tables."""
+    conn = get_connection()
+    cursor = conn.cursor()
+
+    # Create recommendations table
+    cursor.execute("""
+        CREATE TABLE IF NOT EXISTS daily_recommendations (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            date TEXT UNIQUE NOT NULL,
+            summary_total INTEGER,
+            summary_buy INTEGER,
+            summary_sell INTEGER,
+            summary_hold INTEGER,
+            top_picks TEXT,
+            stocks_to_avoid TEXT,
+            created_at TEXT DEFAULT CURRENT_TIMESTAMP
+        )
+    """)
+
+    # Create stock analysis table
+    cursor.execute("""
+        CREATE TABLE IF NOT EXISTS stock_analysis (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            date TEXT NOT NULL,
+            symbol TEXT NOT NULL,
+            company_name TEXT,
+            decision TEXT,
+            confidence TEXT,
+            risk TEXT,
+            raw_analysis TEXT,
+            created_at TEXT DEFAULT CURRENT_TIMESTAMP,
+            UNIQUE(date, symbol)
+        )
+    """)
+
+    # Create index for faster queries
+    cursor.execute("""
+        CREATE INDEX IF NOT EXISTS idx_stock_analysis_date ON stock_analysis(date)
+    """)
+    cursor.execute("""
+        CREATE INDEX IF NOT EXISTS idx_stock_analysis_symbol ON stock_analysis(symbol)
+    """)
+
+    # Create agent_reports table (stores each analyst's detailed report)
+    cursor.execute("""
+        CREATE TABLE IF NOT EXISTS agent_reports (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            date TEXT NOT NULL,
+            symbol TEXT NOT NULL,
+            agent_type TEXT NOT NULL,
+            report_content TEXT,
+            data_sources_used TEXT,
+            created_at TEXT DEFAULT CURRENT_TIMESTAMP,
+            UNIQUE(date, symbol, agent_type)
+        )
+    """)
+
+    # Create debate_history table (stores investment and risk debates)
+    cursor.execute("""
+        CREATE TABLE IF NOT EXISTS debate_history (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            date TEXT NOT NULL,
+            symbol TEXT NOT NULL,
+            debate_type TEXT NOT NULL,
+            bull_arguments TEXT,
+            bear_arguments TEXT,
+            risky_arguments TEXT,
+            safe_arguments TEXT,
+            neutral_arguments TEXT,
+            judge_decision TEXT,
+            full_history TEXT,
+            created_at TEXT DEFAULT CURRENT_TIMESTAMP,
+            UNIQUE(date, symbol, debate_type)
+        )
+    """)
+
+    # Create pipeline_steps table (stores step-by-step execution log)
+    cursor.execute("""
+        CREATE TABLE IF NOT EXISTS pipeline_steps (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            date TEXT NOT NULL,
+            symbol TEXT NOT NULL,
+            step_number INTEGER,
+            step_name TEXT,
+            status TEXT,
+            started_at TEXT,
+            completed_at TEXT,
+            duration_ms INTEGER,
+            output_summary TEXT,
+            UNIQUE(date, symbol, step_number)
+        )
+    """)
+
+    # Create data_source_logs table (stores what raw data was fetched)
+    cursor.execute("""
+        CREATE TABLE IF NOT EXISTS data_source_logs (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            date TEXT NOT NULL,
+            symbol TEXT NOT NULL,
+            source_type TEXT,
+            source_name TEXT,
+            data_fetched TEXT,
+            fetch_timestamp TEXT,
+            success INTEGER DEFAULT 1,
+            error_message TEXT
+        )
+    """)
+
+    # Create indexes for new tables
+    cursor.execute("""
+        CREATE INDEX IF NOT EXISTS idx_agent_reports_date_symbol ON agent_reports(date, symbol)
+    """)
+    cursor.execute("""
+        CREATE INDEX IF NOT EXISTS idx_debate_history_date_symbol ON debate_history(date, symbol)
+    """)
+    cursor.execute("""
+        CREATE INDEX IF NOT EXISTS idx_pipeline_steps_date_symbol ON pipeline_steps(date, symbol)
+    """)
+    cursor.execute("""
+        CREATE INDEX IF NOT EXISTS idx_data_source_logs_date_symbol ON data_source_logs(date, symbol)
+    """)
+
+    conn.commit()
+    conn.close()
+
+
+def save_recommendation(date: str, analysis_data: dict, summary: dict,
+                        top_picks: list, stocks_to_avoid: list):
+    """Save a daily recommendation to the database."""
+    conn = get_connection()
+    cursor = conn.cursor()
+
+    try:
+        # Insert or replace daily recommendation
+        cursor.execute("""
+            INSERT OR REPLACE INTO daily_recommendations
+            (date, summary_total, summary_buy, summary_sell, summary_hold, top_picks, stocks_to_avoid)
+            VALUES (?, ?, ?, ?, ?, ?, ?)
+        """, (
+            date,
+            summary.get('total', 0),
+            summary.get('buy', 0),
+            summary.get('sell', 0),
+            summary.get('hold', 0),
+            json.dumps(top_picks),
+            json.dumps(stocks_to_avoid)
+        ))
+
+        # Insert stock analysis for each stock
+        for symbol, analysis in analysis_data.items():
+            cursor.execute("""
+                INSERT OR REPLACE INTO stock_analysis
+                (date, symbol, company_name, decision, confidence, risk, raw_analysis)
+                VALUES (?, ?, ?, ?, ?, ?, ?)
+            """, (
+                date,
+                symbol,
+                analysis.get('company_name', ''),
+                analysis.get('decision'),
+                analysis.get('confidence'),
+                analysis.get('risk'),
+                analysis.get('raw_analysis', '')
+            ))
+
+        conn.commit()
+    finally:
+        conn.close()
+
+
+def get_recommendation_by_date(date: str) -> Optional[dict]:
+    """Get recommendation for a specific date."""
+    conn = get_connection()
+    cursor = conn.cursor()
+
+    try:
+        # Get daily summary
+        cursor.execute("""
+            SELECT * FROM daily_recommendations WHERE date = ?
+        """, (date,))
+        row = cursor.fetchone()
+
+        if not row:
+            return None
+
+        # Get stock analysis for this date
+        cursor.execute("""
+            SELECT * FROM stock_analysis WHERE date = ?
+        """, (date,))
+        analysis_rows = cursor.fetchall()
+
+        analysis = {}
+        for a in analysis_rows:
+            analysis[a['symbol']] = {
+                'symbol': a['symbol'],
+                'company_name': a['company_name'],
+                'decision': a['decision'],
+                'confidence': a['confidence'],
+                'risk': a['risk'],
+                'raw_analysis': a['raw_analysis']
+            }
+
+        return {
+            'date': row['date'],
+            'analysis': analysis,
+            'summary': {
+                'total': row['summary_total'],
+                'buy': row['summary_buy'],
+                'sell': row['summary_sell'],
+                'hold': row['summary_hold']
+            },
+            'top_picks': json.loads(row['top_picks']) if row['top_picks'] else [],
+            'stocks_to_avoid': json.loads(row['stocks_to_avoid']) if row['stocks_to_avoid'] else []
+        }
+    finally:
+        conn.close()
+
+
+def get_latest_recommendation() -> Optional[dict]:
+    """Get the most recent recommendation."""
+    conn = get_connection()
+    cursor = conn.cursor()
+
+    try:
+        cursor.execute("""
+            SELECT date FROM daily_recommendations ORDER BY date DESC LIMIT 1
+        """)
+        row = cursor.fetchone()
+
+        if not row:
+            return None
+
+        return get_recommendation_by_date(row['date'])
+    finally:
+        conn.close()
+
+
+def get_all_dates() -> list:
+    """Get all available dates."""
+    conn = get_connection()
+    cursor = conn.cursor()
+
+    try:
+        cursor.execute("""
+            SELECT date FROM daily_recommendations ORDER BY date DESC
+        """)
+        return [row['date'] for row in cursor.fetchall()]
+    finally:
+        conn.close()
+
+
+def get_stock_history(symbol: str) -> list:
+    """Get historical recommendations for a specific stock."""
+    conn = get_connection()
+    cursor = conn.cursor()
+
+    try:
+        cursor.execute("""
+            SELECT date, decision, confidence, risk
+            FROM stock_analysis
+            WHERE symbol = ?
+            ORDER BY date DESC
+        """, (symbol,))
+
+        return [
+            {
+                'date': row['date'],
+                'decision': row['decision'],
+                'confidence': row['confidence'],
+                'risk': row['risk']
+            }
+            for row in cursor.fetchall()
+        ]
+    finally:
+        conn.close()
+
+
+def get_all_recommendations() -> list:
+    """Get all daily recommendations."""
+    dates = get_all_dates()
+    return [get_recommendation_by_date(date) for date in dates]
+
+
+# ============== Pipeline Data Functions ==============
+
+def save_agent_report(date: str, symbol: str, agent_type: str,
+                      report_content: str, data_sources_used: list = None):
+    """Save an individual agent's report."""
+    conn = get_connection()
+    cursor = conn.cursor()
+
+    try:
+        cursor.execute("""
+            INSERT OR REPLACE INTO agent_reports
+            (date, symbol, agent_type, report_content, data_sources_used)
+            VALUES (?, ?, ?, ?, ?)
+        """, (
+            date, symbol, agent_type, report_content,
+            json.dumps(data_sources_used) if data_sources_used else '[]'
+        ))
+        conn.commit()
+    finally:
+        conn.close()
+
+
+def save_agent_reports_bulk(date: str, symbol: str, reports: dict):
+    """Save all agent reports for a stock at once.
+
+    Args:
+        date: Date string (YYYY-MM-DD)
+        symbol: Stock symbol
+        reports: Dict with keys 'market', 'news', 'social_media', 'fundamentals'
+    """
+    conn = get_connection()
+    cursor = conn.cursor()
+
+    try:
+        for agent_type, report_data in reports.items():
+            if isinstance(report_data, str):
+                report_content = report_data
+                data_sources = []
+            else:
+                report_content = report_data.get('content', '')
+                data_sources = report_data.get('data_sources', [])
+
+            cursor.execute("""
+                INSERT OR REPLACE INTO agent_reports
+                (date, symbol, agent_type, report_content, data_sources_used)
+                VALUES (?, ?, ?, ?, ?)
+            """, (date, symbol, agent_type, report_content, json.dumps(data_sources)))
+
+        conn.commit()
+    finally:
+        conn.close()
+
+
+def get_agent_reports(date: str, symbol: str) -> dict:
+    """Get all agent reports for a stock on a date."""
+    conn = get_connection()
+    cursor = conn.cursor()
+
+    try:
+        cursor.execute("""
+            SELECT agent_type, report_content, data_sources_used, created_at
+            FROM agent_reports
+            WHERE date = ? AND symbol = ?
+        """, (date, symbol))
+
+        reports = {}
+        for row in cursor.fetchall():
+            reports[row['agent_type']] = {
+                'agent_type': row['agent_type'],
+                'report_content': row['report_content'],
+                'data_sources_used': json.loads(row['data_sources_used']) if row['data_sources_used'] else [],
+                'created_at': row['created_at']
+            }
+        return reports
+    finally:
+        conn.close()
+
+
+def save_debate_history(date: str, symbol: str, debate_type: str,
+                        bull_arguments: str = None, bear_arguments: str = None,
+                        risky_arguments: str = None, safe_arguments: str = None,
+                        neutral_arguments: str = None, judge_decision: str = None,
+                        full_history: str = None):
+    """Save debate history for investment or risk debate."""
+    conn = get_connection()
+    cursor = conn.cursor()
+
+    try:
+        cursor.execute("""
+            INSERT OR REPLACE INTO debate_history
+            (date, symbol, debate_type, bull_arguments, bear_arguments,
+             risky_arguments, safe_arguments, neutral_arguments,
+             judge_decision, full_history)
+            VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
+        """, (
+            date, symbol, debate_type,
+            bull_arguments, bear_arguments,
+            risky_arguments, safe_arguments, neutral_arguments,
+            judge_decision, full_history
+        ))
+        conn.commit()
+    finally:
+        conn.close()
+
+
+def get_debate_history(date: str, symbol: str) -> dict:
+    """Get all debate history for a stock on a date."""
+    conn = get_connection()
+    cursor = conn.cursor()
+
+    try:
+        cursor.execute("""
+            SELECT * FROM debate_history
+            WHERE date = ? AND symbol = ?
+        """, (date, symbol))
+
+        debates = {}
+        for row in cursor.fetchall():
+            debates[row['debate_type']] = {
+                'debate_type': row['debate_type'],
+                'bull_arguments': row['bull_arguments'],
+                'bear_arguments': row['bear_arguments'],
+                'risky_arguments': row['risky_arguments'],
+                'safe_arguments': row['safe_arguments'],
+                'neutral_arguments': row['neutral_arguments'],
+                'judge_decision': row['judge_decision'],
+                'full_history': row['full_history'],
+                'created_at': row['created_at']
+            }
+        return debates
+    finally:
+        conn.close()
+
+
+def save_pipeline_step(date: str, symbol: str, step_number: int, step_name: str,
+                       status: str, started_at: str = None, completed_at: str = None,
+                       duration_ms: int = None, output_summary: str = None):
+    """Save a pipeline step status."""
+    conn = get_connection()
+    cursor = conn.cursor()
+
+    try:
+        cursor.execute("""
+            INSERT OR REPLACE INTO pipeline_steps
+            (date, symbol, step_number, step_name, status,
+             started_at, completed_at, duration_ms, output_summary)
+            VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)
+        """, (
+            date, symbol, step_number, step_name, status,
+            started_at, completed_at, duration_ms, output_summary
+        ))
+        conn.commit()
+    finally:
+        conn.close()
+
+
+def save_pipeline_steps_bulk(date: str, symbol: str, steps: list):
+    """Save all pipeline steps at once.
+
+    Args:
+        date: Date string
+        symbol: Stock symbol
+        steps: List of step dicts with step_number, step_name, status, etc.
+    """
+    conn = get_connection()
+    cursor = conn.cursor()
+
+    try:
+        for step in steps:
+            cursor.execute("""
+                INSERT OR REPLACE INTO pipeline_steps
+                (date, symbol, step_number, step_name, status,
+                 started_at, completed_at, duration_ms, output_summary)
+                VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)
+            """, (
+                date, symbol,
+                step.get('step_number'),
+                step.get('step_name'),
+                step.get('status'),
+                step.get('started_at'),
+                step.get('completed_at'),
+                step.get('duration_ms'),
+                step.get('output_summary')
+            ))
+        conn.commit()
+    finally:
+        conn.close()
+
+
+def get_pipeline_steps(date: str, symbol: str) -> list:
+    """Get all pipeline steps for a stock on a date."""
+    conn = get_connection()
+    cursor = conn.cursor()
+
+    try:
+        cursor.execute("""
+            SELECT * FROM pipeline_steps
+            WHERE date = ? AND symbol = ?
+            ORDER BY step_number
+        """, (date, symbol))
+
+        return [
+            {
+                'step_number': row['step_number'],
+                'step_name': row['step_name'],
+                'status': row['status'],
+                'started_at': row['started_at'],
+                'completed_at': row['completed_at'],
+                'duration_ms': row['duration_ms'],
+                'output_summary': row['output_summary']
+            }
+            for row in cursor.fetchall()
+        ]
+    finally:
+        conn.close()
+
+
+def save_data_source_log(date: str, symbol: str, source_type: str,
+                         source_name: str, data_fetched: dict = None,
+                         fetch_timestamp: str = None, success: bool = True,
+                         error_message: str = None):
+    """Log a data source fetch."""
+    conn = get_connection()
+    cursor = conn.cursor()
+
+    try:
+        cursor.execute("""
+            INSERT INTO data_source_logs
+            (date, symbol, source_type, source_name, data_fetched,
+             fetch_timestamp, success, error_message)
+            VALUES (?, ?, ?, ?, ?, ?, ?, ?)
+        """, (
+            date, symbol, source_type, source_name,
+            json.dumps(data_fetched) if data_fetched else None,
+            fetch_timestamp or datetime.now().isoformat(),
+            1 if success else 0,
+            error_message
+        ))
+        conn.commit()
+    finally:
+        conn.close()
+
+
+def save_data_source_logs_bulk(date: str, symbol: str, logs: list):
+    """Save multiple data source logs at once."""
+    conn = get_connection()
+    cursor = conn.cursor()
+
+    try:
+        for log in logs:
+            cursor.execute("""
+                INSERT INTO data_source_logs
+                (date, symbol, source_type, source_name, data_fetched,
+                 fetch_timestamp, success, error_message)
+                VALUES (?, ?, ?, ?, ?, ?, ?, ?)
+            """, (
+                date, symbol,
+                log.get('source_type'),
+                log.get('source_name'),
+                json.dumps(log.get('data_fetched')) if log.get('data_fetched') else None,
+                log.get('fetch_timestamp') or datetime.now().isoformat(),
+                1 if log.get('success', True) else 0,
+                log.get('error_message')
+            ))
+        conn.commit()
+    finally:
+        conn.close()
+
+
+def get_data_source_logs(date: str, symbol: str) -> list:
+    """Get all data source logs for a stock on a date."""
+    conn = get_connection()
+    cursor = conn.cursor()
+
+    try:
+        cursor.execute("""
+            SELECT * FROM data_source_logs
+            WHERE date = ? AND symbol = ?
+            ORDER BY fetch_timestamp
+        """, (date, symbol))
+
+        return [
+            {
+                'source_type': row['source_type'],
+                'source_name': row['source_name'],
+                'data_fetched': json.loads(row['data_fetched']) if row['data_fetched'] else None,
+                'fetch_timestamp': row['fetch_timestamp'],
+                'success': bool(row['success']),
+                'error_message': row['error_message']
+            }
+            for row in cursor.fetchall()
+        ]
+    finally:
+        conn.close()
+
+
+def get_full_pipeline_data(date: str, symbol: str) -> dict:
+    """Get complete pipeline data for a stock on a date."""
+    return {
+        'date': date,
+        'symbol': symbol,
+        'agent_reports': get_agent_reports(date, symbol),
+        'debates': get_debate_history(date, symbol),
+        'pipeline_steps': get_pipeline_steps(date, symbol),
+        'data_sources': get_data_source_logs(date, symbol)
+    }
+
+
+def save_full_pipeline_data(date: str, symbol: str, pipeline_data: dict):
+    """Save complete pipeline data for a stock.
+
+    Args:
+        date: Date string
+        symbol: Stock symbol
+        pipeline_data: Dict containing agent_reports, debates, pipeline_steps, data_sources
+    """
+    if 'agent_reports' in pipeline_data:
+        save_agent_reports_bulk(date, symbol, pipeline_data['agent_reports'])
+
+    if 'investment_debate' in pipeline_data:
+        debate = pipeline_data['investment_debate']
+        save_debate_history(
+            date, symbol, 'investment',
+            bull_arguments=debate.get('bull_history'),
+            bear_arguments=debate.get('bear_history'),
+            judge_decision=debate.get('judge_decision'),
+            full_history=debate.get('history')
+        )
+
+    if 'risk_debate' in pipeline_data:
+        debate = pipeline_data['risk_debate']
+        save_debate_history(
+            date, symbol, 'risk',
+            risky_arguments=debate.get('risky_history'),
+            safe_arguments=debate.get('safe_history'),
+            neutral_arguments=debate.get('neutral_history'),
+            judge_decision=debate.get('judge_decision'),
+            full_history=debate.get('history')
+        )
+
+    if 'pipeline_steps' in pipeline_data:
+        save_pipeline_steps_bulk(date, symbol, pipeline_data['pipeline_steps'])
+
+    if 'data_sources' in pipeline_data:
+        save_data_source_logs_bulk(date, symbol, pipeline_data['data_sources'])
+
+
+def get_pipeline_summary_for_date(date: str) -> list:
+    """Get pipeline summary for all stocks on a date."""
+    conn = get_connection()
+    cursor = conn.cursor()
+
+    try:
+        # Get all symbols for this date
+        cursor.execute("""
+            SELECT DISTINCT symbol FROM stock_analysis WHERE date = ?
+        """, (date,))
+        symbols = [row['symbol'] for row in cursor.fetchall()]
+
+        # Batch fetch all pipeline steps for the date (avoids N+1)
+        cursor.execute("""
+            SELECT symbol, step_name, status FROM pipeline_steps
+            WHERE date = ?
+            ORDER BY symbol, step_number
+        """, (date,))
+        all_steps = cursor.fetchall()
+        steps_by_symbol = {}
+        for row in all_steps:
+            if row['symbol'] not in steps_by_symbol:
+                steps_by_symbol[row['symbol']] = []
+            steps_by_symbol[row['symbol']].append({'step_name': row['step_name'], 'status': row['status']})
+
+        # Batch fetch agent report counts (avoids N+1)
+        cursor.execute("""
+            SELECT symbol, COUNT(*) as count FROM agent_reports
+            WHERE date = ?
+            GROUP BY symbol
+        """, (date,))
+        agent_counts = {row['symbol']: row['count'] for row in cursor.fetchall()}
+
+        # Batch fetch debates existence (avoids N+1)
+        cursor.execute("""
+            SELECT DISTINCT symbol FROM debate_history WHERE date = ?
+        """, (date,))
+        symbols_with_debates = {row['symbol'] for row in cursor.fetchall()}
+
+        summaries = []
+        for symbol in symbols:
+            summaries.append({
+                'symbol': symbol,
+                'pipeline_steps': steps_by_symbol.get(symbol, []),
+                'agent_reports_count': agent_counts.get(symbol, 0),
+                'has_debates': symbol in symbols_with_debates
+            })
+
+        return summaries
+    finally:
+        conn.close()
+
+
+# Initialize database on module import
+init_db()

frontend/backend/requirements.txt

@@ -0,0 +1,3 @@
+fastapi>=0.109.0
+uvicorn>=0.27.0
+pydantic>=2.0.0

frontend/backend/seed_data.py

@@ -0,0 +1,135 @@
+"""Seed the database with sample data from the Jan 30, 2025 analysis."""
+import database as db
+
+# Sample data from the Jan 30, 2025 analysis
+SAMPLE_DATA = {
+    "date": "2025-01-30",
+    "analysis": {
+        "RELIANCE": {"symbol": "RELIANCE", "company_name": "Reliance Industries Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "TCS": {"symbol": "TCS", "company_name": "Tata Consultancy Services Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "HDFCBANK": {"symbol": "HDFCBANK", "company_name": "HDFC Bank Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "INFY": {"symbol": "INFY", "company_name": "Infosys Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "ICICIBANK": {"symbol": "ICICIBANK", "company_name": "ICICI Bank Ltd", "decision": "BUY", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "HINDUNILVR": {"symbol": "HINDUNILVR", "company_name": "Hindustan Unilever Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "ITC": {"symbol": "ITC", "company_name": "ITC Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "SBIN": {"symbol": "SBIN", "company_name": "State Bank of India", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "BHARTIARTL": {"symbol": "BHARTIARTL", "company_name": "Bharti Airtel Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "KOTAKBANK": {"symbol": "KOTAKBANK", "company_name": "Kotak Mahindra Bank Ltd", "decision": "BUY", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "LT": {"symbol": "LT", "company_name": "Larsen & Toubro Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "AXISBANK": {"symbol": "AXISBANK", "company_name": "Axis Bank Ltd", "decision": "SELL", "confidence": "HIGH", "risk": "HIGH"},
+        "ASIANPAINT": {"symbol": "ASIANPAINT", "company_name": "Asian Paints Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "MARUTI": {"symbol": "MARUTI", "company_name": "Maruti Suzuki India Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "HCLTECH": {"symbol": "HCLTECH", "company_name": "HCL Technologies Ltd", "decision": "SELL", "confidence": "MEDIUM", "risk": "HIGH"},
+        "SUNPHARMA": {"symbol": "SUNPHARMA", "company_name": "Sun Pharmaceutical Industries Ltd", "decision": "SELL", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "TITAN": {"symbol": "TITAN", "company_name": "Titan Company Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "BAJFINANCE": {"symbol": "BAJFINANCE", "company_name": "Bajaj Finance Ltd", "decision": "BUY", "confidence": "HIGH", "risk": "MEDIUM"},
+        "WIPRO": {"symbol": "WIPRO", "company_name": "Wipro Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "ULTRACEMCO": {"symbol": "ULTRACEMCO", "company_name": "UltraTech Cement Ltd", "decision": "BUY", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "NESTLEIND": {"symbol": "NESTLEIND", "company_name": "Nestle India Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "NTPC": {"symbol": "NTPC", "company_name": "NTPC Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "POWERGRID": {"symbol": "POWERGRID", "company_name": "Power Grid Corporation of India Ltd", "decision": "SELL", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "M&M": {"symbol": "M&M", "company_name": "Mahindra & Mahindra Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "TATAMOTORS": {"symbol": "TATAMOTORS", "company_name": "Tata Motors Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "ONGC": {"symbol": "ONGC", "company_name": "Oil & Natural Gas Corporation Ltd", "decision": "SELL", "confidence": "MEDIUM", "risk": "HIGH"},
+        "JSWSTEEL": {"symbol": "JSWSTEEL", "company_name": "JSW Steel Ltd", "decision": "BUY", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "TATASTEEL": {"symbol": "TATASTEEL", "company_name": "Tata Steel Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "ADANIENT": {"symbol": "ADANIENT", "company_name": "Adani Enterprises Ltd", "decision": "HOLD", "confidence": "LOW", "risk": "HIGH"},
+        "ADANIPORTS": {"symbol": "ADANIPORTS", "company_name": "Adani Ports and SEZ Ltd", "decision": "SELL", "confidence": "MEDIUM", "risk": "HIGH"},
+        "COALINDIA": {"symbol": "COALINDIA", "company_name": "Coal India Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "BAJAJFINSV": {"symbol": "BAJAJFINSV", "company_name": "Bajaj Finserv Ltd", "decision": "BUY", "confidence": "HIGH", "risk": "MEDIUM"},
+        "TECHM": {"symbol": "TECHM", "company_name": "Tech Mahindra Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "HDFCLIFE": {"symbol": "HDFCLIFE", "company_name": "HDFC Life Insurance Company Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "SBILIFE": {"symbol": "SBILIFE", "company_name": "SBI Life Insurance Company Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "GRASIM": {"symbol": "GRASIM", "company_name": "Grasim Industries Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "DIVISLAB": {"symbol": "DIVISLAB", "company_name": "Divi's Laboratories Ltd", "decision": "SELL", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "DRREDDY": {"symbol": "DRREDDY", "company_name": "Dr. Reddy's Laboratories Ltd", "decision": "SELL", "confidence": "HIGH", "risk": "HIGH"},
+        "CIPLA": {"symbol": "CIPLA", "company_name": "Cipla Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "BRITANNIA": {"symbol": "BRITANNIA", "company_name": "Britannia Industries Ltd", "decision": "BUY", "confidence": "MEDIUM", "risk": "LOW"},
+        "EICHERMOT": {"symbol": "EICHERMOT", "company_name": "Eicher Motors Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "APOLLOHOSP": {"symbol": "APOLLOHOSP", "company_name": "Apollo Hospitals Enterprise Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "INDUSINDBK": {"symbol": "INDUSINDBK", "company_name": "IndusInd Bank Ltd", "decision": "SELL", "confidence": "HIGH", "risk": "HIGH"},
+        "HEROMOTOCO": {"symbol": "HEROMOTOCO", "company_name": "Hero MotoCorp Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "TATACONSUM": {"symbol": "TATACONSUM", "company_name": "Tata Consumer Products Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "BPCL": {"symbol": "BPCL", "company_name": "Bharat Petroleum Corporation Ltd", "decision": "SELL", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "UPL": {"symbol": "UPL", "company_name": "UPL Ltd", "decision": "HOLD", "confidence": "LOW", "risk": "HIGH"},
+        "HINDALCO": {"symbol": "HINDALCO", "company_name": "Hindalco Industries Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "BAJAJ-AUTO": {"symbol": "BAJAJ-AUTO", "company_name": "Bajaj Auto Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+        "LTIM": {"symbol": "LTIM", "company_name": "LTIMindtree Ltd", "decision": "HOLD", "confidence": "MEDIUM", "risk": "MEDIUM"},
+    },
+    "summary": {
+        "total": 50,
+        "buy": 7,
+        "sell": 10,
+        "hold": 33,
+    },
+    "top_picks": [
+        {
+            "rank": 1,
+            "symbol": "BAJFINANCE",
+            "company_name": "Bajaj Finance Ltd",
+            "decision": "BUY",
+            "reason": "13.7% gain over 30 days (Rs.678 to Rs.771), strongest bullish momentum with robust upward trend.",
+            "risk_level": "MEDIUM",
+        },
+        {
+            "rank": 2,
+            "symbol": "BAJAJFINSV",
+            "company_name": "Bajaj Finserv Ltd",
+            "decision": "BUY",
+            "reason": "14% gain in one month (Rs.1,567 to Rs.1,789) demonstrates clear bullish momentum with sector-wide tailwinds.",
+            "risk_level": "MEDIUM",
+        },
+        {
+            "rank": 3,
+            "symbol": "KOTAKBANK",
+            "company_name": "Kotak Mahindra Bank Ltd",
+            "decision": "BUY",
+            "reason": "Significant breakout on January 20th with 9.2% gain on exceptionally high volume (66.6M shares).",
+            "risk_level": "MEDIUM",
+        },
+    ],
+    "stocks_to_avoid": [
+        {
+            "symbol": "DRREDDY",
+            "company_name": "Dr. Reddy's Laboratories Ltd",
+            "reason": "HIGH CONFIDENCE SELL with 14.9% decline in one month. Severe downtrend with high risk.",
+        },
+        {
+            "symbol": "AXISBANK",
+            "company_name": "Axis Bank Ltd",
+            "reason": "HIGH CONFIDENCE SELL with 10.5% sustained decline. Clear and persistent downtrend.",
+        },
+        {
+            "symbol": "HCLTECH",
+            "company_name": "HCL Technologies Ltd",
+            "reason": "SELL with 9.4% drop from recent highs. High risk rating with continued selling pressure.",
+        },
+        {
+            "symbol": "ADANIPORTS",
+            "company_name": "Adani Ports and SEZ Ltd",
+            "reason": "SELL with 12% monthly decline and consistently lower lows. High risk profile.",
+        },
+    ],
+}
+
+
+def seed_database():
+    """Seed the database with sample data."""
+    print("Seeding database...")
+
+    db.save_recommendation(
+        date=SAMPLE_DATA["date"],
+        analysis_data=SAMPLE_DATA["analysis"],
+        summary=SAMPLE_DATA["summary"],
+        top_picks=SAMPLE_DATA["top_picks"],
+        stocks_to_avoid=SAMPLE_DATA["stocks_to_avoid"],
+    )
+
+    print(f"Saved recommendation for {SAMPLE_DATA['date']}")
+    print(f"  - {len(SAMPLE_DATA['analysis'])} stocks analyzed")
+    print(f"  - Summary: {SAMPLE_DATA['summary']['buy']} BUY, {SAMPLE_DATA['summary']['sell']} SELL, {SAMPLE_DATA['summary']['hold']} HOLD")
+    print("Database seeded successfully!")
+
+
+if __name__ == "__main__":
+    seed_database()

frontend/backend/server.py

@@ -0,0 +1,592 @@
+"""FastAPI server for Nifty50 AI recommendations."""
+from fastapi import FastAPI, HTTPException, BackgroundTasks
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel
+from typing import Optional
+import database as db
+import sys
+import os
+from pathlib import Path
+from datetime import datetime
+import threading
+
+# Add parent directories to path for importing trading agents
+PROJECT_ROOT = Path(__file__).parent.parent.parent
+sys.path.insert(0, str(PROJECT_ROOT))
+
+# Track running analyses
+# NOTE: This is not thread-safe for production multi-worker deployments.
+# For production, use Redis or a database-backed job queue instead.
+running_analyses = {}  # {symbol: {"status": "running", "started_at": datetime, "progress": str}}
+
+app = FastAPI(
+    title="Nifty50 AI API",
+    description="API for Nifty 50 stock recommendations",
+    version="1.0.0"
+)
+
+# Enable CORS for frontend
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # In production, replace with specific origins
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+
+class StockAnalysis(BaseModel):
+    symbol: str
+    company_name: str
+    decision: Optional[str] = None
+    confidence: Optional[str] = None
+    risk: Optional[str] = None
+    raw_analysis: Optional[str] = None
+
+
+class TopPick(BaseModel):
+    rank: int
+    symbol: str
+    company_name: str
+    decision: str
+    reason: str
+    risk_level: str
+
+
+class StockToAvoid(BaseModel):
+    symbol: str
+    company_name: str
+    reason: str
+
+
+class Summary(BaseModel):
+    total: int
+    buy: int
+    sell: int
+    hold: int
+
+
+class DailyRecommendation(BaseModel):
+    date: str
+    analysis: dict[str, StockAnalysis]
+    summary: Summary
+    top_picks: list[TopPick]
+    stocks_to_avoid: list[StockToAvoid]
+
+
+class SaveRecommendationRequest(BaseModel):
+    date: str
+    analysis: dict
+    summary: dict
+    top_picks: list
+    stocks_to_avoid: list
+
+
+# ============== Pipeline Data Models ==============
+
+class AgentReport(BaseModel):
+    agent_type: str
+    report_content: str
+    data_sources_used: Optional[list] = []
+    created_at: Optional[str] = None
+
+
+class DebateHistory(BaseModel):
+    debate_type: str
+    bull_arguments: Optional[str] = None
+    bear_arguments: Optional[str] = None
+    risky_arguments: Optional[str] = None
+    safe_arguments: Optional[str] = None
+    neutral_arguments: Optional[str] = None
+    judge_decision: Optional[str] = None
+    full_history: Optional[str] = None
+
+
+class PipelineStep(BaseModel):
+    step_number: int
+    step_name: str
+    status: str
+    started_at: Optional[str] = None
+    completed_at: Optional[str] = None
+    duration_ms: Optional[int] = None
+    output_summary: Optional[str] = None
+
+
+class DataSourceLog(BaseModel):
+    source_type: str
+    source_name: str
+    data_fetched: Optional[dict] = None
+    fetch_timestamp: Optional[str] = None
+    success: bool = True
+    error_message: Optional[str] = None
+
+
+class SavePipelineDataRequest(BaseModel):
+    date: str
+    symbol: str
+    agent_reports: Optional[dict] = None
+    investment_debate: Optional[dict] = None
+    risk_debate: Optional[dict] = None
+    pipeline_steps: Optional[list] = None
+    data_sources: Optional[list] = None
+
+
+class AnalysisConfig(BaseModel):
+    deep_think_model: Optional[str] = "opus"
+    quick_think_model: Optional[str] = "sonnet"
+    provider: Optional[str] = "claude_subscription"  # claude_subscription or anthropic_api
+    api_key: Optional[str] = None
+    max_debate_rounds: Optional[int] = 1
+
+
+class RunAnalysisRequest(BaseModel):
+    symbol: str
+    date: Optional[str] = None  # Defaults to today if not provided
+    config: Optional[AnalysisConfig] = None
+
+
+def run_analysis_task(symbol: str, date: str, analysis_config: dict = None):
+    """Background task to run trading analysis for a stock."""
+    global running_analyses
+
+    # Default config values
+    if analysis_config is None:
+        analysis_config = {}
+
+    deep_think_model = analysis_config.get("deep_think_model", "opus")
+    quick_think_model = analysis_config.get("quick_think_model", "sonnet")
+    provider = analysis_config.get("provider", "claude_subscription")
+    api_key = analysis_config.get("api_key")
+    max_debate_rounds = analysis_config.get("max_debate_rounds", 1)
+
+    try:
+        running_analyses[symbol] = {
+            "status": "initializing",
+            "started_at": datetime.now().isoformat(),
+            "progress": "Loading trading agents..."
+        }
+
+        # Import trading agents
+        from tradingagents.graph.trading_graph import TradingAgentsGraph
+        from tradingagents.default_config import DEFAULT_CONFIG
+
+        running_analyses[symbol]["progress"] = "Initializing analysis pipeline..."
+
+        # Create config from user settings
+        config = DEFAULT_CONFIG.copy()
+        config["llm_provider"] = "anthropic"  # Use Claude for all LLM
+        config["deep_think_llm"] = deep_think_model
+        config["quick_think_llm"] = quick_think_model
+        config["max_debate_rounds"] = max_debate_rounds
+
+        # If using API provider and key is provided, set it in environment
+        if provider == "anthropic_api" and api_key:
+            os.environ["ANTHROPIC_API_KEY"] = api_key
+
+        running_analyses[symbol]["status"] = "running"
+        running_analyses[symbol]["progress"] = f"Running market analysis (model: {deep_think_model})..."
+
+        # Initialize and run
+        ta = TradingAgentsGraph(debug=False, config=config)
+
+        running_analyses[symbol]["progress"] = f"Analyzing {symbol}..."
+        final_state, decision = ta.propagate(symbol, date)
+
+        running_analyses[symbol] = {
+            "status": "completed",
+            "completed_at": datetime.now().isoformat(),
+            "progress": f"Analysis complete: {decision}",
+            "decision": decision
+        }
+
+    except Exception as e:
+        error_msg = str(e) if str(e) else f"{type(e).__name__}: No details provided"
+        running_analyses[symbol] = {
+            "status": "error",
+            "error": error_msg,
+            "progress": f"Error: {error_msg[:100]}"
+        }
+        import traceback
+        print(f"Analysis error for {symbol}: {type(e).__name__}: {error_msg}")
+        traceback.print_exc()
+
+
+@app.get("/")
+async def root():
+    """API root endpoint."""
+    return {
+        "name": "Nifty50 AI API",
+        "version": "2.0.0",
+        "endpoints": {
+            "GET /recommendations": "Get all recommendations",
+            "GET /recommendations/latest": "Get latest recommendation",
+            "GET /recommendations/{date}": "Get recommendation by date",
+            "GET /recommendations/{date}/{symbol}/pipeline": "Get full pipeline data for a stock",
+            "GET /recommendations/{date}/{symbol}/agents": "Get agent reports for a stock",
+            "GET /recommendations/{date}/{symbol}/debates": "Get debate history for a stock",
+            "GET /recommendations/{date}/{symbol}/data-sources": "Get data source logs for a stock",
+            "GET /recommendations/{date}/pipeline-summary": "Get pipeline summary for all stocks on a date",
+            "GET /stocks/{symbol}/history": "Get stock history",
+            "GET /dates": "Get all available dates",
+            "POST /recommendations": "Save a new recommendation",
+            "POST /pipeline": "Save pipeline data for a stock"
+        }
+    }
+
+
+@app.get("/recommendations")
+async def get_all_recommendations():
+    """Get all daily recommendations."""
+    recommendations = db.get_all_recommendations()
+    return {"recommendations": recommendations, "count": len(recommendations)}
+
+
+@app.get("/recommendations/latest")
+async def get_latest_recommendation():
+    """Get the most recent recommendation."""
+    recommendation = db.get_latest_recommendation()
+    if not recommendation:
+        raise HTTPException(status_code=404, detail="No recommendations found")
+    return recommendation
+
+
+@app.get("/recommendations/{date}")
+async def get_recommendation_by_date(date: str):
+    """Get recommendation for a specific date (format: YYYY-MM-DD)."""
+    recommendation = db.get_recommendation_by_date(date)
+    if not recommendation:
+        raise HTTPException(status_code=404, detail=f"No recommendation found for {date}")
+    return recommendation
+
+
+@app.get("/stocks/{symbol}/history")
+async def get_stock_history(symbol: str):
+    """Get historical recommendations for a specific stock."""
+    history = db.get_stock_history(symbol.upper())
+    return {"symbol": symbol.upper(), "history": history, "count": len(history)}
+
+
+@app.get("/dates")
+async def get_available_dates():
+    """Get all dates with recommendations."""
+    dates = db.get_all_dates()
+    return {"dates": dates, "count": len(dates)}
+
+
+@app.post("/recommendations")
+async def save_recommendation(request: SaveRecommendationRequest):
+    """Save a new daily recommendation."""
+    try:
+        db.save_recommendation(
+            date=request.date,
+            analysis_data=request.analysis,
+            summary=request.summary,
+            top_picks=request.top_picks,
+            stocks_to_avoid=request.stocks_to_avoid
+        )
+        return {"message": f"Recommendation for {request.date} saved successfully"}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+@app.get("/health")
+async def health_check():
+    """Health check endpoint."""
+    return {"status": "healthy", "database": "connected"}
+
+
+# ============== Pipeline Data Endpoints ==============
+
+@app.get("/recommendations/{date}/{symbol}/pipeline")
+async def get_pipeline_data(date: str, symbol: str):
+    """Get full pipeline data for a stock on a specific date."""
+    pipeline_data = db.get_full_pipeline_data(date, symbol.upper())
+
+    # Check if we have any data
+    has_data = (
+        pipeline_data.get('agent_reports') or
+        pipeline_data.get('debates') or
+        pipeline_data.get('pipeline_steps') or
+        pipeline_data.get('data_sources')
+    )
+
+    if not has_data:
+        # Return empty structure with mock pipeline steps if no data
+        return {
+            "date": date,
+            "symbol": symbol.upper(),
+            "agent_reports": {},
+            "debates": {},
+            "pipeline_steps": [],
+            "data_sources": [],
+            "status": "no_data"
+        }
+
+    return {**pipeline_data, "status": "complete"}
+
+
+@app.get("/recommendations/{date}/{symbol}/agents")
+async def get_agent_reports(date: str, symbol: str):
+    """Get agent reports for a stock on a specific date."""
+    reports = db.get_agent_reports(date, symbol.upper())
+    return {
+        "date": date,
+        "symbol": symbol.upper(),
+        "reports": reports,
+        "count": len(reports)
+    }
+
+
+@app.get("/recommendations/{date}/{symbol}/debates")
+async def get_debate_history(date: str, symbol: str):
+    """Get debate history for a stock on a specific date."""
+    debates = db.get_debate_history(date, symbol.upper())
+    return {
+        "date": date,
+        "symbol": symbol.upper(),
+        "debates": debates
+    }
+
+
+@app.get("/recommendations/{date}/{symbol}/data-sources")
+async def get_data_sources(date: str, symbol: str):
+    """Get data source logs for a stock on a specific date."""
+    logs = db.get_data_source_logs(date, symbol.upper())
+    return {
+        "date": date,
+        "symbol": symbol.upper(),
+        "data_sources": logs,
+        "count": len(logs)
+    }
+
+
+@app.get("/recommendations/{date}/pipeline-summary")
+async def get_pipeline_summary(date: str):
+    """Get pipeline summary for all stocks on a specific date."""
+    summary = db.get_pipeline_summary_for_date(date)
+    return {
+        "date": date,
+        "stocks": summary,
+        "count": len(summary)
+    }
+
+
+@app.post("/pipeline")
+async def save_pipeline_data(request: SavePipelineDataRequest):
+    """Save pipeline data for a stock."""
+    try:
+        db.save_full_pipeline_data(
+            date=request.date,
+            symbol=request.symbol.upper(),
+            pipeline_data={
+                'agent_reports': request.agent_reports,
+                'investment_debate': request.investment_debate,
+                'risk_debate': request.risk_debate,
+                'pipeline_steps': request.pipeline_steps,
+                'data_sources': request.data_sources
+            }
+        )
+        return {"message": f"Pipeline data for {request.symbol} on {request.date} saved successfully"}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+# ============== Analysis Endpoints ==============
+
+# Track bulk analysis state
+bulk_analysis_state = {
+    "status": "idle",  # idle, running, completed, error
+    "total": 0,
+    "completed": 0,
+    "failed": 0,
+    "current_symbol": None,
+    "started_at": None,
+    "completed_at": None,
+    "results": {}
+}
+
+# List of Nifty 50 stocks
+NIFTY_50_SYMBOLS = [
+    "RELIANCE", "TCS", "HDFCBANK", "INFY", "ICICIBANK", "HINDUNILVR", "ITC", "SBIN",
+    "BHARTIARTL", "KOTAKBANK", "LT", "AXISBANK", "ASIANPAINT", "MARUTI", "HCLTECH",
+    "SUNPHARMA", "TITAN", "BAJFINANCE", "WIPRO", "ULTRACEMCO", "NESTLEIND", "NTPC",
+    "POWERGRID", "M&M", "TATAMOTORS", "ONGC", "JSWSTEEL", "TATASTEEL", "ADANIENT",
+    "ADANIPORTS", "COALINDIA", "BAJAJFINSV", "TECHM", "HDFCLIFE", "SBILIFE", "GRASIM",
+    "DIVISLAB", "DRREDDY", "CIPLA", "BRITANNIA", "EICHERMOT", "APOLLOHOSP", "INDUSINDBK",
+    "HEROMOTOCO", "TATACONSUM", "BPCL", "UPL", "HINDALCO", "BAJAJ-AUTO", "LTIM"
+]
+
+
+class BulkAnalysisRequest(BaseModel):
+    deep_think_model: Optional[str] = "opus"
+    quick_think_model: Optional[str] = "sonnet"
+    provider: Optional[str] = "claude_subscription"
+    api_key: Optional[str] = None
+    max_debate_rounds: Optional[int] = 1
+
+
+@app.post("/analyze/all")
+async def run_bulk_analysis(request: Optional[BulkAnalysisRequest] = None, date: Optional[str] = None):
+    """Trigger analysis for all Nifty 50 stocks. Runs in background."""
+    global bulk_analysis_state
+
+    # Check if bulk analysis is already running
+    if bulk_analysis_state.get("status") == "running":
+        return {
+            "message": "Bulk analysis already running",
+            "status": bulk_analysis_state
+        }
+
+    # Use today's date if not provided
+    if not date:
+        date = datetime.now().strftime("%Y-%m-%d")
+
+    # Build analysis config from request
+    analysis_config = {}
+    if request:
+        analysis_config = {
+            "deep_think_model": request.deep_think_model,
+            "quick_think_model": request.quick_think_model,
+            "provider": request.provider,
+            "api_key": request.api_key,
+            "max_debate_rounds": request.max_debate_rounds
+        }
+
+    # Start bulk analysis in background thread
+    def run_bulk():
+        global bulk_analysis_state
+        bulk_analysis_state = {
+            "status": "running",
+            "total": len(NIFTY_50_SYMBOLS),
+            "completed": 0,
+            "failed": 0,
+            "current_symbol": None,
+            "started_at": datetime.now().isoformat(),
+            "completed_at": None,
+            "results": {}
+        }
+
+        for symbol in NIFTY_50_SYMBOLS:
+            try:
+                bulk_analysis_state["current_symbol"] = symbol
+                run_analysis_task(symbol, date, analysis_config)
+
+                # Wait for completion
+                import time
+                while symbol in running_analyses and running_analyses[symbol].get("status") == "running":
+                    time.sleep(2)
+
+                if symbol in running_analyses:
+                    status = running_analyses[symbol].get("status", "unknown")
+                    bulk_analysis_state["results"][symbol] = status
+                    if status == "completed":
+                        bulk_analysis_state["completed"] += 1
+                    else:
+                        bulk_analysis_state["failed"] += 1
+                else:
+                    bulk_analysis_state["results"][symbol] = "unknown"
+                    bulk_analysis_state["failed"] += 1
+
+            except Exception as e:
+                bulk_analysis_state["results"][symbol] = f"error: {str(e)}"
+                bulk_analysis_state["failed"] += 1
+
+        bulk_analysis_state["status"] = "completed"
+        bulk_analysis_state["current_symbol"] = None
+        bulk_analysis_state["completed_at"] = datetime.now().isoformat()
+
+    thread = threading.Thread(target=run_bulk)
+    thread.start()
+
+    return {
+        "message": "Bulk analysis started for all Nifty 50 stocks",
+        "date": date,
+        "total_stocks": len(NIFTY_50_SYMBOLS),
+        "status": "started"
+    }
+
+
+@app.get("/analyze/all/status")
+async def get_bulk_analysis_status():
+    """Get the status of bulk analysis."""
+    return bulk_analysis_state
+
+
+@app.get("/analyze/running")
+async def get_running_analyses():
+    """Get all currently running analyses."""
+    running = {k: v for k, v in running_analyses.items() if v.get("status") == "running"}
+    return {
+        "running": running,
+        "count": len(running)
+    }
+
+
+class SingleAnalysisRequest(BaseModel):
+    deep_think_model: Optional[str] = "opus"
+    quick_think_model: Optional[str] = "sonnet"
+    provider: Optional[str] = "claude_subscription"
+    api_key: Optional[str] = None
+    max_debate_rounds: Optional[int] = 1
+
+
+@app.post("/analyze/{symbol}")
+async def run_analysis(symbol: str, background_tasks: BackgroundTasks, request: Optional[SingleAnalysisRequest] = None, date: Optional[str] = None):
+    """Trigger analysis for a stock. Runs in background."""
+    symbol = symbol.upper()
+
+    # Check if analysis is already running
+    if symbol in running_analyses and running_analyses[symbol].get("status") == "running":
+        return {
+            "message": f"Analysis already running for {symbol}",
+            "status": running_analyses[symbol]
+        }
+
+    # Use today's date if not provided
+    if not date:
+        date = datetime.now().strftime("%Y-%m-%d")
+
+    # Build analysis config from request
+    analysis_config = {}
+    if request:
+        analysis_config = {
+            "deep_think_model": request.deep_think_model,
+            "quick_think_model": request.quick_think_model,
+            "provider": request.provider,
+            "api_key": request.api_key,
+            "max_debate_rounds": request.max_debate_rounds
+        }
+
+    # Start analysis in background thread
+    thread = threading.Thread(target=run_analysis_task, args=(symbol, date, analysis_config))
+    thread.start()
+
+    return {
+        "message": f"Analysis started for {symbol}",
+        "symbol": symbol,
+        "date": date,
+        "status": "started"
+    }
+
+
+@app.get("/analyze/{symbol}/status")
+async def get_analysis_status(symbol: str):
+    """Get the status of a running or completed analysis."""
+    symbol = symbol.upper()
+
+    if symbol not in running_analyses:
+        return {
+            "symbol": symbol,
+            "status": "not_started",
+            "message": "No analysis has been run for this stock"
+        }
+
+    return {
+        "symbol": symbol,
+        **running_analyses[symbol]
+    }
+
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8001)

frontend/eslint.config.js

@@ -0,0 +1,23 @@
+import js from '@eslint/js'
+import globals from 'globals'
+import reactHooks from 'eslint-plugin-react-hooks'
+import reactRefresh from 'eslint-plugin-react-refresh'
+import tseslint from 'typescript-eslint'
+import { defineConfig, globalIgnores } from 'eslint/config'
+
+export default defineConfig([
+  globalIgnores(['dist']),
+  {
+    files: ['**/*.{ts,tsx}'],
+    extends: [
+      js.configs.recommended,
+      tseslint.configs.recommended,
+      reactHooks.configs.flat.recommended,
+      reactRefresh.configs.vite,
+    ],
+    languageOptions: {
+      ecmaVersion: 2020,
+      globals: globals.browser,
+    },
+  },
+])

frontend/index.html

@@ -0,0 +1,86 @@
+<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="UTF-8" />
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+
+    <!-- Primary Meta Tags -->
+    <title>Nifty50 AI - Daily Stock Recommendations for Indian Markets</title>
+    <meta name="title" content="Nifty50 AI - Daily Stock Recommendations for Indian Markets" />
+    <meta name="description" content="AI-powered daily stock recommendations for all Nifty 50 stocks. Get actionable buy, sell, and hold signals based on technical analysis, fundamentals, and news sentiment." />
+    <meta name="keywords" content="Nifty 50, stock recommendations, AI stock analysis, Indian stock market, NSE, BSE, trading signals, buy sell hold, stock market India" />
+    <meta name="author" content="Nifty50 AI" />
+    <meta name="robots" content="index, follow" />
+
+    <!-- Favicon -->
+    <link rel="icon" type="image/svg+xml" href="/favicon.svg" />
+    <link rel="apple-touch-icon" sizes="180x180" href="/apple-touch-icon.png" />
+
+    <!-- Open Graph / Facebook -->
+    <meta property="og:type" content="website" />
+    <meta property="og:url" content="https://nifty50ai.com/" />
+    <meta property="og:title" content="Nifty50 AI - Daily Stock Recommendations for Indian Markets" />
+    <meta property="og:description" content="AI-powered daily stock recommendations for all Nifty 50 stocks. Get actionable buy, sell, and hold signals." />
+    <meta property="og:image" content="/og-image.png" />
+    <meta property="og:locale" content="en_IN" />
+    <meta property="og:site_name" content="Nifty50 AI" />
+
+    <!-- Twitter -->
+    <meta property="twitter:card" content="summary_large_image" />
+    <meta property="twitter:url" content="https://nifty50ai.com/" />
+    <meta property="twitter:title" content="Nifty50 AI - Daily Stock Recommendations for Indian Markets" />
+    <meta property="twitter:description" content="AI-powered daily stock recommendations for all Nifty 50 stocks. Get actionable buy, sell, and hold signals." />
+    <meta property="twitter:image" content="/og-image.png" />
+
+    <!-- Theme Color -->
+    <meta name="theme-color" content="#0284c7" />
+    <meta name="msapplication-TileColor" content="#0284c7" />
+
+    <!-- Canonical URL -->
+    <link rel="canonical" href="https://nifty50ai.com/" />
+
+    <!-- Google Fonts -->
+    <link rel="preconnect" href="https://fonts.googleapis.com">
+    <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
+    <link href="https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700&family=Lexend:wght@400;500;600;700&display=swap" rel="stylesheet">
+
+    <!-- Structured Data (JSON-LD) -->
+    <script type="application/ld+json">
+    {
+      "@context": "https://schema.org",
+      "@type": "WebSite",
+      "name": "Nifty50 AI",
+      "description": "AI-powered daily stock recommendations for all Nifty 50 stocks",
+      "url": "https://nifty50ai.com/",
+      "potentialAction": {
+        "@type": "SearchAction",
+        "target": "https://nifty50ai.com/stock/{search_term_string}",
+        "query-input": "required name=search_term_string"
+      }
+    }
+    </script>
+
+    <script type="application/ld+json">
+    {
+      "@context": "https://schema.org",
+      "@type": "Organization",
+      "name": "Nifty50 AI",
+      "url": "https://nifty50ai.com/",
+      "logo": "https://nifty50ai.com/logo.png",
+      "description": "AI-powered stock analysis and recommendations for Indian markets"
+    }
+    </script>
+  </head>
+  <body>
+    <div id="root"></div>
+    <script type="module" src="/src/main.tsx"></script>
+
+    <!-- Noscript fallback -->
+    <noscript>
+      <div style="padding: 20px; text-align: center; font-family: system-ui, sans-serif;">
+        <h1>Nifty50 AI - Stock Recommendations</h1>
+        <p>Please enable JavaScript to view this website.</p>
+      </div>
+    </noscript>
+  </body>
+</html>

frontend/package.json

@@ -0,0 +1,41 @@
+{
+  "name": "frontend",
+  "private": true,
+  "version": "0.0.0",
+  "type": "module",
+  "scripts": {
+    "dev": "vite",
+    "build": "tsc -b && vite build",
+    "lint": "eslint .",
+    "preview": "vite preview"
+  },
+  "dependencies": {
+    "@tailwindcss/postcss": "^4.1.18",
+    "date-fns": "^4.1.0",
+    "lucide-react": "^0.563.0",
+    "react": "^19.2.0",
+    "react-dom": "^19.2.0",
+    "react-router-dom": "^7.13.0",
+    "recharts": "^3.7.0"
+  },
+  "devDependencies": {
+    "@eslint/js": "^9.39.1",
+    "@tailwindcss/vite": "^4.1.18",
+    "@types/node": "^24.10.1",
+    "@types/react": "^19.2.5",
+    "@types/react-dom": "^19.2.3",
+    "@vitejs/plugin-react": "^5.1.1",
+    "autoprefixer": "^10.4.24",
+    "eslint": "^9.39.1",
+    "eslint-plugin-react-hooks": "^7.0.1",
+    "eslint-plugin-react-refresh": "^0.4.24",
+    "globals": "^16.5.0",
+    "playwright": "^1.58.1",
+    "postcss": "^8.5.6",
+    "puppeteer": "^24.36.1",
+    "tailwindcss": "^4.1.18",
+    "typescript": "~5.9.3",
+    "typescript-eslint": "^8.46.4",
+    "vite": "^7.2.4"
+  }
+}

frontend/postcss.config.js

@@ -0,0 +1,6 @@
+export default {
+  plugins: {
+    '@tailwindcss/postcss': {},
+    autoprefixer: {},
+  },
+}

frontend/public/favicon.svg

@@ -0,0 +1,11 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 64 64">
+  <defs>
+    <linearGradient id="bg" x1="0%" y1="0%" x2="100%" y2="100%">
+      <stop offset="0%" style="stop-color:#0ea5e9"/>
+      <stop offset="100%" style="stop-color:#0369a1"/>
+    </linearGradient>
+  </defs>
+  <rect width="64" height="64" rx="14" fill="url(#bg)"/>
+  <path d="M16 44 L26 28 L36 36 L48 20" stroke="white" stroke-width="4" stroke-linecap="round" stroke-linejoin="round" fill="none"/>
+  <circle cx="48" cy="20" r="4" fill="#22c55e"/>
+</svg>

frontend/public/vite.svg

@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" class="iconify iconify--logos" width="31.88" height="32" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 257"><defs><linearGradient id="IconifyId1813088fe1fbc01fb466" x1="-.828%" x2="57.636%" y1="7.652%" y2="78.411%"><stop offset="0%" stop-color="#41D1FF"></stop><stop offset="100%" stop-color="#BD34FE"></stop></linearGradient><linearGradient id="IconifyId1813088fe1fbc01fb467" x1="43.376%" x2="50.316%" y1="2.242%" y2="89.03%"><stop offset="0%" stop-color="#FFEA83"></stop><stop offset="8.333%" stop-color="#FFDD35"></stop><stop offset="100%" stop-color="#FFA800"></stop></linearGradient></defs><path fill="url(#IconifyId1813088fe1fbc01fb466)" d="M255.153 37.938L134.897 252.976c-2.483 4.44-8.862 4.466-11.382.048L.875 37.958c-2.746-4.814 1.371-10.646 6.827-9.67l120.385 21.517a6.537 6.537 0 0 0 2.322-.004l117.867-21.483c5.438-.991 9.574 4.796 6.877 9.62Z"></path><path fill="url(#IconifyId1813088fe1fbc01fb467)" d="M185.432.063L96.44 17.501a3.268 3.268 0 0 0-2.634 3.014l-5.474 92.456a3.268 3.268 0 0 0 3.997 3.378l24.777-5.718c2.318-.535 4.413 1.507 3.936 3.838l-7.361 36.047c-.495 2.426 1.782 4.5 4.151 3.78l15.304-4.649c2.372-.72 4.652 1.36 4.15 3.788l-11.698 56.621c-.732 3.542 3.979 5.473 5.943 2.437l1.313-2.028l72.516-144.72c1.215-2.423-.88-5.186-3.54-4.672l-25.505 4.922c-2.396.462-4.435-1.77-3.759-4.114l16.646-57.705c.677-2.35-1.37-4.583-3.769-4.113Z"></path></svg>

frontend/src/App.css

@@ -0,0 +1,42 @@
+#root {
+  max-width: 1280px;
+  margin: 0 auto;
+  padding: 2rem;
+  text-align: center;
+}
+
+.logo {
+  height: 6em;
+  padding: 1.5em;
+  will-change: filter;
+  transition: filter 300ms;
+}
+.logo:hover {
+  filter: drop-shadow(0 0 2em #646cffaa);
+}
+.logo.react:hover {
+  filter: drop-shadow(0 0 2em #61dafbaa);
+}
+
+@keyframes logo-spin {
+  from {
+    transform: rotate(0deg);
+  }
+  to {
+    transform: rotate(360deg);
+  }
+}
+
+@media (prefers-reduced-motion: no-preference) {
+  a:nth-of-type(2) .logo {
+    animation: logo-spin infinite 20s linear;
+  }
+}
+
+.card {
+  padding: 2em;
+}
+
+.read-the-docs {
+  color: #888;
+}

frontend/src/App.tsx

@@ -0,0 +1,34 @@
+import { Routes, Route } from 'react-router-dom';
+import { ThemeProvider } from './contexts/ThemeContext';
+import { SettingsProvider } from './contexts/SettingsContext';
+import Header from './components/Header';
+import Footer from './components/Footer';
+import SettingsModal from './components/SettingsModal';
+import Dashboard from './pages/Dashboard';
+import History from './pages/History';
+import StockDetail from './pages/StockDetail';
+import About from './pages/About';
+
+function App() {
+  return (
+    <ThemeProvider>
+      <SettingsProvider>
+        <div className="min-h-screen flex flex-col bg-gray-50 dark:bg-slate-900 transition-colors">
+          <Header />
+          <main className="flex-1 max-w-7xl mx-auto w-full px-3 sm:px-4 lg:px-6 py-4">
+            <Routes>
+              <Route path="/" element={<Dashboard />} />
+              <Route path="/history" element={<History />} />
+              <Route path="/stock/:symbol" element={<StockDetail />} />
+              <Route path="/about" element={<About />} />
+            </Routes>
+          </main>
+          <Footer />
+          <SettingsModal />
+        </div>
+      </SettingsProvider>
+    </ThemeProvider>
+  );
+}
+
+export default App;

frontend/src/assets/react.svg

@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" class="iconify iconify--logos" width="35.93" height="32" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 228"><path fill="#00D8FF" d="M210.483 73.824a171.49 171.49 0 0 0-8.24-2.597c.465-1.9.893-3.777 1.273-5.621c6.238-30.281 2.16-54.676-11.769-62.708c-13.355-7.7-35.196.329-57.254 19.526a171.23 171.23 0 0 0-6.375 5.848a155.866 155.866 0 0 0-4.241-3.917C100.759 3.829 77.587-4.822 63.673 3.233C50.33 10.957 46.379 33.89 51.995 62.588a170.974 170.974 0 0 0 1.892 8.48c-3.28.932-6.445 1.924-9.474 2.98C17.309 83.498 0 98.307 0 113.668c0 15.865 18.582 31.778 46.812 41.427a145.52 145.52 0 0 0 6.921 2.165a167.467 167.467 0 0 0-2.01 9.138c-5.354 28.2-1.173 50.591 12.134 58.266c13.744 7.926 36.812-.22 59.273-19.855a145.567 145.567 0 0 0 5.342-4.923a168.064 168.064 0 0 0 6.92 6.314c21.758 18.722 43.246 26.282 56.54 18.586c13.731-7.949 18.194-32.003 12.4-61.268a145.016 145.016 0 0 0-1.535-6.842c1.62-.48 3.21-.974 4.76-1.488c29.348-9.723 48.443-25.443 48.443-41.52c0-15.417-17.868-30.326-45.517-39.844Zm-6.365 70.984c-1.4.463-2.836.91-4.3 1.345c-3.24-10.257-7.612-21.163-12.963-32.432c5.106-11 9.31-21.767 12.459-31.957c2.619.758 5.16 1.557 7.61 2.4c23.69 8.156 38.14 20.213 38.14 29.504c0 9.896-15.606 22.743-40.946 31.14Zm-10.514 20.834c2.562 12.94 2.927 24.64 1.23 33.787c-1.524 8.219-4.59 13.698-8.382 15.893c-8.067 4.67-25.32-1.4-43.927-17.412a156.726 156.726 0 0 1-6.437-5.87c7.214-7.889 14.423-17.06 21.459-27.246c12.376-1.098 24.068-2.894 34.671-5.345a134.17 134.17 0 0 1 1.386 6.193ZM87.276 214.515c-7.882 2.783-14.16 2.863-17.955.675c-8.075-4.657-11.432-22.636-6.853-46.752a156.923 156.923 0 0 1 1.869-8.499c10.486 2.32 22.093 3.988 34.498 4.994c7.084 9.967 14.501 19.128 21.976 27.15a134.668 134.668 0 0 1-4.877 4.492c-9.933 8.682-19.886 14.842-28.658 17.94ZM50.35 144.747c-12.483-4.267-22.792-9.812-29.858-15.863c-6.35-5.437-9.555-10.836-9.555-15.216c0-9.322 13.897-21.212 37.076-29.293c2.813-.98 5.757-1.905 8.812-2.773c3.204 10.42 7.406 21.315 12.477 32.332c-5.137 11.18-9.399 22.249-12.634 32.792a134.718 134.718 0 0 1-6.318-1.979Zm12.378-84.26c-4.811-24.587-1.616-43.134 6.425-47.789c8.564-4.958 27.502 2.111 47.463 19.835a144.318 144.318 0 0 1 3.841 3.545c-7.438 7.987-14.787 17.08-21.808 26.988c-12.04 1.116-23.565 2.908-34.161 5.309a160.342 160.342 0 0 1-1.76-7.887Zm110.427 27.268a347.8 347.8 0 0 0-7.785-12.803c8.168 1.033 15.994 2.404 23.343 4.08c-2.206 7.072-4.956 14.465-8.193 22.045a381.151 381.151 0 0 0-7.365-13.322Zm-45.032-43.861c5.044 5.465 10.096 11.566 15.065 18.186a322.04 322.04 0 0 0-30.257-.006c4.974-6.559 10.069-12.652 15.192-18.18ZM82.802 87.83a323.167 323.167 0 0 0-7.227 13.238c-3.184-7.553-5.909-14.98-8.134-22.152c7.304-1.634 15.093-2.97 23.209-3.984a321.524 321.524 0 0 0-7.848 12.897Zm8.081 65.352c-8.385-.936-16.291-2.203-23.593-3.793c2.26-7.3 5.045-14.885 8.298-22.6a321.187 321.187 0 0 0 7.257 13.246c2.594 4.48 5.28 8.868 8.038 13.147Zm37.542 31.03c-5.184-5.592-10.354-11.779-15.403-18.433c4.902.192 9.899.29 14.978.29c5.218 0 10.376-.117 15.453-.343c-4.985 6.774-10.018 12.97-15.028 18.486Zm52.198-57.817c3.422 7.8 6.306 15.345 8.596 22.52c-7.422 1.694-15.436 3.058-23.88 4.071a382.417 382.417 0 0 0 7.859-13.026a347.403 347.403 0 0 0 7.425-13.565Zm-16.898 8.101a358.557 358.557 0 0 1-12.281 19.815a329.4 329.4 0 0 1-23.444.823c-7.967 0-15.716-.248-23.178-.732a310.202 310.202 0 0 1-12.513-19.846h.001a307.41 307.41 0 0 1-10.923-20.627a310.278 310.278 0 0 1 10.89-20.637l-.001.001a307.318 307.318 0 0 1 12.413-19.761c7.613-.576 15.42-.876 23.31-.876H128c7.926 0 15.743.303 23.354.883a329.357 329.357 0 0 1 12.335 19.695a358.489 358.489 0 0 1 11.036 20.54a329.472 329.472 0 0 1-11 20.722Zm22.56-122.124c8.572 4.944 11.906 24.881 6.52 51.026c-.344 1.668-.73 3.367-1.15 5.09c-10.622-2.452-22.155-4.275-34.23-5.408c-7.034-10.017-14.323-19.124-21.64-27.008a160.789 160.789 0 0 1 5.888-5.4c18.9-16.447 36.564-22.941 44.612-18.3ZM128 90.808c12.625 0 22.86 10.235 22.86 22.86s-10.235 22.86-22.86 22.86s-22.86-10.235-22.86-22.86s10.235-22.86 22.86-22.86Z"></path></svg>

frontend/src/components/AIAnalysisPanel.tsx

@@ -0,0 +1,152 @@
+import { useState } from 'react';
+import { Brain, ChevronDown, ChevronUp, TrendingUp, BarChart2, MessageSquare, AlertTriangle, Target } from 'lucide-react';
+import type { Decision } from '../types';
+
+interface AIAnalysisPanelProps {
+  analysis: string;
+  decision?: Decision | null;
+  defaultExpanded?: boolean;
+}
+
+interface Section {
+  title: string;
+  content: string;
+  icon: typeof Brain;
+}
+
+function parseAnalysis(analysis: string): Section[] {
+  const sections: Section[] = [];
+  const iconMap: Record<string, typeof Brain> = {
+    'Summary': Target,
+    'Technical Analysis': BarChart2,
+    'Fundamental Analysis': TrendingUp,
+    'Sentiment': MessageSquare,
+    'Risks': AlertTriangle,
+  };
+
+  // Split by markdown headers (##)
+  const parts = analysis.split(/^## /gm).filter(Boolean);
+
+  for (const part of parts) {
+    const lines = part.trim().split('\n');
+    const title = lines[0].trim();
+    const content = lines.slice(1).join('\n').trim();
+
+    if (title && content) {
+      sections.push({
+        title,
+        content,
+        icon: iconMap[title] || Brain,
+      });
+    }
+  }
+
+  // If no sections found, treat the whole thing as a summary
+  if (sections.length === 0 && analysis.trim()) {
+    sections.push({
+      title: 'Analysis',
+      content: analysis.trim(),
+      icon: Brain,
+    });
+  }
+
+  return sections;
+}
+
+function AnalysisSection({ section, defaultOpen = true }: { section: Section; defaultOpen?: boolean }) {
+  const [isOpen, setIsOpen] = useState(defaultOpen);
+  const Icon = section.icon;
+
+  return (
+    <div className="border-b border-gray-100 dark:border-slate-700 last:border-0">
+      <button
+        onClick={() => setIsOpen(!isOpen)}
+        className="w-full flex items-center justify-between px-4 py-2.5 text-left hover:bg-gray-50 dark:hover:bg-slate-700/50 transition-colors"
+      >
+        <div className="flex items-center gap-2">
+          <Icon className="w-4 h-4 text-nifty-600 dark:text-nifty-400" />
+          <span className="font-medium text-sm text-gray-900 dark:text-gray-100">{section.title}</span>
+        </div>
+        {isOpen ? (
+          <ChevronUp className="w-4 h-4 text-gray-400" />
+        ) : (
+          <ChevronDown className="w-4 h-4 text-gray-400" />
+        )}
+      </button>
+      {isOpen && (
+        <div className="px-4 pb-3 text-sm text-gray-600 dark:text-gray-300 whitespace-pre-wrap leading-relaxed">
+          {section.content.split('\n').map((line, i) => {
+            // Handle bullet points
+            if (line.trim().startsWith('- ')) {
+              return (
+                <div key={i} className="flex gap-2 mt-1">
+                  <span className="text-nifty-500">•</span>
+                  <span>{line.trim().substring(2)}</span>
+                </div>
+              );
+            }
+            return <p key={i} className={line.trim() ? 'mt-1' : 'mt-2'}>{line}</p>;
+          })}
+        </div>
+      )}
+    </div>
+  );
+}
+
+export default function AIAnalysisPanel({
+  analysis,
+  decision,
+  defaultExpanded = false,
+}: AIAnalysisPanelProps) {
+  const [isExpanded, setIsExpanded] = useState(defaultExpanded);
+  const sections = parseAnalysis(analysis);
+
+  const decisionGradient = {
+    BUY: 'from-green-500 to-emerald-600',
+    SELL: 'from-red-500 to-rose-600',
+    HOLD: 'from-amber-500 to-orange-600',
+  };
+
+  const gradient = decision ? decisionGradient[decision] : 'from-nifty-500 to-nifty-700';
+
+  return (
+    <section className="card overflow-hidden">
+      {/* Header with gradient */}
+      <button
+        onClick={() => setIsExpanded(!isExpanded)}
+        className={`w-full bg-gradient-to-r ${gradient} p-3 text-white flex items-center justify-between`}
+      >
+        <div className="flex items-center gap-2">
+          <Brain className="w-5 h-5" />
+          <span className="font-semibold text-sm">AI Analysis</span>
+          <span className="text-xs bg-white/20 px-2 py-0.5 rounded-full">
+            {sections.length} sections
+          </span>
+        </div>
+        <div className="flex items-center gap-2">
+          <span className="text-xs text-white/80">
+            {isExpanded ? 'Click to collapse' : 'Click to expand'}
+          </span>
+          {isExpanded ? (
+            <ChevronUp className="w-4 h-4" />
+          ) : (
+            <ChevronDown className="w-4 h-4" />
+          )}
+        </div>
+      </button>
+
+      {/* Content */}
+      {isExpanded && (
+        <div className="bg-white dark:bg-slate-800">
+          {sections.map((section, index) => (
+            <AnalysisSection
+              key={index}
+              section={section}
+              defaultOpen={index === 0}
+            />
+          ))}
+        </div>
+      )}
+    </section>
+  );
+}

frontend/src/components/AccuracyBadge.tsx

@@ -0,0 +1,72 @@
+import { Check, X, Minus } from 'lucide-react';
+
+interface AccuracyBadgeProps {
+  correct: boolean | null;
+  returnPercent: number;
+  size?: 'small' | 'default';
+}
+
+export default function AccuracyBadge({
+  correct,
+  returnPercent,
+  size = 'default',
+}: AccuracyBadgeProps) {
+  const isPositiveReturn = returnPercent >= 0;
+  const sizeClasses = size === 'small' ? 'text-xs px-1.5 py-0.5 gap-1' : 'text-sm px-2 py-1 gap-1.5';
+  const iconSize = size === 'small' ? 'w-3 h-3' : 'w-3.5 h-3.5';
+
+  if (correct === null) {
+    return (
+      <span className={`inline-flex items-center rounded-full font-medium bg-gray-100 dark:bg-slate-700 text-gray-500 dark:text-gray-400 ${sizeClasses}`}>
+        <Minus className={iconSize} />
+        <span>Pending</span>
+      </span>
+    );
+  }
+
+  if (correct) {
+    return (
+      <span className={`inline-flex items-center rounded-full font-medium bg-green-100 dark:bg-green-900/30 text-green-700 dark:text-green-400 ${sizeClasses}`}>
+        <Check className={iconSize} />
+        <span className={isPositiveReturn ? '' : 'text-green-600 dark:text-green-400'}>
+          {isPositiveReturn ? '+' : ''}{returnPercent.toFixed(1)}%
+        </span>
+      </span>
+    );
+  }
+
+  return (
+    <span className={`inline-flex items-center rounded-full font-medium bg-red-100 dark:bg-red-900/30 text-red-700 dark:text-red-400 ${sizeClasses}`}>
+      <X className={iconSize} />
+      <span>
+        {isPositiveReturn ? '+' : ''}{returnPercent.toFixed(1)}%
+      </span>
+    </span>
+  );
+}
+
+interface AccuracyRateProps {
+  rate: number;
+  label?: string;
+  size?: 'small' | 'default';
+}
+
+export function AccuracyRate({ rate, label = 'Accuracy', size = 'default' }: AccuracyRateProps) {
+  const percentage = rate * 100;
+  const isGood = percentage >= 60;
+  const isModerate = percentage >= 40 && percentage < 60;
+
+  const sizeClasses = size === 'small' ? 'text-xs' : 'text-sm';
+  const colorClass = isGood
+    ? 'text-green-600 dark:text-green-400'
+    : isModerate
+    ? 'text-amber-600 dark:text-amber-400'
+    : 'text-red-600 dark:text-red-400';
+
+  return (
+    <div className={`flex items-center gap-1.5 ${sizeClasses}`}>
+      <span className="text-gray-500 dark:text-gray-400">{label}:</span>
+      <span className={`font-semibold ${colorClass}`}>{percentage.toFixed(0)}%</span>
+    </div>
+  );
+}

frontend/src/components/AccuracyExplainModal.tsx

@@ -0,0 +1,177 @@
+import { X, HelpCircle, TrendingUp, TrendingDown, Minus, CheckCircle } from 'lucide-react';
+import type { AccuracyMetrics } from '../types';
+
+interface AccuracyExplainModalProps {
+  isOpen: boolean;
+  onClose: () => void;
+  metrics: AccuracyMetrics;
+}
+
+export default function AccuracyExplainModal({ isOpen, onClose, metrics }: AccuracyExplainModalProps) {
+  if (!isOpen) return null;
+
+  const buyCorrect = Math.round(metrics.buy_accuracy * metrics.total_predictions * 0.14); // ~7 buy signals
+  const buyTotal = Math.round(metrics.total_predictions * 0.14);
+  const sellCorrect = Math.round(metrics.sell_accuracy * metrics.total_predictions * 0.2); // ~10 sell signals
+  const sellTotal = Math.round(metrics.total_predictions * 0.2);
+  const holdCorrect = Math.round(metrics.hold_accuracy * metrics.total_predictions * 0.66); // ~33 hold signals
+  const holdTotal = Math.round(metrics.total_predictions * 0.66);
+
+  return (
+    <div className="fixed inset-0 z-50 flex items-center justify-center p-4">
+      {/* Backdrop */}
+      <div
+        className="absolute inset-0 bg-black/50 backdrop-blur-sm"
+        onClick={onClose}
+      />
+
+      {/* Modal */}
+      <div className="relative bg-white dark:bg-slate-800 rounded-xl shadow-xl max-w-lg w-full max-h-[90vh] overflow-y-auto">
+        {/* Header */}
+        <div className="sticky top-0 flex items-center justify-between p-4 border-b border-gray-100 dark:border-slate-700 bg-white dark:bg-slate-800">
+          <div className="flex items-center gap-2">
+            <HelpCircle className="w-5 h-5 text-nifty-600 dark:text-nifty-400" />
+            <h2 className="text-lg font-semibold text-gray-900 dark:text-gray-100">
+              How Accuracy is Calculated
+            </h2>
+          </div>
+          <button
+            onClick={onClose}
+            className="p-1.5 rounded-lg hover:bg-gray-100 dark:hover:bg-slate-700 transition-colors"
+          >
+            <X className="w-5 h-5 text-gray-500 dark:text-gray-400" />
+          </button>
+        </div>
+
+        {/* Content */}
+        <div className="p-4 space-y-5">
+          {/* Overview */}
+          <div className="p-4 rounded-lg bg-nifty-50 dark:bg-nifty-900/20 border border-nifty-100 dark:border-nifty-800">
+            <h3 className="font-semibold text-gray-900 dark:text-gray-100 mb-2">Overall Accuracy</h3>
+            <div className="text-3xl font-bold text-nifty-600 dark:text-nifty-400 mb-1">
+              {(metrics.success_rate * 100).toFixed(1)}%
+            </div>
+            <p className="text-sm text-gray-600 dark:text-gray-400">
+              {metrics.correct_predictions} correct out of {metrics.total_predictions} predictions
+            </p>
+          </div>
+
+          {/* Formula */}
+          <div>
+            <h3 className="font-semibold text-gray-900 dark:text-gray-100 mb-2">Calculation Method</h3>
+            <div className="p-3 rounded-lg bg-gray-50 dark:bg-slate-700/50 font-mono text-sm">
+              <p className="text-gray-700 dark:text-gray-300">
+                Accuracy = (Correct Predictions / Total Predictions) × 100
+              </p>
+              <p className="text-gray-500 dark:text-gray-400 mt-2 text-xs">
+                = ({metrics.correct_predictions} / {metrics.total_predictions}) × 100 = {(metrics.success_rate * 100).toFixed(1)}%
+              </p>
+            </div>
+          </div>
+
+          {/* Decision Type Breakdown */}
+          <div>
+            <h3 className="font-semibold text-gray-900 dark:text-gray-100 mb-3">Breakdown by Decision Type</h3>
+            <div className="space-y-3">
+              {/* BUY */}
+              <div className="p-3 rounded-lg bg-green-50 dark:bg-green-900/20 border border-green-100 dark:border-green-800">
+                <div className="flex items-center justify-between mb-2">
+                  <div className="flex items-center gap-2">
+                    <TrendingUp className="w-4 h-4 text-green-600 dark:text-green-400" />
+                    <span className="font-medium text-green-800 dark:text-green-300">BUY Predictions</span>
+                  </div>
+                  <span className="text-lg font-bold text-green-600 dark:text-green-400">
+                    {(metrics.buy_accuracy * 100).toFixed(0)}%
+                  </span>
+                </div>
+                <p className="text-xs text-green-700 dark:text-green-400">
+                  A BUY prediction is correct if the stock price <strong>increased</strong> after the recommendation
+                </p>
+                <div className="flex items-center gap-2 mt-2 text-xs text-green-600 dark:text-green-500">
+                  <CheckCircle className="w-3 h-3" />
+                  <span>~{buyCorrect} correct / {buyTotal} total BUY signals</span>
+                </div>
+              </div>
+
+              {/* SELL */}
+              <div className="p-3 rounded-lg bg-red-50 dark:bg-red-900/20 border border-red-100 dark:border-red-800">
+                <div className="flex items-center justify-between mb-2">
+                  <div className="flex items-center gap-2">
+                    <TrendingDown className="w-4 h-4 text-red-600 dark:text-red-400" />
+                    <span className="font-medium text-red-800 dark:text-red-300">SELL Predictions</span>
+                  </div>
+                  <span className="text-lg font-bold text-red-600 dark:text-red-400">
+                    {(metrics.sell_accuracy * 100).toFixed(0)}%
+                  </span>
+                </div>
+                <p className="text-xs text-red-700 dark:text-red-400">
+                  A SELL prediction is correct if the stock price <strong>decreased</strong> after the recommendation
+                </p>
+                <div className="flex items-center gap-2 mt-2 text-xs text-red-600 dark:text-red-500">
+                  <CheckCircle className="w-3 h-3" />
+                  <span>~{sellCorrect} correct / {sellTotal} total SELL signals</span>
+                </div>
+              </div>
+
+              {/* HOLD */}
+              <div className="p-3 rounded-lg bg-amber-50 dark:bg-amber-900/20 border border-amber-100 dark:border-amber-800">
+                <div className="flex items-center justify-between mb-2">
+                  <div className="flex items-center gap-2">
+                    <Minus className="w-4 h-4 text-amber-600 dark:text-amber-400" />
+                    <span className="font-medium text-amber-800 dark:text-amber-300">HOLD Predictions</span>
+                  </div>
+                  <span className="text-lg font-bold text-amber-600 dark:text-amber-400">
+                    {(metrics.hold_accuracy * 100).toFixed(0)}%
+                  </span>
+                </div>
+                <p className="text-xs text-amber-700 dark:text-amber-400">
+                  A HOLD prediction is correct if the stock price stayed <strong>relatively stable</strong> (±2% range)
+                </p>
+                <div className="flex items-center gap-2 mt-2 text-xs text-amber-600 dark:text-amber-500">
+                  <CheckCircle className="w-3 h-3" />
+                  <span>~{holdCorrect} correct / {holdTotal} total HOLD signals</span>
+                </div>
+              </div>
+            </div>
+          </div>
+
+          {/* Timeframe */}
+          <div>
+            <h3 className="font-semibold text-gray-900 dark:text-gray-100 mb-2">Evaluation Timeframe</h3>
+            <div className="p-3 rounded-lg bg-gray-50 dark:bg-slate-700/50">
+              <ul className="text-sm text-gray-600 dark:text-gray-400 space-y-1">
+                <li className="flex items-start gap-2">
+                  <span className="text-nifty-600 dark:text-nifty-400">•</span>
+                  <span><strong>1-week return:</strong> Short-term price movement validation</span>
+                </li>
+                <li className="flex items-start gap-2">
+                  <span className="text-nifty-600 dark:text-nifty-400">•</span>
+                  <span><strong>1-month return:</strong> Primary accuracy metric (shown in results)</span>
+                </li>
+              </ul>
+            </div>
+          </div>
+
+          {/* Disclaimer */}
+          <div className="p-3 rounded-lg bg-gray-100 dark:bg-slate-700/30 border border-gray-200 dark:border-slate-600">
+            <p className="text-xs text-gray-500 dark:text-gray-400">
+              <strong>Note:</strong> Past performance does not guarantee future results.
+              Accuracy metrics are based on historical data and are for educational purposes only.
+              Market conditions can change rapidly and predictions may not hold in future periods.
+            </p>
+          </div>
+        </div>
+
+        {/* Footer */}
+        <div className="sticky bottom-0 p-4 border-t border-gray-100 dark:border-slate-700 bg-white dark:bg-slate-800">
+          <button
+            onClick={onClose}
+            className="w-full btn-primary"
+          >
+            Got it
+          </button>
+        </div>
+      </div>
+    </div>
+  );
+}

frontend/src/components/AccuracyTrendChart.tsx

@@ -0,0 +1,92 @@
+import { LineChart, Line, XAxis, YAxis, CartesianGrid, Tooltip, ResponsiveContainer, Legend } from 'recharts';
+import { getAccuracyTrend } from '../data/recommendations';
+
+interface AccuracyTrendChartProps {
+  height?: number;
+  className?: string;
+}
+
+export default function AccuracyTrendChart({ height = 200, className = '' }: AccuracyTrendChartProps) {
+  const data = getAccuracyTrend();
+
+  if (data.length === 0) {
+    return (
+      <div className={`flex items-center justify-center text-gray-400 ${className}`} style={{ height }}>
+        No accuracy data available
+      </div>
+    );
+  }
+
+  // Format dates for display
+  const formattedData = data.map(d => ({
+    ...d,
+    displayDate: new Date(d.date).toLocaleDateString('en-IN', { month: 'short', day: 'numeric' }),
+  }));
+
+  return (
+    <div className={className} style={{ height }}>
+      <ResponsiveContainer width="100%" height="100%">
+        <LineChart data={formattedData} margin={{ top: 5, right: 10, bottom: 5, left: 0 }}>
+          <CartesianGrid strokeDasharray="3 3" className="stroke-gray-200 dark:stroke-slate-700" />
+          <XAxis
+            dataKey="displayDate"
+            tick={{ fontSize: 11 }}
+            className="text-gray-500 dark:text-gray-400"
+          />
+          <YAxis
+            domain={[0, 100]}
+            tick={{ fontSize: 11 }}
+            tickFormatter={(v) => `${v}%`}
+            className="text-gray-500 dark:text-gray-400"
+          />
+          <Tooltip
+            contentStyle={{
+              backgroundColor: 'var(--tooltip-bg, #fff)',
+              border: '1px solid var(--tooltip-border, #e5e7eb)',
+              borderRadius: '8px',
+              fontSize: '12px',
+            }}
+            formatter={(value) => [`${value}%`, '']}
+            labelFormatter={(label) => `Date: ${label}`}
+          />
+          <Legend
+            wrapperStyle={{ fontSize: '11px' }}
+            formatter={(value) => value.charAt(0).toUpperCase() + value.slice(1)}
+          />
+          <Line
+            type="monotone"
+            dataKey="overall"
+            stroke="#0ea5e9"
+            strokeWidth={2}
+            dot={{ fill: '#0ea5e9', r: 3 }}
+            activeDot={{ r: 5 }}
+          />
+          <Line
+            type="monotone"
+            dataKey="buy"
+            stroke="#22c55e"
+            strokeWidth={1.5}
+            dot={{ fill: '#22c55e', r: 2 }}
+            strokeDasharray="5 5"
+          />
+          <Line
+            type="monotone"
+            dataKey="sell"
+            stroke="#ef4444"
+            strokeWidth={1.5}
+            dot={{ fill: '#ef4444', r: 2 }}
+            strokeDasharray="5 5"
+          />
+          <Line
+            type="monotone"
+            dataKey="hold"
+            stroke="#f59e0b"
+            strokeWidth={1.5}
+            dot={{ fill: '#f59e0b', r: 2 }}
+            strokeDasharray="5 5"
+          />
+        </LineChart>
+      </ResponsiveContainer>
+    </div>
+  );
+}

frontend/src/components/BackgroundSparkline.tsx

@@ -0,0 +1,64 @@
+import { AreaChart, Area, ResponsiveContainer, YAxis } from 'recharts';
+import type { PricePoint } from '../types';
+
+interface BackgroundSparklineProps {
+  data: PricePoint[];
+  trend: 'up' | 'down' | 'flat';
+  className?: string;
+}
+
+export default function BackgroundSparkline({
+  data,
+  trend,
+  className = '',
+}: BackgroundSparklineProps) {
+  if (!data || data.length < 2) {
+    return null;
+  }
+
+  // Normalize data to percentage change from first point
+  const basePrice = data[0].price;
+  const normalizedData = data.map(point => ({
+    ...point,
+    normalizedPrice: ((point.price - basePrice) / basePrice) * 100,
+  }));
+
+  // Calculate min/max for domain padding
+  const prices = normalizedData.map(d => d.normalizedPrice);
+  const minPrice = Math.min(...prices);
+  const maxPrice = Math.max(...prices);
+  const padding = Math.max(Math.abs(maxPrice - minPrice) * 0.2, 1);
+
+  // Colors based on trend
+  const colors = {
+    up: { stroke: '#22c55e', fill: '#22c55e' },
+    down: { stroke: '#ef4444', fill: '#ef4444' },
+    flat: { stroke: '#94a3b8', fill: '#94a3b8' },
+  };
+
+  const { stroke, fill } = colors[trend];
+
+  return (
+    <div className={`w-full h-full ${className}`} style={{ filter: 'blur(1px)' }}>
+      <ResponsiveContainer width="100%" height="100%">
+        <AreaChart data={normalizedData} margin={{ top: 0, right: 0, bottom: 0, left: 0 }}>
+          <YAxis domain={[minPrice - padding, maxPrice + padding]} hide />
+          <defs>
+            <linearGradient id={`gradient-${trend}`} x1="0" y1="0" x2="0" y2="1">
+              <stop offset="0%" stopColor={fill} stopOpacity={0.4} />
+              <stop offset="100%" stopColor={fill} stopOpacity={0.05} />
+            </linearGradient>
+          </defs>
+          <Area
+            type="monotone"
+            dataKey="normalizedPrice"
+            stroke={stroke}
+            strokeWidth={1}
+            fill={`url(#gradient-${trend})`}
+            isAnimationActive={false}
+          />
+        </AreaChart>
+      </ResponsiveContainer>
+    </div>
+  );
+}