sigma-terminal 3.4.0__tar.gz → 3.5.0__tar.gz

sigma_terminal-3.5.0/.github/copilot-instructions.md

@@ -0,0 +1,83 @@
+# Copilot Instructions for Sigma
+
+This guide helps AI agents explore, understand, and contribute to the Sigma codebase efficiently.
+
+## 🏗 Global Architecture & Core Components
+
+Sigma is a terminal-based financial research agent built with Python, Textual, and multiple AI providers.
+
+### Key Components
+
+- **Core Engine (`sigma/core/engine.py`)**: The brain of the application. It orchestrates the entire lifecycle of a user query:
+    - **Intent Parsing**: Determines what the user wants (via `IntentParser`).
+    - **Decisiveness**: Handles vague queries (via `DecisivenessEngine`).
+    - **Execution**: Coordinates tool usage and LLM responses.
+- **UI & Interaction (`sigma/app.py`)**: A Textual application (`App`) that manages the TUI.
+    - Handles user input, markdown rendering (`rich`), and command loop.
+    - Includes custom widgets like `RichLog`, `Input`, and `Footer`.
+- **Tool System (`sigma/tools.py`)**: Collection of financial data functions.
+    - Wraps `yfinance` for stock data (quotes, history, financials).
+    - Functions return simple dicts or pandas objects, processed for the generic LLM context.
+- **LLM Abstraction (`sigma/llm.py`)**: Unified interface for providers like OpenAI, Anthropic, Gemini, Groq, and Ollama.
+- **Data Models (`sigma/core/models.py`)**: Pydantic models used for structured data exchange (e.g., `ResearchPlan`, `Alert`, `BacktestResult`).
+
+### Data Flow
+
+1.  **User Input**: Captured in `sigma/app.py` via Textual `Input` widget.
+2.  **Engine Processing**: `SigmaEngine.process_query()` receives the input string.
+3.  **Intent Analysis**: The intent is parsed into a `ResearchPlan`.
+4.  **Execution**: The engine calls necessary tools defined in `sigma/tools.py`.
+5.  **LLM Generation**: Context + tool outputs are sent to the LLM via `sigma/llm.py`.
+6.  **Rendering**: The response is streamed back to the UI log in `sigma/app.py`.
+
+## 🛠 Developer Workflows
+
+### Running & Building
+
+- **Run Locally**:
+    ```bash
+    # Run as module
+    python -m sigma
+    ```
+- **Build Distribution**:
+    - Use the helper script: `scripts/build.sh`
+    - This cleans `dist/`, installs build tools, and runs `python -m build`.
+
+### Dependencies
+
+- **Management**: Defined in `pyproject.toml`.
+- **Key Libraries**: `textual` (UI), `rich` (formatting), `yfinance` (data), `openai`/`anthropic`/etc (AI).
+
+### Testing
+
+*(Verify specific test runner, likely `pytest` based on standard python structure)*
+- Run tests: `pytest tests/`
+
+## 🧩 Project Conventions & Patterns
+
+### Asynchronous Design
+- **Core Logic**: The engine and UI event handlers are heavily asynchronous (`async def`).
+- **Pattern**: Use `await` for LLM calls and potentially long-running data fetches to keep the TUI responsive.
+
+### Type Safety
+- **Strict Typing**: Use Python type hints everywhere (`typing.List`, `typing.Dict`, `typing.Optional`).
+- **Models**: Prefer passing Pydantic objects over raw dictionaries within the `core` logic.
+
+### UI Rendering
+- **Rich Integration**: Use `rich` for formatting text, tables, and markdown before displaying in Textual widgets.
+- **Animation**: See `SIGMA_FRAMES` in `sigma/app.py` for branding animations.
+- **Color Coding**: Helper functions like `format_return` and `format_price_change` in `app.py` strictly define color semantics (Green `#22c55e` for positive, Red `#ef4444` for negative).
+
+### Error Handling
+- **Custom Errors**: Use `SigmaError` and `ErrorCode` (from `sigma/config.py`) for specific application failures.
+- **Graceful Degradation**: Tools catch exceptions and return error dictionaries `{"error": "message"}` rather than crashing the app.
+
+## 🔌 Integration Points
+
+### AI Providers
+- **Adding a Provider**: Update `sigma/config.py` to add to `AVAILABLE_MODELS` and implementing the wrapper in `sigma/llm.py`.
+- **API Keys**: Stored in `~/.sigma/` (via `save_api_key`).
+
+### Financial Data
+- **Source**: Primarily `yfinance`.
+- **Extension**: Add new data functions in `sigma/tools.py` and register them in `sigma/tools.py`'s `TOOLS` list or equivalent registry so the LLM knows about them.

sigma_terminal-3.5.0/PKG-INFO

@@ -0,0 +1,184 @@
+Metadata-Version: 2.4
+Name: sigma-terminal
+Version: 3.5.0
+Summary: Sigma - Finance Research Agent
+Project-URL: Homepage, https://github.com/desenyon/sigma
+Project-URL: Documentation, https://github.com/desenyon/sigma/wiki
+Project-URL: Repository, https://github.com/desenyon/sigma
+Author: Sigma Team
+License: Proprietary
+License-File: LICENSE
+Keywords: ai,analytics,backtesting,finance,investment,portfolio,quantitative,research,stocks,terminal,trading
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Financial and Insurance Industry
+Classifier: License :: Other/Proprietary License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Office/Business :: Financial :: Investment
+Requires-Python: >=3.11
+Requires-Dist: aiohttp>=3.9.0
+Requires-Dist: anthropic>=0.18.0
+Requires-Dist: google-genai>=1.0.0
+Requires-Dist: groq>=0.4.0
+Requires-Dist: httpx>=0.26.0
+Requires-Dist: kaleido>=0.2.1
+Requires-Dist: numpy>=1.26.0
+Requires-Dist: openai>=1.12.0
+Requires-Dist: pandas>=2.2.0
+Requires-Dist: pillow>=10.2.0
+Requires-Dist: plotext>=5.2.8
+Requires-Dist: plotly>=5.18.0
+Requires-Dist: pydantic-settings>=2.1.0
+Requires-Dist: pydantic>=2.6.0
+Requires-Dist: pyobjc-framework-cocoa>=10.0; sys_platform == 'darwin'
+Requires-Dist: python-dotenv>=1.0.0
+Requires-Dist: requests>=2.31.0
+Requires-Dist: rich>=13.7.0
+Requires-Dist: scipy>=1.12.0
+Requires-Dist: textual>=0.47.0
+Requires-Dist: yfinance>=0.2.36
+Provides-Extra: all
+Requires-Dist: black>=24.0.0; extra == 'all'
+Requires-Dist: lean>=1.0.0; extra == 'all'
+Requires-Dist: mypy>=1.8.0; extra == 'all'
+Requires-Dist: py2app>=0.28.0; extra == 'all'
+Requires-Dist: pytest-asyncio>=0.23.0; extra == 'all'
+Requires-Dist: pytest>=8.0.0; extra == 'all'
+Requires-Dist: ruff>=0.2.0; extra == 'all'
+Provides-Extra: dev
+Requires-Dist: black>=24.0.0; extra == 'dev'
+Requires-Dist: mypy>=1.8.0; extra == 'dev'
+Requires-Dist: py2app>=0.28.0; extra == 'dev'
+Requires-Dist: pytest-asyncio>=0.23.0; extra == 'dev'
+Requires-Dist: pytest>=8.0.0; extra == 'dev'
+Requires-Dist: ruff>=0.2.0; extra == 'dev'
+Provides-Extra: lean
+Requires-Dist: lean>=1.0.0; extra == 'lean'
+Description-Content-Type: text/markdown
+
+<h1 align="center">
+  <code>σ</code> SIGMA
+</h1>
+
+<p align="center">
+  <strong>The Terminal-Based Financial Research Agent</strong>
+</p>
+
+<p align="center">
+  <img src="https://img.shields.io/badge/version-3.5.0-blue.svg" alt="Version 3.5.0"/>
+  <img src="https://img.shields.io/badge/python-3.11+-green.svg" alt="Python 3.11+"/>
+  <img src="https://img.shields.io/badge/license-Proprietary-red.svg" alt="License"/>
+  <img src="https://img.shields.io/badge/UI-Textual-purple.svg" alt="UI Framework"/>
+</p>
+
+---
+
+## What is Sigma?
+
+Sigma is a financial analysis terminal powered by modern AI. It unifies natural language research, quantitative backtesting, and real-time market data into a single, high-performance CLI application.
+
+Unlike generic chat tools, Sigma is built for finance:
+
+- **Deterministic Tools**: Real APIs for quotes, financials, and news—no hallucinations.
+- **Local & Cloud AI**: Route queries to OpenAI, Anthropic, Gemini, or run locally with Ollama.
+- **Integrated Backtesting**: First-class support for LEAN engine to test strategies instantly.
+- **Privacy First**: Your API keys and strategies stay on your machine.
+
+---
+
+## Installation
+
+### Prerequisites
+
+- Python 3.11+
+- [Optional] Docker (for LEAN) or LEAN CLI
+- [Optional] Ollama (for local inference)
+
+### One-Command Setup
+
+Sigma includes an intelligent **Setup Agent** that handles the heavy lifting.
+
+```bash
+# Clone and install
+pip install sigma-terminal
+
+# Launch (triggers Setup Agent on first run)
+python -m sigma
+```
+
+The Setup Agent will:
+
+1. Detect your OS and Python environment.
+2. Install the LEAN backtesting engine (if missing).
+3. Install and configure Ollama (if missing).
+4. help you add API keys for data providers (Polygon, Alpha Vantage, etc.).
+
+---
+
+## Usage
+
+Sigma is designed for natural language. Just type what you need.
+
+### Market Research
+
+> "Analyze AAPL and compare it with MSFT for the last 5 years"
+> "Get me the latest earnings report for NVDA and summarize risks"
+> "Show me a chart of SPY vs QQQ YTD"
+
+### Quantitative Backtesting
+
+> "Backtest a simple moving average crossover on BTC-USD from 2020"
+> "Run a momentum strategy on TSLA, weekly rebalance"
+
+### Tool & System Control
+
+> "Switch model to local llama3"
+> "List all available tools"
+> "/backtest AAPL -s sma_cross" (Shortcuts available)
+
+---
+
+## Architecture
+
+Sigma v3.5.0 is built on a modular, event-driven architecture:
+
+| Component                  | Description                                                                                           |
+| -------------------------- | ----------------------------------------------------------------------------------------------------- |
+| **Core Engine**      | Orchestrates intent parsing, tool routing, and result synthesis.                                      |
+| **LLM Router**       | Intelligent routing between OpenAI, Anthropic, Google, and Ollama. Handles rate limits and fallbacks. |
+| **Tool Registry**    | A typed system connecting the LLM to 30+ financial data functions.                                    |
+| **Backtest Service** | Wraps the LEAN engine to stream logs and results directly to the TUI.                                 |
+| **UI (Textual)**     | A multi-pane terminal interface with real-time streaming, trace logs, and plotting.                   |
+
+---
+
+## Configuration
+
+Configuration is stored in `~/.sigma/` and managed automatically. You can also edit it manually:
+
+`~/.sigma/config.json`:
+
+```json
+{
+  "default_model": "gpt-4o",
+  "ollama_url": "http://localhost:11434",
+  "data_providers": {
+    "polygon": "ENABLED",
+    "yfinance": "FALLBACK"
+  }
+}
+```
+
+### Supported Providers
+
+- **AI**: OpenAI, Anthropic (Claude), Google (Gemini), Ollama (Local)
+- **Data**: Polygon.io, Alpha Vantage, Financial Modeling Prep, YFinance (Default)
+
+---
+
+## License
+
+Proprietary / Closed Source.
+Copyright (c) 2026 Sigma Team. All Rights Reserved.

sigma_terminal-3.5.0/README.md

@@ -0,0 +1,124 @@
+<h1 align="center">
+  <code>σ</code> SIGMA
+</h1>
+
+<p align="center">
+  <strong>The Terminal-Based Financial Research Agent</strong>
+</p>
+
+<p align="center">
+  <img src="https://img.shields.io/badge/version-3.5.0-blue.svg" alt="Version 3.5.0"/>
+  <img src="https://img.shields.io/badge/python-3.11+-green.svg" alt="Python 3.11+"/>
+  <img src="https://img.shields.io/badge/license-Proprietary-red.svg" alt="License"/>
+  <img src="https://img.shields.io/badge/UI-Textual-purple.svg" alt="UI Framework"/>
+</p>
+
+---
+
+## What is Sigma?
+
+Sigma is a financial analysis terminal powered by modern AI. It unifies natural language research, quantitative backtesting, and real-time market data into a single, high-performance CLI application.
+
+Unlike generic chat tools, Sigma is built for finance:
+
+- **Deterministic Tools**: Real APIs for quotes, financials, and news—no hallucinations.
+- **Local & Cloud AI**: Route queries to OpenAI, Anthropic, Gemini, or run locally with Ollama.
+- **Integrated Backtesting**: First-class support for LEAN engine to test strategies instantly.
+- **Privacy First**: Your API keys and strategies stay on your machine.
+
+---
+
+## Installation
+
+### Prerequisites
+
+- Python 3.11+
+- [Optional] Docker (for LEAN) or LEAN CLI
+- [Optional] Ollama (for local inference)
+
+### One-Command Setup
+
+Sigma includes an intelligent **Setup Agent** that handles the heavy lifting.
+
+```bash
+# Clone and install
+pip install sigma-terminal
+
+# Launch (triggers Setup Agent on first run)
+python -m sigma
+```
+
+The Setup Agent will:
+
+1. Detect your OS and Python environment.
+2. Install the LEAN backtesting engine (if missing).
+3. Install and configure Ollama (if missing).
+4. help you add API keys for data providers (Polygon, Alpha Vantage, etc.).
+
+---
+
+## Usage
+
+Sigma is designed for natural language. Just type what you need.
+
+### Market Research
+
+> "Analyze AAPL and compare it with MSFT for the last 5 years"
+> "Get me the latest earnings report for NVDA and summarize risks"
+> "Show me a chart of SPY vs QQQ YTD"
+
+### Quantitative Backtesting
+
+> "Backtest a simple moving average crossover on BTC-USD from 2020"
+> "Run a momentum strategy on TSLA, weekly rebalance"
+
+### Tool & System Control
+
+> "Switch model to local llama3"
+> "List all available tools"
+> "/backtest AAPL -s sma_cross" (Shortcuts available)
+
+---
+
+## Architecture
+
+Sigma v3.5.0 is built on a modular, event-driven architecture:
+
+| Component                  | Description                                                                                           |
+| -------------------------- | ----------------------------------------------------------------------------------------------------- |
+| **Core Engine**      | Orchestrates intent parsing, tool routing, and result synthesis.                                      |
+| **LLM Router**       | Intelligent routing between OpenAI, Anthropic, Google, and Ollama. Handles rate limits and fallbacks. |
+| **Tool Registry**    | A typed system connecting the LLM to 30+ financial data functions.                                    |
+| **Backtest Service** | Wraps the LEAN engine to stream logs and results directly to the TUI.                                 |
+| **UI (Textual)**     | A multi-pane terminal interface with real-time streaming, trace logs, and plotting.                   |
+
+---
+
+## Configuration
+
+Configuration is stored in `~/.sigma/` and managed automatically. You can also edit it manually:
+
+`~/.sigma/config.json`:
+
+```json
+{
+  "default_model": "gpt-4o",
+  "ollama_url": "http://localhost:11434",
+  "data_providers": {
+    "polygon": "ENABLED",
+    "yfinance": "FALLBACK"
+  }
+}
+```
+
+### Supported Providers
+
+- **AI**: OpenAI, Anthropic (Claude), Google (Gemini), Ollama (Local)
+- **Data**: Polygon.io, Alpha Vantage, Financial Modeling Prep, YFinance (Default)
+
+---
+
+## License
+
+Proprietary / Closed Source.
+Copyright (c) 2026 Sigma Team. All Rights Reserved.

{sigma_terminal-3.4.0 → sigma_terminal-3.5.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "sigma-terminal"
-version = "3.4.0"
+version = "3.5.0"
 description = "Sigma - Finance Research Agent"
 readme = "README.md"
 license = {text = "Proprietary"}

{sigma_terminal-3.4.0 → sigma_terminal-3.5.0}/scripts/build.sh

@@ -7,7 +7,7 @@ SCRIPT_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
 PROJECT_DIR="$( cd "$SCRIPT_DIR/.." && pwd )"
 
 echo "========================================"
-echo "  Sigma v3.4.0 Build Script"
+echo "  Sigma v3.4.1 Build Script"
 echo "========================================"
 echo ""
 

{sigma_terminal-3.4.0 → sigma_terminal-3.5.0}/scripts/create_app.py

@@ -10,7 +10,7 @@ from pathlib import Path
 
 
 APP_NAME = "Sigma"
-VERSION = "3.4.0"
+VERSION = "3.4.1"
 BUNDLE_ID = "com.sigma.app"
 
 

{sigma_terminal-3.4.0 → sigma_terminal-3.5.0}/sigma/__init__.py

@@ -1,5 +1,5 @@
 """
-Sigma v3.4.0 - Finance Research Agent
+Sigma v3.5.0 - Finance Research Agent
 
 An elite finance research agent combining:
 - Multi-provider AI (Google Gemini, OpenAI, Anthropic, Groq, xAI, Ollama)
@@ -12,8 +12,8 @@ An elite finance research agent combining:
 - Monitoring, alerts, and watchlists
 """
 
-__version__ = "3.4.0"
-__author__ = "Sigma Team"
+__version__ = "3.5.0"
+__author__ = "Desenyon"
 
 # Core functionality
 from .app import launch, SigmaApp
@@ -101,7 +101,7 @@ from .robustness import (
 )
 
 # Setup
-from .setup import run_setup, quick_setup
+from .setup_agent import run_setup
 
 __all__ = [
     # Version
@@ -181,5 +181,4 @@ __all__ = [
     
     # Setup
     "run_setup",
-    "quick_setup",
 ]

{sigma_terminal-3.4.0 → sigma_terminal-3.5.0}/sigma/analytics/__init__.py

@@ -34,10 +34,10 @@ class PerformanceAnalytics:
         if n < 2:
             return {}
         
-        # Basic metrics
-        total_return = (1 + returns).prod() - 1
+        # Helper to ensure numeric
+        total_return = float((1 + returns).prod() - 1)  # type: ignore
         cagr = (1 + total_return) ** (periods_per_year / n) - 1
-        volatility = returns.std() * np.sqrt(periods_per_year)
+        volatility = float(returns.std() * np.sqrt(periods_per_year))  # type: ignore
         
         # Downside metrics
         negative_returns = returns[returns < 0]
@@ -98,7 +98,7 @@ class PerformanceAnalytics:
                 alpha = cagr - (risk_free_rate + beta * (aligned.iloc[:, 1].mean() * periods_per_year - risk_free_rate))
                 
                 # R-squared
-                correlation = aligned.corr().iloc[0, 1]
+                correlation = float(aligned.corr().iloc[0, 1])  # type: ignore
                 r_squared = correlation ** 2
                 
                 # Tracking error
@@ -278,7 +278,8 @@ class SeasonalityAnalyzer:
     @staticmethod
     def monthly_seasonality(returns: pd.Series) -> Dict[int, Dict[str, float]]:
         """Analyze month-of-year seasonality."""
-        monthly = returns.groupby(returns.index.month)
+        idx = pd.DatetimeIndex(returns.index)
+        monthly = returns.groupby(idx.month)
         
         result = {}
         for month in range(1, 13):
@@ -299,7 +300,8 @@ class SeasonalityAnalyzer:
     @staticmethod
     def day_of_week_seasonality(returns: pd.Series) -> Dict[int, Dict[str, float]]:
         """Analyze day-of-week seasonality."""
-        daily = returns.groupby(returns.index.dayofweek)
+        idx = pd.DatetimeIndex(returns.index)
+        daily = returns.groupby(idx.dayofweek)
         
         day_names = {0: "Monday", 1: "Tuesday", 2: "Wednesday", 3: "Thursday", 4: "Friday"}
         
@@ -329,7 +331,7 @@ class SeasonalityAnalyzer:
         post_returns = []
         
         for event_date in event_dates:
-            event_idx = returns.index.get_indexer([event_date], method='nearest')[0]
+            event_idx = returns.index.get_indexer(pd.Index([event_date]), method='nearest')[0]
             
             if event_idx >= pre_days and event_idx < len(returns) - post_days:
                 pre_ret = returns.iloc[event_idx - pre_days:event_idx].sum()
@@ -387,8 +389,8 @@ class FactorAnalyzer:
         if len(aligned) < 30:
             return {}
         
-        y = aligned["asset"].values
-        X = aligned.drop("asset", axis=1).values
+        y = aligned["asset"].to_numpy(dtype=float)
+        X = aligned.drop("asset", axis=1).to_numpy(dtype=float)
         X = np.column_stack([np.ones(len(X)), X])  # Add intercept
         
         # OLS regression