TradingAgents

Commit Graph

Author	SHA1	Message	Date
Joseph O'Brien	1ba647ae4a	feat: add quantitative scoring with multi-timeframe analysis and CLI enhancements Add quantitative scoring pipeline for discovery with technical indicator analysis: - Momentum, volume, relative strength, and risk/reward scoring - Support/resistance level detection - Gap analysis for price momentum signals - Configurable caching to reduce API calls Implement multi-timeframe signal analysis: - Short-term (5/20 day), medium-term (20/50 day), and long-term (50/200 day) signals - Timeframe alignment detection (aligned_bullish, aligned_bearish, mixed, neutral) - Signal strength calculation based on indicator agreement Enhance CLI discovery display: - Color-coded conviction scores (green/yellow/red thresholds) - Signal column showing timeframe alignment status - News mentions count column Update tests to support new quantitative filtering configuration. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-12-03 17:04:18 -05:00
Joseph O'Brien	c39f9aab36	Add pre-commit hooks and ruff code quality configuration - Add .pre-commit-config.yaml with trailing whitespace, ruff linter/formatter - Configure ruff in pyproject.toml with selected rules (E, F, W, I, UP, B, C4, SIM) - Add F401 to unfixable to preserve re-exported imports in __init__.py files - Fix BacktestMetrics import in backtesting/engine.py - Update todos.md with enhanced trade discovery and database implementation tasks 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-12-03 11:22:13 -05:00
Joseph O'Brien	3f6b1e9f39	Add trending stock discovery feature Implement a multi-stage pipeline to discover trending stocks from news: - Entity extraction from news articles using LLM - Stock ticker resolution via Yahoo Finance - Sector classification and event categorization - Scoring algorithm based on mentions, sentiment, and recency - CLI integration with interactive stock selection and analysis flow - Persistence layer for saving discovery results - Comprehensive test suite for all discovery components Update README with uv-based installation instructions and remove emojis. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-12-02 20:19:34 -05:00

Author

SHA1

Message

Date

Joseph O'Brien

1ba647ae4a

feat: add quantitative scoring with multi-timeframe analysis and CLI enhancements

Add quantitative scoring pipeline for discovery with technical indicator analysis:
- Momentum, volume, relative strength, and risk/reward scoring
- Support/resistance level detection
- Gap analysis for price momentum signals
- Configurable caching to reduce API calls

Implement multi-timeframe signal analysis:
- Short-term (5/20 day), medium-term (20/50 day), and long-term (50/200 day) signals
- Timeframe alignment detection (aligned_bullish, aligned_bearish, mixed, neutral)
- Signal strength calculation based on indicator agreement

Enhance CLI discovery display:
- Color-coded conviction scores (green/yellow/red thresholds)
- Signal column showing timeframe alignment status
- News mentions count column

Update tests to support new quantitative filtering configuration.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

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

2025-12-03 17:04:18 -05:00

Joseph O'Brien

c39f9aab36

Add pre-commit hooks and ruff code quality configuration

- Add .pre-commit-config.yaml with trailing whitespace, ruff linter/formatter
- Configure ruff in pyproject.toml with selected rules (E, F, W, I, UP, B, C4, SIM)
- Add F401 to unfixable to preserve re-exported imports in __init__.py files
- Fix BacktestMetrics import in backtesting/engine.py
- Update todos.md with enhanced trade discovery and database implementation tasks

🤖 Generated with [Claude Code](https://claude.com/claude-code)

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

2025-12-03 11:22:13 -05:00

Joseph O'Brien

3f6b1e9f39

Add trending stock discovery feature

Implement a multi-stage pipeline to discover trending stocks from news:
- Entity extraction from news articles using LLM
- Stock ticker resolution via Yahoo Finance
- Sector classification and event categorization
- Scoring algorithm based on mentions, sentiment, and recency
- CLI integration with interactive stock selection and analysis flow
- Persistence layer for saving discovery results
- Comprehensive test suite for all discovery components

Update README with uv-based installation instructions and remove emojis.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

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

2025-12-02 20:19:34 -05:00

3 Commits