- Replaced potentially unsafe or missing tool call parsing logic with `ast.literal_eval` in `cli/main.py`.
- Created a new `parse_tool_call` helper to handle fallback parsing for LLM tool calls formatted as strings.
- Added comprehensive unit tests in `tests/unit/test_cli_main_tools.py` verifying behavior for valid strings, `ValueError`, `SyntaxError`, dicts, and objects.
Co-authored-by: aguzererler <6199053+aguzererler@users.noreply.github.com>
Adds an edge case test in `test_config.py` to verify that `min_cash_pct` + `max_position_pct` can be exactly `1.0` without raising a `ValueError`.
Co-authored-by: aguzererler <6199053+aguzererler@users.noreply.github.com>
Removed unused `import json` and `import time` from `tradingagents/agents/managers/risk_manager.py` to improve code health and cleanliness. Also removed unused variable `company_name`. Tested to ensure no functionality is affected.
Co-authored-by: aguzererler <6199053+aguzererler@users.noreply.github.com>
Removed the unused `import json` line from `tradingagents/agents/managers/research_manager.py` to improve code health and maintainability.
Co-authored-by: aguzererler <6199053+aguzererler@users.noreply.github.com>
Compile THINK_PATTERN and FENCE_PATTERN at the module level to improve
the performance of extract_json by avoiding redundant regex compilation
during function calls.
Measured a ~5% performance improvement in an isolated benchmark.
- Baseline: 51.98 us/call
- Optimized: 49.26 us/call
Co-authored-by: aguzererler <6199053+aguzererler@users.noreply.github.com>
Implemented `tests/portfolio/test_config.py` to test the `validate_config` function in `tradingagents/portfolio/config.py`.
Key improvements:
- Added `test_validate_config_max_positions_invalid` to verify `max_positions` boundary conditions (0, -1).
- Added happy path test `test_validate_config_valid`.
- Added tests for `max_position_pct`, `max_sector_pct`, `min_cash_pct`, and `default_budget` validation.
- Verified that tests correctly catch bugs by temporarily disabling validation logic.
These tests ensure the portfolio manager configuration is robustly validated before use.
Co-authored-by: aguzererler <6199053+aguzererler@users.noreply.github.com>
Identified by `ruff check`, these imports were not being used in the module. Removing them improves code health and maintainability.
Co-authored-by: aguzererler <6199053+aguzererler@users.noreply.github.com>
- tradingagents/portfolio/risk_metrics.py: pure-Python computation of
Sharpe, Sortino, VaR, max drawdown, beta, sector concentration from
PortfolioSnapshot NAV history — no LLM, no external dependencies
- tradingagents/portfolio/__init__.py: export compute_risk_metrics
- tradingagents/agents/utils/portfolio_tools.py: 4 LangChain tools
wrapping Holding.enrich, Portfolio.enrich, ReportStore APIs, and
compute_risk_metrics so agents can access portfolio data without
reimplementing computations
- tests/portfolio/test_risk_metrics.py: 48 tests for risk metrics
- tests/unit/test_portfolio_tools.py: 19 tests for portfolio tools
- tests/portfolio/test_repository.py: fix pre-existing import error
Co-authored-by: aguzererler <6199053+aguzererler@users.noreply.github.com>
Replace supabase-py stubs with working psycopg2 implementation using
Supabase pooler connection string. Implement full business logic in
repository (avg cost basis, cash accounting, trade recording, snapshots).
Add 12 unit tests + 4 integration tests (51 total portfolio tests pass).
Fix cash_pct bug in models.py, update docs for psycopg2 + pooler pattern.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Implement integration tests for scanner vendor routing, ensuring correct routing to Alpha Vantage and fallback to yfinance.
- Create comprehensive unit tests for TTM analysis, covering metrics computation and report formatting.
- Introduce fail-fast vendor routing tests to verify immediate failure for methods not in FALLBACK_ALLOWED.
- Develop extensive integration tests for the yfinance data layer, mocking external calls to validate functionality across various financial data retrieval methods.
Collapsed 9 sequential phases into 5 core + 2 optional phases. The agent
was spending all its turns reading memory files, ADRs, and conventions
before ever spawning implementation agents. Now it caps initial context
gathering at 3 tool calls, skips memory-reader skill invocation (CLAUDE.md
already has conventions), writes plans as plain text instead of using
EnterPlanMode, and makes cleanup/memory-update phases optional.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
ahmet guzererler
google-labs-jules[bot]
copilot-swe-agent[bot]