3 Commits

Author	SHA1	Message	Date
copilot-swe-agent[bot]	9c014a8038	Parallel pre-fetch for analyst agents to reduce LLM round-trips ... Co-authored-by: aguzererler <6199053+aguzererler@users.noreply.github.com> Agent-Logs-Url: https://github.com/aguzererler/TradingAgents/sessions/a8c6b73e-9694-4e34-8767-36e475deb12f	2026-03-23 21:08:15 +00:00
google-labs-jules[bot]	3721aab110	test: add unit tests for analyst agents tool looping ... Added comprehensive unit tests for `fundamentals_analyst`, `market_analyst`, `social_media_analyst`, and `news_analyst` to verify that they correctly handle recursive tool calling via `run_tool_loop`. A MockLLM was created to simulate a two-turn conversation (tool call request followed by a final report generation) to ensure the `.invoke()` bug does not regress. Added missing `build_instrument_context` imports to those agents to prevent NameErrors. Co-authored-by: aguzererler <6199053+aguzererler@users.noreply.github.com>	2026-03-23 17:22:28 +00:00
google-labs-jules[bot]	3b9eef380d	test: add unit tests for _tokenize in FinancialSituationMemory ... Adds comprehensive tests for `_tokenize` method inside `tradingagents/agents/utils/memory.py` focusing on regex behavior `\b\w+\b` with case mixing, punctuation, edges (empty string), numbers, underscores, quoting, and hyphenation strings. Co-authored-by: aguzererler <6199053+aguzererler@users.noreply.github.com>	2026-03-21 01:54:23 +00:00