Zhigong Liu 2cdada6300 fix: suppress memory injection when memory is empty (hallucination guard, closes #572) ... When past_memories is empty, all five agents previously injected an empty string into their prompts while still instructing the LLM to "address reflections and learn from past mistakes" — causing the LLM to hallucinate fabricated lessons on first run. Each agent now conditionally builds its memory section only when past_memories is non-empty, so the injection and its instruction are both absent when there is nothing to recall. Also fixes import ordering in memory.py (logger after imports). Tests: tests/test_hallucination_guard.py covers empty and populated memory for all five agents (bull, bear, trader, research manager, portfolio manager). Companion to #563 (memory persistence). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>		2026-04-18 22:30:31 -04:00
..
agent_states.py	refactor: remove stale imports, use configurable results path (#499)	2026-04-04 07:35:35 +00:00
agent_utils.py	feat: multi-language output support for analyst reports and final decision (#472)	2026-03-29 19:19:01 +00:00
core_stock_tools.py	minor fix	2025-09-26 23:25:33 +08:00
fundamental_data_tools.py	minor fix	2025-09-26 23:25:33 +08:00
memory.py	fix: suppress memory injection when memory is empty (hallucination guard, closes #572)	2026-04-18 22:30:31 -04:00
news_data_tools.py	fix: improve data vendor implementations and tool signatures	2026-02-03 22:27:20 +00:00
technical_indicators_tools.py	fix: normalize indicator names to lowercase (#490)	2026-04-04 07:23:31 +00:00