feat: replace per-agent BM25 memory with persistent append-only decision log

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Zhigong Liu
2026-04-19 22:13:53 -04:00
parent 8536ccacdd
commit 6abc768c1d
15 changed files with 1046 additions and 340 deletions
@@ -1,6 +1,6 @@
def create_bear_researcher(llm, memory):
def create_bear_researcher(llm):
def bear_node(state) -> dict:
investment_debate_state = state["investment_debate_state"]
history = investment_debate_state.get("history", "")
@@ -12,13 +12,6 @@ def create_bear_researcher(llm, memory):
news_report = state["news_report"]
fundamentals_report = state["fundamentals_report"]
curr_situation = f"{market_research_report}\n\n{sentiment_report}\n\n{news_report}\n\n{fundamentals_report}"
past_memories = memory.get_memories(curr_situation, n_matches=2)
past_memory_str = ""
for i, rec in enumerate(past_memories, 1):
past_memory_str += rec["recommendation"] + "\n\n"
prompt = f"""You are a Bear Analyst making the case against investing in the stock. Your goal is to present a well-reasoned argument emphasizing risks, challenges, and negative indicators. Leverage the provided research and data to highlight potential downsides and counter bullish arguments effectively.
Key points to focus on:
@@ -37,8 +30,7 @@ Latest world affairs news: {news_report}
Company fundamentals report: {fundamentals_report}
Conversation history of the debate: {history}
Last bull argument: {current_response}
Reflections from similar situations and lessons learned: {past_memory_str}
Use this information to deliver a compelling bear argument, refute the bull's claims, and engage in a dynamic debate that demonstrates the risks and weaknesses of investing in the stock. You must also address reflections and learn from lessons and mistakes you made in the past.
Use this information to deliver a compelling bear argument, refute the bull's claims, and engage in a dynamic debate that demonstrates the risks and weaknesses of investing in the stock.
"""
response = llm.invoke(prompt)