feat: replace per-agent BM25 memory with persistent decision log (#578, #563, #564, #579)

The previous per-agent BM25 memory was effectively dead code — its only
caller was a commented-out line in main.py. Replace it with a single
append-only markdown decision log driven by the propagate() lifecycle.

Lifecycle:
- store_decision() appends a pending entry at the end of every run
- _resolve_pending_entries() runs at the start of the next same-ticker
  run, fetches yfinance returns + alpha vs SPY, and writes one LLM
  reflection per resolved entry through an atomic temp-file rename
- Portfolio Manager consumes state["past_context"] (5 most recent
  same-ticker entries plus 3 cross-ticker reflection-only excerpts)

Storage at ~/.tradingagents/memory/trading_memory.md
(override: TRADINGAGENTS_MEMORY_LOG_PATH).

Tag schema:
- Pending:  [YYYY-MM-DD | TICKER | Rating | pending]
- Resolved: [YYYY-MM-DD | TICKER | Rating | +X.X% | +Y.Y% | Nd]

Removes rank-bm25 dependency and the legacy reflect_and_remember()
plumbing across reflection.py, trading_graph.py, and the agent factories.

49 new tests in tests/test_memory_log.py cover the storage, deferred
reflection, prompt injection, and legacy-removal paths. Full suite
(58 tests) passes in under 2 seconds without API keys.

tradingagents/agents/managers/portfolio_manager.py

@@ -1,7 +1,7 @@
 from tradingagents.agents.utils.agent_utils import build_instrument_context, get_language_instruction
 
 
-def create_portfolio_manager(llm, memory):
+def create_portfolio_manager(llm):
     def portfolio_manager_node(state) -> dict:
 
         instrument_context = build_instrument_context(state["company_of_interest"])
@@ -15,21 +15,14 @@ def create_portfolio_manager(llm, memory):
         research_plan = state["investment_plan"]
         trader_plan = state["trader_investment_plan"]
 
-        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"
-
+        past_context = state.get("past_context", "")
         lessons_line = (
-            f"- Lessons from past decisions: **{past_memory_str.strip()}**\n"
-            if past_memories
-            else ""
+            f"- Lessons from prior decisions and outcomes:\n{past_context}\n"
+            if past_context else ""
         )
         thesis_instruction = (
-            "3. **Investment Thesis**: Detailed reasoning anchored in the analysts' debate and past reflections."
-            if past_memories
+            "3. **Investment Thesis**: Detailed reasoning anchored in the analysts' debate and the lessons from prior decisions."
+            if past_context
             else "3. **Investment Thesis**: Detailed reasoning anchored in the analysts' debate."
         )
 
@@ -50,6 +43,7 @@ def create_portfolio_manager(llm, memory):
 - Research Manager's investment plan: **{research_plan}**
 - Trader's transaction proposal: **{trader_plan}**
 {lessons_line}
+
 **Required Output Structure:**
 1. **Rating**: State one of Buy / Overweight / Hold / Underweight / Sell.
 2. **Executive Summary**: A concise action plan covering entry strategy, position sizing, key risk levels, and time horizon.

tradingagents/agents/managers/research_manager.py

@@ -2,30 +2,13 @@
 from tradingagents.agents.utils.agent_utils import build_instrument_context
 
 
-def create_research_manager(llm, memory):
+def create_research_manager(llm):
     def research_manager_node(state) -> dict:
         instrument_context = build_instrument_context(state["company_of_interest"])
         history = state["investment_debate_state"].get("history", "")
-        market_research_report = state["market_report"]
-        sentiment_report = state["sentiment_report"]
-        news_report = state["news_report"]
-        fundamentals_report = state["fundamentals_report"]
 
         investment_debate_state = state["investment_debate_state"]
 
-        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"
-
-        past_memory_block = (
-            f'Take into account your past mistakes on similar situations. Use these insights to refine your decision-making and ensure you are learning and improving. Present your analysis conversationally, as if speaking naturally, without special formatting. \n\nHere are your past reflections on mistakes:\n"{past_memory_str.strip()}"\n\n'
-            if past_memories
-            else ""
-        )
-
         prompt = f"""As the portfolio manager and debate facilitator, your role is to critically evaluate this round of debate and make a definitive decision: align with the bear analyst, the bull analyst, or choose Hold only if it is strongly justified based on the arguments presented.
 
 Summarize the key points from both sides concisely, focusing on the most compelling evidence or reasoning. Your recommendation—Buy, Sell, or Hold—must be clear and actionable. Avoid defaulting to Hold simply because both sides have valid points; commit to a stance grounded in the debate's strongest arguments.
@@ -35,7 +18,9 @@ Additionally, develop a detailed investment plan for the trader. This should inc
 Your Recommendation: A decisive stance supported by the most convincing arguments.
 Rationale: An explanation of why these arguments lead to your conclusion.
 Strategic Actions: Concrete steps for implementing the recommendation.
-{past_memory_block}{instrument_context}
+Present your analysis conversationally, as if speaking naturally, without special formatting.
+
+{instrument_context}
 
 Here is the debate:
 Debate History: