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

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

tradingagents/agents/utils/agent_states.py

@@ -70,3 +70,4 @@ class AgentState(MessagesState):
         RiskDebateState, "Current state of the debate on evaluating risk"
     ]
     final_trade_decision: Annotated[str, "Final decision made by the Risk Analysts"]
+    past_context: Annotated[str, "Memory log context injected at run start (same-ticker decisions + cross-ticker lessons)"]