fix: strip trailing newlines from past_memory_str and gate thesis instruction

Addresses gemini-code-assist review feedback:
- All five files (portfolio_manager, research_manager, bear/bull researchers,
  trader) now call .strip() on past_memory_str before injecting it into prompts,
  removing the trailing '\n\n' artifacts from the construction loop.
- portfolio_manager now also makes the 'past reflections' phrasing in the
  Investment Thesis instruction conditional on past_memories being non-empty,
  so an empty memory section can't trigger hallucinated past reflections.

tradingagents/agents/managers/portfolio_manager.py

@@ -23,10 +23,15 @@ def create_portfolio_manager(llm, memory):
             past_memory_str += rec["recommendation"] + "\n\n"
 
         lessons_line = (
-            f"- Lessons from past decisions: **{past_memory_str}**\n"
+            f"- Lessons from past decisions: **{past_memory_str.strip()}**\n"
             if past_memories
             else ""
         )
+        thesis_instruction = (
+            "3. **Investment Thesis**: Detailed reasoning anchored in the analysts' debate and past reflections."
+            if past_memories
+            else "3. **Investment Thesis**: Detailed reasoning anchored in the analysts' debate."
+        )
 
         prompt = f"""As the Portfolio Manager, synthesize the risk analysts' debate and deliver the final trading decision.
 
@@ -48,7 +53,7 @@ def create_portfolio_manager(llm, memory):
 **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.
-3. **Investment Thesis**: Detailed reasoning anchored in the analysts' debate and past reflections.
+{thesis_instruction}
 
 ---
 

tradingagents/agents/managers/research_manager.py

@@ -21,7 +21,7 @@ def create_research_manager(llm, memory):
             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}"\n\n'
+            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 ""
         )

tradingagents/agents/researchers/bear_researcher.py

@@ -20,7 +20,7 @@ def create_bear_researcher(llm, memory):
             past_memory_str += rec["recommendation"] + "\n\n"
 
         memory_section = (
-            f"Reflections from similar situations and lessons learned: {past_memory_str}\n"
+            f"Reflections from similar situations and lessons learned: {past_memory_str.strip()}\n"
             if past_memories
             else ""
         )

tradingagents/agents/researchers/bull_researcher.py

@@ -20,7 +20,7 @@ def create_bull_researcher(llm, memory):
             past_memory_str += rec["recommendation"] + "\n\n"
 
         memory_section = (
-            f"Reflections from similar situations and lessons learned: {past_memory_str}\n"
+            f"Reflections from similar situations and lessons learned: {past_memory_str.strip()}\n"
             if past_memories
             else ""
         )

tradingagents/agents/trader/trader.py

@@ -22,7 +22,7 @@ def create_trader(llm, memory):
                 past_memory_str += rec["recommendation"] + "\n\n"
 
         memory_instruction = (
-            f" Apply lessons from past decisions to strengthen your analysis. Here are reflections from similar situations you traded in and the lessons learned: {past_memory_str}"
+            f" Apply lessons from past decisions to strengthen your analysis. Here are reflections from similar situations you traded in and the lessons learned: {past_memory_str.strip()}"
             if past_memories
             else ""
         )