fix: make confidence visible to users when below 0.7 threshold (#259)

Co-authored-by: rockachopa <alexpaynex@gmail.com>
Co-committed-by: rockachopa <alexpaynex@gmail.com>

src/timmy/session.py

@@ -110,6 +110,10 @@ async def chat(message: str, session_id: str | None = None) -> str:
     confidence = estimate_confidence(response_text)
     logger.debug("Response confidence: %.2f", confidence)
 
+    # Make confidence visible to user when below threshold (SOUL.md requirement)
+    if confidence is not None and confidence < 0.7:
+        response_text += f"\n\n[confidence: {confidence:.0%}]"
+
     # Record Timmy response after getting it
     session_logger.record_message("timmy", response_text, confidence=confidence)
 
@@ -148,6 +152,13 @@ async def chat_with_tools(message: str, session_id: str | None = None):
         )
         confidence = estimate_confidence(response_text) if response_text else None
         logger.debug("Response confidence: %.2f", confidence)
+
+        # Make confidence visible to user when below threshold (SOUL.md requirement)
+        if confidence is not None and confidence < 0.7:
+            response_text += f"\n\n[confidence: {confidence:.0%}]"
+            # Update the run_output content to reflect the modified response
+            run_output.content = response_text
+
         session_logger.record_message("timmy", response_text, confidence=confidence)
         session_logger.flush()
         return run_output
@@ -187,6 +198,13 @@ async def continue_chat(run_output, session_id: str | None = None):
         response_text = result.content if hasattr(result, "content") and result.content else ""
         confidence = estimate_confidence(response_text) if response_text else None
         logger.debug("Response confidence: %.2f", confidence)
+
+        # Make confidence visible to user when below threshold (SOUL.md requirement)
+        if confidence is not None and confidence < 0.7:
+            response_text += f"\n\n[confidence: {confidence:.0%}]"
+            # Update the result content to reflect the modified response
+            result.content = response_text
+
         session_logger.record_message("timmy", response_text, confidence=confidence)
         session_logger.flush()
         return result