Merge pull request #4314 from pipecat-ai/mb/prudent-system-instruction-logging

Log system instruction once at composition time, not on every LLM call

changelog/4314.changed.md

@@ -0,0 +1 @@
+- Reduced debug log noise for LLM services. The system instruction is now logged once when composed (e.g. when turn completion is enabled) instead of on every LLM call. Per-call logs now show only the conversation messages, consistent across Google, Anthropic, AWS, and OpenAI services.

src/pipecat/services/anthropic/llm.py

@@ -345,9 +345,7 @@ class AnthropicLLMService(LLMService):
 
             adapter = self.get_llm_adapter()
             messages_for_logging = adapter.get_messages_for_logging(context)
-            logger.debug(
+            logger.debug(f"{self}: Generating chat from context {messages_for_logging}")
-                f"{self}: Generating chat from context [{params_from_context['system']}] | {messages_for_logging}"
-            )
 
             await self.start_ttfb_metrics()
 

src/pipecat/services/aws/llm.py

@@ -475,9 +475,7 @@ class AWSBedrockLLMService(LLMService):
             # Log request params with messages redacted for logging
             adapter = self.get_llm_adapter()
             messages_for_logging = adapter.get_messages_for_logging(context)
-            logger.debug(
+            logger.debug(f"{self}: Generating chat from context {messages_for_logging}")
-                f"{self}: Generating chat from context [{system}] | {messages_for_logging}"
-            )
 
             async with self._aws_session.client(
                 service_name="bedrock-runtime", **self._aws_params

src/pipecat/services/google/llm.py

@@ -392,7 +392,7 @@ class GoogleLLMService(LLMService):
         )
 
         logger.debug(
-            f"{self}: Generating chat from context [{params['system_instruction']}] | {adapter.get_messages_for_logging(context)}"
+            f"{self}: Generating chat from context {adapter.get_messages_for_logging(context)}"
         )
 
         messages = params["messages"]

src/pipecat/services/llm_service.py

@@ -347,6 +347,7 @@ class LLMService(UserTurnCompletionLLMServiceMixin, AIService):
             parts.append(ASYNC_TOOL_CANCELLATION_INSTRUCTIONS)
         composed = "\n\n".join(p for p in parts if p)
         self._settings.system_instruction = composed or None
+        logger.debug(f"{self}: System instruction composed: {self._settings.system_instruction}")
 
     async def _update_settings(self, delta: LLMSettings) -> dict[str, Any]:
         """Apply a settings delta, handling turn-completion fields.