docs: update for pipecat PR #3932

server/services/llm/anthropic.mdx

@@ -91,7 +91,9 @@ Before using Anthropic LLM services, you need:
 </ParamField>
 
 <ParamField path="system_instruction" type="str" default="None">
-  Optional system instruction to use as the system prompt.
+  Optional system instruction/prompt for the model. Sets the overall behavior
+  and context. If set, this takes precedence over any system message in the
+  context.
 </ParamField>
 
 ### InputParams
@@ -194,6 +196,7 @@ await task.queue_frame(
 - **Extended thinking**: Enabling thinking increases response quality for complex tasks but adds latency. The `budget_tokens` value must be at least 1024 with current models. Extended thinking is disabled by default.
 - **Custom clients**: You can pass custom Anthropic client instances (e.g., `AsyncAnthropicBedrock` or `AsyncAnthropicVertex`) via the `client` parameter to use Anthropic models through other cloud providers.
 - **Retry behavior**: When `retry_on_timeout=True`, the first attempt uses the `retry_timeout_secs` timeout. If it times out, a second attempt is made with no timeout limit.
+- **System instruction precedence**: If both `system_instruction` (from the constructor) and a system message in the context are set, the constructor's `system_instruction` takes precedence and a warning is logged.
 
 ## Event Handlers
 

server/services/llm/aws.mdx

@@ -112,7 +112,9 @@ Before using AWS Bedrock LLM services, you need:
 </ParamField>
 
 <ParamField path="system_instruction" type="str" default="None">
-  Optional system instruction to use as the system prompt.
+  Optional system instruction/prompt for the model. Sets the overall behavior
+  and context. If set, this takes precedence over any system message in the
+  context.
 </ParamField>
 
 ### InputParams
@@ -193,6 +195,7 @@ await task.queue_frame(
 - **No-op tool handling**: AWS Bedrock requires at least one tool to be defined when tool content exists in the conversation. The service automatically adds a placeholder tool when needed to prevent API errors.
 - **Model-specific parameters**: Some models (e.g., Claude Sonnet 4.5) don't allow certain parameter combinations. The service only includes explicitly set parameters in the inference config to avoid conflicts.
 - **Retry behavior**: When `retry_on_timeout=True`, the first attempt uses the `retry_timeout_secs` timeout. If it times out, a second attempt is made with no timeout limit.
+- **System instruction precedence**: If both `system_instruction` (from the constructor) and a system message in the context are set, the constructor's `system_instruction` takes precedence and a warning is logged.
 
 ## Event Handlers
 

server/services/llm/openai.mdx

@@ -103,7 +103,9 @@ Before using OpenAI LLM services, you need:
 </ParamField>
 
 <ParamField path="system_instruction" type="str" default="None">
-  Optional system instruction to prepend to messages.
+  Optional system instruction/prompt for the model. Sets the overall behavior
+  and context. If set, this takes precedence over any system message in the
+  context.
 </ParamField>
 
 ### InputParams
@@ -182,6 +184,7 @@ await task.queue_frame(
 - **OpenAI-compatible providers**: Many third-party LLM providers offer OpenAI-compatible APIs. You can use `OpenAILLMService` with them by setting `base_url` to the provider's endpoint.
 - **Retry behavior**: When `retry_on_timeout=True`, the first attempt uses the `retry_timeout_secs` timeout. If it times out, a second attempt is made with no timeout limit.
 - **Function calling**: Supports OpenAI's tool/function calling format. Register function handlers on the pipeline task to handle tool calls automatically.
+- **System instruction precedence**: If both `system_instruction` (from the constructor) and a system message in the context are set, the constructor's `system_instruction` takes precedence and a warning is logged.
 
 ## Event Handlers