pipecat/changelog/3175.added.md

• Added additional functionality related to "thinking", for Google and Anthropic LLMs.

  1. New typed parameters for Google and Anthropic LLMs that control the models' thinking behavior (like how much thinking to do, and whether to output thoughts or thought summaries):
     • AnthropicLLMService.ThinkingConfig
     • GoogleLLMService.ThinkingConfig
  2. New frames for representing thoughts output by LLMs:
     • LLMThoughtStartFrame
     • LLMThoughtTextFrame
     • LLMThoughtEndFrame
  3. A generic mechanism for associating extra LLM-specific data with a function call in context, used specifically to support Google's function-call-related "thought signatures", which are necessary to ensure thinking continuity between function calls in a chain (where the model thinks, makes a function call, thinks some more, etc.). See:
     • FunctionCallInProgressFrame.llm_specific_extra
     • LLMAssistantAggregator handling of the above field
     • GeminiLLMAdapter handling of"tool_call_extra" context messages
  4. A generic mechanism for recording LLM thoughts to context, used specifically to support Anthropic, whose thought signatures are expected to appear alongside the text of the thoughts within assistant context messages. See:
     • LLMThoughtEndFrame.signature
     • LLMAssistantAggregator handling of the above field
     • AnthropicLLMAdapter handling of "thought" context messages
  5. A generic mechanism for recording standalone thought signatures to context, used specifically to support Gemini 3 Pro, which may return non-function-call-related thought signatures at the end of non-function-call assistant responses. See:
     • LLMThoughtSignatureFrame
     • LLMAssistantAggregator handling of the above frame
     • GeminiLLMAdapter handling of "thought_signature" context messages
  6. An expansion of TranscriptProcessor to process LLM thoughts in addition to user and assistant utterances. See:
     • TranscriptProcessor.thought()
     • ThoughtTranscriptionMessage, which may now also be emitted with the "on_transcript_update" event