Prior to this change, after the model generated an image the conversation would not be able to progress. It would stall out because we were never storing the image in context, so the model would never realize it already did the work of generating an image. We didn't run into issues with Gemini 2.5 Flash Image, because that model always followed up an image with a text message.
Adds support for using Ultravox Realtime as a speech-to-speech service.
Also removes the deprecated Ultravox speech-to-text vllm model integration to avoid confusion.
Changed the on_client_connected system message from a direct greeting to
an instruction that tells the AI to introduce itself, giving the LLM more
flexibility in how it starts the conversation.
Thinking, sometimes called "extended thinking" or "reasoning", is an LLM process where the model takes some additional time before giving an answer. It's useful for complex tasks that may require some level of planning and structured, step-by-step reasoning. The model can output its thoughts (or thought summaries, depending on the model) in addition to the answer. The thoughts are usually pretty granular and not really suitable for being spoken out loud in a conversation, but can be useful for logging or prompt debugging.
Here's what's added:
1. New typed input 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).
2. New frames for representing thoughts output by LLMs.
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.)
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.
5. An expansion of `TranscriptProcessor` to process LLM thoughts in addition to user and assistant utterances.
