Always create UserIdleController (timeout=0 means disabled), removing
all Optional guards. Add UserIdleTimeoutUpdateFrame to allow changing
the idle timeout at runtime.
Replace the continuous heartbeat-based timer (UserSpeakingFrame/BotSpeakingFrame
+ asyncio.Event loop) with a simple one-shot timer that starts when
BotStoppedSpeakingFrame is received and cancels on UserStartedSpeakingFrame or
BotStartedSpeakingFrame. This eliminates false idle triggers caused by gaps
between the user finishing speaking and the bot starting to speak (LLM/TTS
latency).
Guard the timer start with two conditions to prevent false triggers:
- User turn in progress: during interruptions, BotStoppedSpeaking arrives
while the user is still speaking mid-turn.
- Function calls in progress: FunctionCallsStarted arrives before
BotStoppedSpeaking because the bot speaks concurrently with the function
call starting, so the timer must wait for the result and subsequent bot
response.
With all these examples updated, we no longer need dedicated examples illustrating `LLMContext`, so they're removed.
Here’s where we *don’t* yet use `LLMContext` and associated machinery:
- Realtime services: OpenAI Realtime, Gemini Live, and AWS Nova Sonic (support coming soon)
- `GoogleLLMOpenAIBetaService` (it’s deprecated, so we didn’t bother adding support)
- `LLMLogObserver` (support coming soon)
- `GatedOpenAILLMContextAggregator` (support coming soon)
- `LangchainProcessor` (support coming soon)
- `Mem0MemoryService` (support coming soon)
- Examples that use LLM-specific tools definitions as opposed to `ToolsSchema` (these will be updated soon)
- Examples that rely `GoogleLLMContext.upgrade_to_google` (TBD what to do with these)
Examples that use `LLMLogObserver`:
- 30-
Examples that use `GatedOpenAILLMContextAggregator`:
- 22-
Examples that use `LangchainProcessor`:
- 07b-
Examples that use `Mem0MemoryService`:
- 37-
Examples that need updating to use `ToolsSchema`:
- 15-
- 15a-
- 20a-
- 20c-
- 20d-
- 22b-
- 22c-
- 33-
- 36-
Examples that use `GoogleLLMContext.upgrade_to_google`:
- 22d-
- 25-
Skipping over 07b-interruptible-langchain.py for now, as it requires deeper changes involving `LLMUserResponseAggregator` and `LLMAssistantResponseAggregator`.
Pipecat has a pipeline-based architecture. The pipeline consists of frame
processors linked to each other. The elements travelling across the pipeline are
called frames.
To have a deterministic behavior the frames travelling through the pipeline
should always be ordered, except system frames which are out-of-band frames. To
achieve that, each frame processor should only output frames from a single task.
There are synchronous and asynchronous frame processors. The synchronous
processors push output frames from the same task that they receive input frames,
and therefore only pushing frames from one task. Asynchrnous frame processors
can have internal tasks to perform things asynchrnously (e.g. receiving data
from a websocket) but they also have a single task where they push frames from.
