Merge pull request #4217 from pipecat-ai/filipi/async_tools

Supporting async function calls.

changelog/4217.added.2.md

@@ -0,0 +1 @@
+- Added `group_parallel_tools` parameter to `LLMService` (default `True`). When `True`, all function calls from the same LLM response batch share a group ID and the LLM is triggered exactly once after the last call completes. Set to `False` to trigger inference independently for each function call result as it arrives.

changelog/4217.added.md

@@ -0,0 +1 @@
+- Added async function call support to `register_function()` and `register_direct_function()` via `cancel_on_interruption=False`. When set to `False`, the LLM continues the conversation immediately without waiting for the function result. The result is injected back into the context as a `developer` message once available, triggering a new LLM inference at that point.

changelog/4217.changed.md

@@ -0,0 +1 @@
+- When multiple function calls are returned in a single LLM response, by default (when `group_parallel_tools=True`) the LLM is now triggered exactly once after the last call in the batch completes, rather than waiting for all function calls.

changelog/4217.fixed.2.md

@@ -0,0 +1 @@
+- Fixed `BaseOutputTransport` discarding pending `UninterruptibleFrame` items (e.g. function-call context updates) when an interruption arrived. The audio task is now kept alive and only interruptible frames are drained when uninterruptible frames are present in the queue.

changelog/4217.fixed.md

@@ -0,0 +1 @@
+- Fixed spurious LLM inference being triggered when a function call result arrived while the user was actively speaking. The context frame is now suppressed until the user stops speaking.