From e00b98343eb0c04943dddc1be12fc53afd56d167 Mon Sep 17 00:00:00 2001 From: filipi87 Date: Tue, 10 Feb 2026 11:37:21 -0300 Subject: [PATCH] Changelog entries for TTS context tracking --- changelog/3584.added.2.md | 3 +++ changelog/3584.added.md | 4 ++++ changelog/3584.changed.2.md | 3 +++ changelog/3584.changed.3.md | 4 ++++ changelog/3584.changed.md | 3 +++ 5 files changed, 17 insertions(+) create mode 100644 changelog/3584.added.2.md create mode 100644 changelog/3584.added.md create mode 100644 changelog/3584.changed.2.md create mode 100644 changelog/3584.changed.3.md create mode 100644 changelog/3584.changed.md diff --git a/changelog/3584.added.2.md b/changelog/3584.added.2.md new file mode 100644 index 000000000..3113154fe --- /dev/null +++ b/changelog/3584.added.2.md @@ -0,0 +1,3 @@ +- Added `append_to_context` parameter to `TTSSpeakFrame` for conditional LLM context addition. + - Allows fine-grained control over whether text should be added to conversation context + - Defaults to `True` to maintain backward compatibility diff --git a/changelog/3584.added.md b/changelog/3584.added.md new file mode 100644 index 000000000..08a81ee85 --- /dev/null +++ b/changelog/3584.added.md @@ -0,0 +1,4 @@ +- Added TTS context tracking system with `context_id` field to trace audio generation through the pipeline. + - `TTSAudioRawFrame`, `TTSStartedFrame`, `TTSStoppedFrame` now include `context_id` + - `AggregatedTextFrame` and `TTSTextFrame` now include `context_id` + - Enables tracking which TTS request generated specific audio chunks diff --git a/changelog/3584.changed.2.md b/changelog/3584.changed.2.md new file mode 100644 index 000000000..f5356b4c9 --- /dev/null +++ b/changelog/3584.changed.2.md @@ -0,0 +1,3 @@ +- Simplified context aggregators to use `frame.append_to_context` flag instead of tracking internal state. + - Cleaner logic in `LLMResponseAggregator` and `LLMResponseUniversalAggregator` + - More consistent behavior across aggregator implementations diff --git a/changelog/3584.changed.3.md b/changelog/3584.changed.3.md new file mode 100644 index 000000000..426cfbde7 --- /dev/null +++ b/changelog/3584.changed.3.md @@ -0,0 +1,4 @@ +- ⚠️ `TTSService.run_tts()` now requires a `context_id` parameter for context tracking. + - Custom TTS service implementations must update their `run_tts()` signature + - Before: `async def run_tts(self, text: str) -> AsyncGenerator[Frame, None]:` + - After: `async def run_tts(self, text: str, context_id: str) -> AsyncGenerator[Frame, None]:` diff --git a/changelog/3584.changed.md b/changelog/3584.changed.md new file mode 100644 index 000000000..fd535b7d8 --- /dev/null +++ b/changelog/3584.changed.md @@ -0,0 +1,3 @@ +- Updated all 30+ TTS service implementations to support context tracking with `context_id`. + - Services now generate and propagate context IDs through TTS frames + - Enables end-to-end tracing of TTS requests through the pipeline