feat: add inference cancellation support for TTS generation

Add cooperative cancellation via Arc<AtomicBool> cancel flag that
threads through TtsEngine::generate -> Qwen3Tts -> GenerationContext.
The autoregressive loop and streaming decoder check the flag each
iteration and break early when set. The speak WebSocket handler
creates a per-session flag, passes it to generate, and sets it on
Cancel/Stop/Close messages.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

1 files changed, 3 insertions, 1 deletions

diff --git a/makima/src/tts/chatterbox.rs b/makima/src/tts/chatterbox.rs
index e26bc06..712910f 100644
--- a/makima/src/tts/chatterbox.rs
+++ b/makima/src/tts/chatterbox.rs
@@ -6,7 +6,8 @@
 use std::borrow::Cow;
 use std::fs;
 use std::path::{Path, PathBuf};
-use std::sync::Mutex;
+use std::sync::atomic::AtomicBool;
+use std::sync::{Arc, Mutex};
 
 use hf_hub::api::sync::Api;
 use ndarray::{Array2, Array3, Array4, ArrayD, IxDyn};
@@ -427,6 +428,7 @@ impl TtsEngine for ChatterboxTTS {
         text: &str,
         reference_audio: Option<&[f32]>,
         reference_sample_rate: Option<u32>,
+        _cancel_flag: Option<Arc<AtomicBool>>,
     ) -> Result<Vec<AudioChunk>, TtsError> {
         let samples = match reference_audio {
             Some(audio) => {