Fix/playback race by fs generates playback (#1331)

* update to speech-utils that generates playback id

* modify tts and say task to track current playback id and match against start and stop events

* bump speech utils

* wip

* wip

* fix race condition where say with playbackId gets stop event from previous play from cache file

* logging

* wip

* fix comparison when playing cached files

* logging

lib/tasks/tts-task.js

@@ -3,6 +3,16 @@ const { TaskPreconditions } = require('../utils/constants');
 const { SpeechCredentialError } = require('../utils/error');
 const dbUtils = require('../utils/db-utils');
 
+const extractPlaybackId = (str) => {
+  // Match say:{...} and capture the content inside braces
+  const match = str.match(/say:\{([^}]*)\}/);
+  if (!match) return null;
+
+  // Look for playback_id=value within the captured content
+  const playbackMatch = match[1].match(/playback_id=([^,]*)/);
+  return playbackMatch ? playbackMatch[1] : null;
+};
+
 class TtsTask extends Task {
 
   constructor(logger, data, parentTask) {
@@ -22,6 +32,11 @@ class TtsTask extends Task {
     this.disableTtsCache = this.data.disableTtsCache;
     this.options = this.synthesizer.options || {};
     this.instructions = this.data.instructions;
+    this.playbackIds = [];
+  }
+
+  getPlaybackId(offset) {
+    return this.playbackIds[offset];
   }
 
   async exec(cs) {
@@ -280,6 +295,7 @@ class TtsTask extends Task {
             renderForCaching: preCache
           });
           if (!filePath.startsWith('say:')) {
+            this.playbackIds.push(null);
             this.logger.debug(`Say: file ${filePath}, served from cache ${servedFromCache}`);
             if (filePath) cs.trackTmpFile(filePath);
             if (this.otelSpan) {
@@ -309,7 +325,8 @@ class TtsTask extends Task {
             }
           }
           else {
-            this.logger.debug('Say: a streaming tts api will be used');
+            this.playbackIds.push(extractPlaybackId(filePath));
+            this.logger.debug({playbackIds: this.playbackIds}, 'Say: a streaming tts api will be used');
             const modifiedPath = filePath.replace('say:{', `say:{session-uuid=${ep.uuid},`);
             return modifiedPath;
           }