oomi-ai 0.2.24 → 0.2.25

package/lib/spokenMetadata.js

@@ -1,6 +1,10 @@
-function trimString(value, fallback = '') {
-  return typeof value === 'string' && value.trim() ? value.trim() : fallback;
-}
+function trimString(value, fallback = '') {
+  return typeof value === 'string' && value.trim() ? value.trim() : fallback;
+}
+
+function stripAvatarCommandTags(text) {
+  return text.replace(/\[(anim|animation|face|expression|emotion|gesture|look|gaze):[^\]]+\]/gi, ' ');
+}
 
 function clampInteger(value, fallback, { min = 1, max = Number.MAX_SAFE_INTEGER } = {}) {
   if (typeof value !== 'number' || !Number.isFinite(value)) return fallback;
@@ -35,11 +39,11 @@ function inferSpokenLanguage(text) {
   return 'English';
 }
 
-function normalizeSpokenSegment(segment) {
-  if (!segment || typeof segment !== 'object' || Array.isArray(segment)) return null;
-
-  const text = trimString(segment.text);
-  if (!text) return null;
+function normalizeSpokenSegment(segment) {
+  if (!segment || typeof segment !== 'object' || Array.isArray(segment)) return null;
+
+  const text = normalizeSpeechText(trimString(segment.text));
+  if (!text) return null;
 
   const normalized = { text };
   const pace = trimString(segment.pace);
@@ -61,11 +65,11 @@ function stripEmoji(text) {
   return text.replace(/[\uFE0E\uFE0F]/g, '').replace(/\p{Extended_Pictographic}|\p{Emoji_Presentation}/gu, '');
 }
 
-function normalizeSpeechText(text) {
-  return stripEmoji(text)
-    .replace(/\*\*(.*?)\*\*/g, '$1')
-    .replace(/__(.*?)__/g, '$1')
-    .replace(/`([^`]+)`/g, '$1')
+function normalizeSpeechText(text) {
+  return stripEmoji(stripAvatarCommandTags(text))
+    .replace(/\*\*(.*?)\*\*/g, '$1')
+    .replace(/__(.*?)__/g, '$1')
+    .replace(/`([^`]+)`/g, '$1')
     .replace(/[\u2013\u2014]/g, ', ')
     .replace(/\u2026/g, '...')
     .replace(/\s+/g, ' ')
@@ -76,14 +80,14 @@ function normalizeSpeechText(text) {
     .trim();
 }
 
-function splitSpeechSegments(text) {
-  const normalized = normalizeSpeechText(text);
-  if (!normalized) return [];
-
-  const baseSegments = normalized
-    .split(/(?<=[.!?])\s+/)
-    .map((segment) => segment.trim())
-    .filter(Boolean);
+function splitSpeechSegments(text) {
+  const normalized = normalizeSpeechText(text);
+  if (!normalized) return [];
+
+  const baseSegments = normalized
+    .split(/(?<=[.!?])\s+|\n+/)
+    .map((segment) => segment.trim())
+    .filter(Boolean);
 
   const segments = [];
   for (const segment of baseSegments) {
@@ -92,10 +96,10 @@ function splitSpeechSegments(text) {
       continue;
     }
 
-    const clauseParts = segment
-      .split(/,\s+/)
-      .map((part) => part.trim())
-      .filter(Boolean);
+    const clauseParts = segment
+      .split(/(?<=[,;:])\s+/)
+      .map((part) => part.trim())
+      .filter(Boolean);
 
     if (clauseParts.length > 1) {
       for (let index = 0; index < clauseParts.length; index += 1) {
@@ -114,50 +118,62 @@ function splitSpeechSegments(text) {
   return [...segments.slice(0, 4), segments.slice(4).join(' ').trim()];
 }
 
-function inferSegmentStyle(segmentText, index, totalSegments) {
-  const normalized = segmentText.toLowerCase();
-  const exclamatory = /!/.test(segmentText) || /\b(hell yeah|awesome|amazing|stoked|love|perfect|great)\b/.test(normalized);
-  const curious = /\?/.test(segmentText);
-  const reflective =
-    /\b(i think|i'm|i am|i've|i have|lately|right now|before this|each time|understand|it feels like)\b/.test(normalized) ||
-    segmentText.length > 60;
-
-  if (curious) {
-    return {
-      pace: 'medium',
-      pitch: 'slightly_high',
-      energy: 'warm',
-      volume: 'normal',
-      pause_after_ms: 0,
-    };
-  }
+function inferSegmentStyle(segmentText, index, totalSegments) {
+  const normalized = segmentText.toLowerCase();
+  const greeting = /^(hey|hi|hello|yo)\b/.test(normalized);
+  const exclamatory = /!/.test(segmentText) || /\b(hell yeah|awesome|amazing|stoked|love|perfect|great)\b/.test(normalized);
+  const curious = /\?/.test(segmentText);
+  const reassuring = /\b(got it|no worries|all good|you'?re good|sounds good|totally|absolutely)\b/.test(normalized);
+  const reflective =
+    /\b(i think|i'm|i am|i've|i have|lately|right now|before this|each time|understand|it feels like)\b/.test(normalized) ||
+    segmentText.length > 60;
+
+  if (greeting || reassuring) {
+    return {
+      pace: 'medium_fast',
+      pitch: 'slightly_high',
+      energy: 'bright',
+      volume: 'projected',
+      pause_after_ms: index < totalSegments - 1 ? 180 : 0,
+    };
+  }
+
+  if (curious) {
+    return {
+      pace: 'medium',
+      pitch: 'slightly_high',
+      energy: 'warm',
+      volume: 'projected',
+      pause_after_ms: 0,
+    };
+  }
 
   if (exclamatory) {
     return {
-      pace: 'medium_fast',
-      pitch: 'slightly_high',
-      energy: 'bright',
-      volume: 'normal',
-      pause_after_ms: index < totalSegments - 1 ? 220 : 0,
-    };
-  }
-
-  if (reflective) {
-    return {
-      pace: 'medium',
-      pitch: 'neutral',
-      energy: 'warm',
-      volume: 'normal',
-      pause_after_ms: index < totalSegments - 1 ? 260 : 0,
-    };
-  }
-
-  return {
-    pace: 'medium',
-    pitch: 'neutral',
-    energy: 'warm',
-    volume: 'normal',
-    pause_after_ms: index < totalSegments - 1 ? 180 : 0,
+      pace: 'medium_fast',
+      pitch: 'slightly_high',
+      energy: 'bright',
+      volume: 'projected',
+      pause_after_ms: index < totalSegments - 1 ? 220 : 0,
+    };
+  }
+
+  if (reflective) {
+    return {
+      pace: 'slow',
+      pitch: 'slightly_low',
+      energy: 'warm',
+      volume: 'soft',
+      pause_after_ms: index < totalSegments - 1 ? 280 : 0,
+    };
+  }
+
+  return {
+    pace: 'medium',
+    pitch: 'slightly_high',
+    energy: 'warm',
+    volume: 'normal',
+    pause_after_ms: index < totalSegments - 1 ? 180 : 0,
   };
 }
 
@@ -177,11 +193,11 @@ function synthesizeSpokenSegments(text) {
   };
 }
 
-function normalizeSpokenMetadata(spoken) {
-  if (!spoken || typeof spoken !== 'object' || Array.isArray(spoken)) return null;
-
-  const text = trimString(spoken.text);
-  if (!text) return null;
+function normalizeSpokenMetadata(spoken) {
+  if (!spoken || typeof spoken !== 'object' || Array.isArray(spoken)) return null;
+
+  const text = normalizeSpeechText(trimString(spoken.text));
+  if (!text) return null;
 
   const normalized = { text };
   const language = trimString(spoken.language);
@@ -266,8 +282,9 @@ function inferSpokenMetadataFromContent(content) {
   };
 }
 
-export {
-  inferSpokenMetadataFromContent,
-  normalizeSpokenMetadata,
-  normalizeSpeechText,
-};
+export {
+  inferSpokenMetadataFromContent,
+  normalizeSpokenMetadata,
+  normalizeSpeechText,
+  stripAvatarCommandTags,
+};

package/openclaw.plugin.json

@@ -2,7 +2,7 @@
   "id": "oomi-ai",
   "name": "Oomi Channel Plugin",
   "description": "Managed Oomi channel integration for OpenClaw.",
-  "version": "0.2.24",
+  "version": "0.2.25",
   "author": "Oomi",
   "license": "MIT",
   "openclawVersion": ">=0.5.0",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oomi-ai",
-  "version": "0.2.24",
+  "version": "0.2.25",
   "description": "Oomi OpenClaw channel plugin and bridge tooling",
   "bin": {
     "oomi": "bin/oomi-ai.js"