oomi-ai 0.2.19 → 0.2.20

package/bin/oomi-ai.js

@@ -12,6 +12,7 @@ import { scaffoldPersonaApp } from '../lib/scaffold.js';
 import { createPersonaApiClient } from '../lib/personaApiClient.js';
 import { startPersonaJobPoller } from '../lib/personaJobPoller.js';
 import { executePersonaJob } from '../lib/personaJobExecutor.js';
+import { inferSpokenMetadataFromContent, normalizeSpokenMetadata } from '../lib/spokenMetadata.js';
 import {
   buildLocalPersonaRuntime,
   defaultPersonaWorkspaceRoot,
@@ -1648,13 +1649,80 @@ function prepareGatewayFrameForLocalGateway(frameText, gatewayAuth, options = {}
   }
 }
 
-function parseJsonPayload(raw) {
-  try {
-    return JSON.parse(raw);
-  } catch {
-    return null;
-  }
-}
+function parseJsonPayload(raw) {
+  try {
+    return JSON.parse(raw);
+  } catch {
+    return null;
+  }
+}
+
+function extractTextFromGatewayMessage(message) {
+  if (!message || typeof message !== 'object') return '';
+
+  if (typeof message.content === 'string' && message.content.trim()) {
+    return message.content.trim();
+  }
+
+  if (!Array.isArray(message.content)) return '';
+
+  return message.content
+    .filter((block) => block && typeof block === 'object' && block.type === 'text' && typeof block.text === 'string')
+    .map((block) => block.text.trim())
+    .filter(Boolean)
+    .join(' ');
+}
+
+function ensureVoiceAssistantSpokenMetadata(frameText) {
+  const frame = parseJsonPayload(frameText);
+  if (!frame || typeof frame !== 'object') {
+    return { frameText, changed: false, reason: '' };
+  }
+  if (frame.type !== 'event' || frame.event !== 'chat') {
+    return { frameText, changed: false, reason: '' };
+  }
+
+  const payload = frame.payload && typeof frame.payload === 'object' ? frame.payload : null;
+  if (!payload || payload.state !== 'final') {
+    return { frameText, changed: false, reason: '' };
+  }
+
+  const message = payload.message && typeof payload.message === 'object' ? payload.message : null;
+  if (!message || message.role !== 'assistant') {
+    return { frameText, changed: false, reason: '' };
+  }
+
+  const originalMetadata =
+    message.metadata && typeof message.metadata === 'object' && !Array.isArray(message.metadata)
+      ? message.metadata
+      : {};
+  const metadata = { ...originalMetadata };
+  const explicitSpokenPresent = Object.prototype.hasOwnProperty.call(originalMetadata, 'spoken');
+  const spoken =
+    normalizeSpokenMetadata(originalMetadata.spoken) ||
+    (!explicitSpokenPresent ? inferSpokenMetadataFromContent(extractTextFromGatewayMessage(message)) : null);
+  if (!spoken) {
+    return { frameText, changed: false, reason: '' };
+  }
+
+  metadata.spoken = spoken;
+  const nextFrame = JSON.stringify({
+    ...frame,
+    payload: {
+      ...payload,
+      message: {
+        ...message,
+        metadata,
+      },
+    },
+  });
+
+  return {
+    frameText: nextFrame,
+    changed: nextFrame !== frameText,
+    reason: explicitSpokenPresent ? 'normalized' : 'synthesized',
+  };
+}
 
 function extractCorrelationId(params) {
   if (!params || typeof params !== 'object') return '';
@@ -2882,11 +2950,18 @@ async function startOpenclawBridge(flags) {
         flushSessionQueue(sessionBridge);
       });
 
-      gatewaySocket.on('message', runBridgeCallbackSafely((gatewayRaw) => {
-        const frame = typeof gatewayRaw === 'string' ? gatewayRaw : gatewayRaw.toString();
-        const gatewayPayload = parseJsonPayload(frame);
-        if (gatewayPayload?.event === 'connect.challenge') {
-          console.log(`[bridge] gateway.connect.challenge ${sessionId}`);
+      gatewaySocket.on('message', runBridgeCallbackSafely((gatewayRaw) => {
+        let frame = typeof gatewayRaw === 'string' ? gatewayRaw : gatewayRaw.toString();
+        if (classifyBridgeSessionScope(sessionId) === 'voice') {
+          const spokenNormalized = ensureVoiceAssistantSpokenMetadata(frame);
+          if (spokenNormalized.changed) {
+            frame = spokenNormalized.frameText;
+            console.log(`[bridge] voice.spoken_metadata.${spokenNormalized.reason} ${sessionId}`);
+          }
+        }
+        const gatewayPayload = parseJsonPayload(frame);
+        if (gatewayPayload?.event === 'connect.challenge') {
+          console.log(`[bridge] gateway.connect.challenge ${sessionId}`);
           const nonce =
             gatewayPayload.payload && typeof gatewayPayload.payload.nonce === 'string'
               ? gatewayPayload.payload.nonce.trim()
@@ -4119,11 +4194,12 @@ if (__isDirectExecution) {
   });
 }
 
-export {
-  prepareGatewayFrameForLocalGateway,
-  classifyBridgeFailure,
-  classifyBridgeSessionScope,
-  createBridgeProcessFaultHandler,
+export {
+  prepareGatewayFrameForLocalGateway,
+  ensureVoiceAssistantSpokenMetadata,
+  classifyBridgeFailure,
+  classifyBridgeSessionScope,
+  createBridgeProcessFaultHandler,
   computeReconnectDelayMs,
   resolveBridgeStatusForBrokerOpen,
   resolveBridgeStatusForRuntimeFault,

package/lib/spokenMetadata.js

@@ -0,0 +1,273 @@
+function trimString(value, fallback = '') {
+  return typeof value === 'string' && value.trim() ? value.trim() : fallback;
+}
+
+function clampInteger(value, fallback, { min = 1, max = Number.MAX_SAFE_INTEGER } = {}) {
+  if (typeof value !== 'number' || !Number.isFinite(value)) return fallback;
+  const normalized = Math.floor(value);
+  if (normalized < min) return fallback;
+  if (normalized > max) return max;
+  return normalized;
+}
+
+const BOUNDED_LANGUAGE_TYPES = new Set([
+  'Auto',
+  'Chinese',
+  'English',
+  'German',
+  'Italian',
+  'Portuguese',
+  'Spanish',
+  'Japanese',
+  'Korean',
+  'French',
+  'Russian',
+]);
+
+const BOUNDED_PACE_VALUES = new Set(['very_slow', 'slow', 'medium', 'medium_fast', 'fast']);
+const BOUNDED_PITCH_VALUES = new Set(['low', 'slightly_low', 'neutral', 'slightly_high', 'high']);
+const BOUNDED_ENERGY_VALUES = new Set(['soft', 'calm', 'warm', 'bright', 'intense']);
+const BOUNDED_VOLUME_VALUES = new Set(['soft', 'normal', 'projected']);
+
+function inferSpokenLanguage(text) {
+  const normalized = trimString(text);
+  if (!normalized) return 'English';
+  return 'English';
+}
+
+function normalizeSpokenSegment(segment) {
+  if (!segment || typeof segment !== 'object' || Array.isArray(segment)) return null;
+
+  const text = trimString(segment.text);
+  if (!text) return null;
+
+  const normalized = { text };
+  const pace = trimString(segment.pace);
+  const pitch = trimString(segment.pitch);
+  const energy = trimString(segment.energy);
+  const volume = trimString(segment.volume);
+  const pauseAfterMs = clampInteger(segment.pause_after_ms, 0, { min: 0, max: 1200 });
+
+  if (BOUNDED_PACE_VALUES.has(pace)) normalized.pace = pace;
+  if (BOUNDED_PITCH_VALUES.has(pitch)) normalized.pitch = pitch;
+  if (BOUNDED_ENERGY_VALUES.has(energy)) normalized.energy = energy;
+  if (BOUNDED_VOLUME_VALUES.has(volume)) normalized.volume = volume;
+  normalized.pause_after_ms = pauseAfterMs;
+
+  return normalized;
+}
+
+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')
+    .replace(/[–—]/g, ', ')
+    .replace(/…/g, '...')
+    .replace(/\s+/g, ' ')
+    .replace(/\s+([,.;!?])/g, '$1')
+    .replace(/([,.;!?])(?=[^\s])/g, '$1 ')
+    .replace(/,\s*,+/g, ', ')
+    .replace(/\s+/g, ' ')
+    .trim();
+}
+
+function splitSpeechSegments(text) {
+  const normalized = normalizeSpeechText(text);
+  if (!normalized) return [];
+
+  const baseSegments = normalized
+    .split(/(?<=[.!?])\s+/)
+    .map((segment) => segment.trim())
+    .filter(Boolean);
+
+  const segments = [];
+  for (const segment of baseSegments) {
+    if (segment.length <= 96) {
+      segments.push(segment);
+      continue;
+    }
+
+    const clauseParts = segment
+      .split(/,\s+/)
+      .map((part) => part.trim())
+      .filter(Boolean);
+
+    if (clauseParts.length > 1) {
+      for (let index = 0; index < clauseParts.length; index += 1) {
+        const part = clauseParts[index];
+        const needsComma = index < clauseParts.length - 1 && !/[.!?]$/.test(part);
+        segments.push(needsComma ? `${part},` : part);
+      }
+      continue;
+    }
+
+    segments.push(segment);
+  }
+
+  if (segments.length <= 5) return segments;
+
+  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,
+    };
+  }
+
+  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,
+  };
+}
+
+function synthesizeSpokenSegments(text) {
+  const language = inferSpokenLanguage(text);
+  const rawSegments = splitSpeechSegments(text);
+  if (rawSegments.length === 0) return null;
+
+  const segments = rawSegments.map((segmentText, index) => ({
+    text: segmentText,
+    ...inferSegmentStyle(segmentText, index, rawSegments.length),
+  }));
+
+  return {
+    language,
+    segments,
+  };
+}
+
+function normalizeSpokenMetadata(spoken) {
+  if (!spoken || typeof spoken !== 'object' || Array.isArray(spoken)) return null;
+
+  const text = trimString(spoken.text);
+  if (!text) return null;
+
+  const normalized = { text };
+  const language = trimString(spoken.language);
+  if (BOUNDED_LANGUAGE_TYPES.has(language)) {
+    normalized.language = language;
+  }
+
+  const explicitSegments =
+    Array.isArray(spoken.segments)
+      ? spoken.segments.map((segment) => normalizeSpokenSegment(segment)).filter(Boolean)
+      : [];
+  if (explicitSegments.length > 0) {
+    normalized.segments = explicitSegments;
+  }
+
+  const instructions = trimString(spoken.instructions);
+  if (instructions) normalized.instructions = instructions;
+  if (spoken.style && typeof spoken.style === 'object' && !Array.isArray(spoken.style)) {
+    normalized.style = spoken.style;
+  }
+
+  const fallbackSegments = synthesizeSpokenSegments(text);
+  if (!normalized.language && fallbackSegments?.language) {
+    normalized.language = fallbackSegments.language;
+  }
+  if (!normalized.segments && fallbackSegments?.segments?.length) {
+    normalized.segments = fallbackSegments.segments;
+  }
+
+  return normalized;
+}
+
+function inferSpokenMetadataFromContent(content) {
+  const text = normalizeSpeechText(trimString(content));
+  if (!text) return null;
+  const synthesized = synthesizeSpokenSegments(text);
+
+  const normalized = text.toLowerCase();
+  const upbeat =
+    /!/.test(text) ||
+    /\b(hell yeah|awesome|amazing|great|stoked|love|glad|perfect|nice|cool)\b/.test(normalized);
+  const gentle =
+    /\b(sorry|gentle|softly|careful|reassuring|calm|okay|it'?s okay|i know)\b/.test(normalized);
+  const curious = /\?/.test(text);
+
+  if (upbeat) {
+    return {
+      text,
+      language: synthesized?.language || 'English',
+      segments: synthesized?.segments,
+      instructions: 'Speak with warm, upbeat conversational energy and natural pacing.',
+      style: { emotion: 'upbeat', energy: 'medium' },
+    };
+  }
+
+  if (gentle) {
+    return {
+      text,
+      language: synthesized?.language || 'English',
+      segments: synthesized?.segments,
+      instructions: 'Speak gently and reassuringly, with a calm pace and soft emphasis.',
+      style: { emotion: 'gentle', energy: 'low' },
+    };
+  }
+
+  if (curious) {
+    return {
+      text,
+      language: synthesized?.language || 'English',
+      segments: synthesized?.segments,
+      instructions: 'Speak naturally with curious, engaged intonation and a conversational pace.',
+      style: { emotion: 'curious', energy: 'medium' },
+    };
+  }
+
+  return {
+    text,
+    language: synthesized?.language || 'English',
+    segments: synthesized?.segments,
+    instructions: 'Speak naturally with light warmth and conversational pacing.',
+    style: { emotion: 'neutral', energy: 'medium' },
+  };
+}
+
+export {
+  inferSpokenMetadataFromContent,
+  normalizeSpokenMetadata,
+  normalizeSpeechText,
+};

package/openclaw.plugin.json

@@ -2,7 +2,7 @@
   "id": "oomi-ai",
   "name": "Oomi Channel Plugin",
   "description": "Managed Oomi channel integration for OpenClaw.",
-  "version": "0.2.19",
+  "version": "0.2.20",
   "author": "Oomi",
   "license": "MIT",
   "openclawVersion": ">=0.5.0",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oomi-ai",
-  "version": "0.2.19",
+  "version": "0.2.20",
   "description": "Oomi OpenClaw channel plugin and bridge tooling",
   "bin": {
     "oomi": "bin/oomi-ai.js"