APEX/BrowserUse_and_ComputerUse_skills
5
0
Fork 0
Code Issues 6 Pull requests 1 Projects 1 Releases Packages Wiki Activity Actions

merge: salvage PR #327 voice mode branch

Browse source 
Merge contributor branch feature/voice-mode onto current main for follow-up fixes.
This commit is contained in:
teknium1 2026-03-14 06:03:07 -07:00
commit 523a1b6faf
37 changed files with 9248 additions and 228 deletions
Download patch file Download diff file Expand all files Collapse all files

62
gateway/platforms/base.py
View file

@ -351,6 +351,8 @@ class BasePlatformAdapter(ABC):
# Key: session_key (e.g., chat_id), Value: (event, asyncio.Event for interrupt)
self._active_sessions: Dict[str, asyncio.Event] = {}
self._pending_messages: Dict[str, MessageEvent] = {}
# Chats where auto-TTS on voice input is disabled (set by /voice off)
self._auto_tts_disabled_chats: set = set()
@property
def name(self) -> str:
@ -537,6 +539,20 @@ class BasePlatformAdapter(ABC):
text = f"{caption}\n{text}"
return await self.send(chat_id=chat_id, content=text, reply_to=reply_to)
async def play_tts(
self,
chat_id: str,
audio_path: str,
**kwargs,
) -> SendResult:
"""
Play auto-TTS audio for voice replies.
Override in subclasses for invisible playback (e.g. Web UI).
Default falls back to send_voice (shows audio player).
"""
return await self.send_voice(chat_id=chat_id, audio_path=audio_path, **kwargs)
async def send_video(
self,
chat_id: str,
@ -724,7 +740,43 @@ class BasePlatformAdapter(ABC):
if images:
logger.info("[%s] extract_images found %d image(s) in response (%d chars)", self.name, len(images), len(response))
# Send the text portion first (if any remains after extractions)
# Auto-TTS: if voice message, generate audio FIRST (before sending text)
# Skipped when the chat has voice mode disabled (/voice off)
_tts_path = None
if (event.message_type == MessageType.VOICE
and text_content
and not media_files
and event.source.chat_id not in self._auto_tts_disabled_chats):
try:
from tools.tts_tool import text_to_speech_tool, check_tts_requirements
if check_tts_requirements():
import json as _json
speech_text = re.sub(r'[*_`#\[\]()]', '', text_content)[:4000].strip()
if not speech_text:
raise ValueError("Empty text after markdown cleanup")
tts_result_str = await asyncio.to_thread(
text_to_speech_tool, text=speech_text
)
tts_data = _json.loads(tts_result_str)
_tts_path = tts_data.get("file_path")
except Exception as tts_err:
logger.warning("[%s] Auto-TTS failed: %s", self.name, tts_err)
# Play TTS audio before text (voice-first experience)
if _tts_path and Path(_tts_path).exists():
try:
await self.play_tts(
chat_id=event.source.chat_id,
audio_path=_tts_path,
metadata=_thread_metadata,
)
finally:
try:
os.remove(_tts_path)
except OSError:
pass
# Send the text portion
if text_content:
logger.info("[%s] Sending response (%d chars) to %s", self.name, len(text_content), event.source.chat_id)
result = await self.send(
@ -733,7 +785,7 @@ class BasePlatformAdapter(ABC):
reply_to=event.message_id,
metadata=_thread_metadata,
)
# Log send failures (don't raise - user already saw tool progress)
if not result.success:
print(f"[{self.name}] Failed to send response: {result.error}")
@ -746,10 +798,10 @@ class BasePlatformAdapter(ABC):
)
if not fallback_result.success:
print(f"[{self.name}] Fallback send also failed: {fallback_result.error}")
# Human-like pacing delay between text and media
human_delay = self._get_human_delay()
# Send extracted images as native attachments
if images:
logger.info("[%s] Extracted %d image(s) to send as attachments", self.name, len(images))
@ -777,7 +829,7 @@ class BasePlatformAdapter(ABC):
logger.error("[%s] Failed to send image: %s", self.name, img_result.error)
except Exception as img_err:
logger.error("[%s] Error sending image: %s", self.name, img_err, exc_info=True)
# Send extracted media files — route by file type
_AUDIO_EXTS = {'.ogg', '.opus', '.mp3', '.wav', '.m4a'}
_VIDEO_EXTS = {'.mp4', '.mov', '.avi', '.mkv', '.3gp'}