feat(whatsapp): native media sending — images, videos, documents
Add a /send-media endpoint to the WhatsApp bridge and corresponding adapter methods so the agent can send files as native WhatsApp attachments instead of plain-text URLs/paths. - bridge.js: new POST /send-media endpoint using Baileys' native image/video/document/audio message types with MIME detection - base.py: add send_video(), send_document(), send_image_file() with text fallbacks; route MEDIA: tags by file extension instead of always treating them as voice messages - whatsapp.py: implement all media methods via a shared _send_media_to_bridge() helper; override send_image() to download URLs to local cache and send as native photos - prompt_builder.py: update WhatsApp and Telegram platform hints so the agent knows it can use MEDIA:/path tags to send native media
This commit is contained in:
Daniel Sateler
parent
3c13feed4c
commit
3588396263
4 changed files with 272 additions and 15 deletions
|
|
@ -509,7 +509,63 @@ class BasePlatformAdapter(ABC):
|
|||
if caption:
|
||||
text = f"{caption}\n{text}"
|
||||
return await self.send(chat_id=chat_id, content=text, reply_to=reply_to)
|
||||
|
||||
|
||||
async def send_video(
|
||||
self,
|
||||
chat_id: str,
|
||||
video_path: str,
|
||||
caption: Optional[str] = None,
|
||||
reply_to: Optional[str] = None,
|
||||
) -> SendResult:
|
||||
"""
|
||||
Send a video natively via the platform API.
|
||||
|
||||
Override in subclasses to send videos as inline playable media.
|
||||
Default falls back to sending the file path as text.
|
||||
"""
|
||||
text = f"🎬 Video: {video_path}"
|
||||
if caption:
|
||||
text = f"{caption}\n{text}"
|
||||
return await self.send(chat_id=chat_id, content=text, reply_to=reply_to)
|
||||
|
||||
async def send_document(
|
||||
self,
|
||||
chat_id: str,
|
||||
file_path: str,
|
||||
caption: Optional[str] = None,
|
||||
file_name: Optional[str] = None,
|
||||
reply_to: Optional[str] = None,
|
||||
) -> SendResult:
|
||||
"""
|
||||
Send a document/file natively via the platform API.
|
||||
|
||||
Override in subclasses to send files as downloadable attachments.
|
||||
Default falls back to sending the file path as text.
|
||||
"""
|
||||
text = f"📎 File: {file_path}"
|
||||
if caption:
|
||||
text = f"{caption}\n{text}"
|
||||
return await self.send(chat_id=chat_id, content=text, reply_to=reply_to)
|
||||
|
||||
async def send_image_file(
|
||||
self,
|
||||
chat_id: str,
|
||||
image_path: str,
|
||||
caption: Optional[str] = None,
|
||||
reply_to: Optional[str] = None,
|
||||
) -> SendResult:
|
||||
"""
|
||||
Send a local image file natively via the platform API.
|
||||
|
||||
Unlike send_image() which takes a URL, this takes a local file path.
|
||||
Override in subclasses for native photo attachments.
|
||||
Default falls back to sending the file path as text.
|
||||
"""
|
||||
text = f"🖼️ Image: {image_path}"
|
||||
if caption:
|
||||
text = f"{caption}\n{text}"
|
||||
return await self.send(chat_id=chat_id, content=text, reply_to=reply_to)
|
||||
|
||||
@staticmethod
|
||||
def extract_media(content: str) -> Tuple[List[Tuple[str, bool]], str]:
|
||||
"""
|
||||
|
|
@ -676,19 +732,42 @@ class BasePlatformAdapter(ABC):
|
|||
except Exception as img_err:
|
||||
print(f"[{self.name}] Error sending image: {img_err}")
|
||||
|
||||
# Send extracted audio/voice files as native attachments
|
||||
for audio_path, is_voice in media_files:
|
||||
# Send extracted media files — route by file type
|
||||
_AUDIO_EXTS = {'.ogg', '.opus', '.mp3', '.wav', '.m4a'}
|
||||
_VIDEO_EXTS = {'.mp4', '.mov', '.avi', '.mkv', '.3gp'}
|
||||
_IMAGE_EXTS = {'.jpg', '.jpeg', '.png', '.webp', '.gif'}
|
||||
|
||||
for media_path, is_voice in media_files:
|
||||
if human_delay > 0:
|
||||
await asyncio.sleep(human_delay)
|
||||
try:
|
||||
voice_result = await self.send_voice(
|
||||
chat_id=event.source.chat_id,
|
||||
audio_path=audio_path,
|
||||
)
|
||||
if not voice_result.success:
|
||||
print(f"[{self.name}] Failed to send voice: {voice_result.error}")
|
||||
except Exception as voice_err:
|
||||
print(f"[{self.name}] Error sending voice: {voice_err}")
|
||||
from pathlib import Path as _Path
|
||||
ext = _Path(media_path).suffix.lower()
|
||||
if ext in _AUDIO_EXTS:
|
||||
media_result = await self.send_voice(
|
||||
chat_id=event.source.chat_id,
|
||||
audio_path=media_path,
|
||||
)
|
||||
elif ext in _VIDEO_EXTS:
|
||||
media_result = await self.send_video(
|
||||
chat_id=event.source.chat_id,
|
||||
video_path=media_path,
|
||||
)
|
||||
elif ext in _IMAGE_EXTS:
|
||||
media_result = await self.send_image_file(
|
||||
chat_id=event.source.chat_id,
|
||||
image_path=media_path,
|
||||
)
|
||||
else:
|
||||
media_result = await self.send_document(
|
||||
chat_id=event.source.chat_id,
|
||||
file_path=media_path,
|
||||
)
|
||||
|
||||
if not media_result.success:
|
||||
print(f"[{self.name}] Failed to send media ({ext}): {media_result.error}")
|
||||
except Exception as media_err:
|
||||
print(f"[{self.name}] Error sending media: {media_err}")
|
||||
|
||||
# Check if there's a pending message that was queued during our processing
|
||||
if session_key in self._pending_messages:
|
||||
|
|
|
|||
|
|
@ -281,7 +281,102 @@ class WhatsAppAdapter(BasePlatformAdapter):
|
|||
)
|
||||
except Exception as e:
|
||||
return SendResult(success=False, error=str(e))
|
||||
|
||||
|
||||
async def _send_media_to_bridge(
|
||||
self,
|
||||
chat_id: str,
|
||||
file_path: str,
|
||||
media_type: str,
|
||||
caption: Optional[str] = None,
|
||||
file_name: Optional[str] = None,
|
||||
) -> SendResult:
|
||||
"""Send any media file via bridge /send-media endpoint."""
|
||||
if not self._running:
|
||||
return SendResult(success=False, error="Not connected")
|
||||
try:
|
||||
import aiohttp
|
||||
|
||||
if not os.path.exists(file_path):
|
||||
return SendResult(success=False, error=f"File not found: {file_path}")
|
||||
|
||||
payload: Dict[str, Any] = {
|
||||
"chatId": chat_id,
|
||||
"filePath": file_path,
|
||||
"mediaType": media_type,
|
||||
}
|
||||
if caption:
|
||||
payload["caption"] = caption
|
||||
if file_name:
|
||||
payload["fileName"] = file_name
|
||||
|
||||
async with aiohttp.ClientSession() as session:
|
||||
async with session.post(
|
||||
f"http://localhost:{self._bridge_port}/send-media",
|
||||
json=payload,
|
||||
timeout=aiohttp.ClientTimeout(total=120),
|
||||
) as resp:
|
||||
if resp.status == 200:
|
||||
data = await resp.json()
|
||||
return SendResult(
|
||||
success=True,
|
||||
message_id=data.get("messageId"),
|
||||
raw_response=data,
|
||||
)
|
||||
else:
|
||||
error = await resp.text()
|
||||
return SendResult(success=False, error=error)
|
||||
|
||||
except Exception as e:
|
||||
return SendResult(success=False, error=str(e))
|
||||
|
||||
async def send_image(
|
||||
self,
|
||||
chat_id: str,
|
||||
image_url: str,
|
||||
caption: Optional[str] = None,
|
||||
reply_to: Optional[str] = None,
|
||||
) -> SendResult:
|
||||
"""Download image URL to cache, send natively via bridge."""
|
||||
try:
|
||||
local_path = await cache_image_from_url(image_url)
|
||||
return await self._send_media_to_bridge(chat_id, local_path, "image", caption)
|
||||
except Exception:
|
||||
return await super().send_image(chat_id, image_url, caption, reply_to)
|
||||
|
||||
async def send_image_file(
|
||||
self,
|
||||
chat_id: str,
|
||||
image_path: str,
|
||||
caption: Optional[str] = None,
|
||||
reply_to: Optional[str] = None,
|
||||
) -> SendResult:
|
||||
"""Send a local image file natively via bridge."""
|
||||
return await self._send_media_to_bridge(chat_id, image_path, "image", caption)
|
||||
|
||||
async def send_video(
|
||||
self,
|
||||
chat_id: str,
|
||||
video_path: str,
|
||||
caption: Optional[str] = None,
|
||||
reply_to: Optional[str] = None,
|
||||
) -> SendResult:
|
||||
"""Send a video natively via bridge — plays inline in WhatsApp."""
|
||||
return await self._send_media_to_bridge(chat_id, video_path, "video", caption)
|
||||
|
||||
async def send_document(
|
||||
self,
|
||||
chat_id: str,
|
||||
file_path: str,
|
||||
caption: Optional[str] = None,
|
||||
file_name: Optional[str] = None,
|
||||
reply_to: Optional[str] = None,
|
||||
) -> SendResult:
|
||||
"""Send a document/file as a downloadable attachment via bridge."""
|
||||
return await self._send_media_to_bridge(
|
||||
chat_id, file_path, "document", caption,
|
||||
file_name or os.path.basename(file_path),
|
||||
)
|
||||
|
||||
async def send_typing(self, chat_id: str) -> None:
|
||||
"""Send typing indicator via bridge."""
|
||||
if not self._running:
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue