Hua/nanobot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'main' into pr-1535

Browse Source
This commit is contained in:
Re-bin
2026-03-07 15:05:54 +00:00
parent f78d655aba aee358c58e
commit 369dbec70a
38 changed files with 2154 additions and 318 deletions
Download Patch File Download Diff File Expand all files Collapse all files

129
nanobot/channels/discord.py
View File

@@ -13,34 +13,13 @@ from nanobot.bus.events import OutboundMessage
from nanobot.bus.queue import MessageBus
from nanobot.channels.base import BaseChannel
from nanobot.config.schema import DiscordConfig
from nanobot.utils.helpers import split_message
DISCORD_API_BASE = "https://discord.com/api/v10"
MAX_ATTACHMENT_BYTES = 20 * 1024 * 1024 # 20MB
MAX_MESSAGE_LEN = 2000 # Discord message character limit
def _split_message(content: str, max_len: int = MAX_MESSAGE_LEN) -> list[str]:
"""Split content into chunks within max_len, preferring line breaks."""
if not content:
return []
if len(content) <= max_len:
return [content]
chunks: list[str] = []
while content:
if len(content) <= max_len:
chunks.append(content)
break
cut = content[:max_len]
pos = cut.rfind('\n')
if pos <= 0:
pos = cut.rfind(' ')
if pos <= 0:
pos = max_len
chunks.append(content[:pos])
content = content[pos:].lstrip()
return chunks
class DiscordChannel(BaseChannel):
"""Discord channel using Gateway websocket."""
@@ -54,6 +33,7 @@ class DiscordChannel(BaseChannel):
self._heartbeat_task: asyncio.Task | None = None
self._typing_tasks: dict[str, asyncio.Task] = {}
self._http: httpx.AsyncClient | None = None
self._bot_user_id: str | None = None
async def start(self) -> None:
"""Start the Discord gateway connection."""
@@ -95,7 +75,7 @@ class DiscordChannel(BaseChannel):
self._http = None
async def send(self, msg: OutboundMessage) -> None:
"""Send a message through Discord REST API."""
"""Send a message through Discord REST API, including file attachments."""
if not self._http:
logger.warning("Discord HTTP client not initialized")
return
@@ -104,15 +84,31 @@ class DiscordChannel(BaseChannel):
headers = {"Authorization": f"Bot {self.config.token}"}
try:
chunks = _split_message(msg.content or "")
sent_media = False
failed_media: list[str] = []
# Send file attachments first
for media_path in msg.media or []:
if await self._send_file(url, headers, media_path, reply_to=msg.reply_to):
sent_media = True
else:
failed_media.append(Path(media_path).name)
# Send text content
chunks = split_message(msg.content or "", MAX_MESSAGE_LEN)
if not chunks and failed_media and not sent_media:
chunks = split_message(
"\n".join(f"[attachment: {name} - send failed]" for name in failed_media),
MAX_MESSAGE_LEN,
)
if not chunks:
return
for i, chunk in enumerate(chunks):
payload: dict[str, Any] = {"content": chunk}
# Only set reply reference on the first chunk
if i == 0 and msg.reply_to:
# Let the first successful attachment carry the reply if present.
if i == 0 and msg.reply_to and not sent_media:
payload["message_reference"] = {"message_id": msg.reply_to}
payload["allowed_mentions"] = {"replied_user": False}
@@ -143,6 +139,54 @@ class DiscordChannel(BaseChannel):
await asyncio.sleep(1)
return False
async def _send_file(
self,
url: str,
headers: dict[str, str],
file_path: str,
reply_to: str | None = None,
) -> bool:
"""Send a file attachment via Discord REST API using multipart/form-data."""
path = Path(file_path)
if not path.is_file():
logger.warning("Discord file not found, skipping: {}", file_path)
return False
if path.stat().st_size > MAX_ATTACHMENT_BYTES:
logger.warning("Discord file too large (>20MB), skipping: {}", path.name)
return False
payload_json: dict[str, Any] = {}
if reply_to:
payload_json["message_reference"] = {"message_id": reply_to}
payload_json["allowed_mentions"] = {"replied_user": False}
for attempt in range(3):
try:
with open(path, "rb") as f:
files = {"files[0]": (path.name, f, "application/octet-stream")}
data: dict[str, Any] = {}
if payload_json:
data["payload_json"] = json.dumps(payload_json)
response = await self._http.post(
url, headers=headers, files=files, data=data
)
if response.status_code == 429:
resp_data = response.json()
retry_after = float(resp_data.get("retry_after", 1.0))
logger.warning("Discord rate limited, retrying in {}s", retry_after)
await asyncio.sleep(retry_after)
continue
response.raise_for_status()
logger.info("Discord file sent: {}", path.name)
return True
except Exception as e:
if attempt == 2:
logger.error("Error sending Discord file {}: {}", path.name, e)
else:
await asyncio.sleep(1)
return False
async def _gateway_loop(self) -> None:
"""Main gateway loop: identify, heartbeat, dispatch events."""
if not self._ws:
@@ -170,6 +214,10 @@ class DiscordChannel(BaseChannel):
await self._identify()
elif op == 0 and event_type == "READY":
logger.info("Discord gateway READY")
# Capture bot user ID for mention detection
user_data = payload.get("user") or {}
self._bot_user_id = user_data.get("id")
logger.info("Discord bot connected as user {}", self._bot_user_id)
elif op == 0 and event_type == "MESSAGE_CREATE":
await self._handle_message_create(payload)
elif op == 7:
@@ -226,6 +274,7 @@ class DiscordChannel(BaseChannel):
sender_id = str(author.get("id", ""))
channel_id = str(payload.get("channel_id", ""))
content = payload.get("content") or ""
guild_id = payload.get("guild_id")
if not sender_id or not channel_id:
return
@@ -233,6 +282,11 @@ class DiscordChannel(BaseChannel):
if not self.is_allowed(sender_id):
return
# Check group channel policy (DMs always respond if is_allowed passes)
if guild_id is not None:
if not self._should_respond_in_group(payload, content):
return
content_parts = [content] if content else []
media_paths: list[str] = []
media_dir = Path.home() / ".nanobot" / "media"
@@ -269,11 +323,32 @@ class DiscordChannel(BaseChannel):
media=media_paths,
metadata={
"message_id": str(payload.get("id", "")),
"guild_id": payload.get("guild_id"),
"guild_id": guild_id,
"reply_to": reply_to,
},
)
def _should_respond_in_group(self, payload: dict[str, Any], content: str) -> bool:
"""Check if bot should respond in a group channel based on policy."""
if self.config.group_policy == "open":
return True
if self.config.group_policy == "mention":
# Check if bot was mentioned in the message
if self._bot_user_id:
# Check mentions array
mentions = payload.get("mentions") or []
for mention in mentions:
if str(mention.get("id")) == self._bot_user_id:
return True
# Also check content for mention format <@USER_ID>
if f"<@{self._bot_user_id}>" in content or f"<@!{self._bot_user_id}>" in content:
return True
logger.debug("Discord message in {} ignored (bot not mentioned)", payload.get("channel_id"))
return False
return True
async def _start_typing(self, channel_id: str) -> None:
"""Start periodic typing indicator for a channel."""
await self._stop_typing(channel_id)

307
nanobot/channels/feishu.py
View File

@@ -16,26 +16,9 @@ from nanobot.bus.queue import MessageBus
from nanobot.channels.base import BaseChannel
from nanobot.config.schema import FeishuConfig
try:
import lark_oapi as lark
from lark_oapi.api.im.v1 import (
CreateFileRequest,
CreateFileRequestBody,
CreateImageRequest,
CreateImageRequestBody,
CreateMessageReactionRequest,
CreateMessageReactionRequestBody,
CreateMessageRequest,
CreateMessageRequestBody,
Emoji,
GetMessageResourceRequest,
P2ImMessageReceiveV1,
)
FEISHU_AVAILABLE = True
except ImportError:
FEISHU_AVAILABLE = False
lark = None
Emoji = None
import importlib.util
FEISHU_AVAILABLE = importlib.util.find_spec("lark_oapi") is not None
# Message type display mapping
MSG_TYPE_MAP = {
@@ -261,15 +244,22 @@ class FeishuChannel(BaseChannel):
name = "feishu"
def __init__(self, config: FeishuConfig, bus: MessageBus):
def __init__(self, config: FeishuConfig, bus: MessageBus, groq_api_key: str = ""):
super().__init__(config, bus)
self.config: FeishuConfig = config
self.groq_api_key = groq_api_key
self._client: Any = None
self._ws_client: Any = None
self._ws_thread: threading.Thread | None = None
self._processed_message_ids: OrderedDict[str, None] = OrderedDict() # Ordered dedup cache
self._loop: asyncio.AbstractEventLoop | None = None
@staticmethod
def _register_optional_event(builder: Any, method_name: str, handler: Any) -> Any:
"""Register an event handler only when the SDK supports it."""
method = getattr(builder, method_name, None)
return method(handler) if callable(method) else builder
async def start(self) -> None:
"""Start the Feishu bot with WebSocket long connection."""
if not FEISHU_AVAILABLE:
@@ -280,6 +270,7 @@ class FeishuChannel(BaseChannel):
logger.error("Feishu app_id and app_secret not configured")
return
import lark_oapi as lark
self._running = True
self._loop = asyncio.get_running_loop()
@@ -289,14 +280,24 @@ class FeishuChannel(BaseChannel):
.app_secret(self.config.app_secret) \
.log_level(lark.LogLevel.INFO) \
.build()
# Create event handler (only register message receive, ignore other events)
event_handler = lark.EventDispatcherHandler.builder(
builder = lark.EventDispatcherHandler.builder(
self.config.encrypt_key or "",
self.config.verification_token or "",
).register_p2_im_message_receive_v1(
self._on_message_sync
).build()
)
builder = self._register_optional_event(
builder, "register_p2_im_message_reaction_created_v1", self._on_reaction_created
)
builder = self._register_optional_event(
builder, "register_p2_im_message_message_read_v1", self._on_message_read
)
builder = self._register_optional_event(
builder,
"register_p2_im_chat_access_event_bot_p2p_chat_entered_v1",
self._on_bot_p2p_chat_entered,
)
event_handler = builder.build()
# Create WebSocket client for long connection
self._ws_client = lark.ws.Client(
@@ -306,16 +307,28 @@ class FeishuChannel(BaseChannel):
log_level=lark.LogLevel.INFO
)
# Start WebSocket client in a separate thread with reconnect loop
# Start WebSocket client in a separate thread with reconnect loop.
# A dedicated event loop is created for this thread so that lark_oapi's
# module-level `loop = asyncio.get_event_loop()` picks up an idle loop
# instead of the already-running main asyncio loop, which would cause
# "This event loop is already running" errors.
def run_ws():
while self._running:
try:
self._ws_client.start()
except Exception as e:
logger.warning("Feishu WebSocket error: {}", e)
if self._running:
import time
time.sleep(5)
import time
import lark_oapi.ws.client as _lark_ws_client
ws_loop = asyncio.new_event_loop()
asyncio.set_event_loop(ws_loop)
# Patch the module-level loop used by lark's ws Client.start()
_lark_ws_client.loop = ws_loop
try:
while self._running:
try:
self._ws_client.start()
except Exception as e:
logger.warning("Feishu WebSocket error: {}", e)
if self._running:
time.sleep(5)
finally:
ws_loop.close()
self._ws_thread = threading.Thread(target=run_ws, daemon=True)
self._ws_thread.start()
@@ -340,6 +353,7 @@ class FeishuChannel(BaseChannel):
def _add_reaction_sync(self, message_id: str, emoji_type: str) -> None:
"""Sync helper for adding reaction (runs in thread pool)."""
from lark_oapi.api.im.v1 import CreateMessageReactionRequest, CreateMessageReactionRequestBody, Emoji
try:
request = CreateMessageReactionRequest.builder() \
.message_id(message_id) \
@@ -364,7 +378,7 @@ class FeishuChannel(BaseChannel):
Common emoji types: THUMBSUP, OK, EYES, DONE, OnIt, HEART
"""
if not self._client or not Emoji:
if not self._client:
return
loop = asyncio.get_running_loop()
@@ -413,6 +427,34 @@ class FeishuChannel(BaseChannel):
elements.extend(self._split_headings(remaining))
return elements or [{"tag": "markdown", "content": content}]
@staticmethod
def _split_elements_by_table_limit(elements: list[dict], max_tables: int = 1) -> list[list[dict]]:
"""Split card elements into groups with at most *max_tables* table elements each.
Feishu cards have a hard limit of one table per card (API error 11310).
When the rendered content contains multiple markdown tables each table is
placed in a separate card message so every table reaches the user.
"""
if not elements:
return [[]]
groups: list[list[dict]] = []
current: list[dict] = []
table_count = 0
for el in elements:
if el.get("tag") == "table":
if table_count >= max_tables:
if current:
groups.append(current)
current = []
table_count = 0
current.append(el)
table_count += 1
else:
current.append(el)
if current:
groups.append(current)
return groups or [[]]
def _split_headings(self, content: str) -> list[dict]:
"""Split content by headings, converting headings to div elements."""
protected = content
@@ -447,8 +489,124 @@ class FeishuChannel(BaseChannel):
return elements or [{"tag": "markdown", "content": content}]
# ── Smart format detection ──────────────────────────────────────────
# Patterns that indicate "complex" markdown needing card rendering
_COMPLEX_MD_RE = re.compile(
r"```" # fenced code block
r"|^\|.+\|.*\n\s*\|[-:\s|]+\|" # markdown table (header + separator)
r"|^#{1,6}\s+" # headings
, re.MULTILINE,
)
# Simple markdown patterns (bold, italic, strikethrough)
_SIMPLE_MD_RE = re.compile(
r"\*\*.+?\*\*" # **bold**
r"|__.+?__" # __bold__
r"|(?<!\*)\*(?!\*)(.+?)(?<!\*)\*(?!\*)" # *italic* (single *)
r"|~~.+?~~" # ~~strikethrough~~
, re.DOTALL,
)
# Markdown link: [text](url)
_MD_LINK_RE = re.compile(r"\[([^\]]+)\]\((https?://[^\)]+)\)")
# Unordered list items
_LIST_RE = re.compile(r"^[\s]*[-*+]\s+", re.MULTILINE)
# Ordered list items
_OLIST_RE = re.compile(r"^[\s]*\d+\.\s+", re.MULTILINE)
# Max length for plain text format
_TEXT_MAX_LEN = 200
# Max length for post (rich text) format; beyond this, use card
_POST_MAX_LEN = 2000
@classmethod
def _detect_msg_format(cls, content: str) -> str:
"""Determine the optimal Feishu message format for *content*.
Returns one of:
- ``"text"`` – plain text, short and no markdown
- ``"post"`` – rich text (links only, moderate length)
- ``"interactive"`` – card with full markdown rendering
"""
stripped = content.strip()
# Complex markdown (code blocks, tables, headings) → always card
if cls._COMPLEX_MD_RE.search(stripped):
return "interactive"
# Long content → card (better readability with card layout)
if len(stripped) > cls._POST_MAX_LEN:
return "interactive"
# Has bold/italic/strikethrough → card (post format can't render these)
if cls._SIMPLE_MD_RE.search(stripped):
return "interactive"
# Has list items → card (post format can't render list bullets well)
if cls._LIST_RE.search(stripped) or cls._OLIST_RE.search(stripped):
return "interactive"
# Has links → post format (supports <a> tags)
if cls._MD_LINK_RE.search(stripped):
return "post"
# Short plain text → text format
if len(stripped) <= cls._TEXT_MAX_LEN:
return "text"
# Medium plain text without any formatting → post format
return "post"
@classmethod
def _markdown_to_post(cls, content: str) -> str:
"""Convert markdown content to Feishu post message JSON.
Handles links ``[text](url)`` as ``a`` tags; everything else as ``text`` tags.
Each line becomes a paragraph (row) in the post body.
"""
lines = content.strip().split("\n")
paragraphs: list[list[dict]] = []
for line in lines:
elements: list[dict] = []
last_end = 0
for m in cls._MD_LINK_RE.finditer(line):
# Text before this link
before = line[last_end:m.start()]
if before:
elements.append({"tag": "text", "text": before})
elements.append({
"tag": "a",
"text": m.group(1),
"href": m.group(2),
})
last_end = m.end()
# Remaining text after last link
remaining = line[last_end:]
if remaining:
elements.append({"tag": "text", "text": remaining})
# Empty line → empty paragraph for spacing
if not elements:
elements.append({"tag": "text", "text": ""})
paragraphs.append(elements)
post_body = {
"zh_cn": {
"content": paragraphs,
}
}
return json.dumps(post_body, ensure_ascii=False)
_IMAGE_EXTS = {".png", ".jpg", ".jpeg", ".gif", ".bmp", ".webp", ".ico", ".tiff", ".tif"}
_AUDIO_EXTS = {".opus"}
_VIDEO_EXTS = {".mp4", ".mov", ".avi"}
_FILE_TYPE_MAP = {
".opus": "opus", ".mp4": "mp4", ".pdf": "pdf", ".doc": "doc", ".docx": "doc",
".xls": "xls", ".xlsx": "xls", ".ppt": "ppt", ".pptx": "ppt",
@@ -456,6 +614,7 @@ class FeishuChannel(BaseChannel):
def _upload_image_sync(self, file_path: str) -> str | None:
"""Upload an image to Feishu and return the image_key."""
from lark_oapi.api.im.v1 import CreateImageRequest, CreateImageRequestBody
try:
with open(file_path, "rb") as f:
request = CreateImageRequest.builder() \
@@ -479,6 +638,7 @@ class FeishuChannel(BaseChannel):
def _upload_file_sync(self, file_path: str) -> str | None:
"""Upload a file to Feishu and return the file_key."""
from lark_oapi.api.im.v1 import CreateFileRequest, CreateFileRequestBody
ext = os.path.splitext(file_path)[1].lower()
file_type = self._FILE_TYPE_MAP.get(ext, "stream")
file_name = os.path.basename(file_path)
@@ -506,6 +666,7 @@ class FeishuChannel(BaseChannel):
def _download_image_sync(self, message_id: str, image_key: str) -> tuple[bytes | None, str | None]:
"""Download an image from Feishu message by message_id and image_key."""
from lark_oapi.api.im.v1 import GetMessageResourceRequest
try:
request = GetMessageResourceRequest.builder() \
.message_id(message_id) \
@@ -530,6 +691,13 @@ class FeishuChannel(BaseChannel):
self, message_id: str, file_key: str, resource_type: str = "file"
) -> tuple[bytes | None, str | None]:
"""Download a file/audio/media from a Feishu message by message_id and file_key."""
from lark_oapi.api.im.v1 import GetMessageResourceRequest
# Feishu API only accepts 'image' or 'file' as type parameter
# Convert 'audio' to 'file' for API compatibility
if resource_type == "audio":
resource_type = "file"
try:
request = (
GetMessageResourceRequest.builder()
@@ -598,6 +766,7 @@ class FeishuChannel(BaseChannel):
def _send_message_sync(self, receive_id_type: str, receive_id: str, msg_type: str, content: str) -> bool:
"""Send a single message (text/image/file/interactive) synchronously."""
from lark_oapi.api.im.v1 import CreateMessageRequest, CreateMessageRequestBody
try:
request = CreateMessageRequest.builder() \
.receive_id_type(receive_id_type) \
@@ -646,23 +815,50 @@ class FeishuChannel(BaseChannel):
else:
key = await loop.run_in_executor(None, self._upload_file_sync, file_path)
if key:
media_type = "audio" if ext in self._AUDIO_EXTS else "file"
# Use msg_type "media" for audio/video so users can play inline;
# "file" for everything else (documents, archives, etc.)
if ext in self._AUDIO_EXTS or ext in self._VIDEO_EXTS:
media_type = "media"
else:
media_type = "file"
await loop.run_in_executor(
None, self._send_message_sync,
receive_id_type, msg.chat_id, media_type, json.dumps({"file_key": key}, ensure_ascii=False),
)
if msg.content and msg.content.strip():
card = {"config": {"wide_screen_mode": True}, "elements": self._build_card_elements(msg.content)}
await loop.run_in_executor(
None, self._send_message_sync,
receive_id_type, msg.chat_id, "interactive", json.dumps(card, ensure_ascii=False),
)
fmt = self._detect_msg_format(msg.content)
if fmt == "text":
# Short plain text – send as simple text message
text_body = json.dumps({"text": msg.content.strip()}, ensure_ascii=False)
await loop.run_in_executor(
None, self._send_message_sync,
receive_id_type, msg.chat_id, "text", text_body,
)
elif fmt == "post":
# Medium content with links – send as rich-text post
post_body = self._markdown_to_post(msg.content)
await loop.run_in_executor(
None, self._send_message_sync,
receive_id_type, msg.chat_id, "post", post_body,
)
else:
# Complex / long content – send as interactive card
elements = self._build_card_elements(msg.content)
for chunk in self._split_elements_by_table_limit(elements):
card = {"config": {"wide_screen_mode": True}, "elements": chunk}
await loop.run_in_executor(
None, self._send_message_sync,
receive_id_type, msg.chat_id, "interactive", json.dumps(card, ensure_ascii=False),
)
except Exception as e:
logger.error("Error sending Feishu message: {}", e)
def _on_message_sync(self, data: "P2ImMessageReceiveV1") -> None:
def _on_message_sync(self, data: Any) -> None:
"""
Sync handler for incoming messages (called from WebSocket thread).
Schedules async handling in the main event loop.
@@ -670,7 +866,7 @@ class FeishuChannel(BaseChannel):
if self._loop and self._loop.is_running():
asyncio.run_coroutine_threadsafe(self._on_message(data), self._loop)
async def _on_message(self, data: "P2ImMessageReceiveV1") -> None:
async def _on_message(self, data: Any) -> None:
"""Handle incoming message from Feishu."""
try:
event = data.event
@@ -730,6 +926,18 @@ class FeishuChannel(BaseChannel):
file_path, content_text = await self._download_and_save_media(msg_type, content_json, message_id)
if file_path:
media_paths.append(file_path)
# Transcribe audio using Groq Whisper
if msg_type == "audio" and file_path and self.groq_api_key:
try:
from nanobot.providers.transcription import GroqTranscriptionProvider
transcriber = GroqTranscriptionProvider(api_key=self.groq_api_key)
transcription = await transcriber.transcribe(file_path)
if transcription:
content_text = f"[transcription: {transcription}]"
except Exception as e:
logger.warning("Failed to transcribe audio: {}", e)
content_parts.append(content_text)
elif msg_type in ("share_chat", "share_user", "interactive", "share_calendar_event", "system", "merge_forward"):
@@ -762,3 +970,16 @@ class FeishuChannel(BaseChannel):
except Exception as e:
logger.error("Error processing Feishu message: {}", e)
def _on_reaction_created(self, data: Any) -> None:
"""Ignore reaction events so they do not generate SDK noise."""
pass
def _on_message_read(self, data: Any) -> None:
"""Ignore read events so they do not generate SDK noise."""
pass
def _on_bot_p2p_chat_entered(self, data: Any) -> None:
"""Ignore p2p-enter events when a user opens a bot chat."""
logger.debug("Bot entered p2p chat (user opened chat window)")
pass

3
nanobot/channels/manager.py
View File

@@ -74,7 +74,8 @@ class ChannelManager:
try:
from nanobot.channels.feishu import FeishuChannel
self.channels["feishu"] = FeishuChannel(
self.config.channels.feishu, self.bus
self.config.channels.feishu, self.bus,
groq_api_key=self.config.providers.groq.api_key,
)
logger.info("Feishu channel enabled")
except ImportError as e:

4
nanobot/channels/qq.py
View File

@@ -56,6 +56,7 @@ class QQChannel(BaseChannel):
self.config: QQConfig = config
self._client: "botpy.Client | None" = None
self._processed_ids: deque = deque(maxlen=1000)
self._msg_seq: int = 1 # 消息序列号，避免被 QQ API 去重
async def start(self) -> None:
"""Start the QQ bot."""
@@ -102,11 +103,13 @@ class QQChannel(BaseChannel):
return
try:
msg_id = msg.metadata.get("message_id")
self._msg_seq += 1 # 递增序列号
await self._client.api.post_c2c_message(
openid=msg.chat_id,
msg_type=0,
content=msg.content,
msg_id=msg_id,
msg_seq=self._msg_seq, # 添加序列号避免去重
)
except Exception as e:
logger.error("Error sending QQ message: {}", e)
@@ -133,3 +136,4 @@ class QQChannel(BaseChannel):
)
except Exception:
logger.exception("Error handling QQ message")

154
nanobot/channels/telegram.py
View File

@@ -4,6 +4,8 @@ from __future__ import annotations
import asyncio
import re
import time
import unicodedata
from loguru import logger
from telegram import BotCommand, ReplyParameters, Update
@@ -14,6 +16,50 @@ from nanobot.bus.events import OutboundMessage
from nanobot.bus.queue import MessageBus
from nanobot.channels.base import BaseChannel
from nanobot.config.schema import TelegramConfig
from nanobot.utils.helpers import split_message
TELEGRAM_MAX_MESSAGE_LEN = 4000 # Telegram message character limit
def _strip_md(s: str) -> str:
"""Strip markdown inline formatting from text."""
s = re.sub(r'\*\*(.+?)\*\*', r'\1', s)
s = re.sub(r'__(.+?)__', r'\1', s)
s = re.sub(r'~~(.+?)~~', r'\1', s)
s = re.sub(r'`([^`]+)`', r'\1', s)
return s.strip()
def _render_table_box(table_lines: list[str]) -> str:
"""Convert markdown pipe-table to compact aligned text for <pre> display."""
def dw(s: str) -> int:
return sum(2 if unicodedata.east_asian_width(c) in ('W', 'F') else 1 for c in s)
rows: list[list[str]] = []
has_sep = False
for line in table_lines:
cells = [_strip_md(c) for c in line.strip().strip('|').split('|')]
if all(re.match(r'^:?-+:?$', c) for c in cells if c):
has_sep = True
continue
rows.append(cells)
if not rows or not has_sep:
return '\n'.join(table_lines)
ncols = max(len(r) for r in rows)
for r in rows:
r.extend([''] * (ncols - len(r)))
widths = [max(dw(r[c]) for r in rows) for c in range(ncols)]
def dr(cells: list[str]) -> str:
return ' '.join(f'{c}{" " * (w - dw(c))}' for c, w in zip(cells, widths))
out = [dr(rows[0])]
out.append(' '.join('─' * w for w in widths))
for row in rows[1:]:
out.append(dr(row))
return '\n'.join(out)
def _markdown_to_telegram_html(text: str) -> str:
@@ -31,6 +77,27 @@ def _markdown_to_telegram_html(text: str) -> str:
text = re.sub(r'```[\w]*\n?([\s\S]*?)```', save_code_block, text)
# 1.5. Convert markdown tables to box-drawing (reuse code_block placeholders)
lines = text.split('\n')
rebuilt: list[str] = []
li = 0
while li < len(lines):
if re.match(r'^\s*\|.+\|', lines[li]):
tbl: list[str] = []
while li < len(lines) and re.match(r'^\s*\|.+\|', lines[li]):
tbl.append(lines[li])
li += 1
box = _render_table_box(tbl)
if box != '\n'.join(tbl):
code_blocks.append(box)
rebuilt.append(f"\x00CB{len(code_blocks) - 1}\x00")
else:
rebuilt.extend(tbl)
else:
rebuilt.append(lines[li])
li += 1
text = '\n'.join(rebuilt)
# 2. Extract and protect inline code
inline_codes: list[str] = []
def save_inline_code(m: re.Match) -> str:
@@ -79,26 +146,6 @@ def _markdown_to_telegram_html(text: str) -> str:
return text
def _split_message(content: str, max_len: int = 4000) -> list[str]:
"""Split content into chunks within max_len, preferring line breaks."""
if len(content) <= max_len:
return [content]
chunks: list[str] = []
while content:
if len(content) <= max_len:
chunks.append(content)
break
cut = content[:max_len]
pos = cut.rfind('\n')
if pos == -1:
pos = cut.rfind(' ')
if pos == -1:
pos = max_len
chunks.append(content[:pos])
content = content[pos:].lstrip()
return chunks
class TelegramChannel(BaseChannel):
"""
Telegram channel using long polling.
@@ -154,6 +201,7 @@ class TelegramChannel(BaseChannel):
# Add command handlers
self._app.add_handler(CommandHandler("start", self._on_start))
self._app.add_handler(CommandHandler("new", self._forward_command))
self._app.add_handler(CommandHandler("stop", self._forward_command))
self._app.add_handler(CommandHandler("help", self._on_help))
# Add message handler for text, photos, voice, documents
@@ -229,7 +277,9 @@ class TelegramChannel(BaseChannel):
logger.warning("Telegram bot not running")
return
self._stop_typing(msg.chat_id)
# Only stop typing indicator for final responses
if not msg.metadata.get("_progress", False):
self._stop_typing(msg.chat_id)
try:
chat_id = int(msg.chat_id)
@@ -273,25 +323,49 @@ class TelegramChannel(BaseChannel):
# Send text content
if msg.content and msg.content != "[empty message]":
for chunk in _split_message(msg.content):
try:
html = _markdown_to_telegram_html(chunk)
await self._app.bot.send_message(
chat_id=chat_id,
text=html,
parse_mode="HTML",
reply_parameters=reply_params
)
except Exception as e:
logger.warning("HTML parse failed, falling back to plain text: {}", e)
try:
await self._app.bot.send_message(
chat_id=chat_id,
text=chunk,
reply_parameters=reply_params
)
except Exception as e2:
logger.error("Error sending Telegram message: {}", e2)
is_progress = msg.metadata.get("_progress", False)
for chunk in split_message(msg.content, TELEGRAM_MAX_MESSAGE_LEN):
# Final response: simulate streaming via draft, then persist
if not is_progress:
await self._send_with_streaming(chat_id, chunk, reply_params)
else:
await self._send_text(chat_id, chunk, reply_params)
async def _send_text(self, chat_id: int, text: str, reply_params=None) -> None:
"""Send a plain text message with HTML fallback."""
try:
html = _markdown_to_telegram_html(text)
await self._app.bot.send_message(
chat_id=chat_id, text=html, parse_mode="HTML",
reply_parameters=reply_params,
)
except Exception as e:
logger.warning("HTML parse failed, falling back to plain text: {}", e)
try:
await self._app.bot.send_message(
chat_id=chat_id, text=text, reply_parameters=reply_params,
)
except Exception as e2:
logger.error("Error sending Telegram message: {}", e2)
async def _send_with_streaming(self, chat_id: int, text: str, reply_params=None) -> None:
"""Simulate streaming via send_message_draft, then persist with send_message."""
draft_id = int(time.time() * 1000) % (2**31)
try:
step = max(len(text) // 8, 40)
for i in range(step, len(text), step):
await self._app.bot.send_message_draft(
chat_id=chat_id, draft_id=draft_id, text=text[:i],
)
await asyncio.sleep(0.04)
await self._app.bot.send_message_draft(
chat_id=chat_id, draft_id=draft_id, text=text,
)
await asyncio.sleep(0.15)
except Exception:
pass
await self._send_text(chat_id, text, reply_params)
async def _on_start(self, update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
"""Handle /start command."""

13
nanobot/channels/whatsapp.py
View File

@@ -2,6 +2,7 @@
import asyncio
import json
import mimetypes
from collections import OrderedDict
from loguru import logger
@@ -128,10 +129,22 @@ class WhatsAppChannel(BaseChannel):
logger.info("Voice message received from {}, but direct download from bridge is not yet supported.", sender_id)
content = "[Voice Message: Transcription not available for WhatsApp yet]"
# Extract media paths (images/documents/videos downloaded by the bridge)
media_paths = data.get("media") or []
# Build content tags matching Telegram's pattern: [image: /path] or [file: /path]
if media_paths:
for p in media_paths:
mime, _ = mimetypes.guess_type(p)
media_type = "image" if mime and mime.startswith("image/") else "file"
media_tag = f"[{media_type}: {p}]"
content = f"{content}\n{media_tag}" if content else media_tag
await self._handle_message(
sender_id=sender_id,
chat_id=sender, # Use full LID for replies
content=content,
media=media_paths,
metadata={
"message_id": message_id,
"timestamp": data.get("timestamp"),