merge origin/main into pr-1567

This commit is contained in:
Re-bin
2026-03-06 06:51:28 +00:00
16 changed files with 645 additions and 72 deletions

View File

@@ -33,6 +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."""
@@ -149,6 +150,10 @@ 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:
@@ -205,6 +210,7 @@ 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
@@ -212,6 +218,11 @@ 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"
@@ -248,11 +259,32 @@ 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)

View File

@@ -290,16 +290,28 @@ 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()
@@ -398,6 +410,34 @@ 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
@@ -432,8 +472,124 @@ 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",
@@ -642,18 +798,45 @@ 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)

View File

@@ -208,7 +208,9 @@ 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)
@@ -252,23 +254,41 @@ class TelegramChannel(BaseChannel):
# Send text content
if msg.content and msg.content != "[empty message]":
is_progress = msg.metadata.get("_progress", False)
draft_id = msg.metadata.get("message_id")
for chunk in split_message(msg.content, TELEGRAM_MAX_MESSAGE_LEN):
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
)
if is_progress and draft_id:
await self._app.bot.send_message_draft(
chat_id=chat_id,
draft_id=draft_id,
text=html,
parse_mode="HTML"
)
else:
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
)
if is_progress and draft_id:
await self._app.bot.send_message_draft(
chat_id=chat_id,
draft_id=draft_id,
text=chunk
)
else:
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)