chengyongru 462a0dfb0f
refactor(channels): make built-in channels self-contained (#4908)
* refactor(channels): own setup and instance contracts

* refactor(channels): isolate management contracts

* refactor(channels): normalize activation contracts

* fix(channels): enforce management contracts

* refactor(channels): finish setup ownership migration

* fix(channels): harden management contracts

* fix(channels): enforce lazy loading and runtime ownership

* fix(feishu): make multi-instance startup idempotent

* fix(webui): render channel setup contracts cleanly

* fix(feishu): stop websocket clients cleanly

* fix(channels): enforce persistence and activation gates

* fix(channels): preserve global feature action scope

* fix(channels): apply defaults for single plugins

* fix(channels): enforce management contract boundaries

* refactor(feishu): remove identity helper indirection

* fix(channels): preserve management setup contracts

* refactor(channels): generalize instance settings UI

* refactor(channels): package channel plugins with web UI metadata

* refactor(channels): make built-ins self-contained packages

* test(channels): colocate tests with channel packages

* fix(dingtalk): use official brand icon

* feat(channels): colocate webui translations

* docs(channels): clarify plugin ownership

* test(exec): remove output wait race

* refactor(channels): unify plugin descriptors

* fix(channels): enforce descriptor-owned contracts

* refactor(channels): finish package-owned plugin setup

* refactor(channels): use repository-owned packages only

* fix(channels): self-describe dependencies and runtime state

* fix(channels): warn about legacy entry points
2026-07-19 23:30:49 +08:00

295 lines
9.6 KiB
Python

"""Base channel interface for chat platforms."""
from __future__ import annotations
from abc import ABC, abstractmethod
from pathlib import Path
from typing import Any
from loguru import logger
from nanobot.bus.events import InboundMessage, OutboundMessage
from nanobot.bus.queue import MessageBus
from nanobot.pairing import (
PAIRING_CODE_META_KEY,
format_pairing_reply,
generate_code,
is_approved,
)
class BaseChannel(ABC):
"""
Abstract base class for chat channel implementations.
Each channel (Telegram, Discord, etc.) should implement this interface
to integrate with the nanobot message bus.
"""
name: str = "base"
display_name: str = "Base"
send_progress: bool = True
send_tool_hints: bool = False
show_reasoning: bool = True
def __init__(self, config: Any, bus: MessageBus):
"""
Initialize the channel.
Args:
config: Channel-specific configuration.
bus: The message bus for communication.
"""
self.config = config
self.logger = logger.bind(channel=self.name)
self.bus = bus
self._running = False
async def transcribe_audio(self, file_path: str | Path) -> str:
"""Transcribe an audio file via Whisper (OpenAI or Groq). Returns empty string on failure."""
try:
from nanobot.audio.transcription import (
resolve_transcription_config,
transcribe_audio_file,
)
from nanobot.config.loader import load_config
return await transcribe_audio_file(file_path, resolve_transcription_config(load_config()))
except Exception:
self.logger.exception("Audio transcription failed")
return ""
async def login(self, force: bool = False) -> bool:
"""
Perform channel-specific interactive login (e.g. QR code scan).
Args:
force: If True, ignore existing credentials and force re-authentication.
Returns True if already authenticated or login succeeds.
Override in subclasses that support interactive login.
"""
return True
@abstractmethod
async def start(self) -> None:
"""
Start the channel and begin listening for messages.
This should be a long-running async task that:
1. Connects to the chat platform
2. Listens for incoming messages
3. Forwards messages to the bus via _handle_message()
"""
pass
@abstractmethod
async def stop(self) -> None:
"""Stop the channel and clean up resources."""
pass
@abstractmethod
async def send(self, msg: OutboundMessage) -> None:
"""
Send a message through this channel.
Args:
msg: The message to send.
Implementations should raise on delivery failure so the channel manager
can apply any retry policy in one place.
"""
pass
async def send_delta(
self,
chat_id: str,
delta: str,
metadata: dict[str, Any] | None = None,
*,
stream_id: str | None = None,
stream_end: bool = False,
resuming: bool = False,
) -> None:
"""Deliver a streaming text chunk.
Override in subclasses to enable streaming. Implementations should
raise on delivery failure so the channel manager can retry.
Stateful implementations should key buffers by ``stream_id`` rather
than only by ``chat_id`` when it is provided.
"""
pass
async def send_reasoning_delta(
self,
chat_id: str,
delta: str,
metadata: dict[str, Any] | None = None,
*,
stream_id: str | None = None,
) -> None:
"""Stream a chunk of model reasoning/thinking content.
Default is no-op. Channels with a native low-emphasis primitive
(Slack context block, Telegram expandable blockquote, Discord
subtext, WebUI italic bubble, ...) override to render reasoning
as a subordinate trace that updates in place as the model thinks.
Streaming contract mirrors :meth:`send_delta`: stateful implementations
should key buffers by ``stream_id`` rather than only by ``chat_id``.
"""
return
async def send_reasoning_end(
self,
chat_id: str,
metadata: dict[str, Any] | None = None,
*,
stream_id: str | None = None,
) -> None:
"""Mark the end of a reasoning stream segment.
Default is no-op. Channels that buffer ``send_reasoning_delta``
chunks for in-place updates use this signal to flush and freeze
the rendered group; one-shot channels can ignore it entirely.
"""
return
async def send_file_edit_events(
self,
chat_id: str,
edits: list[dict[str, Any]],
metadata: dict[str, Any] | None = None,
) -> None:
"""Deliver structured live file-edit events.
Default is no-op. Channels with a rich activity surface can override
this to render editing progress without receiving empty text messages.
"""
return
async def send_reasoning(self, msg: OutboundMessage) -> None:
"""Deliver a complete reasoning block.
Default implementation reuses the streaming pair so plugins only
need to override the delta/end methods. Equivalent to one delta
with the full content followed immediately by an end marker —
keeps a single rendering path for both streamed and one-shot
reasoning (e.g. DeepSeek-R1's final-response ``reasoning_content``).
"""
if not msg.content:
return
stream_id = getattr(msg.event, "stream_id", None)
await self.send_reasoning_delta(
msg.chat_id,
msg.content,
msg.metadata,
stream_id=stream_id,
)
await self.send_reasoning_end(
msg.chat_id,
msg.metadata,
stream_id=stream_id,
)
@property
def supports_streaming(self) -> bool:
"""True when config enables streaming AND this subclass implements send_delta."""
cfg = self.config
streaming = cfg.get("streaming", False) if isinstance(cfg, dict) else getattr(cfg, "streaming", False)
return bool(streaming) and type(self).send_delta is not BaseChannel.send_delta
def is_allowed(self, sender_id: str) -> bool:
"""Check sender permission: star > allowlist > pairing store > deny."""
if isinstance(self.config, dict):
allow_list = self.config.get("allow_from") or self.config.get("allowFrom") or []
else:
allow_list = getattr(self.config, "allow_from", None) or []
if "*" in allow_list:
return True
# allowFrom entries are opaque tokens — must match exactly.
if str(sender_id) in allow_list:
return True
if is_approved(self.name, str(sender_id)):
return True
return False
async def _handle_message(
self,
sender_id: str,
chat_id: str,
content: str,
media: list[str] | None = None,
metadata: dict[str, Any] | None = None,
session_key: str | None = None,
is_dm: bool = False,
authorization_id: str | None = None,
) -> None:
"""Handle a message after checking its authorization subject.
``sender_id`` is the identity recorded on the inbound message. Channels
where access is scoped to another entity (for example, a group or room)
can pass that entity as ``authorization_id`` without changing the
sender's identity. When omitted, authorization remains sender-based.
"""
permission_id = authorization_id if authorization_id is not None else sender_id
if not self.is_allowed(permission_id):
if is_dm:
code = generate_code(self.name, str(sender_id))
await self.send(
OutboundMessage(
channel=self.name,
chat_id=str(chat_id),
content=format_pairing_reply(code),
metadata={PAIRING_CODE_META_KEY: code},
)
)
self.logger.info(
"Sent pairing code {} to sender {} in chat {}",
code, sender_id, chat_id,
)
else:
self.logger.warning(
"Access denied for sender {}. "
"Add them to allowFrom list in config to grant access.",
sender_id,
)
return
meta = metadata or {}
if self.supports_streaming:
meta = {**meta, "_wants_stream": True}
msg = InboundMessage(
channel=self.name,
sender_id=str(sender_id),
chat_id=str(chat_id),
content=content,
media=media or [],
metadata=meta,
session_key_override=session_key,
)
await self.bus.publish_inbound(msg)
@classmethod
def default_config(cls) -> dict[str, Any]:
"""Return default config for onboard. Override in plugins to auto-populate config.json."""
return {"enabled": False}
@classmethod
def refresh_feature_metadata(
cls,
config_path: Path,
*,
instance_id: str = "default",
) -> bool:
"""Refresh persisted display metadata after an explicit settings action."""
return False
@property
def is_running(self) -> bool:
"""Check if the channel is running."""
return self._running