mirror of
https://github.com/HKUDS/nanobot.git
synced 2026-04-06 11:13:38 +00:00
Merge branch 'main' into nightly
This commit is contained in:
commit
1c7f38a2a7
@ -70,6 +70,8 @@
|
||||
|
||||
</details>
|
||||
|
||||
> 🐈 nanobot is for educational, research, and technical exchange purposes only. It is unrelated to crypto and does not involve any official token or coin.
|
||||
|
||||
## Key Features of nanobot:
|
||||
|
||||
🪶 **Ultra-Lightweight**: A super lightweight implementation of OpenClaw — 99% smaller, significantly faster.
|
||||
|
||||
@ -191,6 +191,10 @@ def _extract_post_content(content_json: dict) -> tuple[str, list[str]]:
|
||||
texts.append(el.get("text", ""))
|
||||
elif tag == "at":
|
||||
texts.append(f"@{el.get('user_name', 'user')}")
|
||||
elif tag == "code_block":
|
||||
lang = el.get("language", "")
|
||||
code_text = el.get("text", "")
|
||||
texts.append(f"\n```{lang}\n{code_text}\n```\n")
|
||||
elif tag == "img" and (key := el.get("image_key")):
|
||||
images.append(key)
|
||||
return (" ".join(texts).strip() or None), images
|
||||
@ -1039,7 +1043,7 @@ class FeishuChannel(BaseChannel):
|
||||
event = data.event
|
||||
message = event.message
|
||||
sender = event.sender
|
||||
|
||||
|
||||
# Deduplication check
|
||||
message_id = message.message_id
|
||||
if message_id in self._processed_message_ids:
|
||||
|
||||
@ -11,6 +11,7 @@ from typing import Any, Literal
|
||||
from loguru import logger
|
||||
from pydantic import Field
|
||||
from telegram import BotCommand, ReplyParameters, Update
|
||||
from telegram.error import TimedOut
|
||||
from telegram.ext import Application, CommandHandler, ContextTypes, MessageHandler, filters
|
||||
from telegram.request import HTTPXRequest
|
||||
|
||||
@ -19,6 +20,7 @@ from nanobot.bus.queue import MessageBus
|
||||
from nanobot.channels.base import BaseChannel
|
||||
from nanobot.config.paths import get_media_dir
|
||||
from nanobot.config.schema import Base
|
||||
from nanobot.security.network import validate_url_target
|
||||
from nanobot.utils.helpers import split_message
|
||||
|
||||
TELEGRAM_MAX_MESSAGE_LEN = 4000 # Telegram message character limit
|
||||
@ -150,6 +152,10 @@ def _markdown_to_telegram_html(text: str) -> str:
|
||||
return text
|
||||
|
||||
|
||||
_SEND_MAX_RETRIES = 3
|
||||
_SEND_RETRY_BASE_DELAY = 0.5 # seconds, doubled each retry
|
||||
|
||||
|
||||
class TelegramConfig(Base):
|
||||
"""Telegram channel configuration."""
|
||||
|
||||
@ -159,6 +165,8 @@ class TelegramConfig(Base):
|
||||
proxy: str | None = None
|
||||
reply_to_message: bool = False
|
||||
group_policy: Literal["open", "mention"] = "mention"
|
||||
connection_pool_size: int = 32
|
||||
pool_timeout: float = 5.0
|
||||
|
||||
|
||||
class TelegramChannel(BaseChannel):
|
||||
@ -225,15 +233,29 @@ class TelegramChannel(BaseChannel):
|
||||
|
||||
self._running = True
|
||||
|
||||
# Build the application with larger connection pool to avoid pool-timeout on long runs
|
||||
req = HTTPXRequest(
|
||||
connection_pool_size=16,
|
||||
pool_timeout=5.0,
|
||||
proxy = self.config.proxy or None
|
||||
|
||||
# Separate pools so long-polling (getUpdates) never starves outbound sends.
|
||||
api_request = HTTPXRequest(
|
||||
connection_pool_size=self.config.connection_pool_size,
|
||||
pool_timeout=self.config.pool_timeout,
|
||||
connect_timeout=30.0,
|
||||
read_timeout=30.0,
|
||||
proxy=self.config.proxy if self.config.proxy else None,
|
||||
proxy=proxy,
|
||||
)
|
||||
poll_request = HTTPXRequest(
|
||||
connection_pool_size=4,
|
||||
pool_timeout=self.config.pool_timeout,
|
||||
connect_timeout=30.0,
|
||||
read_timeout=30.0,
|
||||
proxy=proxy,
|
||||
)
|
||||
builder = (
|
||||
Application.builder()
|
||||
.token(self.config.token)
|
||||
.request(api_request)
|
||||
.get_updates_request(poll_request)
|
||||
)
|
||||
builder = Application.builder().token(self.config.token).request(req).get_updates_request(req)
|
||||
self._app = builder.build()
|
||||
self._app.add_error_handler(self._on_error)
|
||||
|
||||
@ -313,6 +335,10 @@ class TelegramChannel(BaseChannel):
|
||||
return "audio"
|
||||
return "document"
|
||||
|
||||
@staticmethod
|
||||
def _is_remote_media_url(path: str) -> bool:
|
||||
return path.startswith(("http://", "https://"))
|
||||
|
||||
async def send(self, msg: OutboundMessage) -> None:
|
||||
"""Send a message through Telegram."""
|
||||
if not self._app:
|
||||
@ -354,7 +380,22 @@ class TelegramChannel(BaseChannel):
|
||||
"audio": self._app.bot.send_audio,
|
||||
}.get(media_type, self._app.bot.send_document)
|
||||
param = "photo" if media_type == "photo" else media_type if media_type in ("voice", "audio") else "document"
|
||||
with open(media_path, 'rb') as f:
|
||||
|
||||
# Telegram Bot API accepts HTTP(S) URLs directly for media params.
|
||||
if self._is_remote_media_url(media_path):
|
||||
ok, error = validate_url_target(media_path)
|
||||
if not ok:
|
||||
raise ValueError(f"unsafe media URL: {error}")
|
||||
await self._call_with_retry(
|
||||
sender,
|
||||
chat_id=chat_id,
|
||||
**{param: media_path},
|
||||
reply_parameters=reply_params,
|
||||
**thread_kwargs,
|
||||
)
|
||||
continue
|
||||
|
||||
with open(media_path, "rb") as f:
|
||||
await sender(
|
||||
chat_id=chat_id,
|
||||
**{param: f},
|
||||
@ -382,6 +423,21 @@ class TelegramChannel(BaseChannel):
|
||||
else:
|
||||
await self._send_text(chat_id, chunk, reply_params, thread_kwargs)
|
||||
|
||||
async def _call_with_retry(self, fn, *args, **kwargs):
|
||||
"""Call an async Telegram API function with retry on pool/network timeout."""
|
||||
for attempt in range(1, _SEND_MAX_RETRIES + 1):
|
||||
try:
|
||||
return await fn(*args, **kwargs)
|
||||
except TimedOut:
|
||||
if attempt == _SEND_MAX_RETRIES:
|
||||
raise
|
||||
delay = _SEND_RETRY_BASE_DELAY * (2 ** (attempt - 1))
|
||||
logger.warning(
|
||||
"Telegram timeout (attempt {}/{}), retrying in {:.1f}s",
|
||||
attempt, _SEND_MAX_RETRIES, delay,
|
||||
)
|
||||
await asyncio.sleep(delay)
|
||||
|
||||
async def _send_text(
|
||||
self,
|
||||
chat_id: int,
|
||||
@ -392,7 +448,8 @@ class TelegramChannel(BaseChannel):
|
||||
"""Send a plain text message with HTML fallback."""
|
||||
try:
|
||||
html = _markdown_to_telegram_html(text)
|
||||
await self._app.bot.send_message(
|
||||
await self._call_with_retry(
|
||||
self._app.bot.send_message,
|
||||
chat_id=chat_id, text=html, parse_mode="HTML",
|
||||
reply_parameters=reply_params,
|
||||
**(thread_kwargs or {}),
|
||||
@ -400,7 +457,8 @@ class TelegramChannel(BaseChannel):
|
||||
except Exception as e:
|
||||
logger.warning("HTML parse failed, falling back to plain text: {}", e)
|
||||
try:
|
||||
await self._app.bot.send_message(
|
||||
await self._call_with_retry(
|
||||
self._app.bot.send_message,
|
||||
chat_id=chat_id,
|
||||
text=text,
|
||||
reply_parameters=reply_params,
|
||||
|
||||
@ -1,8 +1,30 @@
|
||||
"""LLM provider abstraction module."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from importlib import import_module
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
from nanobot.providers.base import LLMProvider, LLMResponse
|
||||
from nanobot.providers.litellm_provider import LiteLLMProvider
|
||||
from nanobot.providers.openai_codex_provider import OpenAICodexProvider
|
||||
from nanobot.providers.azure_openai_provider import AzureOpenAIProvider
|
||||
|
||||
__all__ = ["LLMProvider", "LLMResponse", "LiteLLMProvider", "OpenAICodexProvider", "AzureOpenAIProvider"]
|
||||
|
||||
_LAZY_IMPORTS = {
|
||||
"LiteLLMProvider": ".litellm_provider",
|
||||
"OpenAICodexProvider": ".openai_codex_provider",
|
||||
"AzureOpenAIProvider": ".azure_openai_provider",
|
||||
}
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from nanobot.providers.azure_openai_provider import AzureOpenAIProvider
|
||||
from nanobot.providers.litellm_provider import LiteLLMProvider
|
||||
from nanobot.providers.openai_codex_provider import OpenAICodexProvider
|
||||
|
||||
|
||||
def __getattr__(name: str):
|
||||
"""Lazily expose provider implementations without importing all backends up front."""
|
||||
module_name = _LAZY_IMPORTS.get(name)
|
||||
if module_name is None:
|
||||
raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
|
||||
module = import_module(module_name, __name__)
|
||||
return getattr(module, name)
|
||||
|
||||
37
tests/test_providers_init.py
Normal file
37
tests/test_providers_init.py
Normal file
@ -0,0 +1,37 @@
|
||||
"""Tests for lazy provider exports from nanobot.providers."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import importlib
|
||||
import sys
|
||||
|
||||
|
||||
def test_importing_providers_package_is_lazy(monkeypatch) -> None:
|
||||
monkeypatch.delitem(sys.modules, "nanobot.providers", raising=False)
|
||||
monkeypatch.delitem(sys.modules, "nanobot.providers.litellm_provider", raising=False)
|
||||
monkeypatch.delitem(sys.modules, "nanobot.providers.openai_codex_provider", raising=False)
|
||||
monkeypatch.delitem(sys.modules, "nanobot.providers.azure_openai_provider", raising=False)
|
||||
|
||||
providers = importlib.import_module("nanobot.providers")
|
||||
|
||||
assert "nanobot.providers.litellm_provider" not in sys.modules
|
||||
assert "nanobot.providers.openai_codex_provider" not in sys.modules
|
||||
assert "nanobot.providers.azure_openai_provider" not in sys.modules
|
||||
assert providers.__all__ == [
|
||||
"LLMProvider",
|
||||
"LLMResponse",
|
||||
"LiteLLMProvider",
|
||||
"OpenAICodexProvider",
|
||||
"AzureOpenAIProvider",
|
||||
]
|
||||
|
||||
|
||||
def test_explicit_provider_import_still_works(monkeypatch) -> None:
|
||||
monkeypatch.delitem(sys.modules, "nanobot.providers", raising=False)
|
||||
monkeypatch.delitem(sys.modules, "nanobot.providers.litellm_provider", raising=False)
|
||||
|
||||
namespace: dict[str, object] = {}
|
||||
exec("from nanobot.providers import LiteLLMProvider", namespace)
|
||||
|
||||
assert namespace["LiteLLMProvider"].__name__ == "LiteLLMProvider"
|
||||
assert "nanobot.providers.litellm_provider" in sys.modules
|
||||
@ -18,6 +18,10 @@ class _FakeHTTPXRequest:
|
||||
self.kwargs = kwargs
|
||||
self.__class__.instances.append(self)
|
||||
|
||||
@classmethod
|
||||
def clear(cls) -> None:
|
||||
cls.instances.clear()
|
||||
|
||||
|
||||
class _FakeUpdater:
|
||||
def __init__(self, on_start_polling) -> None:
|
||||
@ -30,6 +34,7 @@ class _FakeUpdater:
|
||||
class _FakeBot:
|
||||
def __init__(self) -> None:
|
||||
self.sent_messages: list[dict] = []
|
||||
self.sent_media: list[dict] = []
|
||||
self.get_me_calls = 0
|
||||
|
||||
async def get_me(self):
|
||||
@ -42,6 +47,18 @@ class _FakeBot:
|
||||
async def send_message(self, **kwargs) -> None:
|
||||
self.sent_messages.append(kwargs)
|
||||
|
||||
async def send_photo(self, **kwargs) -> None:
|
||||
self.sent_media.append({"kind": "photo", **kwargs})
|
||||
|
||||
async def send_voice(self, **kwargs) -> None:
|
||||
self.sent_media.append({"kind": "voice", **kwargs})
|
||||
|
||||
async def send_audio(self, **kwargs) -> None:
|
||||
self.sent_media.append({"kind": "audio", **kwargs})
|
||||
|
||||
async def send_document(self, **kwargs) -> None:
|
||||
self.sent_media.append({"kind": "document", **kwargs})
|
||||
|
||||
async def send_chat_action(self, **kwargs) -> None:
|
||||
pass
|
||||
|
||||
@ -131,7 +148,8 @@ def _make_telegram_update(
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_start_uses_request_proxy_without_builder_proxy(monkeypatch) -> None:
|
||||
async def test_start_creates_separate_pools_with_proxy(monkeypatch) -> None:
|
||||
_FakeHTTPXRequest.clear()
|
||||
config = TelegramConfig(
|
||||
enabled=True,
|
||||
token="123:abc",
|
||||
@ -151,10 +169,106 @@ async def test_start_uses_request_proxy_without_builder_proxy(monkeypatch) -> No
|
||||
|
||||
await channel.start()
|
||||
|
||||
assert len(_FakeHTTPXRequest.instances) == 1
|
||||
assert _FakeHTTPXRequest.instances[0].kwargs["proxy"] == config.proxy
|
||||
assert builder.request_value is _FakeHTTPXRequest.instances[0]
|
||||
assert builder.get_updates_request_value is _FakeHTTPXRequest.instances[0]
|
||||
assert len(_FakeHTTPXRequest.instances) == 2
|
||||
api_req, poll_req = _FakeHTTPXRequest.instances
|
||||
assert api_req.kwargs["proxy"] == config.proxy
|
||||
assert poll_req.kwargs["proxy"] == config.proxy
|
||||
assert api_req.kwargs["connection_pool_size"] == 32
|
||||
assert poll_req.kwargs["connection_pool_size"] == 4
|
||||
assert builder.request_value is api_req
|
||||
assert builder.get_updates_request_value is poll_req
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_start_respects_custom_pool_config(monkeypatch) -> None:
|
||||
_FakeHTTPXRequest.clear()
|
||||
config = TelegramConfig(
|
||||
enabled=True,
|
||||
token="123:abc",
|
||||
allow_from=["*"],
|
||||
connection_pool_size=32,
|
||||
pool_timeout=10.0,
|
||||
)
|
||||
bus = MessageBus()
|
||||
channel = TelegramChannel(config, bus)
|
||||
app = _FakeApp(lambda: setattr(channel, "_running", False))
|
||||
builder = _FakeBuilder(app)
|
||||
|
||||
monkeypatch.setattr("nanobot.channels.telegram.HTTPXRequest", _FakeHTTPXRequest)
|
||||
monkeypatch.setattr(
|
||||
"nanobot.channels.telegram.Application",
|
||||
SimpleNamespace(builder=lambda: builder),
|
||||
)
|
||||
|
||||
await channel.start()
|
||||
|
||||
api_req = _FakeHTTPXRequest.instances[0]
|
||||
poll_req = _FakeHTTPXRequest.instances[1]
|
||||
assert api_req.kwargs["connection_pool_size"] == 32
|
||||
assert api_req.kwargs["pool_timeout"] == 10.0
|
||||
assert poll_req.kwargs["pool_timeout"] == 10.0
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_send_text_retries_on_timeout() -> None:
|
||||
"""_send_text retries on TimedOut before succeeding."""
|
||||
from telegram.error import TimedOut
|
||||
|
||||
channel = TelegramChannel(
|
||||
TelegramConfig(enabled=True, token="123:abc", allow_from=["*"]),
|
||||
MessageBus(),
|
||||
)
|
||||
channel._app = _FakeApp(lambda: None)
|
||||
|
||||
call_count = 0
|
||||
original_send = channel._app.bot.send_message
|
||||
|
||||
async def flaky_send(**kwargs):
|
||||
nonlocal call_count
|
||||
call_count += 1
|
||||
if call_count <= 2:
|
||||
raise TimedOut()
|
||||
return await original_send(**kwargs)
|
||||
|
||||
channel._app.bot.send_message = flaky_send
|
||||
|
||||
import nanobot.channels.telegram as tg_mod
|
||||
orig_delay = tg_mod._SEND_RETRY_BASE_DELAY
|
||||
tg_mod._SEND_RETRY_BASE_DELAY = 0.01
|
||||
try:
|
||||
await channel._send_text(123, "hello", None, {})
|
||||
finally:
|
||||
tg_mod._SEND_RETRY_BASE_DELAY = orig_delay
|
||||
|
||||
assert call_count == 3
|
||||
assert len(channel._app.bot.sent_messages) == 1
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_send_text_gives_up_after_max_retries() -> None:
|
||||
"""_send_text raises TimedOut after exhausting all retries."""
|
||||
from telegram.error import TimedOut
|
||||
|
||||
channel = TelegramChannel(
|
||||
TelegramConfig(enabled=True, token="123:abc", allow_from=["*"]),
|
||||
MessageBus(),
|
||||
)
|
||||
channel._app = _FakeApp(lambda: None)
|
||||
|
||||
async def always_timeout(**kwargs):
|
||||
raise TimedOut()
|
||||
|
||||
channel._app.bot.send_message = always_timeout
|
||||
|
||||
import nanobot.channels.telegram as tg_mod
|
||||
orig_delay = tg_mod._SEND_RETRY_BASE_DELAY
|
||||
tg_mod._SEND_RETRY_BASE_DELAY = 0.01
|
||||
try:
|
||||
await channel._send_text(123, "hello", None, {})
|
||||
finally:
|
||||
tg_mod._SEND_RETRY_BASE_DELAY = orig_delay
|
||||
|
||||
assert channel._app.bot.sent_messages == []
|
||||
|
||||
|
||||
def test_derive_topic_session_key_uses_thread_id() -> None:
|
||||
@ -231,6 +345,65 @@ async def test_send_reply_infers_topic_from_message_id_cache() -> None:
|
||||
assert channel._app.bot.sent_messages[0]["reply_parameters"].message_id == 10
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_send_remote_media_url_after_security_validation(monkeypatch) -> None:
|
||||
channel = TelegramChannel(
|
||||
TelegramConfig(enabled=True, token="123:abc", allow_from=["*"]),
|
||||
MessageBus(),
|
||||
)
|
||||
channel._app = _FakeApp(lambda: None)
|
||||
monkeypatch.setattr("nanobot.channels.telegram.validate_url_target", lambda url: (True, ""))
|
||||
|
||||
await channel.send(
|
||||
OutboundMessage(
|
||||
channel="telegram",
|
||||
chat_id="123",
|
||||
content="",
|
||||
media=["https://example.com/cat.jpg"],
|
||||
)
|
||||
)
|
||||
|
||||
assert channel._app.bot.sent_media == [
|
||||
{
|
||||
"kind": "photo",
|
||||
"chat_id": 123,
|
||||
"photo": "https://example.com/cat.jpg",
|
||||
"reply_parameters": None,
|
||||
}
|
||||
]
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_send_blocks_unsafe_remote_media_url(monkeypatch) -> None:
|
||||
channel = TelegramChannel(
|
||||
TelegramConfig(enabled=True, token="123:abc", allow_from=["*"]),
|
||||
MessageBus(),
|
||||
)
|
||||
channel._app = _FakeApp(lambda: None)
|
||||
monkeypatch.setattr(
|
||||
"nanobot.channels.telegram.validate_url_target",
|
||||
lambda url: (False, "Blocked: example.com resolves to private/internal address 127.0.0.1"),
|
||||
)
|
||||
|
||||
await channel.send(
|
||||
OutboundMessage(
|
||||
channel="telegram",
|
||||
chat_id="123",
|
||||
content="",
|
||||
media=["http://example.com/internal.jpg"],
|
||||
)
|
||||
)
|
||||
|
||||
assert channel._app.bot.sent_media == []
|
||||
assert channel._app.bot.sent_messages == [
|
||||
{
|
||||
"chat_id": 123,
|
||||
"text": "[Failed to send: internal.jpg]",
|
||||
"reply_parameters": None,
|
||||
}
|
||||
]
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_group_policy_mention_ignores_unmentioned_group_message() -> None:
|
||||
channel = TelegramChannel(
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user