Import AITURK IDE 1.0.0-beta.1 from Hermes 63279301; preserve MIT license

This commit is contained in:
2026-09-05 13:26:46 +03:00
commit 03634b1ca3
11340 changed files with 3442369 additions and 0 deletions
+3
View File
@@ -0,0 +1,3 @@
from .adapter import register
__all__ = ["register"]
File diff suppressed because it is too large Load Diff
+484
View File
@@ -0,0 +1,484 @@
"""WeCom callback-mode adapter for self-built enterprise applications.
Unlike the bot/websocket adapter in ``wecom.py``, this handles the standard
WeCom callback flow: WeCom POSTs encrypted XML to an HTTP endpoint, the
adapter decrypts it, queues the message for the agent, and immediately
acknowledges. The agent's reply is delivered later via the proactive
``message/send`` API using an access-token.
Supports multiple self-built apps under one gateway instance, scoped by
``corp_id:user_id`` to avoid cross-corp collisions.
"""
from __future__ import annotations
import asyncio
import logging
import socket as _socket
import time
from typing import Any, Dict, List, Optional
# Security: parse untrusted, pre-auth request bodies (WeCom callbacks) with
# defusedxml to block billion-laughs / entity-expansion (and XXE) DoS. The
# parsing API (fromstring) is a drop-in for the stdlib calls used below;
# response-building XML lives in wecom_crypto.py and is not parsed here.
try:
import defusedxml.ElementTree as ET
DEFUSEDXML_AVAILABLE = True
except ImportError:
ET = None # type: ignore[assignment]
DEFUSEDXML_AVAILABLE = False
try:
from aiohttp import web
AIOHTTP_AVAILABLE = True
except ImportError:
web = None # type: ignore[assignment]
AIOHTTP_AVAILABLE = False
try:
import httpx
HTTPX_AVAILABLE = True
except ImportError:
httpx = None # type: ignore[assignment]
HTTPX_AVAILABLE = False
from gateway.config import Platform, PlatformConfig
from gateway.platforms.base import BasePlatformAdapter, MessageEvent, MessageType, SendResult
from plugins.platforms.wecom.wecom_crypto import WXBizMsgCrypt, WeComCryptoError
logger = logging.getLogger(__name__)
# ``None`` → aiohttp/asyncio ``create_server`` binds one listening socket per
# address family (IPv4 + IPv6). The old "0.0.0.0" default bound IPv4 ONLY and
# was unreachable over IPv6-only private networks (e.g. Fly.io 6PN) — same
# bug as the LINE adapter (NS-603) and gateway/platforms/webhook.py
# (d542894ad). Pin a host via WECOM_CALLBACK_HOST or extra.host.
DEFAULT_HOST = None
DEFAULT_PORT = 8645
DEFAULT_PATH = "/wecom/callback"
# Cap pre-auth request bodies. WeCom callbacks are small encrypted XML
# envelopes (media is delivered out-of-band via MediaId, never inline), so
# 64 KB is ample for any legitimate message while bounding the work an
# unauthenticated POST can force before signature verification.
_MAX_BODY = 65_536
ACCESS_TOKEN_TTL_SECONDS = 7200
MESSAGE_DEDUP_TTL_SECONDS = 300
def check_wecom_callback_requirements() -> bool:
"""PASSIVE probe: are aiohttp/httpx/defusedxml importable right now?
Registry ``check_fn`` — must never install anything. The ACTIVE
lazy-installer is ``ensure_wecom_callback_requirements`` below.
"""
return AIOHTTP_AVAILABLE and HTTPX_AVAILABLE and DEFUSEDXML_AVAILABLE
def ensure_wecom_callback_requirements() -> bool:
"""ACTIVE lazy-installer for the ``platform.wecom_callback`` feature.
Registered as ``ensure_deps_fn``: the registry's ``create_adapter()``
runs it when the passive probe fails, right before the gateway connects
the platform (#79812). Installs ``defusedxml`` (the only non-core dep;
aiohttp/httpx ship with every messaging install) and rebinds the module
globals. Before this hook existed, the passive ``check_fn`` returned
False forever on installs without the ``wecom`` extra and the
``platform.wecom_callback`` LAZY_DEPS entry was never exercised.
"""
if check_wecom_callback_requirements():
return True
def _import() -> dict:
import defusedxml.ElementTree as _ET
return {"ET": _ET, "DEFUSEDXML_AVAILABLE": True}
try:
from tools.lazy_deps import ensure_and_bind
except Exception: # pragma: no cover — defensive
return False
if not ensure_and_bind("platform.wecom_callback", _import, globals(), prompt=False):
return False
return check_wecom_callback_requirements()
class WecomCallbackAdapter(BasePlatformAdapter):
def __init__(self, config: PlatformConfig):
super().__init__(config, Platform.WECOM_CALLBACK)
extra = config.extra or {}
# Falsy host (None/"") collapses to the dual-stack default.
_raw_host = extra.get("host") or DEFAULT_HOST
self._host = str(_raw_host) if _raw_host else None
self._port = int(extra.get("port") or DEFAULT_PORT)
self._path = str(extra.get("path") or DEFAULT_PATH)
self._apps: List[Dict[str, Any]] = self._normalize_apps(extra)
self._runner: Optional[web.AppRunner] = None
self._site: Optional[web.TCPSite] = None
self._app: Optional[web.Application] = None
self._http_client: Optional[httpx.AsyncClient] = None
self._message_queue: asyncio.Queue[MessageEvent] = asyncio.Queue()
self._poll_task: Optional[asyncio.Task] = None
self._seen_messages: Dict[str, float] = {}
self._user_app_map: Dict[str, str] = {}
self._access_tokens: Dict[str, Dict[str, Any]] = {}
# ------------------------------------------------------------------
# App normalisation
# ------------------------------------------------------------------
@staticmethod
def _user_app_key(corp_id: str, user_id: str) -> str:
return f"{corp_id}:{user_id}" if corp_id else user_id
@staticmethod
def _normalize_apps(extra: Dict[str, Any]) -> List[Dict[str, Any]]:
apps = extra.get("apps")
if isinstance(apps, list) and apps:
return [dict(app) for app in apps if isinstance(app, dict)]
if extra.get("corp_id"):
return [
{
"name": extra.get("name") or "default",
"corp_id": extra.get("corp_id", ""),
"corp_secret": extra.get("corp_secret", ""),
"agent_id": str(extra.get("agent_id", "")),
"token": extra.get("token", ""),
"encoding_aes_key": extra.get("encoding_aes_key", ""),
}
]
return []
# ------------------------------------------------------------------
# Lifecycle
# ------------------------------------------------------------------
async def connect(self, *, is_reconnect: bool = False) -> bool:
# ``is_reconnect`` is forwarded by GatewayRunner on every retry per
# the BasePlatformAdapter.connect contract. Callback adapters have
# no server-side queue to preserve, so the flag is accepted-and-
# ignored — but the kwarg MUST be present or the reconnect watcher
# dies with TypeError and the platform silently stays offline.
del is_reconnect
if not self._apps:
logger.warning("[WecomCallback] No callback apps configured")
return False
if not check_wecom_callback_requirements():
logger.warning("[WecomCallback] aiohttp/httpx not installed")
return False
# Quick port-in-use check.
try:
with _socket.socket(_socket.AF_INET, _socket.SOCK_STREAM) as sock:
sock.settimeout(1)
sock.connect(("127.0.0.1", self._port))
logger.error("[WecomCallback] Port %d already in use", self._port)
return False
except (ConnectionRefusedError, OSError):
pass
try:
# Tighter keepalive so idle CLOSE_WAIT drains promptly (#18451).
from gateway.platforms._http_client_limits import platform_httpx_limits
self._http_client = httpx.AsyncClient(timeout=20.0, limits=platform_httpx_limits())
# client_max_size rejects oversized bodies at the aiohttp layer
# (413) before our handler — and before any signature work — runs.
self._app = web.Application(client_max_size=_MAX_BODY)
self._app.router.add_get("/health", self._handle_health)
self._app.router.add_get(self._path, self._handle_verify)
self._app.router.add_post(self._path, self._handle_callback)
self._runner = web.AppRunner(self._app)
await self._runner.setup()
self._site = web.TCPSite(self._runner, self._host, self._port)
await self._site.start()
self._poll_task = asyncio.create_task(self._poll_loop())
self._mark_connected()
logger.info(
"[WecomCallback] HTTP server listening on %s:%s%s",
self._host, self._port, self._path,
)
for app in self._apps:
try:
await self._refresh_access_token(app)
except Exception as exc:
logger.warning(
"[WecomCallback] Initial token refresh failed for app '%s': %s",
app.get("name", "default"), exc,
)
return True
except Exception:
await self._cleanup()
logger.exception("[WecomCallback] Failed to start")
return False
async def disconnect(self) -> None:
self._running = False
if self._poll_task:
self._poll_task.cancel()
try:
await self._poll_task
except asyncio.CancelledError:
pass
self._poll_task = None
await self._cleanup()
self._mark_disconnected()
logger.info("[WecomCallback] Disconnected")
async def _cleanup(self) -> None:
self._site = None
if self._runner:
await self._runner.cleanup()
self._runner = None
self._app = None
if self._http_client:
await self._http_client.aclose()
self._http_client = None
# ------------------------------------------------------------------
# Outbound: proactive send via access-token API
# ------------------------------------------------------------------
async def send(
self,
chat_id: str,
content: str,
reply_to: Optional[str] = None,
metadata: Optional[Dict[str, Any]] = None,
) -> SendResult:
app = self._resolve_app_for_chat(chat_id)
touser = chat_id.split(":", 1)[1] if ":" in chat_id else chat_id
try:
payload = {
"touser": touser,
"msgtype": "text",
"agentid": int(str(app.get("agent_id") or 0)),
"text": {"content": content[:2048]},
"safe": 0,
}
for _attempt in range(2):
token = await self._get_access_token(app)
resp = await self._http_client.post(
f"https://qyapi.weixin.qq.com/cgi-bin/message/send?access_token={token}",
json=payload,
)
data = resp.json()
errcode = data.get("errcode")
if errcode in {40001, 42001} and _attempt == 0:
# WeCom rejected the token — evict the cached entry so
# the next _get_access_token call forces a fresh fetch.
logger.warning(
"[WecomCallback] Token rejected for app '%s' (errcode=%s), refreshing",
app.get("name", "default"), errcode,
)
self._access_tokens.pop(app["name"], None)
continue
if errcode != 0:
return SendResult(success=False, error=str(data))
return SendResult(
success=True,
message_id=str(data.get("msgid", "")),
raw_response=data,
)
return SendResult(success=False, error="send failed after token refresh")
except Exception as exc:
return SendResult(success=False, error=str(exc))
def _resolve_app_for_chat(self, chat_id: str) -> Dict[str, Any]:
"""Pick the app associated with *chat_id*, falling back sensibly."""
app_name = self._user_app_map.get(chat_id)
if not app_name and ":" not in chat_id:
# Legacy bare user_id — try to find a unique match.
matching = [k for k in self._user_app_map if k.endswith(f":{chat_id}")]
if len(matching) == 1:
app_name = self._user_app_map.get(matching[0])
app = self._get_app_by_name(app_name) if app_name else None
return app or self._apps[0]
async def get_chat_info(self, chat_id: str) -> Dict[str, Any]:
return {"name": chat_id, "type": "dm"}
# ------------------------------------------------------------------
# Inbound: HTTP callback handlers
# ------------------------------------------------------------------
async def _handle_health(self, request: web.Request) -> web.Response:
return web.json_response({"status": "ok", "platform": "wecom_callback"})
async def _handle_verify(self, request: web.Request) -> web.Response:
"""GET endpoint — WeCom URL verification handshake."""
msg_signature = request.query.get("msg_signature", "")
timestamp = request.query.get("timestamp", "")
nonce = request.query.get("nonce", "")
echostr = request.query.get("echostr", "")
for app in self._apps:
try:
crypt = self._crypt_for_app(app)
plain = crypt.verify_url(msg_signature, timestamp, nonce, echostr)
return web.Response(text=plain, content_type="text/plain")
except Exception:
continue
return web.Response(status=403, text="signature verification failed")
async def _handle_callback(self, request: web.Request) -> web.Response:
"""POST endpoint — receive an encrypted message callback."""
msg_signature = request.query.get("msg_signature", "")
timestamp = request.query.get("timestamp", "")
nonce = request.query.get("nonce", "")
# Explicit guard in addition to client_max_size: rejects oversized
# payloads before any XML parse / signature check (DoS, zip bombs).
body_bytes = await request.read()
if len(body_bytes) > _MAX_BODY:
logger.warning("[WecomCallback] Payload too large (%d bytes) — rejected", len(body_bytes))
return web.Response(status=413, text="payload too large")
body = body_bytes.decode("utf-8", errors="replace")
for app in self._apps:
try:
decrypted = self._decrypt_request(
app, body, msg_signature, timestamp, nonce,
)
event = self._build_event(app, decrypted)
if event is not None:
# Deduplicate: WeCom retries callbacks on timeout,
# producing duplicate inbound messages (#10305).
if event.message_id:
now = time.time()
if event.message_id in self._seen_messages:
if now - self._seen_messages[event.message_id] < MESSAGE_DEDUP_TTL_SECONDS:
logger.debug("[WecomCallback] Duplicate MsgId %s, skipping", event.message_id)
return web.Response(text="success", content_type="text/plain")
del self._seen_messages[event.message_id]
self._seen_messages[event.message_id] = now
# Prune expired entries when cache grows large
if len(self._seen_messages) > 2000:
cutoff = now - MESSAGE_DEDUP_TTL_SECONDS
self._seen_messages = {k: v for k, v in self._seen_messages.items() if v > cutoff}
# Record which app this user belongs to.
if event.source and event.source.user_id:
map_key = self._user_app_key(
str(app.get("corp_id") or ""), event.source.user_id,
)
self._user_app_map[map_key] = app["name"]
await self._message_queue.put(event)
# Immediately acknowledge — the agent's reply will arrive
# later via the proactive message/send API.
return web.Response(text="success", content_type="text/plain")
except WeComCryptoError:
continue
except Exception:
logger.exception("[WecomCallback] Error handling message")
break
return web.Response(status=400, text="invalid callback payload")
async def _poll_loop(self) -> None:
"""Drain the message queue and dispatch to the gateway runner."""
while True:
event = await self._message_queue.get()
try:
task = asyncio.create_task(self.handle_message(event))
self._background_tasks.add(task)
task.add_done_callback(self._background_tasks.discard)
except Exception:
logger.exception("[WecomCallback] Failed to enqueue event")
# ------------------------------------------------------------------
# XML / crypto helpers
# ------------------------------------------------------------------
def _decrypt_request(
self, app: Dict[str, Any], body: str,
msg_signature: str, timestamp: str, nonce: str,
) -> str:
root = ET.fromstring(body)
encrypt = root.findtext("Encrypt", default="")
crypt = self._crypt_for_app(app)
return crypt.decrypt(msg_signature, timestamp, nonce, encrypt).decode("utf-8")
def _build_event(self, app: Dict[str, Any], xml_text: str) -> Optional[MessageEvent]:
root = ET.fromstring(xml_text)
msg_type = (root.findtext("MsgType") or "").lower()
# Silently acknowledge lifecycle events.
if msg_type == "event":
event_name = (root.findtext("Event") or "").lower()
if event_name in {"enter_agent", "subscribe"}:
return None
if msg_type not in {"text", "event"}:
return None
user_id = root.findtext("FromUserName", default="")
corp_id = root.findtext("ToUserName", default=app.get("corp_id", ""))
scoped_chat_id = self._user_app_key(corp_id, user_id)
content = root.findtext("Content", default="").strip()
if not content and msg_type == "event":
content = "/start"
msg_id = (
root.findtext("MsgId")
or f"{user_id}:{root.findtext('CreateTime', default='0')}"
)
source = self.build_source(
chat_id=scoped_chat_id,
chat_name=user_id,
chat_type="dm",
user_id=user_id,
user_name=user_id,
)
return MessageEvent(
text=content,
message_type=MessageType.TEXT,
source=source,
raw_message=xml_text,
message_id=msg_id,
)
def _crypt_for_app(self, app: Dict[str, Any]) -> WXBizMsgCrypt:
return WXBizMsgCrypt(
token=str(app.get("token") or ""),
encoding_aes_key=str(app.get("encoding_aes_key") or ""),
receive_id=str(app.get("corp_id") or ""),
)
def _get_app_by_name(self, name: Optional[str]) -> Optional[Dict[str, Any]]:
if not name:
return None
for app in self._apps:
if app.get("name") == name:
return app
return None
# ------------------------------------------------------------------
# Access-token management
# ------------------------------------------------------------------
async def _get_access_token(self, app: Dict[str, Any]) -> str:
cached = self._access_tokens.get(app["name"])
now = time.time()
if cached and cached.get("expires_at", 0) > now + 60:
return cached["token"]
return await self._refresh_access_token(app)
async def _refresh_access_token(self, app: Dict[str, Any]) -> str:
resp = await self._http_client.get(
"https://qyapi.weixin.qq.com/cgi-bin/gettoken",
params={
"corpid": app.get("corp_id"),
"corpsecret": app.get("corp_secret"),
},
)
data = resp.json()
if data.get("errcode") != 0:
raise RuntimeError(f"WeCom token refresh failed: {data}")
token = data["access_token"]
expires_in = int(data.get("expires_in", ACCESS_TOKEN_TTL_SECONDS))
self._access_tokens[app["name"]] = {
"token": token,
"expires_at": time.time() + expires_in,
}
logger.info(
"[WecomCallback] Token refreshed for app '%s' (corp=%s), expires in %ss",
app.get("name", "default"),
app.get("corp_id", ""),
expires_in,
)
return token
+52
View File
@@ -0,0 +1,52 @@
name: wecom-platform
label: WeCom (Enterprise WeChat)
kind: platform
version: 1.0.0
description: >
WeCom / Enterprise WeChat gateway adapter for Hermes Agent. Registers two
platforms: ``wecom`` (Smart Robot over WebSocket) and ``wecom_callback``
(self-built apps over an HTTP callback endpoint with AES message crypto).
Relays messages between WeCom chats and the Hermes agent.
author: NousResearch
requires_env:
- name: WECOM_BOT_ID
description: "WeCom Smart Robot bot ID"
prompt: "WeCom bot ID"
password: false
- name: WECOM_SECRET
description: "WeCom Smart Robot secret"
prompt: "WeCom secret"
password: true
optional_env:
- name: WECOM_WEBSOCKET_URL
description: "WeCom Smart Robot WebSocket URL"
prompt: "WeCom WebSocket URL"
password: false
- name: WECOM_HOME_CHANNEL
description: "Default chat ID for cron / notification delivery"
prompt: "Home channel ID"
password: false
- name: WECOM_ALLOWED_USERS
description: "Comma-separated WeCom user IDs allowed to talk to the bot"
prompt: "Allowed users (comma-separated)"
password: false
- name: WECOM_CALLBACK_CORP_ID
description: "WeCom callback-mode corp ID (self-built apps)"
prompt: "WeCom callback corp ID"
password: false
- name: WECOM_CALLBACK_CORP_SECRET
description: "WeCom callback-mode corp secret"
prompt: "WeCom callback corp secret"
password: true
- name: WECOM_CALLBACK_AGENT_ID
description: "WeCom callback-mode agent ID"
prompt: "WeCom callback agent ID"
password: false
- name: WECOM_CALLBACK_TOKEN
description: "WeCom callback verification token"
prompt: "WeCom callback token"
password: true
- name: WECOM_CALLBACK_ENCODING_AES_KEY
description: "WeCom callback EncodingAESKey for message crypto"
prompt: "WeCom callback EncodingAESKey"
password: true
+142
View File
@@ -0,0 +1,142 @@
"""WeCom BizMsgCrypt-compatible AES-CBC encryption for callback mode.
Implements the same wire format as Tencent's official ``WXBizMsgCrypt``
SDK so that WeCom can verify, encrypt, and decrypt callback payloads.
"""
from __future__ import annotations
import base64
import hashlib
import os
import secrets
import socket
import struct
from typing import Optional
from xml.etree import ElementTree as ET
from cryptography.hazmat.backends import default_backend
from cryptography.hazmat.primitives.ciphers import Cipher, algorithms, modes
class WeComCryptoError(Exception):
pass
class SignatureError(WeComCryptoError):
pass
class DecryptError(WeComCryptoError):
pass
class EncryptError(WeComCryptoError):
pass
class PKCS7Encoder:
block_size = 32
@classmethod
def encode(cls, text: bytes) -> bytes:
amount_to_pad = cls.block_size - (len(text) % cls.block_size)
if amount_to_pad == 0:
amount_to_pad = cls.block_size
pad = bytes([amount_to_pad]) * amount_to_pad
return text + pad
@classmethod
def decode(cls, decrypted: bytes) -> bytes:
if not decrypted:
raise DecryptError("empty decrypted payload")
pad = decrypted[-1]
if pad < 1 or pad > cls.block_size:
raise DecryptError("invalid PKCS7 padding")
if decrypted[-pad:] != bytes([pad]) * pad:
raise DecryptError("malformed PKCS7 padding")
return decrypted[:-pad]
def _sha1_signature(token: str, timestamp: str, nonce: str, encrypt: str) -> str:
parts = sorted([token, timestamp, nonce, encrypt])
return hashlib.sha1("".join(parts).encode("utf-8")).hexdigest()
class WXBizMsgCrypt:
"""Minimal WeCom callback crypto helper compatible with BizMsgCrypt semantics."""
def __init__(self, token: str, encoding_aes_key: str, receive_id: str):
if not token:
raise ValueError("token is required")
if not encoding_aes_key:
raise ValueError("encoding_aes_key is required")
if len(encoding_aes_key) != 43:
raise ValueError("encoding_aes_key must be 43 chars")
if not receive_id:
raise ValueError("receive_id is required")
self.token = token
self.receive_id = receive_id
self.key = base64.b64decode(encoding_aes_key + "=")
self.iv = self.key[:16]
def verify_url(self, msg_signature: str, timestamp: str, nonce: str, echostr: str) -> str:
plain = self.decrypt(msg_signature, timestamp, nonce, echostr)
return plain.decode("utf-8")
def decrypt(self, msg_signature: str, timestamp: str, nonce: str, encrypt: str) -> bytes:
expected = _sha1_signature(self.token, timestamp, nonce, encrypt)
if expected != msg_signature:
raise SignatureError("signature mismatch")
try:
cipher_text = base64.b64decode(encrypt)
except Exception as exc:
raise DecryptError(f"invalid base64 payload: {exc}") from exc
try:
cipher = Cipher(algorithms.AES(self.key), modes.CBC(self.iv), backend=default_backend())
decryptor = cipher.decryptor()
padded = decryptor.update(cipher_text) + decryptor.finalize()
plain = PKCS7Encoder.decode(padded)
content = plain[16:] # skip 16-byte random prefix
xml_length = socket.ntohl(struct.unpack("I", content[:4])[0])
xml_content = content[4:4 + xml_length]
receive_id = content[4 + xml_length:].decode("utf-8")
except WeComCryptoError:
raise
except Exception as exc:
raise DecryptError(f"decrypt failed: {exc}") from exc
if receive_id != self.receive_id:
raise DecryptError("receive_id mismatch")
return xml_content
def encrypt(self, plaintext: str, nonce: Optional[str] = None, timestamp: Optional[str] = None) -> str:
nonce = nonce or self._random_nonce()
timestamp = timestamp or str(int(__import__("time").time()))
encrypt = self._encrypt_bytes(plaintext.encode("utf-8"))
signature = _sha1_signature(self.token, timestamp, nonce, encrypt)
root = ET.Element("xml")
ET.SubElement(root, "Encrypt").text = encrypt
ET.SubElement(root, "MsgSignature").text = signature
ET.SubElement(root, "TimeStamp").text = timestamp
ET.SubElement(root, "Nonce").text = nonce
return ET.tostring(root, encoding="unicode")
def _encrypt_bytes(self, raw: bytes) -> str:
try:
random_prefix = os.urandom(16)
msg_len = struct.pack("I", socket.htonl(len(raw)))
payload = random_prefix + msg_len + raw + self.receive_id.encode("utf-8")
padded = PKCS7Encoder.encode(payload)
cipher = Cipher(algorithms.AES(self.key), modes.CBC(self.iv), backend=default_backend())
encryptor = cipher.encryptor()
encrypted = encryptor.update(padded) + encryptor.finalize()
return base64.b64encode(encrypted).decode("utf-8")
except Exception as exc:
raise EncryptError(f"encrypt failed: {exc}") from exc
@staticmethod
def _random_nonce(length: int = 10) -> str:
alphabet = "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"
return "".join(secrets.choice(alphabet) for _ in range(length))