Files
aios/scripts/wechat_send_backend.py
T

653 lines
22 KiB
Python
Executable File

#!/usr/bin/env python3
"""Hardened WeChat outbound backend for AIOS.
Only the dedicated UCC adapter is a supported send backend. OpenClaw channel
discovery is retained for diagnostics, but generic OpenClaw chat or agent
delivery is never promoted to WeChat delivery.
"""
from __future__ import annotations
import json
import os
import re
import selectors
import signal
import subprocess
import time
import urllib.error
import urllib.parse
import urllib.request
from typing import Any, Dict, List, Optional, Tuple
OPENCLAW_BIN = os.environ.get("AIOS_OPENCLAW_BIN", "openclaw")
WECHAT_ACCOUNT_ID = os.environ.get("AIOS_WECHAT_ACCOUNT_ID", "")
WECHAT_CHANNEL = os.environ.get("AIOS_WECHAT_CHANNEL", "")
SEND_BACKEND = os.environ.get("AIOS_WECHAT_SEND_BACKEND", "")
UCC_ADAPTER_URL = os.environ.get("AIOS_UCC_WECHAT_ADAPTER_URL", "http://127.0.0.1:18800")
UCC_ADAPTER_TOKEN = os.environ.get("AIOS_UCC_WECHAT_ADAPTER_TOKEN") or os.environ.get(
"AIOS_WECHAT_QR_ADAPTER_TOKEN", ""
)
UCC_SEND_PATH = os.environ.get("AIOS_UCC_WECHAT_SEND_PATH", "/api/internal/wechat/send")
_allowed_origins = os.environ.get("AIOS_UCC_WECHAT_ALLOWED_ORIGINS", "").strip()
UCC_ADAPTER_ALLOWED_ORIGINS = tuple(
origin.strip() for origin in _allowed_origins.split(",") if origin.strip()
) or (
"http://127.0.0.1:18800",
"http://[::1]:18800",
)
MAX_TARGET_BYTES = 512
MAX_CONTENT_BYTES = 32 * 1024
MAX_IDENTIFIER_BYTES = 512
MAX_METADATA_BYTES = 8 * 1024
MAX_METADATA_DEPTH = 32
MAX_METADATA_NODES = 1024
MAX_RESPONSE_BYTES = 64 * 1024
MAX_ENDPOINT_BYTES = 256
_DEFAULT_TIMEOUT_SECONDS = 10
_MAX_TIMEOUT_SECONDS = 30
_LEGACY_SEND_PATH = "/internal/channels/wechat/send"
_SAFE_PATH = re.compile(r"^/[A-Za-z0-9._~!$&'()*+,;=:@%/-]+$")
_MAX_PATH_DECODE_ROUNDS = 4
_OPENCLAW_TIMEOUT_RETURN_CODE = 124
_OPENCLAW_OUTPUT_LIMIT_RETURN_CODE = 125
_OPENCLAW_SPAWN_ERROR_RETURN_CODE = 126
def _bounded_timeout(value: str) -> int:
try:
parsed = int(value)
except (TypeError, ValueError):
return _DEFAULT_TIMEOUT_SECONDS
return min(max(parsed, 1), _MAX_TIMEOUT_SECONDS)
REQUEST_TIMEOUT_SECONDS = _bounded_timeout(os.environ.get("AIOS_UCC_WECHAT_TIMEOUT_SECONDS", "10"))
class BackendResult:
def __init__(self, ok: bool, backend: str, status: str, data: Dict[str, Any]) -> None:
self.ok = ok
self.backend = backend
self.status = status
self.data = data
def to_dict(self) -> Dict[str, Any]:
return {"ok": self.ok, "backend": self.backend, "status": self.status, **self.data}
class _BackendProtocolError(Exception):
"""Internal marker whose details must never cross the module boundary."""
def _openclaw_base_args() -> List[str]:
"""Return the OpenClaw 2026.6.11-compatible command prefix.
Gateway/auth global flags are not supported by the installed CLI and would
also expose credentials through the process argument vector.
"""
return [OPENCLAW_BIN]
def _terminate_process_tree(process: Any) -> None:
if os.name == "posix":
try:
os.killpg(process.pid, signal.SIGTERM)
except OSError:
pass
try:
process.wait(timeout=0.5)
except (OSError, subprocess.TimeoutExpired):
pass
time.sleep(0.05)
try:
os.killpg(process.pid, signal.SIGKILL)
except OSError:
pass
try:
process.wait(timeout=0.5)
except (OSError, subprocess.TimeoutExpired):
pass
return
if process.poll() is not None:
return
try:
process.terminate()
process.wait(timeout=1)
return
except (OSError, subprocess.TimeoutExpired):
pass
try:
process.kill()
process.wait(timeout=1)
except (OSError, subprocess.TimeoutExpired):
pass
def _run_openclaw(
args: List[str], timeout: int = 15
) -> subprocess.CompletedProcess[str]:
bounded_timeout = min(max(int(timeout), 1), _MAX_TIMEOUT_SECONDS)
popen_options: Dict[str, Any] = {
"stdout": subprocess.PIPE,
"stderr": subprocess.PIPE,
}
if os.name == "posix":
popen_options["start_new_session"] = True
elif hasattr(subprocess, "CREATE_NEW_PROCESS_GROUP"):
popen_options["creationflags"] = subprocess.CREATE_NEW_PROCESS_GROUP
try:
process = subprocess.Popen(args, **popen_options)
except (OSError, ValueError):
return subprocess.CompletedProcess(args, _OPENCLAW_SPAWN_ERROR_RETURN_CODE, "", "")
selector = selectors.DefaultSelector()
streams = {"stdout": process.stdout, "stderr": process.stderr}
buffers = {"stdout": bytearray(), "stderr": bytearray()}
try:
for name, stream in streams.items():
if stream is not None:
selector.register(stream, selectors.EVENT_READ, name)
except (OSError, ValueError):
selector.close()
_terminate_process_tree(process)
for stream in streams.values():
if stream is not None:
stream.close()
return subprocess.CompletedProcess(args, _OPENCLAW_SPAWN_ERROR_RETURN_CODE, "", "")
deadline = time.monotonic() + bounded_timeout
total_bytes = 0
return_code: Optional[int] = None
try:
while selector.get_map():
remaining = deadline - time.monotonic()
if remaining <= 0:
return_code = _OPENCLAW_TIMEOUT_RETURN_CODE
break
events = selector.select(min(remaining, 0.1))
for key, _mask in events:
allowance = MAX_RESPONSE_BYTES - total_bytes
try:
chunk = os.read(key.fileobj.fileno(), min(8192, allowance + 1))
except OSError:
return_code = _OPENCLAW_SPAWN_ERROR_RETURN_CODE
break
if not chunk:
selector.unregister(key.fileobj)
key.fileobj.close()
continue
if len(chunk) > allowance:
return_code = _OPENCLAW_OUTPUT_LIMIT_RETURN_CODE
break
buffers[key.data].extend(chunk)
total_bytes += len(chunk)
if return_code is not None:
break
finally:
selector.close()
if return_code is not None:
_terminate_process_tree(process)
for stream in streams.values():
if stream is not None and not stream.closed:
stream.close()
return subprocess.CompletedProcess(args, return_code, "", "")
try:
completed_return_code = process.wait(timeout=1)
except subprocess.TimeoutExpired:
_terminate_process_tree(process)
return subprocess.CompletedProcess(args, _OPENCLAW_TIMEOUT_RETURN_CODE, "", "")
stdout = buffers["stdout"].decode("utf-8", errors="replace")
stderr = buffers["stderr"].decode("utf-8", errors="replace")
return subprocess.CompletedProcess(args, completed_return_code, stdout, stderr)
def _json_dict(text: str) -> Dict[str, Any]:
try:
value = json.loads(text or "{}")
except (RecursionError, TypeError, ValueError, json.JSONDecodeError):
return {}
return value if isinstance(value, dict) else {}
def discover_openclaw_wechat_channel() -> Optional[str]:
"""Discover an explicitly typed WeChat/Weixin channel for diagnostics."""
if WECHAT_CHANNEL:
return WECHAT_CHANNEL
try:
proc = _run_openclaw(_openclaw_base_args() + ["channels", "list", "--json"], timeout=15)
except (OSError, subprocess.SubprocessError, ValueError):
return None
if proc.returncode != 0:
return None
data = _json_dict(proc.stdout[:MAX_RESPONSE_BYTES])
candidates: List[str] = []
def walk(value: Any) -> None:
if isinstance(value, dict):
name = value.get("name") or value.get("channel") or value.get("id")
kind = value.get("type") or value.get("kind")
if isinstance(name, str) and isinstance(kind, str):
label = f"{name} {kind}".lower()
if "wechat" in label or "weixin" in label:
candidates.append(name)
for child in value.values():
walk(child)
elif isinstance(value, list):
for child in value:
walk(child)
walk(data)
return candidates[0] if candidates else None
def _auth_headers() -> Dict[str, str]:
headers = {"Content-Type": "application/json", "Accept": "application/json"}
if UCC_ADAPTER_TOKEN:
headers["Authorization"] = "Bearer " + UCC_ADAPTER_TOKEN
return headers
def _safe_path(value: Any) -> Optional[str]:
if not isinstance(value, str):
return None
path = value if value.startswith("/") else "/" + value
try:
encoded_path = path.encode("utf-8")
except UnicodeEncodeError:
return None
if len(encoded_path) > MAX_ENDPOINT_BYTES:
return None
if not _SAFE_PATH.fullmatch(path):
return None
decoded = path
for _ in range(_MAX_PATH_DECODE_ROUNDS):
try:
next_decoded = urllib.parse.unquote_to_bytes(decoded).decode("utf-8")
except UnicodeDecodeError:
return None
if next_decoded == decoded:
break
decoded = next_decoded
if "%" in decoded or "\\" in decoded or "\x00" in decoded:
return None
if not _SAFE_PATH.fullmatch(decoded):
return None
if any(segment in {".", ".."} for segment in decoded.split("/")):
return None
return path
def _unique_paths(paths: List[str]) -> List[str]:
out: List[str] = []
for candidate in paths:
path = _safe_path(candidate)
if path and path not in out:
out.append(path)
if len(out) == 2:
break
return out
def _ucc_send_paths() -> List[str]:
canonical = _safe_path(UCC_SEND_PATH) or "/api/internal/wechat/send"
return _unique_paths([canonical, _LEGACY_SEND_PATH])
def _canonical_origin(value: Any) -> Optional[str]:
if not isinstance(value, str) or not value or len(value) > 2048:
return None
if "\\" in value or any(ord(character) < 32 for character in value):
return None
try:
parsed = urllib.parse.urlsplit(value)
port = parsed.port
except (UnicodeError, ValueError):
return None
scheme = parsed.scheme.lower()
if scheme not in {"http", "https"} or not parsed.hostname:
return None
if parsed.username or parsed.password or parsed.query or parsed.fragment or parsed.path not in {"", "/"}:
return None
try:
host = parsed.hostname.rstrip(".").encode("idna").decode("ascii").lower()
except UnicodeError:
return None
if not host:
return None
if port is None:
port = 80 if scheme == "http" else 443
rendered_host = f"[{host}]" if ":" in host else host
return f"{scheme}://{rendered_host}:{port}"
def _adapter_base_url() -> Optional[str]:
origin = _canonical_origin(UCC_ADAPTER_URL)
allowed = {
canonical
for canonical in (_canonical_origin(value) for value in UCC_ADAPTER_ALLOWED_ORIGINS)
if canonical
}
return origin if origin and origin in allowed else None
class _NoRedirectHandler(urllib.request.HTTPRedirectHandler):
def redirect_request(
self,
req: Any,
fp: Any,
code: int,
msg: str,
headers: Any,
newurl: str,
) -> None:
del req, fp, code, msg, headers, newurl
return None
def _open_no_redirect(request: urllib.request.Request, timeout: int) -> Any:
opener = urllib.request.build_opener(_NoRedirectHandler())
return opener.open(request, timeout=timeout)
def ucc_adapter_alive() -> bool:
base_url = _adapter_base_url()
if not base_url:
return False
request = urllib.request.Request(
base_url + "/health", headers=_auth_headers(), method="GET"
)
try:
with _open_no_redirect(request, timeout=min(5, REQUEST_TIMEOUT_SECONDS)) as response:
return 200 <= int(response.status) < 300
except (OSError, ValueError, urllib.error.URLError):
return False
def select_backend() -> Dict[str, Any]:
explicit = SEND_BACKEND.strip().lower()
if explicit:
if explicit == "ucc-adapter":
return {"backend": "ucc-adapter", "reason": "explicit"}
return {"backend": "unavailable", "reason": "unsupported_backend"}
if ucc_adapter_alive():
return {"backend": "ucc-adapter", "reason": "ucc_adapter_alive"}
return {"backend": "unavailable", "reason": "ucc_adapter_unavailable"}
def _post_ucc(path: str, payload: Dict[str, Any]) -> Tuple[int, Dict[str, Any]]:
base_url = _adapter_base_url()
safe_path = _safe_path(path)
if not base_url or not safe_path:
raise _BackendProtocolError("invalid adapter endpoint")
try:
body = json.dumps(payload, ensure_ascii=False, separators=(",", ":")).encode("utf-8")
except (TypeError, ValueError) as exc:
raise _BackendProtocolError("invalid request payload") from exc
request = urllib.request.Request(
base_url + safe_path,
data=body,
headers=_auth_headers(),
method="POST",
)
with _open_no_redirect(request, timeout=REQUEST_TIMEOUT_SECONDS) as response:
raw = response.read(MAX_RESPONSE_BYTES + 1)
if len(raw) > MAX_RESPONSE_BYTES:
raise _BackendProtocolError("adapter response too large")
try:
text = raw.decode("utf-8")
except UnicodeDecodeError as exc:
raise _BackendProtocolError("adapter response encoding invalid") from exc
data = _json_dict(text)
if not data:
raise _BackendProtocolError("adapter response invalid")
return int(response.status), data
def _ucc_response_sent(data: Dict[str, Any]) -> bool:
return isinstance(data, dict) and data.get("ok") is True and data.get("status") == "sent"
def _ucc_result_is_ok(data: Dict[str, Any], dry_run: bool = False) -> bool:
expected_status = "dry_run" if dry_run else "sent"
return isinstance(data, dict) and data.get("ok") is True and data.get("status") == expected_status
def _utf8_size(value: str) -> Optional[int]:
try:
return len(value.encode("utf-8"))
except UnicodeEncodeError:
return None
def _valid_identifier(value: Any, required: bool = False) -> bool:
if not isinstance(value, str):
return False
if required and not value.strip():
return False
if not value:
return not required
if len(value) > MAX_IDENTIFIER_BYTES:
return False
size = _utf8_size(value)
return size is not None and size <= MAX_IDENTIFIER_BYTES and not any(
ord(character) < 32 or ord(character) == 127 for character in value
)
def _validate_metadata(metadata: Any) -> Optional[str]:
if not isinstance(metadata, dict):
return "invalid_input"
nodes = 0
stack: List[Tuple[Any, int]] = [(metadata, 0)]
while stack:
value, depth = stack.pop()
nodes += 1
if depth > MAX_METADATA_DEPTH or nodes > MAX_METADATA_NODES:
return "input_too_large"
if isinstance(value, dict):
if len(value) + nodes + len(stack) > MAX_METADATA_NODES:
return "input_too_large"
for key, child in value.items():
if (
not isinstance(key, str)
or len(key) > MAX_METADATA_BYTES
or _utf8_size(key) is None
):
return "invalid_input"
stack.append((child, depth + 1))
elif isinstance(value, list):
if len(value) + nodes + len(stack) > MAX_METADATA_NODES:
return "input_too_large"
stack.extend((child, depth + 1) for child in value)
elif isinstance(value, str):
if len(value) > MAX_METADATA_BYTES:
return "input_too_large"
if _utf8_size(value) is None:
return "invalid_input"
elif value is not None and not isinstance(value, (bool, int, float)):
return "invalid_input"
try:
encoded = json.dumps(
metadata,
ensure_ascii=False,
allow_nan=False,
separators=(",", ":"),
).encode("utf-8")
except (RecursionError, TypeError, UnicodeEncodeError, ValueError):
return "invalid_input"
return "input_too_large" if len(encoded) > MAX_METADATA_BYTES else None
def _validate_payload(
target: Any,
content: Any,
account_id: Any,
message_id: Any,
metadata: Any,
dry_run: Any,
) -> Optional[str]:
if not isinstance(target, str) or not isinstance(content, str):
return "invalid_input"
if not target.strip() or not content.strip() or not isinstance(dry_run, bool):
return "invalid_input"
if any(ord(character) < 32 or ord(character) == 127 for character in target):
return "invalid_input"
if "\x00" in content or not _valid_identifier(account_id) or not _valid_identifier(message_id):
return "invalid_input"
if len(target) > MAX_TARGET_BYTES or len(content) > MAX_CONTENT_BYTES:
return "input_too_large"
target_size = _utf8_size(target)
content_size = _utf8_size(content)
if target_size is None or content_size is None:
return "invalid_input"
if target_size > MAX_TARGET_BYTES or content_size > MAX_CONTENT_BYTES:
return "input_too_large"
return _validate_metadata(metadata)
def _safe_provider_message_id(value: Any) -> Optional[str]:
if not isinstance(value, str) or not value:
return None
if len(value) > MAX_IDENTIFIER_BYTES:
return None
size = _utf8_size(value)
if size is None or size > MAX_IDENTIFIER_BYTES:
return None
if any(ord(character) < 32 or ord(character) == 127 for character in value):
return None
return value
def send_ucc_adapter(
target: str,
content: str,
account_id: str = "",
message_id: str = "",
metadata: Optional[Dict[str, Any]] = None,
dry_run: bool = False,
) -> BackendResult:
effective_account = account_id or WECHAT_ACCOUNT_ID
effective_metadata: Any = {} if metadata is None else metadata
error_code = _validate_payload(
target,
content,
effective_account,
message_id,
effective_metadata,
dry_run,
)
if error_code:
return BackendResult(False, "ucc-adapter", "failed", {"code": error_code})
payload = {
"target": target,
"content": content,
"account_id": effective_account,
"message_id": message_id,
"metadata": effective_metadata,
"dry_run": dry_run,
}
last_endpoint: Optional[str] = None
for path in _ucc_send_paths():
last_endpoint = path
try:
http_status, data = _post_ucc(path, payload)
except urllib.error.HTTPError as exc:
if exc.code in {404, 405}:
continue
return BackendResult(
False,
"ucc-adapter",
"failed",
{"code": "ucc_adapter_http_error", "http_status": int(exc.code), "endpoint": path},
)
except (OSError, ValueError, urllib.error.URLError, _BackendProtocolError):
return BackendResult(
False,
"ucc-adapter",
"failed",
{"code": "ucc_adapter_unavailable", "endpoint": path},
)
except Exception:
# Fail closed without returning exception text, type, or chained cause.
return BackendResult(
False,
"ucc-adapter",
"failed",
{"code": "ucc_adapter_unavailable", "endpoint": path},
)
if not (200 <= http_status < 300):
return BackendResult(
False,
"ucc-adapter",
"failed",
{"code": "ucc_adapter_http_error", "http_status": http_status, "endpoint": path},
)
if not _ucc_result_is_ok(data, dry_run):
return BackendResult(
False,
"ucc-adapter",
"failed",
{"code": "ucc_adapter_rejected", "http_status": http_status, "endpoint": path},
)
confirmed_status = "dry_run" if dry_run else "sent"
result_data: Dict[str, Any] = {
"code": confirmed_status,
"http_status": http_status,
"endpoint": path,
}
provider_message_id = _safe_provider_message_id(data.get("provider_message_id"))
if provider_message_id:
result_data["provider_message_id"] = provider_message_id
return BackendResult(True, "ucc-adapter", confirmed_status, result_data)
data: Dict[str, Any] = {"code": "ucc_adapter_unavailable"}
if last_endpoint:
data["endpoint"] = last_endpoint
return BackendResult(False, "ucc-adapter", "failed", data)
def send_openclaw_channel(
target: str,
content: str,
account_id: str = "",
message_id: str = "",
metadata: Optional[Dict[str, Any]] = None,
dry_run: bool = False,
) -> BackendResult:
del target, content, account_id, message_id, metadata, dry_run
return BackendResult(
False,
"openclaw-channel",
"failed",
{"code": "unsupported_backend"},
)
def send_message(
target: str,
content: str,
account_id: str = "",
message_id: str = "",
metadata: Optional[Dict[str, Any]] = None,
dry_run: bool = False,
) -> Dict[str, Any]:
selected = select_backend()
if selected.get("backend") == "ucc-adapter":
return send_ucc_adapter(
target, content, account_id, message_id, metadata, dry_run
).to_dict()
code = "unsupported_backend" if selected.get("reason") == "unsupported_backend" else "wechat_outbound_backend_unavailable"
return BackendResult(False, "unavailable", "failed", {"code": code}).to_dict()
if __name__ == "__main__":
print(json.dumps(select_backend(), ensure_ascii=False, separators=(",", ":")))