hermes-agent/plugins/platforms/telegram/telegram_network.py
alexneyman ca2491f201 fix(telegram): release fallback transport pools on connect failure
The per-IP httpx transports were built once in __init__ and never torn
down. A connect that reached ESTABLISHED and was then closed by the peer
left its socket in CLOSE_WAIT inside the pool, and the failure path only
logged and continued — so the poisoned pool was retained and leaked one
descriptor per retry.

With DNS for api.telegram.org failing, every poll fell through to the
seed IP and leaked another fd every ~2.5s. The bot gateway reached 177
CLOSE_WAIT sockets against launchd's 256 soft limit and wedged: accept()
on the gateway port, config reads and DNS resolution all failed with
EMFILE, which in turn made the primary path fail and fed the loop.

Build fallback transports lazily and discard them on a retryable connect
failure, and bound every pool at 8 connections (httpx defaults to 100,
so two seed IPs plus primary could alone exceed the fd ceiling).

Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
2026-07-26 19:30:27 -07:00

305 lines
12 KiB
Python

"""Telegram-specific network helpers.
Provides a hostname-preserving fallback transport for networks where
api.telegram.org resolves to an endpoint that is unreachable from the current
host. The transport keeps the logical request host and TLS SNI as
api.telegram.org while retrying the TCP connection against one or more fallback
IPv4 addresses.
"""
from __future__ import annotations
import asyncio
import ipaddress
import logging
import socket
from typing import Iterable, Optional
import httpx
logger = logging.getLogger(__name__)
_TELEGRAM_API_HOST = "api.telegram.org"
# DNS-over-HTTPS providers used to discover Telegram API IPs that may differ
# from the (potentially unreachable) IP returned by the local system resolver.
_DOH_TIMEOUT = 4.0 # seconds — bounded so connect() isn't noticeably delayed
_DOH_PROVIDERS: list[dict] = [
{
"url": "https://dns.google/resolve",
"params": {"name": _TELEGRAM_API_HOST, "type": "A"},
"headers": {},
},
{
"url": "https://cloudflare-dns.com/dns-query",
"params": {"name": _TELEGRAM_API_HOST, "type": "A"},
"headers": {"Accept": "application/dns-json"},
},
]
# Last-resort IPs when DoH is also blocked. These are stable Telegram Bot API
# endpoints in the 149.154.160.0/20 block (same seed used by OpenClaw).
_SEED_FALLBACK_IPS: list[str] = ["149.154.166.110", "149.154.167.220"]
def _resolve_proxy_url(target_hosts=None) -> str | None:
# Delegate to shared implementation (env vars + macOS system proxy detection)
from gateway.platforms.base import resolve_proxy_url
return resolve_proxy_url("TELEGRAM_PROXY", target_hosts=target_hosts)
class TelegramFallbackTransport(httpx.AsyncBaseTransport):
"""Retry Telegram Bot API requests via fallback IPs while preserving TLS/SNI.
Requests continue to target https://api.telegram.org/... logically, but on
connect failures the underlying TCP connection is retried against a known
reachable IP. This is effectively the programmatic equivalent of
``curl --resolve api.telegram.org:443:<ip>``.
"""
# Bound every pool. httpx defaults to 100 connections per pool, so a wedged
# endpoint plus the seed IPs can outgrow the process file-descriptor limit
# on its own (#63311).
_POOL_LIMITS = httpx.Limits(max_connections=8, max_keepalive_connections=4)
def __init__(self, fallback_ips: Iterable[str], **transport_kwargs):
self._fallback_ips = list(dict.fromkeys(_normalize_fallback_ips(fallback_ips)))
proxy_url = _resolve_proxy_url(target_hosts=[_TELEGRAM_API_HOST, *self._fallback_ips])
if proxy_url and "proxy" not in transport_kwargs:
transport_kwargs["proxy"] = proxy_url
transport_kwargs.setdefault("limits", self._POOL_LIMITS)
self._transport_kwargs = transport_kwargs
self._primary = httpx.AsyncHTTPTransport(**transport_kwargs)
# Built on demand and discarded on failure — see _reset_fallback.
self._fallbacks: dict[str, httpx.AsyncHTTPTransport] = {}
self._fallback_lock = asyncio.Lock()
self._sticky_ip: Optional[str] = None
self._sticky_lock = asyncio.Lock()
async def _get_fallback(self, ip: str) -> httpx.AsyncHTTPTransport:
async with self._fallback_lock:
transport = self._fallbacks.get(ip)
if transport is None:
transport = httpx.AsyncHTTPTransport(**self._transport_kwargs)
self._fallbacks[ip] = transport
return transport
async def _reset_fallback(self, ip: str) -> None:
"""Discard a failed fallback pool so its dead sockets are released.
A connect that reaches ESTABLISHED and is then closed by the peer leaves
its socket in CLOSE_WAIT inside the pool. Retaining the poisoned pool
leaks one descriptor per retry until the process hits its file limit and
can no longer accept connections or resolve DNS (#63311).
"""
async with self._fallback_lock:
transport = self._fallbacks.pop(ip, None)
if transport is None:
return
try:
await transport.aclose()
except Exception as exc: # closing a broken pool must never mask the real error
logger.debug("[Telegram] Error closing fallback transport %s: %s", ip, exc)
async def handle_async_request(self, request: httpx.Request) -> httpx.Response:
if request.url.host != _TELEGRAM_API_HOST or not self._fallback_ips:
return await self._primary.handle_async_request(request)
sticky_ip = self._sticky_ip
attempt_order: list[Optional[str]] = [sticky_ip] if sticky_ip else [None]
if sticky_ip:
attempt_order.append(None) # retry primary DNS after sticky failure
for ip in self._fallback_ips:
if ip != sticky_ip:
attempt_order.append(ip)
last_error: Exception | None = None
for ip in attempt_order:
candidate = request if ip is None else _rewrite_request_for_ip(request, ip)
transport = self._primary if ip is None else await self._get_fallback(ip)
try:
response = await transport.handle_async_request(candidate)
if ip is not None and self._sticky_ip != ip:
async with self._sticky_lock:
if self._sticky_ip != ip:
self._sticky_ip = ip
logger.warning(
"[Telegram] Primary api.telegram.org path unreachable; using sticky fallback IP %s",
ip,
)
return response
except Exception as exc:
last_error = exc
if not _is_retryable_connect_error(exc):
raise
if ip is not None and ip == self._sticky_ip:
async with self._sticky_lock:
if self._sticky_ip == ip:
self._sticky_ip = None
logger.warning(
"[Telegram] Sticky fallback IP %s failed; resetting to primary DNS path",
ip,
)
if ip is None:
logger.warning(
"[Telegram] Primary api.telegram.org connection failed (%s); trying fallback IPs %s",
exc,
", ".join(self._fallback_ips),
)
continue
logger.warning("[Telegram] Fallback IP %s failed: %s", ip, exc)
await self._reset_fallback(ip)
continue
if last_error is None:
raise RuntimeError("All Telegram fallback IPs exhausted but no error was recorded")
raise last_error
async def aclose(self) -> None:
await self._primary.aclose()
async with self._fallback_lock:
transports = list(self._fallbacks.values())
self._fallbacks.clear()
for transport in transports:
await transport.aclose()
def _normalize_fallback_ips(values: Iterable[str]) -> list[str]:
normalized: list[str] = []
for value in values:
raw = str(value).strip()
if not raw:
continue
try:
addr = ipaddress.ip_address(raw)
except ValueError:
logger.warning("Ignoring invalid Telegram fallback IP: %r", raw)
continue
if addr.version != 4:
logger.warning("Ignoring non-IPv4 Telegram fallback IP: %s", raw)
continue
if addr.is_private or addr.is_loopback or addr.is_link_local or addr.is_unspecified:
logger.warning("Ignoring private/internal Telegram fallback IP: %s", raw)
continue
normalized.append(str(addr))
return normalized
def parse_fallback_ip_env(value: str | None) -> list[str]:
if not value:
return []
parts = [part.strip() for part in value.split(",")]
return _normalize_fallback_ips(parts)
def _resolve_system_dns() -> set[str]:
"""Return the IPv4 addresses that the OS resolver gives for api.telegram.org."""
try:
results = socket.getaddrinfo(_TELEGRAM_API_HOST, 443, socket.AF_INET)
return {addr[4][0] for addr in results}
except Exception:
return set()
async def _query_doh_provider(
client: httpx.AsyncClient, provider: dict
) -> list[str]:
"""Query one DoH provider and return A-record IPs."""
try:
resp = await client.get(
provider["url"], params=provider["params"], headers=provider["headers"]
)
resp.raise_for_status()
data = resp.json()
ips: list[str] = []
for answer in data.get("Answer", []):
if answer.get("type") != 1: # A record
continue
raw = answer.get("data", "").strip()
try:
ipaddress.ip_address(raw)
ips.append(raw)
except ValueError:
continue
return ips
except Exception as exc:
logger.debug("DoH query to %s failed: %s", provider["url"], exc)
return []
async def discover_fallback_ips() -> list[str]:
"""Auto-discover Telegram API IPs via DNS-over-HTTPS.
Resolves api.telegram.org through Google and Cloudflare DoH and returns all
unique A records. IPs that match the local system resolver are kept rather
than excluded: in many networks the system-DNS IP is the most reliable path
to api.telegram.org and a transient primary-path failure should be retried
against the same address via the IP-rewrite path before the seed list is
consulted (#14520). Falls back to a hardcoded seed list only when DoH
yields no usable answers.
"""
async with httpx.AsyncClient(timeout=httpx.Timeout(_DOH_TIMEOUT)) as client:
doh_tasks = [_query_doh_provider(client, p) for p in _DOH_PROVIDERS]
system_dns_task = asyncio.ensure_future(asyncio.to_thread(_resolve_system_dns))
results = await asyncio.gather(*doh_tasks, return_exceptions=True)
# The system-resolver leg runs socket.getaddrinfo in a worker thread with
# no timeout of its own — a wedged OS resolver (broken VPN/DNS) can sit for
# minutes. Its result only feeds the no-usable-answers log line below, so
# it must never gate discovery: bound it and move on (#63309). The DoH legs
# are already bounded by the client timeout above.
system_ips: set[str] = set()
try:
system_result = await asyncio.wait_for(system_dns_task, timeout=_DOH_TIMEOUT)
if isinstance(system_result, set):
system_ips = system_result
except Exception:
logger.debug("System-DNS resolution for %s did not complete in time", _TELEGRAM_API_HOST)
doh_ips: list[str] = []
for r in results:
if isinstance(r, list):
doh_ips.extend(r)
# Deduplicate preserving order
seen: set[str] = set()
candidates: list[str] = []
for ip in doh_ips:
if ip not in seen:
seen.add(ip)
candidates.append(ip)
# Validate through existing normalization
validated = _normalize_fallback_ips(candidates)
if validated:
logger.debug("Discovered Telegram fallback IPs via DoH: %s", ", ".join(validated))
return validated
logger.info(
"DoH discovery yielded no usable IPs (system DNS: %s); using seed fallback IPs %s",
", ".join(system_ips) or "unknown",
", ".join(_SEED_FALLBACK_IPS),
)
return list(_SEED_FALLBACK_IPS)
def _rewrite_request_for_ip(request: httpx.Request, ip: str) -> httpx.Request:
original_host = request.url.host or _TELEGRAM_API_HOST
url = request.url.copy_with(host=ip)
headers = request.headers.copy()
headers["host"] = original_host
extensions = dict(request.extensions)
extensions["sni_hostname"] = original_host
return httpx.Request(
method=request.method,
url=url,
headers=headers,
stream=request.stream,
extensions=extensions,
)
def _is_retryable_connect_error(exc: Exception) -> bool:
return isinstance(exc, (httpx.ConnectTimeout, httpx.ConnectError))