mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-07-21 16:18:55 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

fix(telegram): classify and dedup post-reconnect probe failures (#63243)

Browse source
This commit is contained in:
SilentKnight87 2026-07-12 11:19:27 -04:00 • committed by kshitij
parent 7452467f54
commit 2a0dd95ccf
2 changed files with 96 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

28
plugins/platforms/telegram/adapter.py
View file

@ -2349,8 +2349,13 @@ class TelegramAdapter(BasePlatformAdapter):
wedged httpx pool fails this probe; a healthy one returns
well under the timeout.
On any failure, re-enter the reconnect ladder so the existing
MAX_NETWORK_RETRIES path can ultimately escalate to fatal-error.
On connectivity failure, re-enter the reconnect ladder (via
``_schedule_polling_recovery`` so the in-flight guard and task
bookkeeping apply) and let the existing MAX_NETWORK_RETRIES path
ultimately escalate to fatal-error. Auth/validation failures
(``InvalidToken``, ``BadRequest``, ...) are not connectivity symptoms
and must not trigger reconnect churn — same policy as the heartbeat
loop and the pending-update probe (#62098, #63243).
"""
HEARTBEAT_PROBE_DELAY = 60
PROBE_TIMEOUT = 10
@ -2364,8 +2369,9 @@ class TelegramAdapter(BasePlatformAdapter):
"[%s] Updater not running %ds after reconnect — treating as wedged",
self.name, HEARTBEAT_PROBE_DELAY,
)
await self._handle_polling_network_error(
RuntimeError("Updater not running after reconnect heartbeat")
self._schedule_polling_recovery(
RuntimeError("Updater not running after reconnect heartbeat"),
reason="post-reconnect probe: updater not running",
)
return
@ -2373,11 +2379,21 @@ class TelegramAdapter(BasePlatformAdapter):
await asyncio.wait_for(self._app.bot.get_me(), PROBE_TIMEOUT)
self._send_path_degraded = False
except Exception as probe_err:
if not self._looks_like_network_error(probe_err):
logger.warning(
"[%s] Post-reconnect probe hit a non-connectivity error"
" (not retrying): %s",
self.name, _redact_telegram_error_text(probe_err),
)
return
logger.warning(
"[%s] Polling heartbeat probe failed %ds after reconnect: %s",
self.name, HEARTBEAT_PROBE_DELAY, probe_err,
self.name, HEARTBEAT_PROBE_DELAY,
_redact_telegram_error_text(probe_err),
)
self._schedule_polling_recovery(
probe_err, reason="post-reconnect probe failure"
)
await self._handle_polling_network_error(probe_err)
def _disarm_ptb_retry_loop(self) -> None:
"""Synchronously stop PTB's internal polling retry loop.