fix(telegram): prevent duplicate message delivery on send timeout (#5153)

TimedOut is a subclass of NetworkError in python-telegram-bot. The
inner retry loop in send() and the outer _send_with_retry() in base.py
both treated it as a transient connection error and retried — but
send_message is not idempotent. When the request reaches Telegram but
the HTTP response times out, the message is already delivered. Retrying
sends duplicates. Worst case: up to 9 copies (inner 3x × outer 3x).

Inner loop (telegram.py):
- Import TimedOut separately, isinstance-check before generic
  NetworkError retry (same pattern as BadRequest carve-out from #3390)
- Re-raise immediately — no retry
- Mark as retryable=False in outer exception handler

Outer loop (base.py):
- Remove 'timeout', 'timed out', 'readtimeout', 'writetimeout' from
  _RETRYABLE_ERROR_PATTERNS (read/write timeouts are delivery-ambiguous)
- Add 'connecttimeout' (safe — connection never established)
- Keep 'network' (other platforms still need it)
- Add _is_timeout_error() + early return to prevent plain-text fallback
  on timeout errors (would also cause duplicate delivery)

Connection errors (ConnectionReset, ConnectError, etc.) are still
retried — these fail before the request reaches the server.

Credit: tmdgusya (PR #3899), barun1997 (PR #3904) for identifying the
bug and proposing fixes.

Closes #3899, closes #3904.
This commit is contained in:
Teknium
2026-04-04 19:05:34 -07:00
committed by GitHub
parent c8220e69a1
commit 85cefc7a5a
4 changed files with 132 additions and 11 deletions

View File

@@ -377,23 +377,26 @@ class SendResult:
message_id: Optional[str] = None
error: Optional[str] = None
raw_response: Any = None
retryable: bool = False # True for transient errors (network, timeout) — base will retry automatically
retryable: bool = False # True for transient connection errors — base will retry automatically
# Error substrings that indicate a transient network failure worth retrying
# Error substrings that indicate a transient *connection* failure worth retrying.
# "timeout" / "timed out" / "readtimeout" / "writetimeout" are intentionally
# excluded: a read/write timeout on a non-idempotent call (e.g. send_message)
# means the request may have reached the server — retrying risks duplicate
# delivery. "connecttimeout" is safe because the connection was never
# established. Platforms that know a timeout is safe to retry should set
# SendResult.retryable = True explicitly.
_RETRYABLE_ERROR_PATTERNS = (
"connecterror",
"connectionerror",
"connectionreset",
"connectionrefused",
"timeout",
"timed out",
"connecttimeout",
"network",
"broken pipe",
"remotedisconnected",
"eoferror",
"readtimeout",
"writetimeout",
)
@@ -927,6 +930,18 @@ class BasePlatformAdapter(ABC):
lowered = error.lower()
return any(pat in lowered for pat in _RETRYABLE_ERROR_PATTERNS)
@staticmethod
def _is_timeout_error(error: Optional[str]) -> bool:
"""Return True if the error string indicates a read/write timeout.
Timeout errors are NOT retryable and should NOT trigger plain-text
fallback — the request may have already been delivered.
"""
if not error:
return False
lowered = error.lower()
return "timed out" in lowered or "readtimeout" in lowered or "writetimeout" in lowered
async def _send_with_retry(
self,
chat_id: str,
@@ -958,6 +973,11 @@ class BasePlatformAdapter(ABC):
error_str = result.error or ""
is_network = result.retryable or self._is_retryable_error(error_str)
# Timeout errors are not safe to retry (message may have been
# delivered) and not formatting errors — return the failure as-is.
if not is_network and self._is_timeout_error(error_str):
return result
if is_network:
# Retry with exponential backoff for transient errors
for attempt in range(1, max_retries + 1):

View File

@@ -772,6 +772,11 @@ class TelegramAdapter(BasePlatformAdapter):
except ImportError:
_BadReq = None # type: ignore[assignment,misc]
try:
from telegram.error import TimedOut as _TimedOut
except (ImportError, AttributeError):
_TimedOut = None # type: ignore[assignment,misc]
for i, chunk in enumerate(chunks):
should_thread = self._should_thread_reply(reply_to, i)
reply_to_id = int(reply_to) if should_thread else None
@@ -833,6 +838,11 @@ class TelegramAdapter(BasePlatformAdapter):
continue
# Other BadRequest errors are permanent — don't retry
raise
# TimedOut is also a subclass of NetworkError but
# indicates the request may have reached the server —
# retrying risks duplicate message delivery.
if _TimedOut and isinstance(send_err, _TimedOut):
raise
if _send_attempt < 2:
wait = 2 ** _send_attempt
logger.warning("[%s] Network error on send (attempt %d/3), retrying in %ds: %s",
@@ -850,7 +860,12 @@ class TelegramAdapter(BasePlatformAdapter):
except Exception as e:
logger.error("[%s] Failed to send Telegram message: %s", self.name, e, exc_info=True)
return SendResult(success=False, error=str(e))
# TimedOut means the request may have reached Telegram —
# mark as non-retryable so _send_with_retry() doesn't re-send.
_to = locals().get("_TimedOut")
err_str = str(e).lower()
is_timeout = (_to and isinstance(e, _to)) or "timed out" in err_str
return SendResult(success=False, error=str(e), retryable=not is_timeout)
async def edit_message(
self,