chore(logs): reduce decrypt-error noise (~75% fewer lines per recover… (#391)

chore(logs): reduce decrypt-error noise (~75% fewer lines per recover… (#391)
This commit is contained in:
Renato Alcara
2026-04-26 11:36:21 -03:00
committed by GitHub
parent 1dffe3b311
commit df1acc8f0c
3 changed files with 46 additions and 5 deletions
+12 -1
View File
@@ -341,7 +341,18 @@ export const addTransactionCapability = (
return result
} catch (error) {
logger.error({ error }, 'transaction failed, rolling back')
// SessionError is part of the normal Bad MAC recovery flow
// (retry receipt → sender resends as pkmsg → new session within ~1.3s).
// Logging it as ERROR creates 2 noise lines per recoverable Bad MAC cycle.
// Downgrade to debug for SessionError; keep ERROR for everything else.
// The error is still re-thrown — recovery behavior is unchanged.
const errName = (error as { name?: string })?.name
if (errName === 'SessionError') {
logger.debug({ error }, 'transaction failed (SessionError — recoverable via retry receipt)')
} else {
logger.error({ error }, 'transaction failed, rolling back')
}
throw error
}
})
+23 -2
View File
@@ -58,7 +58,11 @@ export const BAD_MAC_ERROR_TEXT = 'Bad MAC'
export const DECRYPTION_RETRY_CONFIG = {
maxRetries: 3,
baseDelayMs: 100,
sessionRecordErrors: ['No session record', 'SessionError: No session record'],
// 'No matching sessions found' is the libsignal error when decryptWithSessions exhausts
// all stored sessions for a JID. Same recovery flow (retry receipt → pkmsg → new session)
// — categorise it as session-record so the caller logs DEBUG on retry, ERROR only when
// retries are exhausted (instead of dumping the full stack as an unknown error).
sessionRecordErrors: ['No session record', 'SessionError: No session record', 'No matching sessions found'],
corruptedSessionErrors: ['Bad MAC', 'MessageCounterError', MISSING_KEYS_ERROR_TEXT]
}
@@ -421,9 +425,26 @@ export const decryptMessageNode = (
const isCorrupted = isCorruptedSessionError(originalError)
const isSessionRecord = isSessionRecordError(originalError)
// Slim error projection — keep name/message/type for diagnosis,
// drop `stack` which adds 4-5 lines of node_modules paths per log
// for known-recoverable libsignal errors.
//
// CRITICAL: only slim for KNOWN-RECOVERABLE categories (corrupted /
// session-record). The unknown-error branch keeps the full Error so
// protobuf/parsing/runtime bugs still emit a stack trace where it
// matters most. Catches Copilot/Codex P2 review on PR #391.
const slimErr = originalError
? {
name: (originalError as { name?: string }).name,
message: (originalError as { message?: string }).message,
type: (originalError as { type?: string }).type
}
: undefined
const isRecoverableCategory = isCorrupted || isSessionRecord
const errorContext = {
key: fullMessage.key,
err: originalError,
err: isRecoverableCategory ? slimErr : originalError,
messageType: tag === 'plaintext' ? 'plaintext' : attrs.type,
sender,
author,
+11 -2
View File
@@ -28,7 +28,16 @@ console.info = function (...args: unknown[]) {
// Track errors by type + JID to avoid duplicates (using Map for better performance)
const _errorTimestamps = new Map<string, number>()
const DEDUP_WINDOW_MS = 150
// Dedup window for repeated decrypt-error console lines (Bad MAC / Counter / etc).
// Was 150ms, but retry attempts of the SAME message are typically ~300-1000ms apart,
// so the second attempt fell outside the window and double-printed.
//
// TRADE-OFF: dedup key is `errorType + JID` (no message-id). With 5s, a burst of
// errors for the SAME JID — even of slightly different categories or different
// messages — collapses to one log line every 5s. This is intentional for a noisy
// production stream; if you need per-message visibility, set BAILEYS_LOG_LEVEL=debug
// to bypass this console-side dedup and see the structured pino logs in full.
const DEDUP_WINDOW_MS = 5000
console.error = function (...args: unknown[]) {
if (args.length > 0 && typeof args[0] === 'string') {
@@ -70,7 +79,7 @@ console.error = function (...args: unknown[]) {
const lastTime = _errorTimestamps.get(dedupeKey)
if (lastTime && now - lastTime < DEDUP_WINDOW_MS) {
return // Skip duplicate within 150ms window
return // Skip duplicate within DEDUP_WINDOW_MS window
}
_errorTimestamps.set(dedupeKey, now)