You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
- Telegram: preserve the channel-specific 10-option poll cap in the unified outbound adapter so over-limit polls are rejected before send. (#78762) Thanks @obviyus.
10
10
- Runtime/install: raise the supported Node 22 floor to `22.16+` so native SQLite query handling can rely on the `node:sqlite` statement metadata API while continuing to recommend Node 24. (#78921)
11
11
- Discord/voice: stream ElevenLabs TTS directly into Discord playback and send ElevenLabs latency optimization as the documented query parameter so spoken replies can start sooner.
12
+
- Slack: preserve explicit Slack mention targets, user-group ids, implicit thread wake reasons, and mention source metadata in inbound prompt context, and nudge implicit thread wakes without direct bot mentions to stay quiet unless they add specific value while keeping existing mention-gating behavior unchanged. Fixes #79025. Thanks @bek91.
12
13
- Discord/voice: keep TTS playback running when another user starts speaking, ignore new capture during playback to avoid feedback loops, and downgrade expected receive-stream aborts to verbose diagnostics.
13
14
- Telegram: treat successful same-chat `message` tool outbound sends during an inbound telegram turn as delivered when deciding whether to emit the rewritten silent reply fallback (#78685). Thanks @neeravmakwana.
14
15
- Gateway/tasks: reconcile stale CLI run-context tasks whose live run context disappeared even when a child session row remains, and apply the default bounded reload deferral timeout to channel hot reloads so stale task records cannot block Discord/Slack/Telegram reloads forever.
- implicit reply-to-bot thread behavior (disabled when `thread.requireExplicitMention` is `true`)
909
909
910
+
Slack prompt metadata preserves the collapsed wake decision (`was_mentioned`) and the provider-native mention detail for that turn, including `explicitly_mentioned_bot`, `mentioned_user_ids`, `mentioned_subteam_ids`, `implicit_mention_kinds`, and `mention_source`. This lets agents distinguish an explicit mention of another Slack user inside an implicitly waking thread from a direct bot mention. When a turn wakes from implicit thread participation without an explicit bot mention, OpenClaw also nudges the agent to reply only when it has specific additive value, such as correcting an important mistake or adding requested context.
911
+
910
912
Per-channel controls (`channels.slack.channels.<id>`; names only via startup resolution or `dangerouslyAllowNameMatching`):
"This turn woke from implicit thread participation, not a direct bot mention.",
99
+
"If the message is addressed to someone else, reply only when you have a specific useful addition, such as correcting an important mistake or adding requested context; otherwise use the current chat's no-response behavior.",
0 commit comments