mirror of
https://github.com/openclaw/openclaw.git
synced 2026-05-06 17:00:50 +00:00
fix(telegram): frame audio transcripts as untrusted
This commit is contained in:
@@ -546,6 +546,9 @@ curl "https://api.telegram.org/bot<bot_token>/getUpdates"
|
||||
|
||||
- default: audio file behavior
|
||||
- tag `[[audio_as_voice]]` in agent reply to force voice-note send
|
||||
- inbound voice-note transcripts are framed as machine-generated,
|
||||
untrusted text in the agent context; mention detection still uses the raw
|
||||
transcript so mention-gated voice messages continue to work.
|
||||
|
||||
Message action example:
|
||||
|
||||
|
||||
Reference in New Issue
Block a user