admin/VolcanicAgenticCore
1
0
Fork 1
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(telegram): cut the voice transcript echo to 1024 characters

Browse Source
This commit is contained in:
EugeneTes
2026-10-02 09:51:57 +00:00
parent 3a57b81d88
commit 39e7849039
4 changed files with 19 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/telegram-bot.md
View File

@@ -132,7 +132,7 @@ question in that chat (for example from an extension) replaces the pending promp
GIF) up to 3.75 MB (`Telegram:InlineImageMaxBytes`) is also shown to the model; a larger one, or one whose contents
aren't really one of those formats, reaches it as a path only.
- **Voice messages and audio files** are transcribed with OpenAI (`gpt-4o-transcribe` by default). The bot echoes
`🎤 <transcript>` and the agent gets `[Voice message] <transcript>` (an audio file also gets its `[File received: …]`
`🎤 <transcript>` (cut to 1024 characters) and the agent gets `[Voice message] <transcript>` (an audio file also gets its `[File received: …]`
line). Without an API key the bot replies with how to set one up (`OPENAI_API_KEY`).
- Telegram lets bots download at most 20 MB. A bigger file is refused with a note, and nothing reaches the agent.
- A message with an attachment is never a command and never answers a pending question: its caption is prompt text.