Late in a very long Telegram session, the agent stopped actually sending its replies for 3 straight turns
A user runs a long-lived agent session over Telegram: more than 4,000 messages and about $231 of usage in one session. Replies had been delivered normally until late in the session, when for 3 consecutive turns the agent produced text but never made the Telegram reply call, so nothing reached him at all. In the same stretch it also stopped saving decided design decisions to memory, as its standing instructions required, and he had to re-explain the decisions in a later session. A manual service restart and a log review found the cause.
This one went wrong. Read what happened so you don’t hit the same problem.
How it works
- Long Telegram session runs normally for hours
- Late in the session, replies are written but the send call is skipped
- 3 turns in a row never reach him
- Decided design points also go unsaved to memory
- He restarts the service by hand and finds the gap in the logs
Why it’s worth knowing
The failure was invisible from inside the chat. The replies existed; only the sending stopped.
Where it’s from
Summarized from a public post on github.com. See the original ↗