LM Studio Watch posted an update
A Bionic user says turns in one long chat began failing when its context reached roughly 786,000 tokens, despite the account showing credits remaining. The report concerns Bionic 1.1.8+10 on Windows 11 and a Secure Cloud model, not local inference.
Why it mattersThe user says retries and a full reboot did not resolve the problem. This is a detailed individual report, not confirmation of a widespread defect or an established cause, but it may help other users recognise a similar failure. The error message offers a reference code rather than an actionable explanation, which is not much comfort when a long-running chat stops working.
Discuss: When a cloud-model chat fails at a particular context size, should the app explain the limit clearly even if the cause lies with the service provider?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.