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
{{ message }}
Repository navigation
Proposal: public status/health reporting for hosted models (Big Pickle via Zen) #9248
The BigPickle model is down today in the traditional sense: latencies of 240+ seconds for basic tasks (e.g., take console context and write to a file) and general failures spiked (e.g., </tool_call> gibberish in console logs).
Proposal: as agent-interaction becomes a primary browser of the internet, centralized crowd-sourced reporting of agent problems — similar to downdetector.com — would be immensely useful. OpenCode is well positioned to differentiate by establishing this as a principle.
The metadata is already available in the workflow: request latency per user, plus implicit failure signals such as duplicate prompts (an implicit failure) and tool-call crashes in console logs. Simple statistics over anonymized data would let users confirm ahead of time whether Big Pickle (or any LLM) is having an outage morning.
Additional metadata that would be valuable: per-request timing, backend model identity, and change indicators when a model is substituted.
Happy to help lead a PR or contribute to the design of this telemetry in Python.
Plugins
No response
OpenCode version
No response
Steps to reproduce
No response
Screenshot and/or share link
No response
Operating System
No response
Terminal
No response
Reacted by Chindriș Mihai - Alexandru, Ari Abramowitz, Etienne, André Mácola and Wanjohi
These issues collectively address aspects of your feature request for centralized LLM performance reporting and monitoring. The infrastructure for collecting and displaying performance metadata has been requested across multiple issues.
Feel free to ignore if your specific case is different or if these don't fully address your needs.
changed the title [-]Big Pickle via OpenCode Zen is down this morning? [reporting similar to downdetector.com?][/-][+]Proposal: public status/health reporting for hosted models (Big Pickle via Zen)[/+]on Aug 6, 2026
Activity
github-actions commentedon Jan 18, 2026
This issue might be related to several existing issues discussing model performance monitoring and status reporting. Please check:
These issues collectively address aspects of your feature request for centralized LLM performance reporting and monitoring. The infrastructure for collecting and displaying performance metadata has been requested across multiple issues.
Feel free to ignore if your specific case is different or if these don't fully address your needs.
github-actions commentedon Mar 27, 2026
To stay organized issues are automatically closed after 90 days of no activity. If the issue is still relevant please open a new one.
[-]Big Pickle via OpenCode Zen is down this morning? [reporting similar to downdetector.com?][/-][+]Proposal: public status/health reporting for hosted models (Big Pickle via Zen)[/+]