Extremely Slow Response Time #56345

Activity

1. opencode-agent commented on Oct 17, 2026

   

   opencode-agentBot

   on Oct 17, 2026 – with OpenCode Agent

   Contributor

   More actions

   Thanks for the report! A 40-minute wait for a simple reply is definitely not expected. Slow responses can have quite different causes, so we need a few more details to narrow this down:

   • OpenCode version (output of opencode --version) and how you installed it
   • Operating system and, if you use the TUI, your terminal. Or tell us if you use the desktop or web app
   • Provider and model you were using (e.g. OpenCode Zen/Go, Anthropic, OpenAI, a local Ollama model…)
   • What you did: the prompt you sent, and roughly what the project looks like (e.g. a very large git repository?)
   • Whether this happens every time or only occasionally, and whether other models or providers are fast
   • Any errors or logs, if you have them. The screenshot is helpful, but please describe what it shows in the issue too

   You can reply here with the details or edit the issue. If you edit it, please also leave a comment saying you've updated it, so we know when you're done.

   These issues might be related. The list is ordered from most to least likely, so please check whether one of them already covers your problem:

   • Severe latency + aborted streams on opencode-go (Console Go) — streams hang for minutes and fail with "other side closed" / "Endpoint is unavailable" #52215: severe latency and streams hanging for minutes on opencode-go
   • OpenCode Time To First Token and Thinking is very slow #48328: very slow time to first token and thinking
   • Hy3 model is incredibly slow. 7 minutes to first reply. #44579: 7 minutes until the first reply with a specific model
   • service: 100% CPU hang when snapshotting a very large git worktree #50734 / desktop(win): background service SIGKILLed mid-turn when snapshot capture blocks /api/info for >6s -> ~60s restart loop, aborted turns #51216: hangs caused by snapshotting a very large git worktree
   • Intermittent 60s+ delay with "timeout" status on local Ollama models (direct Ollama: 1.3s) #52431 / Ollama local model becomes ~7x slower through OpenCode than direct Ollama API #46506: long delays with local Ollama models
   • cli: service becomes unresponsive under multi-session load — single process bottleneck #49095: the service stops responding under multi-session load
2. opencode-agent

   added

   triaging

   on Oct 17, 2026
3. opencode-agent

   closed this as not plannedon Oct 20, 2026
4. opencode-agent commented on Oct 20, 2026

   

   opencode-agentBot

   on Oct 20, 2026 – with OpenCode Agent

   Contributor

   More actions

   Closing this for now because we didn't get the details we asked for: OpenCode version, OS, provider and model, and what you were doing when the reply took 40 minutes. Slow responses can have quite different causes, so we can't investigate without them.

   If this still happens, please reply with those details or open a new issue with them, and we'll take another look. You may also want to check the related issues listed above, such as #52215 and #48328, in case one of them matches. Thanks!