"OpenAI Chat stream ended without finish_reason" #56858

Activity

1. opencode-agent commented on Oct 18, 2026

   

   opencode-agentBot

   on Oct 18, 2026 – with OpenCode Agent

   Contributor

   More actions

   Thanks for the report! I'd like to look into why the session keeps showing as generating instead of recovering. Could you add a few details?

   • OpenCode version (opencode --version)
   • Provider and model you were using (e.g. OpenCode Go / Zen, OpenRouter, a custom OpenAI-compatible endpoint), since this error often depends on the provider
   • OS and terminal
   • What the session shows when it gets stuck: do you see a Retry due · attempt N banner that then stops changing, or does the error appear once and then nothing else happens? Roughly how long did you wait before pressing Esc?

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

   These existing issues look related, ordered by likelihood, in case one of them already covers your problem:

   • server: model step hangs with no timeout, session stays busy until interrupted #53747: a model step hangs with no timeout and the session stays busy until it's interrupted
   • opencode-go: GLM-5.3-Flash long streams cut off without finish_reason, repeated retries #50146: streams cut off with OpenAI Chat stream ended without finish_reason and repeated retries (OpenCode Go)
   • cli: provider stream failures retry silently forever - looks like a hang with no console feedback #49030: provider stream failures retry silently forever, which looks like a hang
   • run: openai-compatible provider (Z.AI) stream always ends without finish_reason; interactive sessions unaffected #55124: an OpenAI-compatible provider's stream always ends without finish_reason in opencode run
   • session: auto-continue after a stream interruption is delivered as an unmarked synthetic user message #56295: how auto-continue works after a stream interruption
2. opencode-agent

   added

   triaging

   on Oct 18, 2026
3. opencode-agent

   closed this as not plannedon Oct 21, 2026
4. opencode-agent commented on Oct 21, 2026

   

   opencode-agentBot

   on Oct 21, 2026 – with OpenCode Agent

   Contributor

   More actions

   We haven't heard back about the details we asked for, so I'm closing this issue for now. To look into the session staying on "generating" after OpenAI Chat stream ended without finish_reason, we need your OpenCode version, the provider and model you were using, and whether a Retry due banner appears before it stops.

   If it happens again, please reply with those details and we'll reopen this. These issues may also cover the same problem and are worth following:

   • server: model step hangs with no timeout, session stays busy until interrupted #53747: a model step hangs with no timeout until it's interrupted
   • opencode-go: GLM-5.3-Flash long streams cut off without finish_reason, repeated retries #50146: streams cut off without finish_reason, with repeated retries
   • cli: provider stream failures retry silently forever - looks like a hang with no console feedback #49030: provider stream failures retry silently, which looks like a hang

   Thanks for the report!