Truncated model response for OpenCode Go models

Description

Today, many OpenCode Go models interrupt their response mid-stream. I've observed this for DeepSeek-V4-Pro, Kimi-K3 and MiMo-V2-Pro. Other users report this issue for DeepSeek-V4-Flash.

I am using the streaming API with my own client, so this is a server issue. I did not see any suspicious streaming packages in terms of "data: ..." chat.completion.chunks. The server simply closes the HTTP connection mid-stream. This also happens in the middle of tool calls, which results in invalid JSON.

The following issues are somewhat related, but not quite the same:

• DeepSeek-v4-Flash-free model, not with paid subscription
  • https://github.com/anomalyco/opencode/issues/41528
  • https://github.com/anomalyco/opencode/issues/39393
  • https://github.com/anomalyco/opencode/issues/39582
• gpt-5.6-luna
  • https://github.com/anomalyco/opencode/issues/39881

Plugins

NA

OpenCode version

NA

Steps to reproduce

1. Use any model
2. Write a prompt that results in a long response
3. Response stops after 3 to 5 minutes

Screenshot and/or share link

Incomplete reasoning

Incomplete tool call

Operating System

NA

Terminal

NA