OpenCode v2.3.1

OpenCode v2.3.1 was released on .

Summary

Long builds no longer get killed at timeout: OpenCode 2.3.1 moves them to the background so they finish and report back. Compaction now happens quietly behind the scenes too. What else changed in this one?

Release Context

  • This was the 213th OpenCode release of 2026 tracked by Havoptic.
  • It shipped 1 day after OpenCode v1.19.6 (November 17, 2026).
  • OpenCode: ships every 2.2 days — 12 releases in the last month.

Why it matters: Shell commands no longer die at timeout.

Shipped around the same time

Within 3 days of this release, other AI coding tools also shipped:

Compare OpenCode

Release Notes

Highlights - Timed-Out Shell Commands Keep Running: A shell command still running when its timeout expires now moves to the background instead of being killed, so long builds and test runs finish and report back. A foreground timeout: 0 now means the default 120 seconds. (63699) - Compaction Without the Wait: As a session nears automatic compaction, the summary is now written in the background, so your next prompt doesn't pause for it. Set compaction.background: false to turn it off; a background summary that ends up unused still costs tokens. (64290) - GPT 6.2 with ChatGPT Sign-In: GPT 6.2 Sol and GPT 6.2 Astra, plus their fast variants, now show up in the model picker when you sign in with ChatGPT. (64508) - Update Plugins from Settings: Open Settings › Extensions, click Check for updates, then Update on any plugin with a new version. (64511) - Comment on Selected Code: Selecting code in diff and file viewers now just selects it, so you can copy it, and an Add comment toolbar appears beside the selection. (64410) Core Improvements - Shell commands still running when their timeout expires now move to the background instead of being killed, in every build. The shelltimeoutbackground flag is gone; configs that still set it keep loading. A foreground timeout: 0 now uses the default 120 second timeout instead of waiting until the command exits. (63699) - Background compaction is now on by default: as a session nears automatic compaction, the summary is written in the background so the next prompt doesn't wait for it. Turn it off with compaction.background: false; a background summary that is never used still costs tokens. The experimental.backgroundcompaction setting is removed. (64290) - OpenCode again reads CLAUDE.md in any directory that has no AGENTS.md, and falls back to ~/.claude/CLAUDE.md when the global AGENTS.md is missing. This also applies to instructions found when the agent reads nested files. Set OPENCODEDISABLECLAUDECODE or OPENCODEDISABLECLAUDECODEPROMPT to skip every CLAUDE.md. (64474, 64533) - Added GPT 6.2 Sol and GPT 6.2 Astra, plus their fast variants, to the ChatGPT model list. (64508) - websearch now returns a flat list of results, each with its url, title, content and published date. (64471) - Code Mode and plugins get a simpler structured result from read: text (with offset, lineCount and next), directory (entry names) or media (a URI instead of base64). What the model sees is unchanged. (64361) - Code Mode programs can use Node's Buffer for encoding and decoding bytes. (64365) - In Code Mode, search("issues") now works as shorthand for search({ query: "issues" }). (64347) - Code Mode tool summaries in the catalog can now be up to 500 characters instead of 120, so the model sees more of each tool's description. (64341) - The glob and grep tools now report a malformed filename glob (for example ) as an error that names the parameter to fix, instead of returning no results. ([63960) - Server requests that crash now return a 500 with a readable JSON UnknownError body instead of an empty one. Storage problems name the cause (for example "Storage is full" or "Storage is read-only"); other crashes include a ref you can find in the server log. (64022) - The shell tool description now tells the model that its session ID is in the OPENCODESESSIONID environment variable. (63718) - Experimental schedules are now automations, behind the automations flag (the old schedules flag still works). An automation runs on a time, an interval, a cron or a pushed MCP event, and either sends a prompt (to the creating session, another session or a new subagent) or runs a Code Mode program that decides whether to send one. Use /automation or the automation tools. Active or paused plain prompt schedules carry over; schedules with a condition or run limit, and finished ones, are dropped. (64160) Bug fixes - Fixed finished shell commands leaving zombie processes under opencode-pty. The process daemon now cleans each command up when it exits. Background processes started by a successful command (cmd &) keep running, and a failed command's leftovers are stopped. (64266, 64251) - Fixed ChatGPT and OpenAI subscription logins losing their sharing-limit safeguards and context caps when a token refresh failed. (64470) - Fixed Claude Agent models falling back to a 200K context window when Claude Code adds or renames a model. Thanks @Tarquinen. (64107) - Fixed requests being rejected after switching models mid-session on OpenAI-compatible providers. Models that declare a different reasoning field (such as reasoningcontent) no longer receive reasoning...

View original release

Other Recent OpenCode Releases

Upgrading from v2.3.1? See all 1 release since.

All OpenCode releases · All AI coding tool releases on Havoptic