Skip to content

OpenCode v2.2.7

Released · OpenCode / SST

BreakingSecurity fixChanges skills and plugins, MCP server config, context and compaction settings

What the release notes say

Highlights

  • GitHub Copilot Auto: Pick Auto in the model picker when your Copilot account has an Auto pool, and Copilot's router chooses the model for each session at the Auto discount. If routing fails, OpenCode falls back to the account's default chat model. (#62997)

  • Side Panel Tab Shortcuts: Right-click a side panel tab and choose Close tabs to the right. ⌘W now closes side panel tabs wherever focus is, ⌥⌘W or Ctrl+Alt+W always closes the session tab, and ⌘⇧T reopens the last closed tab of either kind where it was. (#62922)

  • Mark Sessions Read or Unread: Open the menu on a tab, Home row, project row or inbox card and choose Mark as unread to keep its dot until you next visit. (#62889)

Breaking changes

@opencode/ai: ImageResponse.image is removed

This affects code that imports @opencode/ai directly. Read response.images[0] instead of response.image. (#63011)

SDK: fewer endpoints wait for plugins to load

On a Location that is still loading plugins, agent.list returns the agents loaded so far, and integration.list, usage.limits, vcs.init, rpc.call and artifact.* no longer wait up to 5 seconds. Entries and actions that a plugin provides appear when it finishes loading, so refresh on the matching *.updated event. Model, provider, generate.*, voice.* and websearch.query endpoints still wait. (#62796, #63040)

Core

Improvements

  • MCP Logins Stay Signed In: Remote MCP servers that rotate refresh tokens no longer sign you out when several clients refresh at once or the token endpoint fails for a moment. (#62827, #63012)

  • read accepts a negative offset to read from the end of a file, such as -50 for the last 50 lines. An offset past the end returns the last lines and the file's line count instead of failing. (#62147)

  • When read can't find a file, it suggests close names: different capitalization, another extension, a small typo, or the matching path inside the project. (#62147)

  • Shell results end with Exit code: N. Commands killed by a signal show the signal name, and timeouts say how long they waited and suggest a larger timeout. (#62141)

  • Prompt cache warming times its pings from the model's cache.ttl by default (interval: "auto"), or every 4 minutes without a TTL. Models whose cache outlasts the warming duration are no longer pinged. (#62831)

  • When MCP servers connect, disconnect or change tools, Code Mode sends the model a short list of what changed instead of the whole tool catalog. (#62176)

Bug fixes

  • GitHub Copilot session costs use the amount Copilot charged instead of the catalog estimate, and content-filter errors name the filter that blocked the response. (#62034)

  • GitHub Copilot picks up a new API endpoint after a plan change on its next model refresh, so you no longer have to sign in again. (#62171)

  • Remote MCP servers that rotate refresh tokens no longer log you out when the TUI, desktop app, background service or several projects refresh the same login at once. (#62827)

  • A temporary failure while refreshing an MCP OAuth token keeps your login for the next try instead of marking the server needs_auth. (#63012)

  • MCP tool calls no longer fail when the server's result doesn't match the tool's own output schema, so completed actions aren't reported as failed. (#61254)

  • MCP prompts stay available when refreshing a server's prompt list fails. (#62266)

  • With background_compaction on, a background summary no longer stops a running Claude Agent session mid tool call. (#63025)

  • After opencode auth logout on a .well-known integration, its remote providers and policies stop applying until you log back in. (#62760)

  • OpenCode Console workspace policies still apply when Console's instructions or skills fail to load. (#62702)

  • Cloudflare AI Gateway providers set up with only gatewayApiKey now send that key. (#62574)

  • A v1 model override that sets only some capabilities no longer resets the others, so catalog capabilities like PDF input are kept. (#62573)

  • A v1 provider config that sets both api and options.baseURL keeps options.baseURL. (#62570)

  • Legacy model references with an inline variant, such as "openai/gpt-5#high", keep the variant. (#62254)

  • A fresh install imports saved provider credentials from the legacy auth.json, and skips an invalid one with a warning instead of stopping setup. (#62568)