Changelog

Improvements

• Upgraded the bundled Bun runtime to 1.4.4, which includes security fixes for Brotli, TLS, HTTP/1.1, HTTP/2, HTTP/3, WebSocket, and fetch, and updates root certificates to NSS 3.131.1. (#58087)
• Generated session titles now use the lowest suitable model variant and more focused naming instructions. (#51939, #57648)
• Windows managed services now use port 28894, avoiding ranges reserved by Windows and WSL mirrored networking. (#57428)

Bug fixes

• Custom provider baseURL settings now override catalog model endpoints as expected. Thanks @Tarquinen and @bercedev. (#57810)
• Compaction summaries can use the same model output limit as normal responses, preventing incomplete summaries. (#57564)
• Legacy apply_patch permissions now migrate to the edit permission. (#57900)
• V1 sessions with relative working directories now migrate using their project worktree. Thanks @MohammadAlMasalmeh. (#57618)
• Unsupported legacy agent colors no longer prevent agents from loading. Thanks @4sDriven. (#57910)

Bug fixes

• The TUI no longer crashes when file watchers are unavailable or system watch limits are exhausted. Thanks @ANSHSINGH050404. (#51536)

Improvements

• Code blocks, streaming output, file views, and review diffs now use Pierre Highlights for faster highlighting and lower memory use on large inputs. (#57937)

Bug fixes

• Renaming a session tab now pastes plain text instead of formatted content. (#58036)
• Dragging the session scrollbar no longer forces the timeline back to its end. (#57831)
• RPM packages no longer conflict with build-ID links installed by other Electron applications. (#58093)

Improvements

• Added client.voice.models() to list experimental voice models, availability, and supported WebRTC or WebSocket transports. (#57194)
• Voice sessions can now use GPT-Live hosted by a connected OpenCode Console workspace. Hosted sessions expose an ID and support instruction updates through client.voice.instructions(). (#57735)

Bug fixes

• MCP results now keep supported media inline, decode textual resources, and save unsupported binary resources to files instead of creating invalid model attachments. (#57640)
• Updates to MCP instructions, skills, and project references now send only changed entries instead of repeating the full list. (#57626)

Improvements

• Added OPENCODE_DISABLE_FREE_MODELS for hiding free OpenCode and OpenCode Go models. (#57478)
• Added experimental.location_idle_timeout, accepting a duration string or false. (#57476)

Bug fixes

• Fixed fresh zsh and Fish installations not adding OpenCode to PATH when their configuration file did not exist. (#57348)
• Kept locations loaded while sessions are waiting for input, running long tools, or owning background jobs. (#57416)
• Fixed legacy console.opencode.ai credentials not being forwarded to opencode.ai/console. (#57588)
• Reused recent Console configuration checks when inference is rejected, avoiding unnecessary repeated checks. (#57465)

Improvements

• Added an inline free-limit notice with the reset time and /connect and /models actions, while restoring the submitted prompt when the composer is empty. (#57467)
• Restored the animated “Free limit reached” OpenCode Go dialog with Subscribe, Dismiss, and Don’t show again actions. (#57471)

Bug fixes

• Stopped showing redundant failure notifications when the free-message limit is reached. (#57467)
• Only shows “location unavailable” when the server explicitly reports the location as missing. (#57594)

Bug fixes

• Restored the free-limit dialog, reset-time timeline notice, and submitted prompt after free usage is exhausted. Subscribing to OpenCode Go now updates the current session’s model instead of opening another draft. (#57466)

Improvements

• Added retryAfterMs to structured session errors so clients can display provider-supplied retry timing. (#57146)

Bug fixes

• Fixed retry timing being dropped from quota, rate-limit, and provider-internal session errors. (#57589)
• Fixed OpenAI realtime client-secret requests by supplying the required expires_after.anchor.

Bug fixes

• Fixed Code Mode async jobs interleaving in the middle of statements and losing writes, while preserving concurrent tool calls. Thanks @RhysSullivan! (#54276)

Version 2.1 makes intentional changes to public SDK, HTTP message/event, and plugin contracts so provider replay data and compaction use consistent names and shapes. Integrations must adopt the new fields. Existing stored sessions, credentials, and older session imports remain readable through compatibility decoders; no database migration is required. (#57260)

Provider replay data is now native

Provider-owned replay data previously used different names on different surfaces. Read and write native instead; a tool's execution state and UI metadata are separate and are not renamed.

Surface	Before	After
Text and reasoning parts	state	native
Assistant and compaction messages	providerState	native
Text/reasoning lifecycle events and session.tool.called	state	native
session.step.ended, session.step.failed, and session.compaction.ended	providerState	native
session.tool.success and session.tool.failed	resultState	native
Exported replay-data schema	SessionMessage.ProviderState	SessionMessage.Native
Plugin compaction hook result	SessionCompactionResult.providerState	SessionCompactionResult.native

Tool call and result data share tool.native

Tool parts no longer have separate providerState and providerResultState fields:

 tool
-  providerState?
-  providerResultState?
+  native?
   state

Success and failure events shallow-merge their native into the call's existing native. Missing result data preserves call data; result values win on duplicate keys. Provider/protocol implementations must use distinct keys when call and result values differ. There is no state.native, resultNative, or nested { call, result } envelope.

Replay passes the merged blob to the protocol, which reads the fields it needs. Tool calls receive it only for the same provider and model. Provider-run results receive it for the same provider, including after a model switch. Local results receive it only for the same provider and model when the step did not fail. Legacy stored or imported providerResultState is merged into tool.native when read. Execution status and readable output remain in tool.state.

Key credential setup answers move to metadata

Credential.Key.configuration is removed. Public credential writes must put setup-form answers in the existing metadata field:

 { type: "key", key: "...",
-  configuration: { account: "example" }
+  metadata: { account: "example" }
 }

Existing stored credentials and opencode auth import still accept the old shape. Legacy configuration is merged into metadata; the legacy configuration value wins when both contain the same key. This compatibility is for storage/import, not a reason to keep sending configuration in public writes.

Summary compactions reference kept messages

Compaction messages and session.compaction.started / session.compaction.ended no longer expose recent. New summary compactions reference the first message retained verbatim through metadata.keepID instead of storing a second, flattened copy:

 summary compaction
-  recent: "[User]: ... [Assistant]: ..."
+  metadata: { keepID: "msg_..." }

History reconstructs the kept text from that message up to the compaction boundary. Forks remap the reference to their copied messages, and compaction hooks can override keepID through metadata. Kept text from pre-2.1 compactions and V1 imports remains available as metadata.recent. New compactions store the reference, not the duplicated text.

Provider compaction windows move to native.messages

Completed compactions and session.compaction.ended no longer have providerContext. The replacement message window now lives in native.messages:

-  providerContext: { version, provenance, messages }
+  native: { messages }

Native compaction replay now matches the compaction's provider ID and model ID, rather than route/protocol/endpoint provenance. If they do not match, history uses the original messages. Endpoint changes alone no longer block replay, and request hooks that rewrite the base URL no longer block native compaction or replay.

Summary compactions no longer save the summary call's unused provider data in native. A compaction hook's result.native is still stored; if it contains messages, that window is replayed instead of the summary. Old providerContext rows and events are converted when read, including the media format used before 2.0.15.

Remove the unused session.compacted event

The transitional session.compacted event is removed from the public event surface. Update event subscriptions and schema imports to use the current compaction lifecycle events, including session.compaction.started and session.compaction.ended.

Improvements

• Added persistent PTY support for Windows x64 and ARM64. (#56245)
• Restored the todowrite tool behind { "experimental": { "todo": true } }; it accepts the complete list as { todos: [{ content, status }] }. (#56947)
• Restored session archiving, including archive-state filtering and restoring archived sessions. (#53759)
• Added support for editing saved permission actions and resource patterns. (#56659)
• Summary compaction now covers the whole conversation while retaining recent text verbatim, and begins earlier by default to leave more response room. (#57091)
• Added the streamUsage model compatibility option for providers that reject stream_options. (#57255)

Bug fixes

• Prevented long-running TUI, run, and mini requests from hitting Bun’s default fetch deadline. Thanks @Finn763. (#55149)
• Retried broken-pipe transport failures. Thanks @sdivyanshu90. (#56307)
• Retried transient failures from buffered model generations instead of immediately failing. (#56497)
• Ignored provider keep-alives and unknown stream events while continuing to reject malformed known events. (#56286, #56669)
• Limited the OpenAI-compatible store field to OpenAI, Azure, and providers that explicitly opt in. (#57239)
• Preserved more complete context during compaction and stabilized image trimming and instruction baselines to improve prompt-cache reuse. Thanks @rrauenza for the revert fix. (#56983, #54410)
• Ensured shell completion is reported only after output capture finishes, and reported removed running shells as killed. (#56321, #56982)
• Prevented undefined permission metadata from breaking pending-request responses. (#54090)
• Bounded skill discovery and file watches, and tolerated filesystem permission denials during sandboxed startup. (#55597, #55817)
• Included the root script/ directory in Nix CLI builds. (#55494)

Improvements

• Added todo lists to session output, compact cards, and the sidebar when experimental todo support is enabled. (#56947)
• /models now opens on the current model and preserves the server’s preferred model order. (#57151)
• Added visible keyboard focus and reverse Shift+Tab navigation to export options. (#57154)

Bug fixes

• Kept long-running commands connected beyond Bun’s fetch deadline and restored the composer with an error toast when an existing-session shell command fails. Thanks @Finn763. (#55149)
• Retried session.wait after transport interruptions in mini. (#57062)
• Highlighted the selected file in the diff tree. Thanks @Tarquinen. (#57227)
• Removed per-row resize listeners from selection dialogs. Thanks @tobwen. (#56234)
• Corrected spacing above simple-dialog footers. (#56092)
• Fixed Mermaid flowchart rendering in the TUI when labels contain apostrophes. (#57060)

Bug fixes

• Show free OpenCode models alongside their paid counterparts by default instead of hiding them when they share the same model family and release date. (#55712)

Improvements

• Extended the existing experimental server voice API, client.voice.session(...), with Gemini Live support for gemini-3.8-live* models over WebSocket. The server uses a stored Google key or GEMINI_API_KEY, GOOGLE_GENERATIVE_AI_API_KEY, or GOOGLE_API_KEY. (#56888)
• Added client.permission.saved.update(...) for changing a saved permission’s action or resource. (#56659)
• Added archive filtering to client.session.list(...) and archive updates to client.session.update(...). (#53759)
• Added idle to the supported client.message.list(...) type filter. (#56504)

Improvements

• Added paginated ctx.session.list(...) to both Effect and Promise plugin APIs. (#56264)

Bug fixes

• Prevented opencode auth login from crashing when no browser opener such as xdg-open is available. (#56082)
• Gemini sessions now retry or continue after intermittent MALFORMED_RESPONSE finishes instead of immediately failing. (#56232)
• Made snapshot capture resilient to concurrent Git object writes on Windows. (#56190)

Improvements

• Changed /copy to copy the latest assistant message; the full transcript remains available from the command palette or /export. (#56053)

Bug fixes

• /copy now copies a completed compaction summary when it is the latest response. (#56055)

Improvements

• Added the experimental client.voice.session(...) API for server-brokered OpenAI GPT-Live and Realtime WebRTC sessions, OpenAI Realtime WebSocket sessions, and xAI Grok Voice WebSocket sessions. It uses an API key stored on the server or OPENAI_API_KEY/XAI_API_KEY; ChatGPT sign-in credentials are not used. (#55951)

Improvements

• Load local glob patterns and remote URLs configured through instructions, and refresh them when configuration changes. (#55539)
• Honor OPENCODE_DISABLE_CLAUDE_CODE and OPENCODE_DISABLE_CLAUDE_CODE_SKILLS when discovering .claude skills. (#55774)
• Publish a configuration schema that accepts both V1 and V2 configuration shapes during migration. (#55524)
• Remove the retired session-sharing backend and unavailable /share command. (#55716)

Bug fixes

• Use protocol-specific inference endpoints for OpenCode providers and accept null namespaces in Responses API function calls. (#55680, #55631)
• Fit compaction output limits to the request actually sent. (#55613)
• Restore authenticated TinyFish web search by initializing its MCP session. Thanks @terry-an-investor. (#54730)
• Improve MCP compatibility by skipping unsupported catalog and codemode calls, advertising spec-compliant elicitation capabilities, and accepting *.localhost OAuth token endpoints. Thanks @tsehla42 and @donbowman. (#55474, #55618, #53196, #55627)
• Treat empty provider and model names as omitted, and substitute an empty value for missing configuration-file references. (#55465, #55388)
• Default the Windows background service to port 45278. (#55547)

Improvements

• Open /diff beside the current session by default, retain state when toggling full screen with f, and adapt the file tree and patch layout to terminal width. (#47152, #55574, #55780)

Bug fixes

• Show /fork’s pending view reliably and keep it aligned with the file list. (#55746, #55751)
• Correct spacing and inactive key-hint styling in the docked diff panel. (#55452, #55467)

Improvements

• Show each completed turn’s changed files, line counts, and expandable diffs when Settings → Preferences → Timeline → Changed files is enabled. (#55064)
• Navigate session tabs with Option+↑/↓, or add Shift to jump to the previous or next unread tab. (#54277)
• Display delegations from the iOS app as Voice messages. (#54426)

Bug fixes

• Open PowerShell in the selected project directory on Windows. (#55710)
• Keep project settings accessible when the project folder is missing. (#55553)
• Show the requested URL while webfetch is running. (#55590)

Bug fixes

• Include MCP tool input as metadata.input in permission requests, allowing permission hooks to inspect the proposed call. Thanks @lu-zero. (#51062)

Improvements

• Automatically continue responses after an output-token limit, with bounded retries and clearer recovery for truncated tool calls. (#53876)
• Stabilize access policies under the top-level policies configuration key while retaining compatibility with experimental.policies. (#55297)

Bug fixes

• Give centrally managed configuration precedence over local and user configuration. (#55267)
• Allow migrated V1 npm provider configuration to target built-in provider routes. (#55254)

Improvements

• Report working sessions and sessions awaiting permission or input through terminal program-status notifications. (#55172)

Improvements

• Pair devices from Settings → Pairing through OpenTunnel remote access, with a QR code and copyable link. (#55306)
• Manage provider accounts from the connect dialog and Settings → Providers, including switching, renaming, removal, and adding another account. (#54101)
• Show session context tokens and accumulated family cost in the session view. (#53785)
• Pinch to zoom and use two-finger scrolling to pan image and SVG previews; select Fit to reset. (#54590)
• Cycle side-panel tabs with the configured previous-tab and next-tab shortcuts while the side panel is focused. (#54899)
• Refresh the question composer and clarify timeline notices that apply only to a model variant. (#54822, #54880)
• Refine diff colors and move unread indicators into session tabs. (#52551, #53570)

Bug fixes

• Show steered messages as pending immediately and render inline attachments before their server echo arrives. (#55251, #54650)
• Preserve raw media data up to 256 MiB so artifact previews remain available. (#55018)
• Retain session model selections when the model catalog refreshes. (#54481)
• Close browser tabs from the address field and suppress incorrect missing-file notices for restored or already-open tabs. (#54501, #55022)
• Prevent a project-store eviction loop during launch and remove hover gaps between vertical tabs. (#55078, #54866)

Improvements

• Export lastAssistantWithUsage from the Solid client to consistently locate the assistant step that determines current context usage. (#53785)

Bug fixes

• Include all paginated child sessions when loading a session family for usage totals. (#53785)
• Admit inline data-URL files into optimistic pending messages so attachments render immediately. (#54650)

Improvements

• Add ctx.permission.assert for Effect and Promise plugins, allowing plugins to use configured permission rules and the native approval prompt. (#54930)

Bug fixes

• Use Figma's public endpoint and default OAuth configuration, and support Git installations and development releases. (#55252, #55304)
• Resolve the Figma plugin peer dependency from its workspace. (#55269)
• Associate each rejected Promise hook with its own tool call. Thanks @1052326311. (#55263)

Improvements

• Continued split Gemini and Vertex Gemini responses automatically using provider continuation tokens. (#55056)
• Added settings.encoding with zstd, gzip, and none values for provider, model, and variant HTTP request bodies. ChatGPT authentication defaults to Zstandard compression when no custom baseURL is set. Thanks @esafak. (#54932)
• Added provider-level compatibility defaults and compatibility.cacheFormat for Anthropic- and Alibaba-style prompt-cache markers. (#54911, #54945)
• Added official WinGet packages and WinGet-aware upgrade and uninstall support. (#54808)
• Raised the default streamed-chunk timeout from 5 to 15 minutes for models that pause while reasoning. (#55032)

Bug fixes

• Disabled Bun’s fetch idle timeout for provider requests, preventing long-running streams from ending early. (#55007)
• Preserved mixed CRLF and LF line endings when the edit tool changes files. (#53166)
• Preserved unknown V1 OpenAI-compatible model options in migrated request bodies. (#54694)
• Stopped querying Azure resources during startup; Azure connections now ask for the resource name directly. (#54870)
• Loaded the system configuration directory at the lowest precedence. Thanks @rntdrts. (#54921)
• Installed the native CLI and extracted ripgrep without PowerShell on Windows ARM64. (#54955, #54981)

Improvements

• Added the post-update highlights dialog, /highlights, and the highlights alert setting. (#54969)

Bug fixes

• Restricted slash-command autocomplete to the start of the prompt. Thanks @OpeOginni. (#54857)
• Reported x64 emulation correctly when the TUI runs on Windows ARM64. (#54984)
• Removed the stale todowrite label from tool output. (#53966)

Improvements

• Added per-project auto-accept permission overrides under Settings → Projects, with mod+shift+a controlling the current project. (#54839)
• Added a native Windows (ARM64) option to the download page. (#54971)

Bug fixes

• Bundled native ARM64 terminal and CLI binaries in Windows ARM64 desktop builds, and moved emulated x64 installations to native ARM64 updates. Thanks @mweinbach. (#54689, #54983)
• Included subagent sessions in displayed session costs. (#55052)
• Loaded image and audio attachments in the review panel and opened video previews in an in-window theatre view. (#55015, #54696)
• Showed submitted prompts immediately and kept the Working marker above undelivered steers. (#54047, #55023)
• Fixed tab closing when collapsed side-panel tabs exist and restored focus correctly after stacked dialogs close. (#54695, #55038)

Improvements

• Added request-body encoding and model/provider cache-format fields to generated client types. (#54932, #54945)
• Exported CredentialApi from the Promise client API. (#52797)

Improvements

• Added an optional official Figma plugin with its MCP connection and six bundled Figma skills. (#55049, #55061)
• Exposed credential.activate to Effect and Promise server plugins. Thanks @remorses. (#52797)

Bug fixes

• Converted rejected Promise-based plugin tools into normal tool failures instead of crashing their execution path. (#54913)
• Fixed the VS Code extension launching the V2 CLI with the removed --port argument. Thanks @uyencss. (#49084)

Improvements

• Added the built-in Code Mode tools opencode.worktree_create, opencode.worktree_list, and opencode.worktree_remove. Removing a worktree requires edit approval, and force: true can discard modified or untracked files. (#53981)
• Added confirmation before opencode pair --remote first enables internet access, plus --yes/-y for scripts and other non-interactive use. (#54561)
• Automatically archived projects when all known directories disappear. Reopening a project restores it, while surviving clones and linked worktrees keep it active. (#54354)
• Raised the ChatGPT OAuth input limit for gpt-6.1-sol and gpt-6.1-sol-fast to 500,000 tokens. (#54668)
• Added Vertex AI routes for Interactions and Mistral models. (#54175, #54058)

Bug fixes

• Fixed updater detection for symlinked home directories and package-manager installations, increased probe timeouts, and now report unavailable updates clearly when the installation method cannot be detected. (#54609, #54622, #54672)
• Fixed GitHub Copilot routing for Gemini, Anthropic, and Responses models when live model metadata is unavailable, and accepted interleaved Claude reasoning values. (#54208, #54210, #54201)
• Fixed Google Vertex Application Default Credentials when CLOUDSDK_CONFIG points to a custom gcloud configuration directory. Thanks @H-Max. (#54164)
• Prevented ChatGPT token-sharing sessions from sending unsupported mid-session reasoning-effort updates. (#54085)
• Blocked file:// access through Code Mode’s fetch, which now returns a clear filesystem-access error. Thanks @ferdinandyb. (#54510)
• Fixed remote workspace file operations so driver-provided filesystem overrides are used correctly.
• Preserved subagent notifications when location services are evicted, and propagated well-known configuration updates across locations with bounded HTTP timeouts. (#54072, #53821)

Bug fixes

• Displayed session execution failures that occur before or between model steps directly in the timeline. (#53826)
• Preserved a saved session’s unavailable model selection instead of silently replacing it with a fallback. (#53822)
• Added syntax highlighting for C++ module interface files such as .cppm, .ixx, and .cxxm. (#53853)
• Summarized integrations with multiple credentials as a connection count, preventing long labels from crowding the integration name. (#54054)

Improvements

• Made the web app installable from Chrome and Edge, including deployments behind cookie-based authenticating proxies. (#53905)
• Updated the session column layout and text wrapping for clearer long content. (#54020)

Bug fixes

• Displayed session execution failures that occur before or between model steps directly in the timeline. (#53826)
• Fixed command-palette selection so newly arriving higher-ranked results become active until you explicitly choose a result. (#54275)
• Preserved bold, code, emphasis, and strike-through formatting inside Markdown link labels. (#54451)
• Fixed timeline file links and complete patch rendering, including unusual filenames and patches whose original alignment can be reused. (#53641, #54017)
• Showed complete tool error text when an error is expanded. (#53816)
• Fixed browser-panel controls, page visibility, corner masks, and closed side-region overlays. (#53907, #54038, #52461, #54052)
• Made the third-party notices dialog scrollable. (#53911)

Improvements

• Added startup plugin seeding to Effect embedded hosts and workerd through OpenCode.create({ plugins }) and OpenCodeWorkerd.create({ plugins }).
• Re-exported WorkspaceDriver, EnvironmentDriver, and EnvironmentFiles from @opencode/sdk/effect.

Bug fixes

• Ensured embedded hosts activate supplied plugins before model discovery, generation, and recovery begin. (#54219)

Improvements

• Extended BridgeLayout with viewport dimensions and optional border information so native extension surfaces can track window resizing and preserve rounded card borders.

Bug fixes

• Kept desktop browser-panel corner masks and borders aligned while resizing or using custom themes. (#52461)
• Kept the browser site button clickable after the embedded page takes focus. (#53907)

Improvements

• Added Google Cloud credentials (gcloud auth or environment) to the Vertex connection flow, with project and location choices discovered from environment variables, gcloud configurations, and Application Default Credentials. (#53798)
• Reduced session snapshot overhead, accelerated multi-file restores, made capture resilient to crashes and concurrent processes, and added lossless background packing of snapshot objects. (#51996)
• Added Step 5 Preview Free to OpenCode’s free models for a limited time and removed the retired Fledge Alpha Free listing.

Bug fixes

• Prevented working-tree diffs from timing out or stalling the server in repositories with many untracked files by batching Git operations. (#53449)
• Fixed large revert selections failing when their paths exceeded the operating system’s command-line limit. (#53956)
• Fixed snapshot and undo handling for literal filenames containing Git pathspec characters, corrupted or locked snapshot indexes, concurrent captures, and project directories whose names begin with ... (#51996)
• Changed opencode service remote-access URLs to use a persistent random subdomain rather than a predictable route. Disabling and re-enabling remote access generates a new address. (#53962)

Improvements

• Enabled OSC 8 hyperlinks in more terminals, including VS Code and other xterm.js terminals, Zed, mintty, and newer VTE terminals; FORCE_HYPERLINK=1 now overrides terminal detection. (#53904)

Bug fixes

• Fixed transcript links not opening when clicked, including URLs wrapped across multiple rows. (#53903)
• Kept activity summaries in place when expanding or collapsing details with session.verbosity: "low". (#52357)
• Prevented the home-screen version footer from overlapping keyboard hints in short terminals. Thanks @fihaaade. (#53891)