OpenCode Changelog

better tldr; source aware/data miner style changelogs generated for OpenCode releases. unofficial

[OpenCode Changelog @OpenCodeLog]

𝙊𝙥𝙚𝙣𝘾𝙤𝙙𝙚 v2.0.27 released. TL;DR:
Agents can now create and remove git worktrees, projects whose folders are gone get archived automatically, Vertex AI adds Interactions and Mistral routes, and pair --remote now asks before putting your server on the internet.

𝗔𝗽𝗽
Added
• Made the web app installable as a PWA.
• Added more reliable file links in the session timeline. Supports path:line, :start-end, #L ranges and file:// URLs. Relative paths are looked up in the workspace, and a picker opens when more than one file matches.

Changed
• Updated the session column layout to match the design and switched message text to pretty wrapping.

Fixed
• Fixed failed session runs so they now show an error row in the timeline instead of ending silently.
• Fixed expanded tool error cards so they show the full error text and subtitle instead of a cut-off one-liner.
• Fixed complete patches being diffed a second time. The diff view now reuses the patch's own hunks, which is faster and keeps the producer's line alignment.
• Fixed the command palette so it follows the first result while results stream in, until you pick a row yourself.
• Fixed markdown link labels so bold, code and other inline formatting render inside links.
• Fixed the embedded browser panel flashing blank when popups cover it, misaligned corner masks, and a site button that stopped responding after the page took focus.
• Fixed a stray shadow line over the side terminal and made the third-party notices dialog scrollable.

𝗧𝗨𝗜
• Fixed a session's saved model choice being dropped when that model is temporarily unavailable.
• Changed the integrations dialog to show a count when there are several connections, so long labels no longer push the name off the row.
• Added syntax highlighting for C++ module interface files (.cppm, .ccm, .cxxm, .c++m, .ixx).

𝗔𝗴𝗲𝗻𝘁
• Added worktree_create, worktree_list and worktree_remove to the built-in opencode tools. Removing a worktree needs the edit permission on its directory, and forced removal discards uncommitted changes.
• Fixed background subagent completion messages getting lost when the parent session's location was unloaded while it sat idle.
• Fixed Code Mode fetch so file:// URLs are rejected instead of being usable to read the filesystem.

𝗣𝗿𝗼𝘃𝗶𝗱𝗲𝗿𝘀
Added
• Added a native Vertex AI Interactions route (ADC, access token or Express-mode API key) and native routing for Vertex-hosted Mistral models.
• Raised gpt-6.1-sol over ChatGPT OAuth to 500k input and 628k total context. Other models keep the Codex limits of 272k input and 400k context.

Fixed
• Fixed Google Vertex ADC so it honors CLOUDSDK_CONFIG, including ~ paths, when finding credentials and the project.
• Added on/off thinking variants for Vertex MaaS models: DeepSeek, GLM and Gemma.
• Fixed GitHub Copilot routing: Gemini now uses Chat Completions. When the live model list is unavailable, https://t.co/0Tykrz1EhK packages decide the API (Anthropic Messages stays native, OpenAI models use Responses).
• Fixed GitHub Copilot interleaved Claude thinking failing on multiple reasoning_opaque values. The latest value is now replayed with the combined reasoning text.
• Turned off mid-session reasoning-effort updates for ChatGPT token-sharing sessions.
• Fixed Databricks and Neon setup variables (such as base URLs) being treated as API keys.
• Stopped local providers like Ollama from falling back to the default localhost address inside remote workspaces and sandboxed environments.

𝗖𝗟𝗜
• Changed opencode pair --remote to ask before it first exposes the server through OpenTunnel. Use --yes or -y to accept without an interactive terminal.
• Fixed update checks: curl-install detection now resolves symlinked home folders, the package manager matching the binary's path is checked first, and the probe timeout is now 30s.
• Changed update checks to report "unavailable" with manual-update instructions when the install method can't be detected, instead of failing.

𝗖𝗼𝗿𝗲
• Added automatic archiving of projects whose directories are all gone, checked hourly. If another main checkout survives, it becomes the project's directory instead, and opening the project again unarchives it.
• Fixed file operations in remote workspaces so they go through the workspace's own connection and wake it when needed.
• Added a 15s timeout to .well-known config fetches, and config updates now reach every location.
• Upgraded the runtime to Effect 4.0.1.

𝗦𝗲𝗿𝘃𝗲𝗿
• Changed model list, default model and text generation to wait up to 5s for plugins to finish loading, returning 503 instead of incomplete results.
• Added an archived=true filter to the project list endpoint. Archived projects are hidden by default.
• Changed the fs list endpoint to return a typed not-found error for missing or non-directory paths.

𝗦𝗗𝗞
• Fixed embedded and workerd hosts so plugins are registered before suspended sessions are resumed. workerd create now accepts plugins.
• Exported the environment and workspace driver interfaces from the Effect SDK entrypoint for custom workspace providers.

𝗭𝗲𝗻
• Changed Zen API routes to pass requests straight to the new inference backend, including keyless free models, BYOK requests and model listing.
• Changed Go and Zen login links to go directly to Console.

𝗥𝗲𝗹𝗲𝗮𝘀𝗲
• Added redirects from release artifact filenames to the latest release download URLs in the update service.

No noticeable bundle change

Compare: https://t.co/YYgOO67r17

[OpenCode Changelog @OpenCodeLog]

𝙊𝙥𝙚𝙣𝘾𝙤𝙙𝙚 v1.19.0 released. TL;DR:
The TUI no longer installs updates on its own and adds a /update flow, opencode upgrade --major moves you to OpenCode 2, GitHub Copilot interleaved reasoning no longer errors, and PTY websocket connections are checked more strictly.

𝗧𝗨𝗜
Added
• Added a /update dialog. It checks for new versions every 10 minutes and offers a newer OpenCode 1 release first. OpenCode 2.0 is offered only when v1 is already current. Nothing installs until you confirm, then it asks you to restart.
• Added an update hint under the home-screen logo, such as "/update to install vX" or "/update to upgrade to OpenCode 2.0". After an install it changes to "/exit" to restart.

Changed
• Changed update behavior so patch releases are never installed silently in the background. autoupdate true and "notify" now do the same thing, and false turns update checks off.
• Changed how skipping works: skipping a v1 version hides it until a newer one ships, and dismissing the OpenCode 2.0 offer hides it for 7 days.

Fixed
• Fixed syntax highlighting for C++ module interface files (.cppm, .ccm, .cxxm, .c++m, .ixx).

𝗖𝗟𝗜
• Added opencode upgrade --major to replace OpenCode 1 with OpenCode 2. It works with curl, Homebrew, npm, pnpm, bun and yarn. With a package manager it removes opencode-ai, installs @opencode/cli, and reinstalls your current v1 if the v2 install fails.
• Changed opencode upgrade to mention that OpenCode 2 is available, both after an upgrade and when you're already on the latest version.

𝗣𝗿𝗼𝘃𝗶𝗱𝗲𝗿𝘀
• Fixed GitHub Copilot streams with interleaved thinking (Claude). Several reasoning tokens in one response no longer cause an error. The latest one is kept and sent back with all the reasoning text joined, the same way the Copilot VS Code client does it.
• Added support for OpenAI's "ultrafast" service tier in both the Chat and Responses APIs.

𝗦𝗲𝗿𝘃𝗲𝗿
• Tightened PTY websocket connections. The origin is now checked on every connection, not only ones with a ticket, and bad origins or invalid tickets get a 403 before the server looks up the PTY. A missing PTY can no longer be detected from a 404.

𝗭𝗲𝗻
• Changed requests to free Zen models that have no API key so they go to the new inference backend anonymously, with credentials removed.
• Fixed proxied 404 errors being replaced by the site's "route not found" page. They now come back as 400 with the original inference error.

𝗖𝗼𝗻𝘀𝗼𝗹𝗲
• Added Claude Haiku 5.5 and Step 5 Preview Free (limited time) to the Go model lists, plan limits, privacy FAQ and workspace promo. The Go page also shows more model provider logos.
• Added an optional monthly inference spend field to the Enterprise contact form. It is validated and included in sales leads.

𝗗𝗮𝘁𝗮
• Changed stats to count usage of the Exo stealth model under an unknown provider instead of naming a real model author.

𝗥𝗲𝗹𝗲𝗮𝘀𝗲
• Changed OpenCode 1 releases and the v1 web app deploy to come from the dedicated v1 branch.

No noticeable bundle change

Compare: https://t.co/zosSUErKcw

[OpenCode Changelog @OpenCodeLog]

𝙊𝙥𝙚𝙣𝘾𝙤𝙙𝙚 v2.0.26 released. TL;DR:
Faster and more robust session snapshots, guided Google Cloud credential setup for Vertex, unguessable remote-access URLs, and clickable transcript links in the TUI.

𝗧𝗨𝗜
• Added plain-click opening for links in the transcript, including links that wrap across rows. Ctrl, Alt, and Shift clicks are left to the terminal's own link handling.
• Fixed expanding or collapsing a low-verbosity activity summary so its header stays on the same screen row instead of jumping the scroll position.
• Fixed the home footer overlapping the hint row in short terminals. It is now hidden below 14 rows.
• Updated OpenTUI to 0.5.17.

𝗔𝗴𝗲𝗻𝘁
Changed
• Improved time to first token: the workspace snapshot taken at the start of each turn now runs while the provider request is in flight. Tools still wait for the snapshot before running.
• Changed snapshot capture to work on a temporary Git index that is renamed into place. Concurrent OpenCode processes no longer fight over index.lock, and a killed process cannot leave a half-written index.
• Added background packing of loose snapshot objects and merging of small packs. Nothing is pruned, so old snapshots stay restorable.
• Improved revert speed: file restores are batched into one checkout per snapshot tree instead of two Git processes per file.
• Improved working-tree diffs: untracked files are diffed in about three Git processes total instead of two per file.

Fixed
• Fixed snapshot capture recovering from an unreadable snapshot index by rebuilding it, instead of failing on every turn.
• Fixed snapshot stores that several processes create at the same time. Store setup is now atomic, so no process sees a half-initialized store.
• Fixed files whose names contain glob characters like * or [ by treating paths literally in snapshot capture, diff, and restore.
• Fixed large snapshot diffs on every platform by batching path lists to fit command-line limits.

𝗣𝗿𝗼𝘃𝗶𝗱𝗲𝗿𝘀
• Added a Google Cloud credentials sign-in option for Vertex that uses gcloud auth or environment credentials. The project picker is prefilled from gcloud configurations and the ADC quota project. The location picker offers global, us, eu, and configured regions.
• Changed Vertex to reload providers and models immediately when the selected credential changes or is updated.
• Fixed an ambient GOOGLE_VERTEX_API_KEY overriding Google credentials when a project or location is set. This now matches the precedence used by Google's Gen AI SDK.

𝗖𝗟𝗜
• Changed remote access (opencode pair --remote and the service remote setting) to use a random, unguessable subdomain instead of a predictable per-channel one. Tunnel hostnames show up in public certificate logs, so the old address was discoverable.
• The random remote route is kept across service restarts and replaced with a new one when remote access is turned off and on again. Older boolean configs are migrated automatically, and the route is hidden from service get output.

𝗗𝗼𝗰𝘀
• Added Step 5 Preview Free to the Zen and Go model lists and removed Fledge Alpha Free.

𝗥𝗲𝗹𝗲𝗮𝘀𝗲
• Added a CHANGELOG.md for V2 releases. Reviewed release notes are now written to it during publishing, with highlights listed first.

No noticeable bundle change

Compare: https://t.co/lOusf8vg2D

[OpenCode Changelog @OpenCodeLog]

𝙊𝙥𝙚𝙣𝘾𝙤𝙙𝙚 v2.0.25 released. TL;DR:
Remote pairing over OpenTunnel, Azure CLI and AWS profile sign-in, Office file previews in the App, and policy controls for MCP servers, plugins and skills.

𝗔𝗽𝗽
Added
• Added in-app previews for Word, Excel and PowerPoint files.
• Added a menu of recently closed tabs to the titlebar.
• Added recent sessions to the command palette when the search box is empty.
• Added a pairing-link-first connect flow: paste or scan a one-time link, with password login as a fallback and clear errors for expired, old-style or unreachable links.
• Redesigned the desktop browser bar and polished mobile session navigation and drawers.

Fixed
• Fixed live terminals dropping during brief connection failures.
• Fixed the waiting state of steered prompts so it follows the actual run state.
• Fixed the thinking summary heading so the latest one shows while a response streams.
• Fixed Markdown text in sessions so it can be selected again.
• Fixed a server signed in again at the same address so it uses the new credentials.
• Fixed desktop so old staged CLI versions are deleted after an update.

Removed
• Removed the configurable default server setting from the App and desktop.

𝗧𝗨𝗜
• Fixed dialogs reading outdated transcript rows after a session resync.
• Fixed the queued prompt dock sitting flush against the composer.
• Changed the execute dialog to the two-toned dialog layout.

𝗖𝗟𝗜
Added
• Added opencode pair --remote, which shows a public HTTPS pairing URL through OpenTunnel. It shares the device's existing tunnel and gives each release channel its own subdomain.
• Changed pairing QR codes to include every reachable address and leave out loopback-only ones.

Changed
• Changed opencode uninstall to keep data, config and state (sessions, credentials, settings, prompt history) and only remove the cache.
• Changed the embedded web UI to be stored as raw bytes and served brotli-compressed.

Fixed
• Fixed npm installs silently keeping an older platform binary when the matching version is not on the registry yet.

𝗣𝗿𝗼𝘃𝗶𝗱𝗲𝗿𝘀
Added
• Added Azure sign-in through the Azure CLI (Entra ID). The resource picker lists your Azure OpenAI and AI Services resources, and tokens are fetched per request.
• Added Amazon Bedrock sign-in with an AWS profile (SSO or named), with profiles found in ~/.aws/config and ~/.aws/credentials.
• Added bundled Anthropic-compatible and OpenAI-compatible Responses provider packages.

Fixed
• Changed the default Google Vertex location from us-central1 to global.
• Fixed xAI requests failing on GIFs and other image types by sending only PNG, JPEG and WebP.
• Fixed ChatGPT requests to send Codex-style session headers so prompt caching works across turns.
• Fixed API key metadata being merged into the request body.

𝗖𝗼𝗿𝗲
• Added integration.use policies that can block MCP servers, external plugins, hosted integrations and skills. Blocked MCP servers are disconnected, and blocked skills disappear from the catalog and tools.
• Renamed the permission policy action to tool.use. Console-managed config now skips unknown policy actions instead of rejecting the whole config.
• Fixed remote (well-known) config so the last good copy is kept when a refresh fails or the source is offline at startup.

𝗔𝗴𝗲𝗻𝘁
• Changed default agents to stop asking before accessing directories outside the project.
• Fixed malformed or unfinished tool calls: they no longer run with guessed arguments and now fail with a message asking the model to call the tool again.
• Removed length limits on tool names and namespaces, so long MCP tool names register.
• Fixed session last-updated times so they change as steps start and finish.
• Fixed edited Markdown agents and commands sometimes loading stale frontmatter.

𝗔𝗖𝗣
• Added standard ACP terminal auth: clients can run opencode acp --login to sign in.
• Fixed tool calls to report tool names and full-file diffs.
• Changed session handling to reject a relative cwd or a fork with the wrong cwd, and session/delete now cancels an active prompt first.
• Fixed the first catalog read in a new directory so it waits for plugins to load.

𝗟𝗟𝗠
• Added between_tools thinking for Anthropic Messages and Bedrock.
• Added the OpenAI fast and ultrafast service tiers and the Google deferred tier.
• Fixed replays of OpenAI Responses history failing on empty, unfinished reasoning items.

𝗦𝗲𝗿𝘃𝗲𝗿
• Changed file reads to stream, with HTTP Range requests, ETag/Last-Modified checks and 304 responses.
• Fixed the MCP client name so it is always reported as opencode.

𝗣𝗹𝘂𝗴𝗶𝗻
• Changed plugins to use OpenCode's own effect module, so plugins share one Effect runtime with the host and should list effect as a peer dependency.
• Added an external connection method so plugins can define form-driven credential sources, usable from the CLI, TUI and App.

𝗨𝗜
• Fixed $...$ math so it renders next to punctuation without treating prices as math.
• Added inline custom answers for choice fields in connect forms.
• Added an animated segmented control and fixed its click targets.

Bundle +5.9 MB because mostly Web UI assets +68.8 MB and Bundle metadata -36.6 MB

Compare: https://t.co/ow6SMPovhW

[OpenCode Changelog @OpenCodeLog]

𝙊𝙥𝙚𝙣𝘾𝙤𝙙𝙚 v1.18.35 released. TL;DR:
Images in xAI tool results now reach the model, OpenCode Data pages get Markdown, JSON and llms.txt versions for agents, and Space Bunny becomes a paid Go model.

𝗣𝗿𝗼𝘃𝗶𝗱𝗲𝗿𝘀
• Fixed images returned by tools not reaching xAI models by updating the xAI SDK integration to 3.0.139.
• Fixed xAI requests failing completely on an unsupported image type: tool-result images other than PNG, JPEG or WebP (for example GIF) are now dropped instead of causing an invalid_image error.
• Updated the GitLab AI provider to 6.19.0.

𝗗𝗮𝘁𝗮
Added
• Added Markdown and JSON versions of the home, lab and model pages, plus Markdown for model comparisons. Add .md or .json to the URL, or send Accept: text/markdown.
• Added /data/llms.txt so agents can find these formats and their URL patterns.
• Added 301 redirects from lab and model URL variants to the canonical page, keeping any extension and query string.

Fixed
• Fixed canonical links, 404 handling and missing sitemap entries on data pages.
• Fixed stealth model pages so they show public specs (context and output limits, modalities, knowledge cutoff, release date) taken from their OpenCode listings.
• Added a configurable hidden-model list that removes the listed models from usage, geo and retention stats.

𝗭𝗲𝗻
• Changed Space Bunny in Go from a limited-time free model (space-bunny-free) to a paid model (space-bunny) at $0.15 input, $0.60 output and $0.03 cached per 1M tokens, with per-plan usage limits.

𝗜𝗻𝗳𝗿𝗮
• Removed the old S3 data lake and its ingestion pipeline from the stats stack.

No noticeable bundle change

Compare: https://t.co/ScHbgbl6OR

[OpenCode Changelog @OpenCodeLog]

𝙊𝙥𝙚𝙣𝘾𝙤𝙙𝙚 v2.0.24 released. TL;DR:
Vercel AI Gateway now runs on the native runtime, the explore agent can use read-only shell commands, the shell permission scanner handles bash, zsh, and PowerShell more accurately, and the desktop app shows queued, pending, and running work more clearly.

𝗧𝗨𝗜
• Changed the open-session menu so sessions waiting for a permission or question reply appear at the top, even when they are already open in a tab.
• Fixed the subagent active/inactive filter resetting when you navigate between sessions.
• Fixed crossing branches in Mermaid flowcharts rendered in the terminal.
• Removed the error icon from grouped exploration activity.

𝗔𝗽𝗽
Added
• Added a header indicator for running subagent sessions and a clearer running-work menu with "+N working" and "+N running" counts.
• Added a "Pending" label to steer messages that have not been delivered yet, plus clearer move-to-queue and undo icons.
• Added each /btw answer in its own tab, which stays open until you close it. /btw now applies the composer's selected model first.
• Restored the prompt shown when a session's directory is missing, so you can pick another directory or worktree and move the session there.

Fixed
• Fixed staged reverts being lost when switching models. The revert is now committed after the agent switch and before the model switch.
• Fixed the Working state disappearing while reads joined a read group.
• Fixed spacing between errors and grouped updates in the session timeline.
• Fixed side panel tab clipping and alignment, and kept the phone titlebar clear of the iOS status bar.
• Fixed desktop update manifests reusing the first file's sha512 for every file.

𝗣𝗿𝗼𝘃𝗶𝗱𝗲𝗿𝘀
Added
• Added native Vercel AI Gateway routing. @ai-sdk/gateway models now run on OpenCode's own runtime instead of the AI SDK package.
• Added reasoning variants for GitLab Duo Claude and GPT/Codex models, and updated gitlab-ai-provider to 6.19.0.

Changed
• Changed sign in with ChatGPT to use a fixed model list instead of syncing with OpenAI's /models API, as a temporary workaround for OpenAI bugs. The list adds the gpt-6 luna/sol and gpt-6.1-sol models.
• Renamed the legacy OpenAI OAuth login methods to "Codex browser (legacy)" and "Codex device code (legacy)".
• Changed unversioned official @ai-sdk/* provider packages to install the ai-v6 dist-tag, because those packages now publish AI SDK v7 under latest.
• Consolidated local model discovery for vLLM, LM Studio, and Ollama into one shared implementation.

Fixed
• Fixed Azure catalog models that use the completions API being sent to the Responses route. They now use chat completions.
• Fixed non-text models (for example, image-only models) appearing in the catalog and being chosen as the default model.
• Fixed unread Console config responses (404s and errors) staying open until garbage collection.

𝗔𝗴𝗲𝗻𝘁
• Changed the explore subagent to allow shell commands, while its prompt now requires commands to be read-only and forbids creating or changing files.
• Improved the bash/POSIX shell permission scanner. It now uses bash, zsh, or POSIX rules based on your shell and is tested against real shells.
• Improved PowerShell permission scanning, including abbreviated -Path/-LiteralPath parameters, -- end-of-parameters, and braced ${HOME}/${PWD} variables.
• Fixed subagent results joining separate text blocks together. They are now separated by blank lines.
• Fixed the instruction-file walk on Windows going past the project root when the drive letter case differs (c:\ vs C:\).

𝗟𝗟𝗠
• Added Vercel AI Gateway chat, messages, and responses routes. They keep gateway response metadata and apply OpenRouter-style prompt caching: automatic for Anthropic, Qwen-specific for Qwen, none for others.
• Fixed changes to reasoning effort not being sent on the Vertex Claude route.
• Changed the Anthropic Messages and OpenAI Responses stream parsers to keep unknown event fields instead of dropping them.

𝗠𝗖𝗣
• Fixed the MCP OAuth callback page showing success before the token exchange finished. Failed exchanges now show an error page, and duplicate callbacks are rejected.

𝗗𝗮𝘁𝗮
• Added a hover ripple on the stats pattern and highlighted bar dots, and aligned the chart's dot grid with its bars.

𝗨𝗜
• Changed bold text in Markdown to a slightly lighter weight (670).

No noticeable bundle change

Compare: https://t.co/q4aGYlAhla

[OpenCode Changelog @OpenCodeLog]

𝙊𝙥𝙚𝙣𝘾𝙤𝙙𝙚 v2.0.23 released. TL;DR:
Native Venice, Cohere, Google Interactions, and Bedrock Mantle Anthropic routes • App queue and steer behavior now matches the TUI, plus a header menu for running work • background service restarts and upgrades are more reliable • ACP gets spec-aligned permissions and compaction updates

𝗔𝗽𝗽
Added
• Added a menu in the session header that lists running subagents and shell commands. Each entry can be interrupted or killed from the menu.
• Added the model variant to message metadata, shown as model (variant).
• Restored Git initialization for projects without version control, using a new server endpoint that supports git and hg.

Changed
• Changed composer inbox, steer, queue, and revert behavior to match the TUI. You can now move pending prompts to the queue or delete them, see queued compaction, and get guidance when a revert blocks queue edits.
• Moved review controls, including the sidebar toggle and Open in app, into the review and file panels.
• Rebuilt the built-in terminal, review, files, browser, SSH, WSL, updater, and pairing features on a typed extension SDK with explicit lifecycle states. A disabled, failed, or restarting feature now shows as unavailable instead of breaking the window.
• Moved What's New into the updater. It shows desktop highlights since the last version you saw, adds a Don't show these in the future option, and tries again on the next start if fetching the changelog fails.
• Improved desktop startup by preloading stored state and extension enable state when the window opens, instead of waiting on an IPC round trip. Renamed extensions keep their enabled or disabled setting.

Fixed
• Fixed the Working indicator disappearing during turns that only produce reasoning.
• Fixed side panel tabs being lost when a session moves to another directory.
• Fixed markdown images with Windows paths not loading.
• Fixed the web app's QR scanner failing to start in browsers without BarcodeDetector, such as Safari and desktop Chrome on Windows and Linux.
• Fixed stale branch info in session details, duplicated update-check failure toasts, and leftover browser pane errors.

𝗧𝗨𝗜
• Added line ranges after file paths in Read tool rows, for example path:10-50.
• Fixed the transcript blinking and remounting as older history pages load. This was most visible with Low verbosity.
• Changed terminal panes to depend on whether the connected server supports persistent PTYs, instead of on the local platform.
• Fixed question form highlights rendering off the raised surface.

𝗣𝗿𝗼𝘃𝗶𝗱𝗲𝗿𝘀
• Added a native Venice provider with streaming tools, reasoning effort and toggle variants, encrypted reasoning and Gemini thought-signature replay, and cache-write usage. It replaces the AI SDK Venice plugin.
• Added a native Cohere chat provider and mapped @ai-sdk/cohere and OpenAI-compatible Cohere configs to it.
• Added the Google Interactions API as a native Gemini route. It supports streamed function calls, thought signatures, multimodal input, and optional server-side continuation.
• Added Anthropic Messages on Amazon Bedrock Mantle, with prompt caching. Mid-conversation effort updates are limited to Opus 5.1 and later.
• Fixed configs whose top-level model uses a retired provider ID, such as azure-cognitive-services or google-vertex-anthropic. These IDs are now renamed automatically.

𝗟𝗟𝗠
• Fixed placement of Anthropic mid-conversation system updates. They are held and sent right before the next assistant turn, falling back to wrapped user text when Anthropic would not accept a native system message there.
• Fixed Gemini, Mistral, and Cohere so multiple system parts are sent separately instead of being joined into one.
• Improved streaming performance by parsing partial tool-input JSON only when needed.

𝗔𝗴𝗲𝗻𝘁
• Fixed compaction ignoring the model set on the compaction agent. Summaries now use that model and its context limits.
• Added support for disable-model-invocation in skill frontmatter, which hides a skill from the model's list. opencode/autoinvoke takes priority when both are set.
• Improved compaction errors blocked by the provider's content filter to include the category and explanation.
• Improved request preparation performance by reusing unchanged messages.

𝗖𝗟𝗜
Added
• Added opencode upgrade support for the Homebrew Core opencode formula, checking versions against https://t.co/QubrrPDjP1.

Fixed
• Fixed curl-based upgrades on Windows picking up the WSL bash. Upgrades now use Git Bash, which can be overridden with OPENCODE_GIT_BASH_PATH.
• Fixed managed service startup failing on temporary port conflicts. It now retries binding for up to 15 seconds.
• Fixed background service startup hiding the real error behind a generic timeout. Restarts now also wait for the previous service to shut down.
• Fixed reconnecting replacing a running service when only the health protocol differed.
• Fixed a server restart failing when persistent terminals could not be handed off. Terminals are now best-effort and shut down cleanly instead.
• Fixed console windows flashing for background processes on Windows.
• Fixed pairing QR code indentation on Windows.

𝗔𝗖𝗣
• Changed compaction to be reported through standard ACP session updates.
• Changed permission requests to follow the ACP tool-call spec. Requests answered in another client now settle, and request failures have typed errors.
• Fixed turns ending as interrupted when a question cannot be shown in the client. The model now gets a message telling it to continue without an answer.
• Fixed remote image links being sent as inline content instead of references, and sessions staying attached after a failed setup.

𝗦𝗲𝗿𝘃𝗲𝗿
• Changed requests for a missing location directory to return a typed 404 instead of a generic error.
• Added a persistent-PTY capability flag to server info so clients can tell whether terminals are supported.

𝗣𝗹𝘂𝗴𝗶𝗻
• Added custom search and footer actions with keybindings to the TUI plugin select dialog.
• Fixed plugin keymap layers so they can be registered from setup, including after an await. Layers are removed when the plugin deactivates.

𝗠𝗖𝗣
• Added retries for transient MCP connection and listing failures: 408, 429, 5xx except 501, and network errors. Retries stop at the startup timeout.

𝗖𝗼𝗿𝗲
• Fixed formatter config so it merges across config files per formatter instead of the last file replacing all earlier ones. Setting true resets to the built-ins, and false disables formatting.

No noticeable bundle change

Compare: https://t.co/gM6z6fgRFv

[OpenCode Changelog @OpenCodeLog]

𝙊𝙥𝙚𝙣𝘾𝙤𝙙𝙚 v2.0.22 released. TL;DR:
Desktop features now run as built-in extensions, OpenCode finds Azure deployments on its own, provider HTTP timeouts default to five minutes, and ACP adds form elicitation, extra workspace roots, and compaction markers.

𝗔𝗽𝗽
Added
• Added a Last turn changes mode to the review panel. For Git projects it shows the session's last-turn diff and keeps that choice after a reload.

Changed
• Moved terminal, review, file browser, browser pane, SSH, WSL, updater, usage, and session summary into built-in GUI extensions running on a new desktop extension host.
• Increased the weight of bold markdown text in session messages.

Fixed
• Restored behavior that broke in the extension move, covering the composer, mobile session layout, WSL settings, browser pane restore, and saved review state.
• Fixed the embedded browser surface drifting out of alignment during layout transitions.
• Fixed sticky timeline headers getting caught in the title fade.

𝗣𝗿𝗼𝘃𝗶𝗱𝗲𝗿𝘀
Added
• Added Azure deployment discovery. OpenCode lists your resource's deployments and shows them instead of the whole catalog, with limits, costs, and capabilities taken from the matching catalog models. It uses the management API with Azure CLI auth and the legacy inventory with API keys.
• Added headerTimeout and chunkTimeout provider settings. Both default to 5 minutes and false disables them. A timed-out request is retried at most 3 times, so a dead provider can't hold a step for most of an hour.
• Added prompt caching for DigitalOcean inference, with cache read and write usage accounting.
• Enabled prompt caching for Qwen models on Alibaba chat.

Fixed
• Fixed context-overflow detection for Together, DeepInfra, Novita, and https://t.co/1vRYC3CvdP rejections, so they go through overflow handling instead of failing as generic errors.
• Fixed xAI invalid keys and https://t.co/1vRYC3CvdP permission, balance, and plan rejections so they are reported as auth or quota errors, and stopped retrying https://t.co/1vRYC3CvdP Responses model and permission rejections.
• Fixed partial capabilities in provider model config: fields you leave unset now come from the base model.
• Fixed content-filter failures to include the provider's category and explanation (Anthropic) instead of a bare blocked message.

𝗔𝗖𝗣
Added
• Added additional workspace directories for ACP sessions. They are granted as external_directory permissions that persist on the server session.
• Added answering question and web search provider forms through ACP form elicitation. Forms with fields that look like credentials are skipped.
• Added compaction started, completed, and failed markers for ACP clients, both live and when a session is replayed.
• Added following model and agent changes made to the same session from other clients.

Fixed
• Fixed token usage reporting to cover the whole turn, not just the last step.
• Fixed native file tools to report file locations, and stopped echoing edited files back to the client.
• Fixed unreadable resource links to fall back to a reference instead of failing the prompt.
• Fixed available commands being sent before the session response, and invalid requests now return invalid-params errors.

Changed
• Changed the ACP process to exit when its backing server dies.

𝗟𝗟𝗠
Fixed
• Fixed connection drops in the middle of a stream being reported as decode errors. They now show as transport errors: Connection lost while reading the response.
• Fixed tool history so tool calls left unanswered at the end get placeholder results, and mid-conversation system updates wait until pending tool results arrive.
• Fixed Groq and Vertex Anthropic routes reusing OpenAI and Anthropic provider metadata keys.

Changed
• Changed Bedrock tool-result images to stay inline only for Claude and Nova. For other model families they are moved next to the tool results.
• Changed capability defaults to cover future versions: per-turn effort updates for GPT-6 and later, system updates and per-turn effort for newer Claude versions, and tool streaming for GLM-4.6 and later.

𝗠𝗖𝗣
• Improved MCP error messages. They now include HTTP status and network error codes, the exit code and last stderr output of stdio servers, the reason a connection closed, and a pointer to reconnect or sign in from /mcps.
• Fixed legacy streamable HTTP MCP sessions not being terminated when the connection closes.

𝗣𝗹𝘂𝗴𝗶𝗻
• Added session compaction and session removal to the plugin session API.
• Added parentID to session creation in plugins and the HTTP API, which creates a linked child session at the parent's location.
• Fixed session updates from plugins dropping metadata.

𝗔𝗴𝗲𝗻𝘁
• Fixed instruction discovery picking up directories named AGENTS.md.
• Fixed an AGENTS.md that was read directly also being loaded again as an automatic instruction.

𝗖𝗟𝗜
• Changed update checks to repeat every 10 minutes in long-running sessions, taking turns with /update and manual installs.
• Added a lock so separate OpenCode processes can't install upgrades at the same time.

𝗥𝗲𝗹𝗲𝗮𝘀𝗲
• Removed the x86_64-darwin Nix target and fixed flake evaluation on nixpkgs 26.11.

No noticeable bundle change

Compare: https://t.co/Uxivid4wut

[OpenCode Changelog @OpenCodeLog]

𝙊𝙥𝙚𝙣𝘾𝙤𝙙𝙚 v2.0.21 released. TL;DR:
The desktop browser lets you comment on page elements, ACP now uses the server's default model and agent and picks up catalog changes live, non-interactive runs keep going when the agent asks a question, and prompt caching works better on OpenRouter and Cloudflare AI Gateway.

𝗔𝗽𝗽
Added
• Added element comments in the desktop in-app browser. Turn on inspect mode, click an element and write a comment. The agent receives the element's role, accessible name, text, selector and browser ref. Comments come back into the composer after a revert or fork.
• Added clickable session IDs in markdown. Session IDs mentioned in a transcript now open as a session tab. A toast appears if the session is missing or archived on the current server.
• Added grouping of adjacent file reads into one collapsible timeline row.
• Changed the open "Used" tool group header to stay pinned while you scroll through its contents.

Fixed
• Fixed agent-response and error system notifications firing for sessions that have no open tab. They now follow the same rule as sounds.
• Fixed new-session project selection when the current directory doesn't match a known worktree path. The app now falls back to the resolved project ID.
• Updated the ChatGPT usage-limit wording and links so they no longer promise a reset time.

𝗧𝗨𝗜
• Tightened spacing in expanded instruction groups.
• Updated OpenTUI to 0.5.14.

𝗔𝗴𝗲𝗻𝘁
• Changed browser tools to be hidden by default. The agent only gets them while a desktop browser is attached to the session.
• Added element targeting to the browser evaluate tool. Scripts can run against an element ref from a snapshot or from a user's browser comment.
• Fixed the read tool re-adding AGENTS.md files from the project root or its parent directories, which initial instructions already include.
• Changed question cancellations that include a message: the model now gets the message as tool feedback and continues, instead of the step ending.

𝗖𝗟𝗜
• Changed opencode run so a question from the agent is cancelled with an explanation and the model continues on stated assumptions. Previously the run was marked failed. V1 compatibility mode keeps the old behavior.

𝗔𝗖𝗣
• Changed new ACP sessions to use the server's default model and agent instead of fixing them at creation time.
• Added live catalog refresh. Model, agent and command changes now push updated config options and slash commands to connected ACP clients.
• Fixed model, mode and effort selection against a stale catalog. ACP now reloads the catalog and retries before rejecting.

𝗟𝗟𝗠
• Added prompt-cache breakpoints for OpenRouter: automatic caching for Anthropic models and system plus conversation-tail breakpoints for Qwen. Other upstreams, such as Gemini, get no breakpoints because extra ones would add cache writes.
• Fixed OpenAI Chat-compatible cache_control placement. Breakpoints now go on text content parts of assistant and tool messages instead of on the message itself.
• Added context-overflow detection for Cloudflare Workers AI 413 errors and Amazon Nova on Bedrock input-length errors, so compaction and recovery can kick in.

𝗣𝗿𝗼𝘃𝗶𝗱𝗲𝗿𝘀
• Changed Cloudflare AI Gateway to route Claude and OpenAI models through the gateway's native Anthropic and OpenAI passthrough endpoints. This avoids request shapes the REST API rejects, such as system prompt blocks and minimal reasoning effort.
• Fixed GitHub Copilot Responses dropping settings based on model-name guesses. Reasoning effort and summary, temperature, top_p and service tier are now passed through as configured, and system prompts are sent with the system role.

𝗖𝗼𝗿𝗲
• Added x-opencode-session-id and x-opencode-parent-session-id headers to model requests, next to the existing session headers, so gateways and proxies can link requests to sessions.

𝗦𝗲𝗿𝘃𝗲𝗿
• Added an optional message to the cancel-form endpoint, so clients can tell the asker why a form wasn't answered. The change is reflected in OpenAPI and the generated clients.

𝗗𝗮𝘁𝗮
• Fixed the stats site's document background so it matches the page theme.

No noticeable bundle change

Compare: https://t.co/9Z58ixMD28

[OpenCode Changelog @OpenCodeLog]

𝙊𝙥𝙚𝙣𝘾𝙤𝙙𝙚 v1.18.34 released. TL;DR:
macOS CLI binaries are now Developer ID signed, LLM requests carry namespaced session headers, the Go page adds Go Plus plans, and OpenCode Data gets daily model rankings.

𝗧𝗨𝗜
• Fixed plugin names in the /status dialog on Windows. File-based plugin paths are now split using the platform's path separator instead of always "/".

𝗥𝗲𝗹𝗲𝗮𝘀𝗲
• Added Developer ID signing for the macOS CLI builds (arm64, x64, x64-baseline) with hardened runtime and entitlements. The signed zips replace the unsigned release assets.
• Fixed local macOS compiles by re-signing them ad hoc. Embedding the bundle breaks the linker's signature, and macOS 27+ kills binaries with invalid pages.

𝗣𝗿𝗼𝘃𝗶𝗱𝗲𝗿𝘀
• Added x-opencode-session-id and x-opencode-parent-session-id headers to model requests for every provider, in both the legacy and v2 session runners. The existing affinity and session headers are still sent.

𝗖𝗼𝗻𝘀𝗼𝗹𝗲
Added
• Added Go Plus ($40/month) to the Go page, with a side-by-side chart of Go and Go Plus limits per model.
• Added a warning for referral-link visitors that the referral program has ended and links no longer earn credit.

Changed
• Changed the Go page hero, plan cards, and model limits list, and removed several older models from the list.
• Changed OpenCode Black so it cannot renew: renewals made in the billing portal are automatically set to cancel at period end, and the workspace billing page no longer offers "Manage Subscription".

Fixed
• Fixed Go page layout and the limits chart on mobile screens.

𝗗𝗮𝘁𝗮
• Added a daily view to model rankings next to the weekly one. Rank changes are hidden in the daily view so partial days don't show misleading movement.
• Fixed usage attribution by resolving model labs from the model catalog. Duplicate "unknown" rows are dropped, and per-model country data falls back to them when needed.
• Fixed chart tooltips so they stay readable.

𝗭𝗲𝗻
• Updated the Zen docs with GPT 6.1 Sol endpoint and pricing (corrected cached-input rates) and the Jev API data-retention policy.

No noticeable bundle change

Compare: https://t.co/8FjLzibNGX

[OpenCode Changelog @OpenCodeLog]

𝙊𝙥𝙚𝙣𝘾𝙤𝙙𝙚 v2.0.20 released. TL;DR:
ChatGPT plan token sharing for OpenAI, auth export/import plus an opt-out for the background service in the CLI, non-interactive runs that keep going after a permission is rejected, and provider errors that show the provider's actual explanation.

𝗔𝗽𝗽
• Added a one-time welcome dialog after connecting OpenAI through ChatGPT token sharing, with a link to ChatGPT usage settings.
• Added a ChatGPT usage-limit dialog that appears when a session step hits the plan limit. It shows at most once every 24 hours.
• Added a "Using ChatGPT plan" footer with a Manage usage link to the model selector when OpenAI is connected via OAuth.
• Changed the session "moved to" location notice to render as a timeline divider, so it no longer gets folded into grouped context rows.
• Improved diff readability with calmer word-level highlights and less prominent collapsed-row separators in dark mode.

𝗧𝗨𝗜
• Added a recently closed tabs list to the new session menu. Reopening a tab removes only that entry, and the closed-tab history grows from 10 to 25.
• Added "Sign in required" markers in the integrations dialog. Selecting one opens the SSO URL or restarts sign-in.
• Changed failed activity groups to keep the normal expand/collapse icon instead of showing a ✗.

𝗣𝗿𝗼𝘃𝗶𝗱𝗲𝗿𝘀
Added
• Added a separate "Sign in with ChatGPT" OAuth method for OpenAI that uses ChatGPT plan token sharing. It uses PKCE and verifies the ID token, and fails clearly if the user didn't grant token sharing.
• Added per-account model discovery for ChatGPT token sharing. The model list refreshes every 15 minutes and is cached, with a fallback list of GPT-5.5, GPT-5.6 and GPT-6 Astra models.
• Added OpenCode Console connection status: expired SSO or revoked sessions now mark the connection as needing sign-in, and generic 401/403 inference errors are replaced with steps to fix it.

Changed
• Changed ChatGPT-plan models to show zero cost, use summary compaction, and hide pro reasoning modes that token sharing doesn't support.
• Changed token-sharing failures (usage limit, not eligible, unsupported capability, invalid user) to stop retrying and show clear messages.
• Changed Cloudflare Workers AI to turn thinking off through chat-template flags, because most models ignore reasoning_effort "none".

𝗖𝗟𝗜
• Added opencode auth export, which prints stored credentials as JSON for one integration or all of them and warns when the output goes to a terminal.
• Added opencode auth import, which reads from a file or stdin, skips credentials that already exist, and keeps the current account selections on the destination.
• Added opencode service set disabled true, which stops the shared background service and makes CLI commands start a private server instead. Pairing is blocked while it is disabled.
• Changed opencode run: when a permission can't be approved, it is rejected with feedback so the model continues without that action, instead of stopping the run and exiting with code 1.
• Fixed opencode run so permission asks and questions from subagent child sessions are answered too, while sessions belonging to other clients on a shared server are left alone.

𝗟𝗟𝗠
• Added explicit prompt caching on Alibaba, Cloudflare AI Gateway, Meta, MiniMax, Moonshot and https://t.co/1vRYC3CvdP coding message routes.
• Changed Bedrock Claude 5.1+ to drop mismatched thinking blocks by default, so sessions keep working after the system prompt changes.
• Improved provider error messages: common error body formats are now recognized, including AWS and RFC 9457 problem details. Otherwise the raw body is shown, trimmed, and HTML error pages are skipped.
• Fixed Bedrock redacted reasoning so it is finished at the end of each block.
• Fixed Mistral thinking metadata being streamed before the block was complete.

𝗔𝗴𝗲𝗻𝘁
• Changed permission rejections that include feedback to apply to the whole batch of parallel asks, so the model gets the feedback and continues instead of ending the step.
• Added the provider's raw response body to session errors, so clients can show the full failure details.

𝗦𝗲𝗿𝘃𝗲𝗿
• Added endpoints to list and create credentials, with an activate flag and a conflict error when the ID already exists. Credentials created with activate set to false don't replace the current selection.

𝗦𝘁𝗼𝗿𝗮𝗴𝗲
• Fixed database file permissions: the SQLite file and its -wal and -shm files are now owner-only (0600) on POSIX systems.

𝗣𝗹𝘂𝗴𝗶𝗻
• Added a plugin API for reporting or clearing a connection's status, such as needing sign-in, with an optional sign-in URL shown in the TUI and App.

No noticeable bundle change

Compare: https://t.co/YO0BfdEWuS

[OpenCode Changelog @OpenCodeLog]

𝙊𝙥𝙚𝙣𝘾𝙤𝙙𝙚 v2.0.19 released. TL;DR:
Compaction is rebuilt to shrink and retry instead of failing, output-token limits now fit the context window, prompt-cache reuse improves across sessions and subagents, and the TUI diff viewer gains a Last turn view.

𝗧𝗨𝗜
Added
• Added a Last turn source to /diff that shows the files the session changed in its latest turn and refreshes when each turn finishes. You can make it the default with diffs.source: "turn". Outside a session it falls back to branch.

Fixed
• Fixed --prompt auto-submit firing before the agent, model and catalog were ready.
• Fixed duplicate entries in the open-project picker when older project records point to the same checkout.
• Fixed shell tool rows so a command still running in the background no longer looks like an interrupted one.
• Fixed the TUI jumping to model selection after connecting an MCP integration.
• Fixed long /btw questions so they collapse to one truncated line.
• Fixed the OpenCode web search provider label capitalization.

𝗔𝗴𝗲𝗻𝘁
Changed
• Rebuilt session compaction. When a provider says a request is too long, it now retries at 70%, 50% and then 35% of the rejected size. If the request is still too big, it sends history as trimmed text, dropping media first and then the oldest exchanges. Native OpenAI compaction retries smaller instead of switching to a summary.
• Changed the default compaction buffer from a fixed 20k tokens to 10% of the model's limit, with a 16k minimum on larger windows. With auto compaction off, only manual /compact runs, including after a too-long rejection.
• Changed the default max output tokens for main and compaction requests to fit the room left in the context window. It is capped at 256k, uses 32k when the model's limit is unknown, and is limited to 32k for summaries.
• Reordered system instructions from most to least shared, putting date and environment last, and removed the session ID from the environment block. This keeps the reused prompt-cache prefix the same across sessions.

Added
• Added AGENT=1, OPENCODE=1, AI_AGENT=opencode and OPENCODE_SESSION_ID to the environment of shell tool commands, so scripts can tell they are running under an agent.
• Added a warning log when a provider's too-long rejection triggers compaction.

𝗖𝗟𝗜
Added
• Added support for passing an unused ID to --session in the TUI and opencode run. OpenCode now creates a session with that ID instead of failing with "Session not found".
• Added a grouped, searchable picker to opencode auth login, with MCP, Popular and Services groups and markers for connected integrations.
• Changed opencode mcp auth so the server name is optional and an interactive picker lists OAuth-capable servers. It flags servers with expired credentials, and re-authenticating replaces the old credential instead of adding another.

Fixed
• Fixed Ctrl+C during auth login so it cancels the pending OAuth or command attempt instead of exiting and leaving it running.
• Fixed opencode run showing a misleading interruption error after a declined permission or dismissed question. It now exits with code 1.
• Changed command-based auth to print the command's output line by line instead of inside a spinner.

𝗣𝗿𝗼𝘃𝗶𝗱𝗲𝗿𝘀
Changed
• Changed session and affinity headers, including the ChatGPT session-id and GitHub Copilot interaction ID, so child sessions send their parent's ID and forks send the source session's ID. This lets subagents share the parent's provider cache.
• Changed OpenAI context and compaction requests to omit the output-token limit, because the ChatGPT backend rejects it and OpenAI counts it against rate limits.
• Changed xAI Responses variants to request reasoning summaries and encrypted reasoning.
• Changed Anthropic-compatible providers to use their own route so they get Anthropic-style cache hints. xAI routes also get distinct IDs.

Fixed
• Fixed Gemini parallel tool calls over its OpenAI-compatible endpoint by keeping and replaying thought signatures.
• Fixed invalid Google API keys being retried; they are now reported as authentication errors.
• Fixed Cloudflare AI Gateway and Workers AI so configured account and gateway IDs take priority, with CLOUDFLARE_ACCOUNT_ID and CLOUDFLARE_GATEWAY_ID used only as fallbacks.
• Fixed one-off generation calls so they carry session attribution, which gateways require.

𝗟𝗟𝗠
Added
• Added ElevenLabs Scribe transcription with word timestamps and diarized speaker turns.
• Added retries with backoff and jitter for transient failures when checking queued media jobs. Starting and cancelling a job are never retried.
• Added per-answer confidence to evaluation results.

Fixed
• Fixed aborted calls so they reject with signal.reason, like fetch, instead of ending quietly.
• Fixed failed video jobs so they report the provider's error type, such as authentication, rate limit or invalid request, instead of a generic internal error.
• Fixed cut-off or blocked Gemini speech and transcription results so they are reported instead of dropped.
• Fixed OpenAI and Deepgram speech results reporting a different audio format than the one actually requested.

𝗖𝗼𝗿𝗲
• Fixed repository hosts containing relative path segments so they are rejected before being used as cache directories.

𝗗𝗼𝗰𝘀
• Added Go Plus plan documentation and synced the V2 Go model list.
• Listed LongCat 2.5 Preview Free among the free Console models and added the Jev data-retention policy to the Zen docs.

No noticeable bundle change

Compare: https://t.co/DjdLCL2Ewu

[OpenCode Changelog @OpenCodeLog]

𝙊𝙥𝙚𝙣𝘾𝙤𝙙𝙚 v1.18.33 released. TL;DR:
GPT-6 Sol and Luna now work with Codex sign-in, Cloudflare AI Gateway respects timeout settings, browser launches only accept http(s) URLs, and debug config output hides secrets.

𝗧𝗨𝗜
• Changed clickable links, Open docs, and retry-dialog actions to go through a shared browser opener that refuses anything other than http and https URLs.

𝗣𝗿𝗼𝘃𝗶𝗱𝗲𝗿𝘀
Added
• Added gpt-6-sol and gpt-6-luna to the models allowed when signing in with ChatGPT/Codex OAuth.

Fixed
• Fixed Cloudflare AI Gateway models ignoring timeout, headerTimeout, and chunkTimeout (SSE idle). Gateway and Workers AI requests now go through the same timeout-aware fetch as other providers.
• Changed Gemini thinking defaults to use a list of older models instead of checking for gemini-3. Newer Gemini models now get thinkingLevel high by default, and OpenRouter Gemini models get high reasoning effort, while Gemini 1.x and 2.x keep the older behavior.
• Fixed Gemma 4 reasoning variants so they only offer minimal (thinking off) and high (thinking on).
• Tightened Gemini 2.5 model detection so thinking budgets and variants no longer match any ID that merely contains 2.5.
• Updated gitlab-ai-provider to 6.18.0.

𝗠𝗖𝗣
• Fixed MCP OAuth browser launches on Windows and WSL, where the launcher can exit before OpenCode checks it. A failed launch is now reported instead of silently hanging.
• Added a check that rejects MCP authorization URLs using any scheme other than http or https, with an error naming the server.

𝗖𝗟𝗜
• Fixed opencode debug config printing credentials. API keys, tokens, secrets, passwords, header values, and URLs carrying credentials or secret query parameters are now shown as ***. The config used at runtime is unchanged.
• Changed opencode web, account login, and the DigitalOcean and Snowflake Cortex OAuth flows to open the browser only for http and https URLs.

𝗖𝗼𝗻𝘀𝗼𝗹𝗲
Changed
• Changed legacy Console sign-in and workspace access to require a Black subscription. Other accounts are redirected to the new Console, and sign-in no longer creates new accounts or default workspaces.
• Moved Go subscriptions to the new Console. Legacy Go checkout now fails, and the Go workspace page redirects to /console/go.

Added
• Added GPT 6 Luna and the limited-time free models Space Bunny Free and LongCat 2.5 Preview Free to Go pages. The limits graph shows unlimited models as ∞.
• Made DeepSeek V4.1 Flash's higher Go allowance permanent and removed the limited-time 4x promo.

𝗗𝗮𝘁𝗮
• Fixed the model comparison radar showing missing benchmarks as zero. Reasoning and tool-use axes now fall back to capability support (50/100 if supported, 0 if not), show fallbacks as hollow points, and explain each score in hover tooltips.
• Fixed Hy4 preview traffic being counted under an unknown provider instead of Tencent.
• Added Muse Spark Contributor pricing entries without letting them skew benchmark normalization, and grouped Space Bunny under stealth-model stats.

𝗗𝗼𝗰𝘀
• Documented Claude Opus 5.5, GPT 6 Sol, GPT 6 Luna, and Qwen3.8 Max in the Zen docs, and updated the Go model pages.

No noticeable bundle change

Compare: https://t.co/HV8zZYA84X

[OpenCode Changelog @OpenCodeLog]

𝙊𝙥𝙚����𝘾𝙤𝙙𝙚 v2.0.18 released. TL;DR:
A small hardening release: TUI, CLI, and MCP OAuth only open http/https URLs now, and sessions with older compaction checkpoints that contain images or files load again.

𝗧𝗨𝗜
• Changed clickable links, OAuth authorization prompts, and external-link form fields to open only http and https URLs. Other schemes such as file:, javascript:, and ms-msdt:, plus UNC paths, are refused. Where a prompt has an error path, it tells you to copy the URL and continue manually.
• Kept "Open in system file manager" for the working directory on a separate path-opening route, so it still works under the new URL rules.

𝗔𝗴𝗲𝗻𝘁
• Fixed loading of compaction checkpoints written before 2.0.15 that contain image or file attachments. Old checkpoints stored media in a different format, which now fails to decode. They are upgraded on read, so older sessions can be restored and continued.

𝗠𝗖𝗣
• Changed MCP OAuth to reject authorization URLs that are not http or https. You get an error naming the server instead of a handoff to an arbitrary system URL handler.

𝗖𝗟𝗜
• Changed browser opening in CLI prompts to use the same http/https-only check as the TUI and core, so all three behave the same way.

No noticeable bundle change

Compare: https://t.co/gNdPwoaBgt

[OpenCode Changelog @OpenCodeLog]

𝙊𝙥𝙚𝙣𝘾𝙤𝙙𝙚 v2.0.17 released. TL;DR:
Pairing now uses one-time connect links instead of shared passwords, the TUI gets transcript verbosity levels and queued-prompt undo, Console can push hosted MCP servers, and thinking budgets now fit inside each model's output limit across more providers.

𝗧𝗨𝗜
Added
• Added a session.verbosity setting with low, medium, and high levels, plus a cycle keybind. Low collapses each run of tools and thoughts into a summary like "3 commands, 1 edit, 2 reads". High opens exploration and instruction groups.
• Added undo for queued prompts (ctrl+u), which pulls a queued prompt back into the input and keeps its file, agent, and paste references.

Fixed
• Fixed large added-file diffs by virtualizing them so they no longer mount every line at once.
• Fixed crashes when the storage file watcher throws, for example ENOSPC from running out of inotify watches, both at startup and later.
• Fixed missing-directory recovery so it opens the workspace picker and actually moves the session, including into a new worktree.
• Changed failed activity groups to show a plain ✗ marker.

𝗔𝗽𝗽
Added
• Added provider account switching in Settings, so you can add, switch between, and remove multiple credentials for one provider.
• Added undo for queued prompts in the composer's queue panel.
• Made the bottom navigation setting available in production mobile builds.

Changed
• Replaced password-based server pairing with one-time links: scanned or opened links are exchanged for a session token.
• Grouped nested subagent tabs in the titlebar and made the session header show the full session path.

Fixed
• Fixed the desktop browser pane disappearing when floating content was drawn over it.
• Fixed inconsistent project icons and names when several projects share an ID or a session sits in a sandbox.

𝗦𝗲𝗿𝘃𝗲𝗿
• Added pairing endpoints that issue random single-use codes that expire after 5 minutes. Redeeming one gives a browser an HttpOnly session cookie scoped per port, or gives an API client a token that works in place of the password.
• Made pairing sessions last 30 days and signed them with a key derived from the server password, so rotating the password revokes every session.

𝗖𝗟𝗜
• Changed opencode pair to print one-time connect links and a QR code instead of printing the username and password, and to show the link expiry.
• Added SSH port-forwarding hints to opencode pair when the service only listens on localhost.

𝗣𝗿𝗼𝘃𝗶𝗱𝗲𝗿𝘀
• Changed GitHub Copilot session titles to use Copilot's free gpt-4o-mini utility model when it is available. If that fails, the normal title path runs instead.
• Added a default of low text verbosity for OpenAI GPT-5.x and GPT-6 models, whether reached directly or through Azure, Bedrock Mantle, or AI gateways, unless the model or variant sets its own value.
• Capped Alibaba thinking-budget variants at 64k.
• Fixed Grok reasoning effort not being sent on Bedrock Converse.
• Fixed provider error messages being lost when an AI SDK stream error arrives as a plain object.

𝗠𝗖𝗣
• Added MCP servers hosted by Console, delivered through the OpenCode Console config. Only remote servers are accepted, a server you configured under the same name wins, and servers can opt in to reusing your Console credential. They reload when your credential changes.

𝗟𝗟𝗠
Added
• Added prompt-cache preservation across reasoning-effort switches on GPT-6 Sol and Luna. Pro mode is excluded.
• Improved the media client API with promise-based file helpers, a single client layer, and a shared request shape for image, speech, transcription, and video.

Fixed
• Fixed thinking budgets on Anthropic, Gemini, Alibaba, OpenRouter, and Claude on Bedrock Converse so they fit under the requested output limit instead of being rejected.
• Fixed Nova 2 at high reasoning effort by no longer sending maxTokens.
• Fixed tool schema roots so they are always declared as objects, and applied the schema rules once per request.
• Fixed several media bugs: Gemini TTS WAV output, AssemblyAI speaker labels, OpenAI transcription stream parsing, fal Kontext aspect-ratio sizing, Runway cancel deleting finished tasks, and Black Forest Labs cost reporting.

𝗔𝗴𝗲𝗻𝘁
• Changed truncated tool and shell output to say which line range is shown out of the total, and restored the "(no output)" placeholder for shell commands.
• Added reporting for shell commands killed by a signal ("Killed by SIGTERM") instead of treating them as plain exits.
• Raised the tool name limit from 64 to 128 characters, so long MCP and plugin tool names register.
• Fixed streamed text and reasoning deltas so they are published before the next block starts, keeping transcript order the same as the model's.
• Expanded the code-mode interpreter with WeakMap, WeakSet, this and arguments bindings, call/apply/bind, and more spec-accurate conversions and error subclassing.

𝗣𝗹𝘂𝗴𝗶𝗻
• Added a TUI plugin API to read the selected model and to list or set its variant.

No noticeable bundle change

Compare: https://t.co/FkDaqdSAdw

[OpenCode Changelog @OpenCodeLog]

𝙊𝙥𝙚𝙣𝘾𝙤𝙙𝙚 v2.0.16 released. TL;DR:
MCP resources are now available as Code Mode tools, the App can sign in to Console and Go with a device code, GitLab gets OAuth and workflow model discovery back, and @opencode/ai gains video, speech, transcription and queued image generation.

𝗔𝗽���
Added
• Added sign-in to OpenCode Console and Go from the provider connect dialog using a device code, with copy-link and reopen-browser options. Provider and model settings were redesigned to match.
• Added worktree and branch details to the desktop home session list. Hold Alt to see them.
• Added a project options menu in settings with edit, rename, reveal in file manager, clear notifications and close.

Changed
• Changed the session summary to open as an overlay, so the timeline no longer slides or shifts when it opens.
• Moved the tab layout option from Experimental into General settings and removed the other experimental toggles.
• Changed desktop update checks to send an identifying User-Agent.

Fixed
• Fixed settings pages so a refresh keeps you on the same settings page.
• Fixed timeline scroll resetting when switching models.
• Fixed the composer losing focus after you attach files.
• Fixed file previews showing stale contents. Files are now reread every time a preview opens.
• Fixed MCP rows that need sign-in: clicking the row now starts sign-in instead of only toggling the server.
• Fixed attachment remove buttons being hidden on touch devices.

𝗧𝗨𝗜
• Improved long-transcript mounting: the loading budget now counts rendered entries, so a collapsed group costs one entry.
• Added memory of expanded groups and exact scroll positions for each session tab.
• Fixed history paging splitting a tool group at a page boundary. Loading continues until the oldest group is complete.
• Fixed failed execute tool calls so clicking them opens the full details dialog.
• Removed a stale MCP failure error message.

𝗔𝗴𝗲𝗻𝘁
• Changed the read tool to cap limit at 2000 lines instead of rejecting larger values, and to cap very long lines on full-file reads too.
• Improved read errors: an out-of-range offset now reports how many lines the file has.
• Fixed read path recovery for filenames that differ only by curly quotes or Unicode normalization, such as accented characters.
• Fixed subagent calls failing when the model sends an empty model or sessionID.
• Fixed OpenAI system prompt selection: the Astra prompt now goes to Astra models instead of every model named gpt-6.
• Improved the Code Mode interpreter: added Object.freeze, seal, create, getPrototypeOf, structuredClone and Uint8Array callback methods; == now follows spec loose equality.

𝗠𝗖𝗣
• Added list_mcp_resources and read_mcp_resource tools, available in Code Mode, with per-server permission checks. Images and PDFs in resources are passed to the model directly.
• Added Code Mode defaults for known servers: Code Mode is turned off for https://t.co/GSXNvH19zl, and PostHog is asked for plain tools instead of its own server-side Code Mode. Servers with codemode set in config are left alone.

𝗣𝗿𝗼𝘃����𝗱𝗲𝗿𝘀
• Added GitLab OAuth login with PKCE and restored duo-workflow-* model discovery for logins stored with /connect.
• Fixed GitHub Copilot routing for Grok, Gemini and MAI Code models, which now go through the Responses API.
• Changed requests to OpenCode Console to include a User-Agent identifying the client.

𝗟𝗟𝗠
Added
• Added video generation to @opencode/ai via queued routes for Google, fal, Runway and xAI.
• Added speech generation with streaming for OpenAI, ElevenLabs, Cartesia, Deepgram and Google.
• Added transcription (inline, streamed and queued) for OpenAI, Deepgram, AssemblyAI and Google, with speaker labels and word timestamps.
• Added queued image routes, OpenAI partial-image streaming, and Black Forest Labs, fal, Replicate and Stability as image providers.

Fixed
• Fixed Gemini tool schemas, which are now sent as parametersJsonSchema. Gemini and Kimi schema cleanup now also applies by model name behind gateways and OpenAI-compatible endpoints, and can be turned off with a none option.
• Fixed Moonshot tool schemas rejecting enums without a type.
• Fixed Vertex streams breaking on keepalives sent as SSE data.
• Fixed PDFs on OpenAI Chat routes, which are now sent as inline file parts instead of being rejected.
• Fixed long-running reasoning turns timing out on WebSocket transport: the idle timeout went from 5 to 30 minutes, and the provider chunkTimeout setting is now respected.

𝗦𝘁𝗼𝗿𝗮𝗴𝗲
• Added a note when migrating V1 sessions that tells the model about renamed or removed tools and changed arguments (bash to shell, task to subagent, filePath to path), so it stops calling the old versions.

𝗖𝗟𝗜
• Fixed debug config output leaking secrets. API keys, tokens, headers and credentialed URLs are now redacted.

𝗦𝗗𝗞
• Improved client error messages to include the server's error detail.

𝗨𝗜
• Added site icons to external Markdown links (loaded through Google's favicon service) and a GitHub mark on GitHub links.
• Completed V2 translations across all supported languages.
• Fixed desktop theme background colors, light-mode contrast and color-name typos.

𝗗𝗮𝘁𝗮
• Fixed stats so Hy4 preview traffic counts toward Tencent instead of an unknown provider.

Bundle +1.8 MB because mostly CLI/TUI JS +2.1 MB and Bundle metadata +1.9 MB

Compare: https://t.co/A8o7ZeDUZ4

[OpenCode Changelog @OpenCodeLog]

𝙊𝙥𝙚𝙣𝘾𝙤𝙙𝙚 v2.0.15 released. TL;DR:
Windows upgrades and uninstalls no longer get blocked by the running binary, API errors now show the server's real message in the TUI, CLI and SDK, opencode pair prints a direct connect link, and projects are sorted by recent activity.

𝗧𝗨𝗜
Added
• Added support for any hue name in custom themes. Only accent, interactive and neutral are required now, and missing hue references fail with a clear validation error.
• Changed the embedded terminal's ANSI palette to follow the active theme and light/dark mode. Blue and magenta come from the closest theme hue, and bright colors are derived from the normal ones.

Fixed
• Fixed toasts and auth/plugin/migration dialogs showing "An unknown error has occurred". They now show the error message returned by the server.
• Fixed transcript copy and export so they fetch the full session from the server instead of only the messages loaded in the view.
• Fixed the per-turn token summary adding up every step. It now shows the latest step's new, cached and total tokens, which matches the current context size.
• Fixed the Open dialog showing duplicate entries for sandboxes and sessions. It now lists one canonical entry per project, in recent-activity order.

𝗔𝗽𝗽
• Fixed the Console sign-in row disappearing from Providers when only a Zen API key is stored, including keys imported from a v1 auth.json. It now stays until you sign in with OAuth.
• Changed the pairing QR scanner to accept full /connect URLs as well as raw pairing codes.
• Fixed the side-panel divider staying visible after the panel closes.

𝗖𝗟𝗜
• Changed opencode pair to print a direct /connect link and encode that link in the QR code. Credentials stay in the URL fragment, so scanning opens the server directly.
• Fixed opencode upgrade and uninstall on Windows for package-manager and curl installs. A running service or upgrade no longer locks the executable, and uninstall retries folders still held by a service that is shutting down.
• Fixed opencode run showing a generic error instead of the server's error message.

𝗔𝗴𝗲𝗻𝘁
• Changed shell tool output to drop "exited with code 0" and "(no output)" filler. Truncated output now ends with a short note saying where the full log was saved.
• Improved the code-mode JS interpreter: added tagged templates and String.raw, match/search/split now accept any pattern value, for...in accepts any assignment target, and duplicate non-strict parameters bind to the last one as in JavaScript.

𝗦𝗲𝗿𝘃𝗲𝗿
• Added session metadata updates via PATCH /api/session/:id. Each update is recorded as a durable session.metadata.updated event, and forks and child sessions inherit the current metadata.
• Added a https://t.co/5RsPhGyLQc field to projects. Project lists are now sorted by it instead of by last metadata edit.

𝗦𝗗𝗞
• Changed the promise client to throw documented API errors as real Error objects with a proper message. The response fields stay on the error, and the error tag becomes its name.
• Fixed the promise client and PTY websocket URLs dropping the path prefix of the base URL, so servers hosted under a subpath now work.

𝗖𝗼𝗿𝗲
• Added project activity tracking. Session activity marks a project as active at most once a minute, and a database migration adds the column used to sort projects.

𝗟𝗟𝗠
• Fixed streams aborting when OpenAI-compatible proxies send a bare data: null SSE frame. These frames are now ignored.
• Fixed AI SDK providers that overlap, repeat or skip text/reasoning start and end markers. Output is normalized so the session always has one open text part and one open reasoning part at a time.
• Added a shared media model for image inputs and image generation across the OpenAI, Google, xAI, https://t.co/1vRYC3CvdP and Meta protocols. Remote media no longer counts toward the inline image size limit.
• Added experimental evaluation support for Vercel AI Gateway and OpenRouter, with checks that answers match the questions asked.

𝗣𝗿𝗼𝘃𝗶𝗱𝗲𝗿𝘀
• Fixed Kimi thinking in multi-turn chats: the stream-only index Kimi rejects is removed when history is sent back, reasoning_content is always included, and the thinking summary is no longer shown twice.
• Updated gitlab-ai-provider to 6.16.0.

𝗔𝗖𝗣
• Added forwarding of provider retry status (attempt, next retry time, error) to ACP clients. The status clears when the next step starts and is included in the response if a prompt is interrupted mid-retry.

𝗣𝗹𝘂𝗴𝗶𝗻
• Fixed installing git-hosted plugins from a subdirectory of a branch.

𝗠𝗖𝗣
• Improved logs for MCP OAuth and credential failures. They now include the error message along with the error type and code.

No noticeable bundle change

Compare: https://t.co/EUL4awyp6E

[OpenCode Changelog @OpenCodeLog]

𝙊𝙥𝙚𝙣𝘾𝙤𝙙𝙚 v2.0.14 released. TL;DR:
A small fix release: the TUI open dialog stops listing worktrees as separate projects, and desktop IPC calls with optional fields no longer fail.

𝗧𝗨𝗜
• Fixed the open dialog listing session worktree directories as separate projects. Sessions that belong to a known project now show up under that project, and only sessions without a project get their own directory entry.

𝗔𝗽𝗽
• Fixed desktop renderer-to-main RPC calls failing when optional fields were left undefined. The main process decodes payloads as JSON, so undefined keys are now removed before sending, the same way JSON.stringify drops them. Binary data is passed through unchanged.

𝗗𝗼𝗰𝘀
• Added Console API reference docs for inference, BYOK, usage, and budgets.

𝗣𝗿𝗼𝘃𝗶𝗱𝗲𝗿𝘀
• Updated the bundled https://t.co/0Tykrz1EhK snapshot, so the offline model catalog is current.

No noticeable bundle change

Compare: https://t.co/dO9g6w4HQm

[OpenCode Changelog @OpenCodeLog]

𝙊𝙥𝙚𝙣𝘾𝙤𝙙𝙚 v2.0.13 released. TL;DR:
OpenCode Console organization policies are now enforced, desktop gets local device pairing and a /btw side-question panel, OpenCode Go and Console sign-in happens in the browser, and the Code Mode interpreter behaves more like real JavaScript.

𝗔𝗽𝗽
Added
• Added local device pairing on desktop: a new Pairing settings page and a Pair device command show a QR code and a copyable /connect link, so another device on the same network can connect to this machine's server.
• Added a Keep screen active setting that stops the display from sleeping while OpenCode is running.
• Added /btw on desktop: it answers a quick side question in its own panel tab, with copy and retry, and the answer is never added to the conversation.
• Added browser sign-in for OpenCode Go and OpenCode Console: the dialog opens the Console, shows a confirmation code, and keeps a small link for connecting with an API key or service account instead.

Changed
• Changed provider settings to tag OAuth-connected providers as Account, and to connect or disconnect Console-managed providers through the Console integration.
• Changed OAuth connect flows to open the browser automatically, show a clear message when authorization expires, offer Try again, and cancel unfinished attempts when the dialog closes.
• Changed new provider connections to show every non-deprecated model they unlock in the model picker.
• Updated Electron to 44.4.3.

𝗧𝗨𝗜
Added
• Added tabs.mode with auto, on, and off. The default, auto, turns session tabs off inside Herdr. The old tabs.enabled key still works and is converted to mode.
• Restored the Getting started card in the sidebar. It appears when no provider is connected, links to /connect, and can be dismissed.
• Added /q as an exit alias in Mini, alongside /exit and /quit.

Changed
• Changed /clear from an alias of /new into its own command, which closes the active session tab and returns to home.
• Changed the /btw dialog to fill up to 60% of the terminal height, scroll with j/k, and page by the visible height.
• Changed the MCP sidebar section to remember whether it is collapsed or expanded.

𝗖𝗼𝗿𝗲
• Added enforcement of organization policies from a connected OpenCode Console workspace. These policies run after all local ones, so they have the final say on provider.use and permission rules, and denials name the organization.
• Changed policy behavior so the last known organization policy stays in effect when the Console is unreachable, while switching workspaces or disconnecting replaces or clears it.

𝗔𝗴𝗲𝗻𝘁
Added
• Added Iterator helpers, Iterator.from, Promise.withResolvers, and Promise.try to the Code Mode interpreter.
• Added the closest matching tool name to unknown-tool errors in Code Mode, and let search accept namespaces that start with tools.

Fixed
• Fixed built-in functions in Code Mode to convert arguments the way JavaScript does, instead of rejecting anything that is not already a number or string.
• Fixed several Code Mode generator and collection bugs: generator arguments are bound when the generator is called, Map/Set forEach sees live changes, and repeated function declarations and delete work correctly.
• Changed the Code Mode instructions to say plainly that catalog tools and search only work inside execute, and that search is synchronous.

𝗣𝗹𝘂𝗴𝗶𝗻
• Fixed session HTTP request hooks so they also run for providers served through the AI SDK route, not only native routes.
• Changed plugin config so repository settings cannot disable the Console plugin or the policy plugin.

𝗣𝗿𝗼𝘃𝗶𝗱𝗲𝗿𝘀
• Fixed Google Vertex tool calling by keeping function call IDs in the conversation history instead of removing them.
• Changed subagent sessions to reuse their parent session's prompt cache key, which improves cache hits across child sessions.

𝗟𝗟𝗠
• Added an experimental evaluation API to @opencode/ai. It answers typed choice, score, and yes/no questions about a piece of text, and works with TypeSafeAI and OpenCode Zen.

𝗖𝗟𝗜
• Improved opencode upgrade errors: failures now show which step failed, the last lines of the installer's error output, the command that ran, and what to try next.

𝗦𝗲𝗿𝘃𝗲𝗿
• Changed the built-in web server to serve the web UI before API authentication, so pairing links to /connect can load, while /api and /openapi.json still require auth.
• Added a method field (key or oauth) to integration credentials in the API.

𝗠𝗖𝗣
• Fixed MCP OAuth login so it no longer forces a consent screen when offline_access is requested.

𝗖𝗼𝗻𝘀𝗼𝗹𝗲
• Removed the $5 first-month OpenCode Go promotion. Go is now $10/month in every language, and checkout no longer applies the 50% first-month coupon.

𝗗𝗼𝗰𝘀
• Added a Policies guide that covers statement matching, precedence, permission rules, and Console-delivered organization policy.

No noticeable bundle change

Compare: https://t.co/iXLyJgNGen

[OpenCode Changelog @OpenCodeLog]

𝙊𝙥𝙚𝙣𝘾𝙤𝙙𝙚 v2.0.12 released. TL;DR:
Files the agent references now open as rich artifact tabs in the App, the agent gets a browser.preview tool, Anthropic thinking-budget variants are capped at 32k again, and plugin tools can now be cancelled.

𝗔𝗽𝗽
Added
• Added rich artifact tabs. Local links and inline file paths in the timeline now open in the side panel, including path:line citations and files outside the workspace. A tab only opens after the file is confirmed to exist.
• Added previews for images, SVG, audio, video, PDF, Markdown, Mermaid, CSV/TSV tables and fonts, with a Preview/Source toggle. Other files show highlighted source. Tables show the first 1,000 rows, and media over 25 MB shows a placeholder instead of loading.
• Added a browser.preview tool to the desktop browser plugin. The agent can use it to show a file it created in the Review pane instead of pasting or describing it.
• Added the option to open HTML artifacts in the desktop browser pane as file:// pages. This only works on the built-in local sidecar, and both page loads and subresource requests outside the session workspace are blocked.

Fixed
• Fixed browser focus requests from background sessions. The Review pane and the matching browser tab are now already selected when you switch back to that session.
• Fixed the Review pane loading forever in projects without VCS. It now shows the empty state.
• Restored spacing in the server status settings view.

𝗧𝗨𝗜
• Added a Copy session ID action to the session tab right-click menu, with a toast confirming the copy.

𝗔𝗴𝗲𝗻𝘁
Added
• Added toLocaleString, Error.isError and Map.getOrInsert to the code-mode sandbox.

Changed
• Improved code-mode tool search so whole-word path matches rank above substring matches (for example, zones matches get_zones ahead of timezones).

Fixed
• Fixed code-mode error locations so line and column point at the code the model submitted, not the internal wrapper.
• Improved "is not a function" errors in code mode to name the full call chain, like native JS engines do.

𝗣𝗿𝗼𝘃𝗶𝗱𝗲𝗿𝘀
• Fixed Anthropic thinking-budget variants so high and max stay under Anthropic's 32k output limit (high is 16,000 and max is 31,999 tokens), instead of growing with the model's advertised output limit. This applies to Anthropic, Claude on Bedrock (Converse and AI SDK paths) and Anthropic models on SAP AI Core.
• Updated the bundled https://t.co/0Tykrz1EhK model catalog snapshot.

𝗣𝗹𝘂𝗴𝗶𝗻
• Fixed cancellation for Promise-based plugin tools. They now receive an AbortSignal in their tool context, and cancelling a tool call aborts the running Promise execution and its progress updates.

𝗖𝗟𝗜
• Fixed fatal startup errors being printed to stdout. They now go to stderr, so the desktop app and service startup can show why the server failed to start.

No noticeable bundle change

Compare: https://t.co/jNvIG9b8aR