OpenCode

持续追踪核心框架、最新模型规格与重要系统接口的更新迭代轨迹。

v1.18.15

v1.18.15

Core Bugfixes Chronological message ordering now stays correct even when imported or legacy message IDs are out of order. Revert and fork actions now use real message chronology instead of message ID ordering. Truncation cleanup now removes stale files by file timestamp more reliably. Repeated compaction now keeps earlier tool-call history in summaries instead of dropping orphaned results. Blob-based attachments now load correctly in the web UI. ( @rexdotsh ) Desktop Improvements Added much broader locale coverage across the desktop app. Export full session transcripts as JSON from the UI. Bug...

v1.18.14

v1.18.14

Core Improvements Simplified xAI login to a single device-code flow that works better in headless and remote environments. Bugfixes Preserved structured mid-stream provider errors so compatible providers can retry failed responses. Retried more transient provider and network errors instead of failing immediately. Counted cache writes in ACP usage totals. Logged remote workspace 5xx response bodies in the host logs to make proxy failures easier to debug. ( @jamesmurdza ) Stopped sending the host directory path to remote workspaces so prompts resolve from the remote project root. ( @jamesmurdza ...

v1.18.13

v1.18.13

TUI Bugfixes GitHub pull request reviews now include the pull request number and URL in context. Desktop Bugfixes Fixed several right-to-left layout issues across tabs, drawers, resizing, and titlebar interactions. Fixed shared right-to-left UI behavior such as directional icons and drawer placement. Sessions without titles now fall back to generated names instead of appearing blank. Moved markdown parsing off the main thread to keep the app more responsive while rendering messages. Improvements Localized more desktop UI copy, including native menus, update dialogs, and help content. Added ear...

[ 重大突破 ] v1.18.12

v1.18.12

Core Bugfixes Fixed Azure GPT-5.5+ completion requests failing when reasoning is enabled. ( @frederiknsgo ) Desktop Bugfixes Reduced composer lag when drafts include large pasted images or attachments. Let project search match any known recent project instead of only the first five. ( @NumerousJLs ) Cleared stale assistant errors from the timeline once the same turn resumes streaming. Skipped legacy config reads against v2 servers to avoid spurious config loading issues. ( @resetsix ) Thank you to 4 community contributors: @resetsix : fix(app): skip legacy config reads for v2 ( #40211 ) @Numer...

[ 重大突破 ] v1.18.11

v1.18.11

Core Bugfixes Stopped MCP SSE connections from getting stuck in reconnect loops after server error responses. Fixed provider model configs that use interleaved reasoning fields like reasoning_text or custom field names. Desktop Bugfixes Open external links in the system browser instead of inside the app. Fixed stale session tab state in the desktop title bar. ( @OpeOginni ) Open the legacy directory picker at your home folder when no home path is loaded yet. Prevent the file tree tab from clipping when resized smaller. ( @OpeOginni ) Fixed debug gutter labels and values misaligning. Thank you ...

v1.18.10

v1.18.10

Core Discover available Modal models automatically. ( @devennavani ) Desktop Improvements Prevent adding the same attachment more than once. Always show the new session button. Improve toast notifications with better stacking, dismissal, and mobile layout. Refine tab hover, active, and overflow states. Bugfixes Repair malformed saved tabs so broken tab state no longer persists across launches. ( @OpeOginni ) Hide the model variant selector until model data finishes loading. Preserve the custom agent picker for existing users. Thank you to 3 community contributors: @lakshyaag-tavily : docs(ecos...

v1.18.9

v1.18.9

Core Bugfixes Restored compatibility with legacy MCP SDK clients. Desktop Bugfixes Fixed a Solid cleanup crash that could break navigation in the desktop app. Fixed home session loading so the session list can update without suspending the whole page. Improvements Removed the extra vertical borders from the V2 home projects view. Added an opt-in V2 desktop sidecar backed by the bundled CLI service. Added collapsible model provider sections in V2 settings. Thank you to 1 community contributor: @roborew : fix(desktop): patch @dnd-kit/solid to preserve core scroll plugins ( #38119 )

v1.18.8

v1.18.8

Core Improvements Improved compatibility with newer MCP servers and OAuth flows. Bugfixes Reconnects MCP servers after expired SDK sessions, including concurrent requests. Honors configured MCP OAuth callback ports in mcp debug . Stops sending deprecated sampling defaults to newer Gemini models. Desktop Improvements Added a shortcut to open the project selector in new sessions. Bugfixes Tab keyboard navigation now follows the visible tab order. Opening files now expands Windows folders with trailing separators. Server status uses blue when an integration needs attention. Provider connection st...

[ 重大突破 ] v1.18.5

v1.18.5

Core Bugfixes Improve Claude adaptive thinking handling across more response shapes. Avoid OpenAI Responses phase handling that could break some conversations. Preserve grep symlink paths in search results. ( @remixz ) Preserve Mistral reasoning history across turns. Stabilize Mistral prompt caching. Use the correct prompt cache keys for each SDK. Fix MiniMax M3 thinking variant selection. Desktop Improvements Support the current server terminal transport. Support current-server review data in the desktop app. Update server discovery flows for current servers. Support current-server session ac...

v1.18.6

v1.18.6

Core Bugfixes Fixed branch-specific repository caches so refreshing one reference no longer moves another branch checkout. Desktop Improvements Improved compatibility with the newer client API across directory, project, session, and terminal flows. Bugfixes Fixed legacy MCP state refreshing when opening a V1 workspace. Fixed provider lists not refreshing after connecting a provider or finishing provider OAuth on V1 servers.

v1.18.7

v1.18.7

Desktop Bugfixes Remove the extra titlebar inset in fullscreen on macOS. Keep command palette entries from reappearing incorrectly when shadowed commands are removed. Add scrolling to the project selector dropdown when the list is long. ( @david1gp ) Thank you to 2 community contributors: @ProdigyRahul : fix(ui): keep mutable selects open ( #39027 ) @david1gp : fix(app): add scroll to project selector dropdown ( #39016 )

PR #38252 verification videos

Before/after verification recordings for PR #38252 .

[ 重大突破 ] v1.18.4

v1.18.4

Core Improvements Use adaptive thinking controls for Kimi models on Anthropic-compatible providers, with summarized reasoning output by default. ( @chouqin ) Bugfixes Reduce OpenAI provider header timeouts during slow connection setup. Respect provider-defined reasoning options instead of falling back to the wrong reasoning controls. Restore Azure Cognitive Services endpoint support for Azure-hosted models. Desktop Improvements Sync the embedded terminal theme with the app theme. Improve the review panel so open file tabs can stay aligned with the current diff view. Rewrite the v2 prompt input...

v1.18.3

v1.18.3

Core Improvements Added an Up Arrow shortcut to close the subagent picker when the first item is selected. Desktop Bugfixes Fixed home page scrolling so sticky headers and the session list behave correctly. Fixed startup readiness so WSL server loading is included before the desktop app reports ready. Removed the inactive help button from the app layout. Fixed custom agent selector visibility when custom agents are available. Improvements Home page command palette search can now find and open sessions.

[ 重大突破 ] v1.18.2

v1.18.2

Core Bugfixes Stopped subagents from launching nested subagents by default, with a configurable subagent_depth limit when needed. Improved default reasoning depth for Meta models. Desktop Improvements Added Mod+N as another shortcut for opening a new tab. Bugfixes Restored the Help button in release builds. Kept sessions with null archive times visible instead of dropping them from the home list. Hid the drawer close button on Windows where it conflicts with the window chrome. Thank you to 1 community contributor: @BB-84C : fix(core): tolerate AlreadyExists in FSUtil.ensureDir ( #36542 )

v1.18.0

v1.18.0

Desktop Improvements Completed the Desktop v2 migration, including upgrade handling for the new layout and first-launch onboarding. Added a setting to switch between the new and old Desktop layouts during the transition period. Bugfixes Fixed file views using the wrong background in the v2 layout. Fixed connected project picker positioning when its anchor is still loading. Kept permission auto-accept state separate for each server. Fixed a project picker positioning crash. Kept terminal tab rename focused while editing. Enabled remote sessions to auto-accept permissions correctly. Fixed termin...

v1.18.1

v1.18.1

Desktop Bugfixes Fixed spacing between model provider sections in Settings.

[ 重大突破 ] v1.17.19

v1.17.19

Core Bugfixes Supported OpenAI pro reasoning mode. Disabled response storage by default for xAI Responses. ( @geraint0923 ) Added OAuth support for Luna Responses Lite. Switched to another available org after logging out in the console. Used Codex context limits for GPT-5.6 over OAuth. ( @nabilfreeman ) TUI Bugfixes Forwarded CLI environment variables to the TUI worker. Desktop Bugfixes Removed interface transition changes that were accidentally shipped to dev . Fixed clipped labels and branch tooltips. Stopped the review panel width from jumping when opening or closing it. Focused the prompt ...

[ 重大突破 ] v1.17.20

v1.17.20

Core Bugfixes Removed an obsolete Codex workaround that could interfere with OpenAI Luna Responses Lite requests. Improvements Updated Azure AI support for GPT-5.6.

PR #36567 verification evidence

Automated OpenCode Drive verification artifact for PR #36567 .

[ 重大突破 ] v1.17.17

v1.17.17

Core Bugfixes Improved Meta model handling for reasoning variants and provider requests. Desktop Bugfixes Fixed clipped descenders in model selector labels. Improvements Added a dismissible tabs intro popup and refreshed the help entry point. Updated sub-agent task rows to match the v2 session design more closely. Restyled the revert dock in v2 sessions for clearer restore actions. Added a v2 free-model selector with faster access to more providers.

v1.17.18

v1.17.18

Core Bugfixes Prevent crashes and bad pricing data when GitHub Copilot returns models with a zero billing batch size. Improvements Add a model-specific system prompt for Meta Muse Spark.

[ 重大突破 ] v1.17.16

v1.17.16

Core Bugfixes Exposed reasoning effort variants for Grok models. Improved xAI prompt cache routing and PDF file support in Responses models. Desktop Improvements Added an Open containing folder action for projects on the home screen. Added a composer add menu for files, commands, context, and shell mode without losing draft text. Added a provider setup tip on new sessions when no external providers are connected. Remember review panel mode and selected file per session. Added inline file browser tabs for opening and previewing files from the side panel. Updated desktop translations. Bugfixes K...

v1.17.15

v1.17.15

Core Bugfixes Better classify Z.ai context-window overflow errors so oversized requests surface the right failure mode ( @fengjikui ) Handle unavailable config directories more gracefully when reading config files Desktop Improvements Restore model details tooltips in the model picker ( @arvsrn ) Refresh the v2 command palette to better match the rest of the new desktop UI ( @arvsrn ) Bugfixes Make terminal shortcuts take priority when the terminal is focused Show unread state on tabs with pending questions Keep session tab titles available after reloads while session data is still loading App...

[ 重大突破 ] v1.17.14

v1.17.14

Core Improvements Added a code mode MCP adapter for running confined orchestration scripts against connected MCP tools. Hid the execute tool unless code mode is enabled. Bugfixes Fixed paginated MCP tool catalogs losing tool metadata and output schema validation. Preserved low reasoning effort for OpenRouter small-model variants instead of disabling it. Fixed GitHub Copilot model routing to honor each model's advertised chat or responses endpoint. Fixed session lists to match equivalent instance directories reliably. Fixed Cerebras reasoning replay so earlier assistant reasoning is sent back i...

[ 重大突破 ] v1.17.13

v1.17.13

Core Bugfixes Force reasoning mode for OpenAI-compatible reasoning models so reasoning settings apply reliably on custom deployments Stop replaying stale GitHub Copilot response item IDs, avoiding follow-up request failures Desktop Bugfixes Let question prompts be minimized and restored without dismissing them ( @arvsrn ) Clean up stale empty and old draft store files to reduce desktop state buildup Keep pending question requests open while reviewing them, instead of dismissing them accidentally ( @eXamadeus ) Keep session page failures scoped to the affected tab instead of breaking the whole ...

v1.17.12

v1.17.12

Core Bugfixes Enable adaptive thinking for Claude Sonnet 5. Prefer MCP content responses over structured output when both are present. Reconnect MCP servers after OAuth even if the server was disabled. ( @MaxAnderson95 ) Request MCP refresh-token scope during OAuth. Show MCP OAuth completion errors instead of a generic failure. Refresh cached remote skills. Preserve skill resource paths. Pick better default small models across providers. Scope MCP auth status to each server URL. TUI Improvements Add a yolo mode to auto-approve permissions. Pass ServerAuth headers through external served TUI co...

[ 重大突破 ] v1.17.10

v1.17.10

Core Improvements Added MCP server instructions to session context. ( @Arcadi4 ) Added Opencode-managed provider integration support. Added MCP resource template listing. Added MCP resource read tools. Added a --mini CLI mode. Bugfixes Hid MCP resource template tools when access is denied. Prevented MCP resource tools from colliding when servers expose the same keys. Emitted skill base directories as filesystem paths instead of file:// URLs. ( @shyuan ) Restored legacy MCP tool names for existing integrations. Restored v1 account config loading. Bound MCP OAuth callbacks to IPv4 loopback for b...

v1.17.11

v1.17.11

Core Improvements Add session snapshots and revert controls so you can roll a session back to an earlier message, including file changes. Bugfixes Always print the MCP OAuth URL so manual sign-in still works when opening the browser flow. Desktop Improvements Add Chrome-style tab cycle shortcuts with mod+1 through mod+9 . Add draggable tabs. ( @arvsrn ) Improve the empty home state when you have no sessions. ( @arvsrn ) Restyle the jump-to-latest button in the v2 session view. ( @arvsrn ) Improve the redesigned desktop layout, including better titlebar tabs and archived sessions. ( @arvsrn ) B...

PR #33649 visual proof

Visual verification asset for draft PR #33649 . This prerelease can be deleted after the PR is merged or closed.

v1.17.9

v1.17.9

Core Bugfixes Honor configured agent step limits by forcing a final text response instead of failing mid-run. Fix Devstral model detection when provider IDs use different casing. ( @Robin1987China ) Pass configured custom headers to Copilot model requests. Improvements Add high and max thinking variants for GLM-5.2 across supported providers. ( @imranshaiedi-byte ) Stop wrapping follow-up user messages in a steering reminder so prompt caching stays effective. TUI Bugfixes Only show the background subagent shortcut when the server supports it. Thank you to 4 community contributors: @Grantmartin...

v1.17.8

v1.17.8

Core Improvements Session timelines load much faster and avoid flicker or scroll jumps. Bugfixes OpenAI-compatible providers now accept MCP tool schemas that previously failed validation. ( @jquense ) Cloudflare AI Gateway now receives the configured API key correctly. ( @keefetang ) MCP tools without declared schema properties now work with providers that expect object properties. Long-running MCP tools now keep their timeout alive when they report progress. ( @Nomadcxx ) The MCP OAuth callback server now shuts down once authorization finishes or is cancelled. MCP tool failures now surface th...

v1.17.7

v1.17.7

Core Bugfixes Plugin client requests now reuse the active server instead of assuming the default local port. ACP shell tool calls now show the command and working directory from the start. Plugin-provided shell environment variables now apply to PTY sessions. Improvements MCP servers can now receive the current workspace as a client root. TUI Bugfixes MCP debug now uses the SDK's latest protocol version. Desktop Bugfixes The new session route now stays scoped to its own draft server, so prompts and state target the right workspace. SDK Improvements SDK clients now refresh model and provider av...

v1.17.5

v1.17.5

Core Improvements Added external browser OAuth for the Snowflake Cortex provider ( @santigc6 ) Improved project copy management and move-session flows in v2 Bugfixes Recovered expired MCP sessions instead of leaving MCP tools disconnected Cleared closed MCP clients so stale MCP connections do not linger Returned structured MCP tool output in a readable form Fixed duplicate renderable IDs that could break TUI rendering Fixed commands using $ARGUMENTS so file contents are not injected twice ( @verdverm ) TUI Bugfixes Added auth headers to RunCommand fetch requests ( @OpeOginni ) Desktop Improvem...

v1.17.6

v1.17.6

Core Bugfixes Improved MCP server compatibility by declaring OpenCode's supported client capabilities.

v1.17.4

v1.17.4

Core Improvements Added cwd support for local MCP servers so they can start from a workspace-relative directory. ( @Grantmartin2002 ) Added connector-based authentication flows and support for stored provider credentials. Added v2 API endpoints to create and fetch sessions, list session questions, and resolve the active location. File reads now return raw content with the correct content type for API and SDK clients. MCP server log notifications are now surfaced in opencode logs. Bugfixes Fixed Gemini tool schemas that used multi-type fields so compatible tools keep working. ( @Killusions ) Co...

v1.17.2

v1.17.2

Core Bugfixes Recover from expired remote config auth by prompting you to log in again instead of failing to load config ( @Ayushlm10 ) Let subagents use their own configured permissions again Desktop Bugfixes Restore Linux launcher and icon identity so pinned apps keep opening correctly ( @neriousy ) Restore the device attachment picker ( @rexdotsh ) Thank you to 3 community contributors: @Ayushlm10 : fix: recover from expired enterprise auth on remote config load ( #31661 ) @rexdotsh : fix(app): restore device attachment picker ( #31707 ) @neriousy : fix(desktop): restore linux launcher iden...

v1.17.1

v1.17.1

Core Improvements References can include usage descriptions for agents, show up in the new docs, and be hidden from @ autocomplete when needed. Bugfixes Deprecated reference config entries continue to load under the newer references config key. MCP prompt and resource requests now respect configured server timeouts. Anthropic fallback responses are handled correctly again. MCP servers that fail during client setup now fail cleanly instead of leaving a broken connection behind. Desktop Improvements The new desktop session flow now has a dedicated /new-session route with draft tabs that keep you...

[ 重大突破 ] v1.17.0

v1.17.0

Core Improvements Faster file search across large projects with the new fff -backed search tools. ( @dmtrKovalenko ) Added X-Session-Id headers for proxy setups that need sticky routing. ( @songchaow ) Added Cohere North model support. Added reasoning as an interleaved field option for vLLM providers. ( @delta9000 ) mcp add now works in non-interactive flows. auth logout now supports search when choosing an account. Bugfixes Improved MCP connection status messages so failures are easier to act on. Added Claude Fable reasoning support. MCP tool calls now receive abort signals, so cancellations ...

[ 重大突破 ] v1.16.2

v1.16.2

Core Bugfixes Reasoning summaries now only run on providers that support them, avoiding GPT-5 request failures on compatible backends. Edit operations now refuse loose matches that could overwrite the wrong code or replace an existing file by mistake. Fixed Bedrock sessions hanging before a model response starts. ( @alblez ) Improvements Diff viewer now supports next and previous hunk navigation. Terminal themes now refresh after live terminal reloads without stale colors or broken highlighting. Running subagents can now be sent to the background so you can keep working. Sessions now persist s...

[ 重大突破 ] v1.16.0

v1.16.0

Core Improvements Added managed workspace cloning that keeps dirty and untracked files. Added moving sessions between workspaces and directories. Added proper OpenAI model support through AWS Bedrock. Added skill discovery and file-based agent loading. Updated GitHub Copilot usage tracking for token-based billing. Added run --replay for interactive session replay. Improved startup time. ( @StarpTech ) Bugfixes Added Vue syntax highlighting. Restored full ACP session replay when loading saved sessions. ( @imnotlxy ) Fixed shell cancellation races. Fixed SAP AI Core OpenAI reasoning variants. ( ...

v1.2.25

github-v1.2.25

fix(github): enforce existing git author identity ( #30507 )

[ 重大突破 ] v1.15.13

v1.15.13

Core Bugfixes Gateway Anthropic Opus 4.7+ adaptive reasoning now keeps summarized thinking instead of returning empty thinking blocks. Improvements Sessions can now store custom metadata through the API and SDK. ( @shantur ) Config now loads from the opened location upward, so directory-specific settings and provider policies apply more predictably. TUI Bugfixes Wrapped inline tool rows now stay aligned, and failed inline tools can expand their error details in place. Thank you to 1 community contributor: @shantur : feat(core): add session metadata support ( #23068 )