OpenCode

v1.18.21

August 21, 2026

• •Continue responses when a model reports an unknown finish reason instead of stopping early
• •Route Vertex AI eu and us multi-region Gemini requests through REP endpoints
• •Keep file search results visible while the next search is loading
• •Register the archive session command in both desktop layouts (@NathanTCode)
• •@NathanTCode:
• •fix(app): register archive session command in both layouts (#41741)

v1.18.20

August 21, 2026

• •Surface failed subagent tool calls with a resumable task_id.
• •Retry provider responses that end with finish_reason: network_error.
• •Retry more network error variants, including network-error and network_error.
• •Surface resumable subagent failures instead of returning an empty result.
• •Preserve Cerebras max_completion_tokens without applying an extra output cap.
• •Answer permission requests triggered by subagents during opencode run.
• •Retry xAI capacity and temporary unavailability stream errors.

v1.18.19

August 20, 2026

• •Added native OpenAI and Anthropic passthroughs for Cloudflare AI Gateway models.
• •Matched Codex rate limits more closely to ChatGPT subscription limits. (@GameOn223)
• •Removed built-in Qwen sampling defaults that could send unsupported settings.
• •Properly show authenticated providers in /connect. (@OpeOginni)
• •Ignore malformed model pricing instead of breaking usage cost calculation.
• •Fall back when OpenAI websocket requests exceed message size limits.
• •Forward ChatGPT workspace compute residency to Codex requests.
• •Updated the default Console URL used by account connection flows.

v1.18.18

August 13, 2026

## Core ### Bugfixes - Select the Kimi system prompt correctly for official Moonshot and Kimi providers - Fix xhigh reasoning effort for xai models

v1.18.17

August 12, 2026

• •Made session compaction keep complete recent turns and produce clearer summaries for smaller models.
• •Added MERGE Gateway reasoning variants so those model options work correctly. (@MatthewFeroz)
• •Capped automatic session retries and added jitter to reduce repeated retry storms.
• •Enabled PDF attachments for GitHub Copilot models that advertise PDF vision support. (@stevenao)
• •Applied the correct sampling defaults to DeepSeek V4 Flash on supported providers.
• •Routed all Muse family models to the correct Meta system prompt. (@mreso)
• •Updated Chinese developer terminology to use more widely recognized translations.
• •Used the server's current default model instead of stale local config when choosing the default model.

v1.18.16

August 10, 2026

• •Ignore unknown top-level config fields instead of failing config parsing
• •Register projects opened from Home so they are available to the rest of the app
• •Open the project menu with a right-click in Home
• •Fall back to listing and matching local directories when the project picker server does not support search
• •Use 词元 instead of 令牌 for token-related labels in Simplified Chinese (@Speechlessmanbilibili)
• •Keep the macOS app running after the last window closes and reopen a window when the app is activated
• •@Speechlessmanbilibili:
• •fix(i18n): use 词元 instead of 令牌 for token in zh locale (#40977)

v1.18.15

August 7, 2026

• •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)
• •Added much broader locale coverage across the desktop app.
• •Export full session transcripts as JSON from the UI.
• •Session timelines now respect chronological message boundaries more reliably.

v1.18.14

August 5, 2026

• •Simplified xAI login to a single device-code flow that works better in headless and remote environments.
• •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)
• •Waited for queued ACP session updates before ending a turn.
• •@jamesmurdza:

v1.18.13

August 4, 2026

• •GitHub pull request reviews now include the pull request number and URL in context.
• •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.
• •Localized more desktop UI copy, including native menus, update dialogs, and help content.
• •Added early right-to-left layout support across the app and session views.
• •Added locale-aware plural rules so translated counts and summaries read correctly.

v1.18.12

August 4, 2026

• •Fixed Azure GPT-5.5+ completion requests failing when reasoning is enabled. (@frederiknsgo)
• •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)
• •fix(app): skip legacy config reads for v2 (#40211)
• •@NumerousJLs:
• •fix(app): search every known project in the open project dialog (#40202)

v1.18.11

August 1, 2026

• •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.
• •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.
• •@devennavani:

v1.18.10

July 30, 2026

• •Discover available Modal models automatically. (@devennavani)
• •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.
• •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.

v1.18.9

July 28, 2026

• •Restored compatibility with legacy MCP SDK clients.
• •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.
• •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.
• •fix(desktop): patch @dnd-kit/solid to preserve core scroll plugins (#38119)

v1.18.8

July 28, 2026

• •Improved compatibility with newer MCP servers and OAuth flows.
• •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.
• •Added a shortcut to open the project selector in new sessions.
• •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.

v1.18.7

July 27, 2026

• •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)
• •@ProdigyRahul:
• •fix(ui): keep mutable selects open (#39027)
• •fix(app): add scroll to project selector dropdown (#39016)

v1.18.6

July 27, 2026

• •Fixed branch-specific repository caches so refreshing one reference no longer moves another branch checkout.
• •Improved compatibility with the newer client API across directory, project, session, and terminal flows.
• •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.

v1.18.5

July 24, 2026

• •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.
• •Support the current server terminal transport.

v1.18.4

July 20, 2026

• •Use adaptive thinking controls for Kimi models on Anthropic-compatible providers, with summarized reasoning output by default. (@chouqin)
• •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.
• •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 for more reliable command, context, shell, attachment, and history interactions.
• •Improve review panel resizing and sticky controls.

v1.18.3

July 16, 2026

• •Added an Up Arrow shortcut to close the subagent picker when the first item is selected.
• •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.
• •Home page command palette search can now find and open sessions.

v1.18.2

July 15, 2026

• •Stopped subagents from launching nested subagents by default, with a configurable subagent_depth limit when needed.
• •Improved default reasoning depth for Meta models.
• •Added Mod+N as another shortcut for opening a new tab.
• •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.
• •fix(core): tolerate AlreadyExists in FSUtil.ensureDir (#36542)

v1.18.1

July 14, 2026

• •Fixed spacing between model provider sections in Settings.

v1.18.0

July 14, 2026

• •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.
• •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.

v1.17.20

July 13, 2026

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

v1.17.19

July 13, 2026

• •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)
• •Forwarded CLI environment variables to the TUI worker.
• •Removed interface transition changes that were accidentally shipped to dev.
• •Fixed clipped labels and branch tooltips.

v1.17.18

July 9, 2026

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

v1.17.17

July 9, 2026

• •Improved Meta model handling for reasoning variants and provider requests.
• •Fixed clipped descenders in model selector labels.
• •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.

v1.17.16

July 9, 2026

• •Exposed reasoning effort variants for Grok models.
• •Improved xAI prompt cache routing and PDF file support in Responses models.
• •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.

v1.17.15

July 7, 2026

• •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
• •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)
• •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
• •Apply theme changes only after you select them in Settings

v1.17.14

July 6, 2026

• •Added a code mode MCP adapter for running confined orchestration scripts against connected MCP tools.
• •Hid the execute tool unless code mode is enabled.
• •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 in the provider-supported field.
• •Fixed spinner registration so loading indicators keep rendering across TUI surfaces.

v1.17.13

July 1, 2026

• •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
• •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 app
• •Improve markdown and message layout alignment in the v2 session UI (@arvsrn)
• •Add a searchable v2 model picker and model management flow in the composer (@arvsrn)