Core
- Allow Codex OAuth model filtering to recognize integer GPT versions like `gpt-6`
- Fixes issue of gpt-6-astra not showing up for openai subscription users
Changelog
New updates and improvements to OpenCode
Core
- Send the session ID as GitHub Copilot's interaction header to improve request tracking across a session.
Desktop
- Use the desktop client ID during OpenCode account device authentication.
- Increase the open-in app icon size for better visibility.
Core
- Default provider header timeouts to five minutes so slow model startups fail less often.
- Default streamed chunk timeouts to five minutes, with `false` supported to disable them.
- Let Anthropic `thinking.blockBinding` opt out via config when you need to keep the provider default.(@dkindlund)
- Limit Anthropic thinking block binding to Claude 5.1+ models so older deployments do not reject requests.
- Avoid unhandled errors when canceling timed-out SSE reads.(@AlexanderWillner)
Core
- Claude 5 sessions now tolerate stale thinking blocks instead of failing after prompt or tool changes.
- Bedrock GPT-5.6 models now accept `none` reasoning effort.
- Bedrock reasoning and replay handling is more reliable.(@pengzh1)
- Tool call timing now stays accurate when tools update their metadata while still running.(@bartlettroscoe)
- `apply_patch` no longer emits an empty move path in permission metadata.(@altendky)
- Azure CLI sign-in now asks for the resource name directly instead of querying Azure management APIs.
Desktop
- Session renames now save reliably from the title editor and tab context menu.
Core
- Fixed Azure authentication so Azure CLI sign-in works without requiring Bun.
Core
- Bedrock reasoning responses no longer get cached into unreplayable empty messages.
- Azure providers can now sign in with Microsoft Entra ID through the Azure CLI instead of requiring an API key.
- V1 now reads supported V2 config fields so newer config files keep working in more mixed setups.
Desktop
- Archived sessions disappear from the Home list immediately.(@NathanTCode)
Core
- Fixed Cloudflare AI Gateway routing for third-party providers so non-Workers models work through the gateway's REST API.(@superhighfives)
- Fixed Anthropic models through Cloudflare AI Gateway by converting dotted model IDs like `claude-haiku-4.5` to the dashed slug Anthropic expects.(@superhighfives)
- Fixed parent session IDs being sent in request headers for session-aware providers.
TUI
- Fixed GitHub auth for immutable OIDC subject tokens.
Core
- Removed outdated OpenCode Go first-month discount messaging and pricing.
- Fixed OpenCode device login links when servers return relative verification URLs or use a base path.
- Fixed `textVerbosity` being sent to OpenAI-compatible providers that do not support it.(@joelstucki-taulia)
- Updated the Amazon Bedrock provider for compatibility fixes.
Desktop
- Keep model provider headers visible while scrolling the model picker.
Core
- 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
Desktop
- Keep file search results visible while the next search is loading
- Register the archive session command in both desktop layouts(@NathanTCode)
Core
- 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.
Core
- 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.
- Enabled web search when using the OpenCode Go provider.
- Preserved compatibility with existing v1 databases.
Desktop
- Kept saved server details editable in the server dialog.
Core
- Select the Kimi system prompt correctly for official Moonshot and Kimi providers
- Fix xhigh reasoning effort for xai models
Core
- 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)
Desktop
- 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.
Core
- 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
Desktop
- 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
Core
- 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
- 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.
- Stored messages now stay ordered by creation time.
- Session lists now sort by persisted activity time more reliably.
- Language names now stay native in the locale picker.
- Filled in missing translations across existing locales.
Core
- 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.
TUI
- GitHub pull request reviews now include the pull request number and URL in context.
Desktop
- 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.
- Expanded translation coverage and added more supported desktop languages.
Core
- Fixed Azure GPT-5.5+ completion requests failing when reasoning is enabled.(@frederiknsgo)
Desktop
- 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)
Core
- 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
- 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.
Core
- Discover available Modal models automatically.(@devennavani)
Desktop
- 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.