Core

Bugfixes

• Fixed Azure authentication so Azure CLI sign-in works without requiring Bun.

Core

Bugfixes

• Bedrock reasoning responses no longer get cached into unreplayable empty messages.

Improvements

• 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

Bugfixes

• Archived sessions disappear from the Home list immediately. (@NathanTCode)

Thank you to 3 community contributors:

• @NathanTCode:
  • fix(app): drop archived sessions from home list right away (#44905)
• @OpeOginni:
  • fix(ui): restore focus in stacked dialogs (#44928)
• @dondetir:
  • docs: mention Exa and Parallel as web search backends (#38395)

Core

Bugfixes

• 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

Bugfixes

• Fixed GitHub auth for immutable OIDC subject tokens.

Thank you to 1 community contributor:

• @superhighfives:
  • fix(provider): send Anthropic's dashed native slug through the AI Gateway (#44281)
  • fix(provider): route non-native Cloudflare AI Gateway providers via the REST API (#44828)

Core

Bugfixes

• Removed outdated OpenCode Go first-month discount messaging and pricing.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

Bugfixes

• Keep model provider headers visible while scrolling the model picker.

Thank you to 1 community contributor:

• @joelstucki-taulia:
  • fix(provider): guard textVerbosity injection for @ai-sdk/openai-compatible providers (#43915)

Core

Bugfixes

• 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

Bugfixes

• Keep file search results visible while the next search is loading
• Register the archive session command in both desktop layouts (@NathanTCode)

Thank you to 1 community contributor:

• @NathanTCode:
  • fix(app): register archive session command in both layouts (#41741)

Core

Bugfixes

• 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

Improvements

• Added native OpenAI and Anthropic passthroughs for Cloudflare AI Gateway models.
• Matched Codex rate limits more closely to ChatGPT subscription limits. (@GameOn223)

Bugfixes

• 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

Bugfixes

• Kept saved server details editable in the server dialog.

Thank you to 4 community contributors:

• @TechyAditya:
  • fix(skills): Update global config path in documentation (#42337)
• @GameOn223:
  • tweak: match codex limits for openai models exactly when using chatgpt subscription (#39082)
• @OpeOginni:
  • fix(opencode): properly show authed providers on /connect command (#39915)
• @bhuvan2134686:
  • docs: add SCX.ai to the providers list (#42520)

Core

Bugfixes

• Select the Kimi system prompt correctly for official Moonshot and Kimi providers
• Fix xhigh reasoning effort for xai models

Core

Bugfixes

• 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

Bugfixes

• 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.

Thank you to 6 community contributors:

• @mreso:
  • fix(session): route all Muse family models to the Meta system prompt (#41581)
• @OpeOginni:
  • fix(ui): correct OC-2 weak icon color (#41504)
• @peculiarnewbie:
  • feat(console): add go usage endpoint (#16513)
• @stevenao:
  • fix(opencode): detect Copilot PDF input support (#41522)
• @MatthewFeroz:
  • fix(provider): add Merge Gateway reasoning variants (#41867)
• @skyzhao1223:
  • docs: fix broken DigitalOcean and Daytona links (#42048)
  • docs: fix provider display name and PAT typos (#42034)

Core

Bugfixes

• 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

Improvements

• Open the project menu with a right-click in Home

Bugfixes

• 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

Thank you to 1 community contributor:

• @Speechlessmanbilibili:
  • fix(i18n): use 词元 instead of 令牌 for token in zh locale (#40977)