megachangelog
Improvement0.0.11

Desktop v0.0.11

Desktop v0.0.11 brings clipboard image pasting to the composer, improved folder handling with better error reporting and git detection, session persistence improvements, and numerous stability and performance fixes including better MCP server handling, network retry logic, and UI polish.

  • Images can now be pasted straight from the clipboard into the composer.
  • Opening a folder that isn't a git repo no longer shows git jargon, and the welcome suggestions now adapt to what's actually in the folder instead of assuming a code project.
  • The folder picker now reports failures instead of doing nothing, and offers a manual path entry as a fallback.
  • Opening an existing session no longer overwrites the model you had selected.
  • The diff panel now resolves file paths against the session's working directory, so diffs open correctly for sessions rooted outside the app's own directory.
  • /team prompts now run through the core runtime.
  • Failed turns surface their error in the transcript instead of leaving the chat blank.
  • Plugins left behind as empty install directories are no longer listed as installed, and plugin settings and contributions are now managed centrally with atomic toggles.
  • Fixed a startup script-load error, and webview errors are now attributed to the source URL that caused them.
  • Signing out is handled as a normal state rather than surfacing as a command error.
  • Native-feel and performance polish: the browser context menu is suppressed on app chrome (kept for text fields and selections), UI chrome is no longer text-selectable while chat content still is, inner scrollers no longer rubber-band the window, Settings/Sessions/Onboarding/Diff load lazily, the composer no longer flickers the caret on every keystroke, slash commands are cached across menu opens, and Escape closes the provider/model picker.
  • Tool output no longer nests its own scrollbar.
  • Prompts queued during a turn now survive being interrupted — they're preserved across aborts, drained after a turn aborts itself, and the stop is surfaced instead of the queue being silently dropped. Queued turns that fail are reported as failures.
  • Session context stays durable across aborts and hub restarts.
  • A hung MCP server no longer takes down session creation, and stdio servers that were never configured get a 30-second initialize budget instead of blocking indefinitely.
  • Remote SSE MCP servers surface an OAuth authorization prompt on a 401 instead of failing outright.
  • LiteLLM requests route through Chat Completions instead of the Responses API.
  • Network interruptions mid-stream but before any model output are retried instead of failing the turn.
  • Checkpoints are picked up when git is initialized part-way through a session, and checkpoint diffs include files that were untracked when the snapshot was taken.
  • Scheduled run reports carry execution context — schedule metadata, durations, and lifecycle error details.

Full Changelog: desktop-v0.0.10...desktop-v0.0.11

desktopstabilityperformanceuxmcp

Source: original entry ↗

More from Cline

Follow Cline to get its new changes in your feed and email digest.

Improvement0.0.48

Desktop v0.0.48

Added support for GPT-6 models on OpenAI and Azure OpenAI endpoints by fixing the max_tokens parameter issue. Updated default models across multiple providers and refreshed the model catalog with new CommandCode and Reflection providers.

modelsapiopenaiazureproviders
Improvement3.0.73

CLI v3.0.73

GPT-6 models now work with OpenAI and Azure OpenAI endpoints after fixing a token parameter issue. Claude Sonnet 5.5 is restored as the default model when none is selected, and the model catalog has been refreshed with new providers and updated default models across multiple services.

climodelsopenaiazureproviders
Improvement0.0.95

SDK v0.0.95

OpenAI-compatible requests for GPT-6 and later models now use max_completion_tokens instead of max_tokens to prevent rejection by OpenAI and Azure. The hub daemon now tracks client launcher information as OTel resource attributes, the model catalog expanded from 6,952 to 7,041 models with new providers, and default models were updated across multiple providers with Claude Sonnet 5.5 restored as the primary recommended option.

sdkapimodelstelemetryopenai-compatible
See all Cline changes →