v4.1.24 — model defaults, catalog refresh, and bug fixes
Cline and OpenRouter now default to Claude Sonnet 5.5 when no model is chosen, the model catalog has been refreshed with new providers and model updates, and multiple bugs have been fixed including reasoning mode errors, MCP server crashes, token estimation issues, and settings migration problems.
Changed
- With no model chosen, the Cline and OpenRouter providers now use Claude Sonnet 5.5. For Cline, that's the first model in Cline's recommended list.
- Selecting ai& shows its own API key and model picker, instead of the generic OpenAI-compatible form with base URL and custom headers.
- Refreshed the model catalog. Adds Claude Haiku 5.5 and the AI/ML API, LowRouter, and Prime Inference providers. The Cline free list adds Step 5 Preview. The v0 provider now offers only its default model,
v0-1.5-md, and OpenCode Go uses its newhttps://opencode.ai/inference/go/v1endpoint. Default models change for 302.AI, Cortecs, CrossModel, DevPass, DigitalOcean, Eden AI, GitHub Copilot, Google Vertex AI, LLM Gateway, Meta, Moark, NanoGPT, NEAR AI Cloud, Neuralwatt, Novita AI, Ofox, OpenCode Go, Requesty, Vivgrid, and a few others (most now Claude Haiku 5.5 or Muse Wonder 1.0). If you use one of those providers without pinning a model, expect a different default.
Fixed
- Turning reasoning off no longer fails with a 400 error on GPT-6 Astra, GPT-6.1 Sol, Claude Fable 5 or Claude Opus 5.5, and now works on every provider. Level-only Gemini models no longer reject the request with a thinking-budget error.
- An MCP server or hook that exits before reading all of its input no longer crashes the extension host about 3 seconds later.
- A 404 from a stale or retired model id is no longer shown as a sign-in problem. Cline shows the real error instead of the logged-out card.
- Errors in the Cline output log keep their details. Production builds used to drop them, so a line like "Cline OAuth login failed:" showed no reason.
- Deleting a slash command from the input keeps the spacing of the text around it.
- Screenshots and other images no longer inflate the token estimate, which made auto-compaction run long before the conversation was near its limit.
- Auto-compaction uses the selected model's context window when the catalog entry has none.
- Rule files that are symlinks now load, and skills in
.claude/skillsare now discovered. - The editor tool no longer receives null in place of the text to replace from some models.
- Settings migrated from older versions no longer add an empty SAP AI Core provider.
Full Changelog: v4.1.23...v4.1.24
Source: original entry ↗
More from Cline
Follow Cline to get its new changes in your feed and email digest.
Fix SDK packages plugins import in production build
Fixed an issue where SDK packages plugins were not being properly imported in production builds, ensuring all dependencies are correctly included.
Desktop v0.0.46
Added a new outline view showing all prompts sent in the conversation with hover preview and jump-to functionality. Improved error handling for plugins, Cloud sign-in, session management, and skill installation. Enhanced scheduled routines with proper run queueing and model failure handling. Fixed token estimation for images, reasoning toggle across providers, symlink rule loading, and skill discovery in .claude/skills. Updated model catalog with new providers and default models.
CLI v3.0.71
Plugins now load inside the hub without requiring a separate JavaScript runtime, with improved error reporting and status tracking. Added thinking support in ACP mode, environment variable provider configuration, improved reasoning control across providers, and numerous fixes for scheduled runs, token estimation, and model catalog updates.