CLI v3.0.68
Fixed performance degradation and database bloat in agent teams during long sessions by optimizing how team state is saved during streaming; existing team data will be compacted automatically. Updated the model catalog with new default models across multiple cloud providers.
- Agent teams stay fast in long sessions and while teammates are streaming. Every streamed chunk used to re-save the whole team state, so team runs got slower over time and
~/.cline/data/db/teams.dbcould grow to gigabytes. Existing team data is compacted automatically the first time it's opened - Refreshed the model catalog. Default models change for DigitalOcean (GPT-6.1 Sol), GMI Cloud (Qwen 3.8 Flash), NanoGPT (Pareto 26.10 Preview), Nvidia (DeepSeek V4.1 Flash), and Ofox (GPT-6.1 Sol)
Full Changelog: cli-v3.0.67...cli-v3.0.68
Source: original entry ↗
More from Cline
Follow Cline to get its new changes in your feed and email digest.
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.
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.
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.