Releasesby Glyphcline 3.83.0
Fixed Show a clear "Searching..." state in the @-mention file picker Improve @-mention file search performance Allow write_to_file to create or overwrite files with empty content. Fix validation failures for MCP servers that require an object. Enable OpenRouter prompt cache control for Qwen models.
Also shipped May 13, 2026Cline in May 2026 →
Diarization v2: Improved Batch Speaker Diarization
A new batch diarization model is available today via the diarize_model API parameter. Deepgram is rolling out v2 of our batch speaker diarization model. v2 is a new architecture available today on an opt-in basis through the new diarize_model parameter.
Seer’s Claude integration is now generally available
Trigger Claude to fix bugs using Seer’s root cause
Non-Unique Emails is Now Generally Available
Non-Unique Emails is now Generally Available (GA) for all Auth0 customers. This feature allows multiple user accounts to share the same email address within a database connection, supporting real-world use cases like families, small businesses, and multi-role users who need separate accounts tied to the same email.
Quick filters and data grouping are now generally available
Quick filters and grouping are now generally available in Grafana! The new Filter and Group by dashboard control makes it faster and easier to explore data by combining filtering and grouping in a single, intuitive experience.
Ask Amplitude AI button in Slack Previews
Description: Amplitude link previews in Slack just got a lot more useful. When someone shares an Amplitude chart or dashboard link in Slack, the updated unfurl card now surfaces chart context, suggested questions, and a direct way to kick off a Global Agent conversation , right from the preview.
GitHub CLI 2.92.0
Security A security vulnerability has been identified, and fixed, that could allow terminal escape sequence injection when users view GitHub Actions workflow logs using gh run view --log or gh run view --log-failed . Users are advised to update gh to version v2.92.0 as soon as possible.
More from clineEvery cline release →
CLI v3.0.0
Introducing our new Cline CLI built on our new SDK and comes with a snappy new TUI. Install: sh npm install -g cline For nightly builds: sh npm install -g cline@nightly
cline 3.84.0
Added Add SAP AI Core support for additional hosted models Fixed Disable the MCP "Restart Server" button when a server is toggled off. Changed Remove the Cline Kanban launch modal and bundled demo media from the VS Code extension startup flow.
cline 3.85.0
Added Add GPT-5.5 support to SAP AI Core. Add DeepSeek V4 Flash and Pro models. Add Gemini 3.5 Flash to Gemini and Vertex providers. Add /lg-task URI webhook integration for LG dashboard flows. Fixed Fix Vertex AI global endpoint handling for Claude models. Route Poolside Laguna models through next-gen prompts and native tool calling.
cline 3.82.0
Added Restore VS Code foreground terminal support and settings. Add latest OpenAI, SAP AI Core, and Z AI models. Fixed Fix hook template JSON escaping. Improve ripgrep file search error handling. Changed Remove hardcoded model lists from docs.
cline 3.86.0
Added Add Claude Opus 4.8 provider support, including 1M-context variants where available. Add Moonshot Kimi K2.6 model support. Fixed Show prompt-cache support for Qwen 3.7 Max in the Cline provider. Fix the VS Code nightly publish workflow startup permissions. Changed Move the VS Code extension project into apps/vscode.
cline 3.81.0
Added Add GPT-5.5 model support for OpenAI Codex subscription users. Fixed Remove hardcoded "What’s New" fallback items in webview; only remote-configured welcome banners are shown.
cline 3.87.0
Added Add MiniMax M3 model support. Fixed Update VS Code extension dependencies to resolve security issues in @xmldom/xmldom, basic-ftp, axios, undici, and other direct/transitive packages.
cline 3.80.0
Added Wire up remote globalSkills from enterprise remote config with full UI, toggle support, and system prompt integration , enterprise-managed skills now appear under a dedicated "Enterprise Skills" section and support alwaysEnabled enforcement Onboarding flow now uses dynamically fetched recommended models instead of a hardcoded list, with a fallback to...