Cline v4.1.23
Cline v4.1.23 was released on .
Summary
Changed - If a model's response ends without a recognized finish reason, Cline asks it to continue once instead of treating the response as complete. - Refreshed the model catalog. The Cline recomm...
Release Context
- This was the 89th Cline release of 2026 tracked by Havoptic.
- It shipped 7 days after Cline v4.1.22 (September 30, 2026).
Shipped around the same time
Within 3 days of this release, other AI coding tools also shipped:
- Antigravity CLI v1.3.3 (October 10, 2026)
- Factory Droid v0.238.0 (October 10, 2026)
- Amp 2026.10.10 (October 10, 2026)
- OpenAI Codex CLI rust-v0.162.1 (October 9, 2026)
- Claude Code v2.1.296 (October 9, 2026)
Compare Cline
- Cline vs Claude Code
- Cline vs OpenAI Codex CLI
- Cline vs Cursor
- Cline vs Gemini CLI
- Cline vs Kiro CLI
- Cline vs GitHub Copilot CLI
- Cline vs Devin Desktop
- Cline vs Antigravity CLI
- Cline vs Grok Build
- Cline vs OpenCode
- Cline vs Zed
- Cline vs Factory Droid
- Cline vs Devin
- Cline vs Lovable
- Cline vs Amp
- Cline vs GitHub Copilot in VS Code
- Cline vs Replit Agent
- Cline vs Bolt
- Cline vs v0
Release Notes
Changed - If a model's response ends without a recognized finish reason, Cline asks it to continue once instead of treating the response as complete. - Refreshed the model catalog. The Cline recommended list adds GPT-6.1 Sol, and the free list adds Solar Mini 4 and drops DeepSeek V4.1 Flash and space-bunny-alpha. Default models change for 302.AI, AKI.IO, Blue Claw, CoralBricks, CrossModel, DevPass, DigitalOcean, GMI Cloud, LLM Gateway, Mistral, NanoGPT, Neon, Nvidia, Ofox, Requesty, Subconscious, The Grid AI, Vivgrid, and Vultr. Vultr's model ids were renamed upstream, so a pinned Vultr model may need to be re-selected. If you use one of those providers without pinning a model, expect a different default. Fixed - Generate Commit Message now follows your .clinerules, so conventions like language, format, and ticket references apply to commit messages too. - Claude through a custom Anthropic base URL (Azure AI Foundry, corporate gateways) no longer fails with a 400 error. 4.1.22 started sending an option only Anthropic's own API accepts. - Kimi K3 and other models that only accept certain reasoning levels no longer reject requests. Cline picks the closest level the model supports. - When an MCP tool returns more output than fits in context, Cline can now read the rest. It gets a preview plus a link it can page through with readfiles, so the output past the cutoff is no longer lost. - Approve and Reject on a tool approval work right away, even while the panel is still updating. A late update failure no longer rejects a later, unrelated approval. - Old tasks no longer show leftover Focus Chain checklist rows when reopened. Full Changelog: https://github.com/cline/cline/compare/v4.1.22...v4.1.23
Other Recent Cline Releases
- v4.1.25 (October 16, 2026)
- v4.1.21 (September 24, 2026)
- v4.1.20 (September 22, 2026)
- v4.1.19 (September 17, 2026)
- v4.1.17 (September 2, 2026)
Upgrading from v4.1.23? See all 2 releases since.
All Cline releases · All AI coding tool releases on Havoptic