Cline VS Code extension shipped v4.1.21 on 2026-09-24 with a new Japan OpenAI-compatible provider (ai&), a refreshed catalog of 6,386 models across 209 providers (19 unpinned defaults change—11 to Claude Opus 5.5 including GitHub Copilot and Vertex), and compact-and-retry once when local servers (llama.cpp/Ollama/LM Studio) hit output-token limits. Minimum js-yaml raised to 4.3.2 for frontmatter parsing security.
Key Takeaways
- ✓New provider ai& (Japan OpenAI-compatible open-weight endpoint)
- ✓Catalog: 6,386 models / 209 providers; 19 unpinned defaults shift (11 → Opus 5.5 incl. Copilot & Vertex)
- ✓Local models compact-and-retry once on output-token caps
- ✓js-yaml floor 4.3.2 for rule/skill frontmatter
- ✓Install via Marketplace or cline-4.1.21.vsix
Key Decision Metrics at a Glance
Not enough VRAM? Compare cloud API and self-hosting costs
Compare 40 dev plans & simulate token costs vs $20/mo subscriptions
Project Links & Resources
Direct AccessIn-Depth Technical Analysis
Background
Coding agents need fresh multi-provider catalogs and reliable local long replies. Cline v4.1.21 refreshes the catalog and adds compact-and-retry for local servers.
Architecture
New ai& OpenAI-compatible Japan open-weight provider. Catalog: 6,386 models / 209 providers; 19 unpinned defaults change (11 → Opus 5.5 incl. Copilot & Vertex). Local llama.cpp/Ollama/LM Studio replies that hit output caps compact once and retry. js-yaml floor 4.3.2 for frontmatter security.
Benchmarks
No coding benchmark scores in the notes—only catalog counts (6,386/209) and default-shift coverage (19/11).
Get started
Install https://github.com/cline/cline/releases/tag/v4.1.21 or the vsix asset; pin models if you relied on prior defaults; see https://docs.cline.bot/.
Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.