Cline v4.1.23: cut-off replies continue and Claude on custom Anthropic URLs works again

4 days ago

What changed in Cline v4.1.23: replies that stop without a finish reason now continue, Claude through Azure AI Foundry and corporate gateways works again, MCP output too long for context can be paged, Generate Commit Message follows .clinerules, and nineteen providers get a new default model. https://github.com/cline/cline/releases/tag/v4.1.23 https://github.com/cline/cline/blob/v4.1.23/CHANGELOG.md https://github.com/cline/cline/compare/v4.1.22...v4.1.23

Ask

Ask about this presentation

Answers are generated from this presentation.

Chapters

  1. 0:00Replies that stop short
  2. 0:12Custom Anthropic base URLs
  3. 0:26Long MCP tool output
  4. 0:37Commit messages
  5. 0:48New default models
  6. 1:04Recommended and free models
  7. 1:16Smaller fixes
  8. 1:32Release notes
Show transcript

Replies that stop short

Cline
v4.1.23

Cline asks the model to finish a reply that stopped short

Once, when a response ends without a recognized finish reason

CHANGELOG.md · cline/cline

When a model's reply ends without a finish reason Cline recognizes, Cline now asks the model to continue, once. Before this release, Cline treated a reply like that as complete.

Custom Anthropic base URLs

ClineCline
Fixed

Claude through Azure AI Foundry and corporate gateways works again

The 400 error from the previous release is gone

CHANGELOG.md · cline/cline

If you reach Claude through a custom Anthropic base URL, such as Azure AI Foundry or a corporate gateway, the 400 errors stop. The previous release sent an option that only Anthropic's own API accepts.

Long MCP tool output

ClineCline
Fixed

Cline can page through MCP output that overflows its context

It gets a preview, plus a link it pages through with read_files

CHANGELOG.md · cline/cline

When an MCP tool returns more than fits in context, Cline gets a preview and a link it can page through with its read_files tool. The output past the cutoff used to be lost.

Commit messages

ClineCline
Fixed

Generate Commit Message now follows your .clinerules

Language, format and ticket references apply to commits too

CHANGELOG.md · cline/cline

Generate Commit Message now follows your .clinerules. The conventions you already set there, like the language, the format and ticket references, now shape your commit messages as well.

New default models

ClineCline
Changed

Nineteen providers switch to a new default model

Vultr renamed its model ids, so a pinned Vultr model may need picking again

CHANGELOG.md · cline/cline

Nineteen providers get a new default model, including Mistral, Nvidia and DigitalOcean. If you haven't pinned a model there, expect a different one. Vultr renamed its model ids upstream, so a pinned Vultr model may need selecting again.

Recommended and free models

ClineCline
Changed

GPT-6.1 Sol joins Cline’s recommended models

  • Free list adds Solar Mini 4
  • Free list drops DeepSeek V4.1 Flash
  • Free list drops space-bunny-alpha
CHANGELOG.md · cline/cline

GPT 6.1 Sol joins Cline's recommended list. On the free list, Solar Mini 4 comes in, while DeepSeek V4.1 Flash and space-bunny-alpha drop off it.

Smaller fixes

ClineCline
Fixed

Fixes for Kimi K3, tool approvals and reopened tasks

  • Kimi K3 gets the closest reasoning level it supports
  • Approve and Reject respond while the panel updates
  • Reopened tasks drop leftover Focus Chain rows
CHANGELOG.md · cline/cline

Kimi K3 and other models that only accept certain reasoning levels stop rejecting requests. Cline picks the closest level they support. Approve and Reject on a tool approval work right away. Reopened tasks lose their leftover Focus Chain rows.

Release notes

Cline

Every provider’s new default is in the release notes

CHANGELOG.md in the cline/cline repository on GitHub

CHANGELOG.md · cline/cline

The full list of providers with a new default model is in the release notes. They live in the changelog in Cline's GitHub repository.