Intel / repo

cline v4.1.26

Source: github.com
Author: github-actions[bot]
Date: Published Oct 26, 2026

Context

Cline 4.1.26 changes which model many users get without them touching a setting. Cline is an open-source coding that runs in the editor and can send requests to dozens of model providers. In this release, Cline's own provider goes back to Claude Sonnet 5.5 from Anthropic when no model is chosen, and ClinePass now defaults to Kimi K3.1 Pro from Moonshot AI, the model Moonshot introduced on October 23. Defaults for most other providers also move, mostly to Kimi K3.1 Pro, MiniMax M3.1 Flash or DeepSeek V4.1 Flash 1017. The release notes say plainly that anyone using a provider without pinning a model should expect a different default, so a team that cares about consistent results or costs should set the model explicitly.

The release also builds out cloud tasks, where the agent works in a remote instead of on the user's machine. Settings gain a Local or Cloud switch so cloud tasks can use a different model from local ones, and starting a sandbox shows its progress through starting the sandbox, cloning the repository and starting the agent. Among the fixes, GPT-6 models now work on OpenAI and Azure-compatible endpoints, free-tier Gemini API keys no longer fail every turn with quota errors caused by Cline requesting Google Search, and model requests now retry at most three times instead of five.

Key takeaways · AI-distilled

Free-tier Gemini API keys failed every turn with a 429 quota error on Gemini 3+ because Cline's gemini provider sent native Google Search, and on Gemini 2.x every Cline tool was dropped. Cline 4.1.26 stops sending native Google Search on that provider.
GPT-6 models such as gpt-6-sol and gpt-6.1-sol now work on OpenAI and Azure OpenAI-compatible endpoints, and SAP AI Core stops rejecting requests over 'max_tokens', because Cline now sends max_completion_tokens to both.
Most providers get new default models in this release, mostly Kimi K3.1 Pro, MiniMax M3.1 Flash or DeepSeek V4.1 Flash 1017, and ClinePass now defaults to Kimi K3.1 Pro. The catalog adds CommandCode, Reflection, Liquid Inference and Munito AI and drops CrofAI, iFlow and Llama.
Two long-task fixes: a turn whose connection drops after the model streamed only reasoning is now retried instead of ending the task, and auto- no longer runs for models with an unknown limit or re-runs every few tool calls after the first compaction.

Terms in this piece · Glossary

AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
sandbox — An isolated environment where AI-generated code or agent actions run without being able to touch anything real.
context compaction — Summarizing an agent's earlier conversation to free room in the context window so a long session can keep going.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.

Read the source github.com