Skip to content
DevAgentRadarDevAgentRadar
Sign in
Proposals/Pin Local and Cloud models after Cline v4.1.26 c
proposaleveryoneP4High impactCline

Pin Local and Cloud models after Cline v4.1.26 catalog swap

Cline v4.1.26 splits Local vs Cloud model picks, refreshes the catalog (new defaults, dropped providers), and restores Claude Sonnet 5.5 when no Cline model is chosen. Pin models on both sides so tasks do not silently switch.

Why this loop

v4.1.26 changes which model actually runs if a provider is left unpinned. The Cline provider with no model chosen uses Claude Sonnet 5.5 again. ClinePass defaults to Kimi K3.1 Pro and adds MiniMax M3.1 Flash and DeepSeek V4.1 Flash 1017; most other providers also change defaults to those three. CrofAI, iFlow, and Llama are removed; CommandCode, Reflection, Liquid Inference, and Munito AI are added. The free list drops Mimo V2.6 Flash and Muse Spark 1.3 Contributor. Cloud tasks now have a Local | Cloud toggle in Settings > API Configuration, and the cloud model is saved separately from local. Gemini API keys no longer send native Google Search. Pinning models on both Local and Cloud, and migrating off dropped providers, keeps existing workflows from silently switching models or failing on removed backends.

Proposed actions

  1. In Cline Settings > API Configuration, enable cloud sessions, use the Local | Cloud toggle, and pin an explicit model on Local and a separate explicit model on Cloud (cloud picks are saved separately from local).
  2. Pin a model id on every provider you use. Unpinned providers now default mostly to Kimi K3.1 Pro, MiniMax M3.1 Flash, or DeepSeek V4.1 Flash 1017; the Cline provider with no model chosen uses Claude Sonnet 5.5.
  3. If any workspace still uses CrofAI, iFlow, or Llama, switch that provider to CommandCode, Reflection, Liquid Inference, or Munito AI (or another remaining provider) and pin the model id.
  4. On ClinePass, keep or override the new default Kimi K3.1 Pro, or pin MiniMax M3.1 Flash / DeepSeek V4.1 Flash 1017. On the Cline free list, replace Mimo V2.6 Flash and Muse Spark 1.3 Contributor with Reflection Beam, Nemotron 3.5 Lightning, or Laguna S 2.1.
  5. If you used the gemini provider for native Google Search, remove that dependency: v4.1.26 no longer sends native Google Search on Gemini API keys (it caused 429s on free-tier Gemini 3+ and dropped tools on 2.x).

Agent prompt

Paste into your agent or query via MCP (get_agent_prompt) — free, no extra AI cost

Cline / .clinerules task

DevAgentRadar → Cline

You are helping me adopt a real coding-assistant change. Work only from the facts below. Do not invent features.

Context

Assistant: Cline Proposal: Pin Local and Cloud models after Cline v4.1.26 catalog swap Summary: Cline v4.1.26 splits Local vs Cloud model picks, refreshes the catalog (new defaults, dropped providers), and restores Claude Sonnet 5.5 when no Cline model is chosen. Pin models on both sides so tasks do not silently switch. Primary source: https://github.com/cline/cline/releases/tag/v4.1.26

Why it matters

v4.1.26 changes which model actually runs if a provider is left unpinned. The Cline provider with no model chosen uses Claude Sonnet 5.5 again. ClinePass defaults to Kimi K3.1 Pro and adds MiniMax M3.1 Flash and DeepSeek V4.1 Flash 1017; most other providers also change defaults to those three. CrofAI, iFlow, and Llama are removed; CommandCode, Reflection, Liquid Inference, and Munito AI are added. The free list drops Mimo V2.6 Flash and Muse Spark 1.3 Contributor. Cloud tasks now have a Local | Cloud toggle in Settings > API Configuration, and the cloud model is saved separately from local. Gemini API keys no longer send native Google Search. Pinning models on both Local and Cloud, and migrating off dropped providers, keeps existing workflows from silently switching models or failing on removed backends.

Suggested actions

  1. In Cline Settings > API Configuration, enable cloud sessions, use the Local | Cloud toggle, and pin an explicit model on Local and a separate explicit model on Cloud (cloud picks are saved separately from local).
  2. Pin a model id on every provider you use. Unpinned providers now default mostly to Kimi K3.1 Pro, MiniMax M3.1 Flash, or DeepSeek V4.1 Flash 1017; the Cline provider with no model chosen uses Claude Sonnet 5.5.
  3. If any workspace still uses CrofAI, iFlow, or Llama, switch that provider to CommandCode, Reflection, Liquid Inference, or Munito AI (or another remaining provider) and pin the model id.
  4. On ClinePass, keep or override the new default Kimi K3.1 Pro, or pin MiniMax M3.1 Flash / DeepSeek V4.1 Flash 1017. On the Cline free list, replace Mimo V2.6 Flash and Muse Spark 1.3 Contributor with Reflection Beam, Nemotron 3.5 Lightning, or Laguna S 2.1.
  5. If you used the gemini provider for native Google Search, remove that dependency: v4.1.26 no longer sends native Google Search on Gemini API keys (it caused 429s on free-tier Gemini 3+ and dropped tools on 2.x).

After you finish

Do not report this as applied to DevAgentRadar. You cannot write the visitor's loop.

Tell the human: open https://devagentradar.com/proposals/cline-v4-1-26-pin-local-and-cloud-models-after-cline-v4-1-26-catalog-swa and mark Applied, Skipped, or Failed. Proposal id: bed86b8c-463c-4270-9d85-4548b11c096d

Your job

  1. Restate the change in one sentence.
  2. Propose a minimal plan for my repo (or a throwaway pilot).
  3. Implement only what I approve; prefer small diffs and tests.
  4. Call out risks (permissions, breaking APIs, cost).

Start by confirming you understood the proposal.

agentmodelsecuritycliRelease source ↗

Your loop

This browser · no sign-in · not shared as “you”

After you run the prompt

Only you can mark this. Agents cannot write your loop.

Your decision stays on this device. A public tally appears after a few votes.

Originating release signal

Clinev4.1.26Oct 26, 2026

v4.1.26

Cloud tasks: Settings > API Configuration has a Local | Cloud toggle when cloud sessions are on. · Cloud picks the Cline model new cloud tasks run on, saved separately from your local models. · Clicking the model label in a cloud session's composer opens it there. · Starting or resuming a cloud sandbox shows a progress card with the repo, branch and steps (start sandbox, clone repository, start agent). · It collapses once the agent starts. · Cloud sessions hide the Plan/Act toggle and the auto-approve bar instead of showing them disabled. · +23 more changes
Verified excerpt — the source's own words

Added

  • Cloud tasks: Settings > API Configuration has a Local | Cloud toggle when cloud sessions are on. Cloud picks the Cline model new cloud tasks run on, saved separately from your local models. Clicking the model label in a cloud session's composer opens it there.
  • Starting or resuming a cloud sandbox shows a progress card with the repo, branch and steps (start sandbox, clone repository, start agent). It collapses once the agent starts.

Changed

  • Cloud sessions hide the Plan/Act toggle and the auto-approve bar instead of showing them disabled.
  • With no model chosen, the Cline provider uses Claude Sonnet 5.5 again, which is back at the top of Cline's recommended list.
  • Model requests retry at most 3 times instead of 5.
  • Kimi K3 now gets max reasoning for Extra High and Max, instead of an xhigh setting it rejects.
  • Refreshed the model catalog. Adds the CommandCode, Reflection, Liquid Inference and Munito AI providers and drops CrofAI, iFlow and Llama. The Cline free list adds Reflection Beam, Nemotron 3.5 Lightning and Laguna S 2.1 and drops Mimo V2.6 Flash and Muse Spark 1.3 Contributor. ClinePass now defaults to Kimi K3.1 Pro and adds MiniMax M3.1 Flash and

Excerpt ends here — this release continues at the source ↗.

Primary source ↗