Cline v4.1.11 Adds Inline Image Generation, Fixes VS Code 1.134 Compatibility Break
Cline's v4.1.11 update adds inline image generation for supported models and fixes a code actions bug that broke on VS Code 1.134. The release also expands the model catalog with eight new providers including AMD, Arcee, and RunInfra.
Cline Ships v4.1.11 With Inline Image Generation and VS Code Fixes
Cline, the open-source AI coding agent extension, released version 4.1.11 on August 21, 2025, adding support for models that can generate images during a task and fixing a compatibility break with VS Code 1.134.
The update, distributed through Cline's SDK bundle, patches a bug where code actions failed with a "command not found" error on the latest VS Code release. It also fixes broken @-file mentions for paths containing spaces and corrects diff-edit rendering for multi-line edits in files using CRLF line endings.
What's New
Models that support image generation can now produce images mid-task, with the output rendering inline in the conversation view. Cline did not disclose which specific models or providers support this capability in the release notes.
Key Fixes
The release addresses several session-handling issues:
- Resuming a task now continues the surviving session rather than rebuilding it from the original task text.
- Task-scoped settings no longer leak between tasks when switching or clearing the task view.
- LiteLLM input token limits are now preserved instead of being overwritten by catalog values.
- Custom base URLs for Gemini are restored, with legacy host-root values normalized for continued compatibility.
On the tooling side, Cline fixed a case where run_commands failed with an ENOENT error when a structured command carried a full command line without separate arguments. PowerShell commands now fail-fast, stopping at the first error in a pipeline instead of flooding output while still falsely reporting success.
The update also corrects hook behavior: a PreToolUse hook's contextModification is delivered to the model again, and Cline now waits for PostToolUse hooks so their output and cancel controls are honored. Tool activity run by providers internally — such as everything the Claude Code provider executes inside its own session — is now shown in the conversation rather than dropped.
Provider and Catalog Changes
Cline refreshed its model catalog, adding eight new providers: AMD, Arcee, Echo, Jalapeno, Kosmik, LLM Gateway, RunInfra, and SCNet. The update also revises model lists, pricing, and per-provider default models across the board, and now displays billed cost for Cline gateway usage directly in the interface.
Chat model pickers no longer surface image, voice, or other non-chat models, and provider signup links now point to each provider's specific API key page instead of a generic landing page.
A separate fix in the legacy bundle narrows how Cline detects context-overflow errors from Anthropic's API — it now only triggers recovery when the invalid_request_error message explicitly references context overflow, preventing false triggers from unrelated errors like bad tool schemas or oversized images.
What This Means
This is a maintenance release focused on stability rather than new model capabilities — the inline image generation feature depends on underlying model support that Cline doesn't control. The bigger practical impact for developers is the VS Code 1.134 fix, which resolves a hard compatibility break, and the session-handling corrections, which address real reliability issues in long-running agent tasks. The expanded provider catalog (now including AMD, Arcee, and five other new entries) reflects Cline's continued strategy of maximizing model choice through its gateway rather than betting on a single backend.
Related Articles
Cline v4.1.22 Adds New AI Providers, Fixes Anthropic Failover and Bedrock Routing Bugs
Cline's v4.1.22 release adds two new model providers, refreshes default models across more than a dozen gateways including a switch to GPT-6.1 Sol, and fixes bugs in Anthropic content-filter handling, Bedrock inference profiles, and reasoning token accounting.
Cline v4.1.21 Fixes Local Model Timeouts, Expands Catalog to 6,386 Models Across 209 Providers
Cline's v4.1.21 update adds a new OpenAI-compatible provider called ai&, refreshes its model catalog to 6,386 models across 209 providers, and fixes a bug that ended tasks prematurely when local models hit output-token limits. Eleven unpinned providers, including GitHub Copilot and Vertex, now default to Claude Opus 5.5.
Vercel's AI SDK Adds Support for Unannounced OpenAI Model 'GPT-6.1 Sol'
Vercel released @ai-sdk/openai version 3.0.121, a patch that adds SDK support for a model string called 'GPT-6.1 Sol.' OpenAI has not publicly announced or confirmed this model, and no specs, pricing, or benchmarks are available.
Vercel's AI SDK Adds Support for Unreleased 'GPT-6.1 Sol' Model Identifier
Vercel's @ai-sdk/openai package version 2.0.132 quietly adds support for a model identifier called 'GPT-6.1 Sol.' OpenAI has not confirmed the model's existence, specs, or release date.
Comments
Loading...