product update

Cline v3.87.0 Adds MiniMax M3 Support, Patches 5 Security Vulnerabilities

TL;DR

Cline, the open-source AI coding assistant, released v3.87.0 on June 3, 2025, adding support for MiniMax's M3 model. The update patches security vulnerabilities in five packages including @xmldom/xmldom, basic-ftp, axios, and undici.

1 min read
0

Cline v3.87.0 Adds MiniMax M3 Support, Patches 5 Security Vulnerabilities

Cline, the open-source AI coding assistant VS Code extension, released v3.87.0 on June 3, 2025, adding support for MiniMax's M3 model and addressing multiple security issues.

What Changed

The release adds integration with MiniMax M3, a multimodal model from Chinese AI company MiniMax. Cline users can now select M3 alongside existing provider options including Claude, GPT-4, and other supported models.

The security updates resolve vulnerabilities in five packages:

  • @xmldom/xmldom
  • basic-ftp
  • axios
  • undici
  • Additional direct and transitive dependencies

Cline updated its VS Code extension dependencies to address these security issues, though specific CVE numbers were not disclosed in the release notes.

About Cline

Cline is a fork of the Claude Dev project that enables AI-assisted coding directly in VS Code. The extension supports autonomous code editing, terminal command execution, and browser automation. It works with multiple LLM providers through a provider-agnostic architecture.

The project has 19 commits to main since this release, indicating active development continues.

What This Means

MiniMax M3 support expands Cline's model options beyond Western providers, giving developers access to Chinese frontier models. This follows a pattern of coding assistants adding regional model support as non-US AI companies release competitive alternatives.

The security patches address dependency vulnerabilities that could affect the 100,000+ developers using Cline. Users should update to v3.87.0 to resolve these issues, particularly if their development environments have strict security requirements.

Related Articles

product update

OpenRouter Launches Auto Router Beta: Task-Aware Model Routing Based on Community Spend

OpenRouter has released Auto Router Beta, a task-aware routing system that classifies incoming requests and automatically routes them to popular models based on community spending patterns. The router allows users to filter selections by cost-quality tradeoff preferences.

product update

OpenAI restores chat sidebar in Mac app after user backlash over confusing redesign

OpenAI has updated its ChatGPT Mac app to restore direct access to chat conversations through a prominent sidebar toggle. The fix addresses user complaints following a July 10 redesign that replaced the native Mac client with an Electron-based app and buried the standard chat interface behind Work and Codex features.

product update

NVIDIA NeMo Automodel integrates with Hugging Face Diffusers for distributed video and image model fine-tuning

NVIDIA and Hugging Face have integrated NeMo Automodel with the Diffusers library, enabling distributed fine-tuning of video and image diffusion models without checkpoint conversion. The integration supports models including FLUX.1-dev (12B), Wan 2.1 (1.3B/14B), and HunyuanVideo (13B) with full fine-tuning and LoRA options.

product update

AWS launches Managed Knowledge Base for Bedrock with 6 enterprise connectors and automatic ACL enforcement

Amazon Web Services launched Managed Knowledge Base for Bedrock in general availability, offering a fully managed retrieval solution with six native enterprise connectors including SharePoint, Confluence, and Google Drive. The service handles document parsing up to 500 MB for PDFs, 2 GB for audio, and 10 GB for video, with real-time access control list verification at query time.

Comments

Loading...