product updateAnthropic

Cline v3.79.0 adds Claude Opus 4.7 support, Azure Blob Storage integration

TL;DR

Cline, the AI coding assistant, released version 3.79.0 on April 16, 2025, adding support for Anthropic's Claude Opus 4.7 model and Azure Blob Storage as a storage provider. The update also patches an action injection security vulnerability and fixes cache reflection issues.

2 min read
0

Cline v3.79.0 adds Claude Opus 4.7 support, Azure Blob Storage integration

Cline released version 3.79.0 on April 16, 2025, adding support for Anthropic's Claude Opus 4.7 model and introducing Azure Blob Storage as a storage provider option.

New features

The update enables developers to use Claude Opus 4.7, Anthropic's latest model, directly within Cline's coding assistant interface. This follows the recent release of Claude Opus 4.7, which offers improved performance over previous Claude models.

Cline now supports Azure Blob Storage as a storage provider, expanding deployment options for enterprise users already invested in Microsoft's cloud infrastructure. The update also adds globalSkills to remote configuration, allowing teams to define shared capabilities across instances.

Security and bug fixes

Version 3.79.0 patches an action injection security vulnerability that could have allowed malicious prompts to execute unintended actions. The severity level and exploitation details were not disclosed in the release notes.

The update fixes cache reflection issues affecting both Cline and Vercel API handlers, which previously caused inconsistent behavior when retrieving cached data. Another fix addresses a bug where terminal commands ending unexpectedly would cause the command_output process to hang indefinitely.

The release adds use_subagents to the system prompt for GLM, Hermes, and XS models, improving multi-agent coordination for these model families.

Deprecated features

Cline removed its deprecated evals tool in this release. The company has not specified whether a replacement evaluation framework is planned or if users should migrate to third-party solutions.

What this means

This update demonstrates Cline's strategy of rapidly integrating newly released models while expanding enterprise deployment options. The Claude Opus 4.7 integration arrives within weeks of Anthropic's release, showing tight coupling with frontier model providers. The security patch for action injection highlights ongoing challenges in securing AI coding assistants against prompt-based attacks. Enterprise users gain more flexibility with Azure Blob Storage support, though the removal of the evals tool may force teams to build custom testing infrastructure.

Related Articles

product update

Cline v3.86.0 Adds Claude Opus 4.8 and Moonshot Kimi K2.6 Support

Cline v3.86.0 adds provider support for Claude Opus 4.8, including 1M-context variants where available, and Moonshot Kimi K2.6 models. The update also fixes prompt-cache support display for Qwen 3.7 Max.

product update

Microsoft strips color from Copilot interface in pursuit of 'intelligence that feels present but not imposing'

Microsoft has rolled out a visual overhaul for Copilot in Microsoft 365, replacing the colorful interface with a predominantly black-and-white, text-forward design. The redesign, aimed at making the AI assistant feel "present but not imposing," includes a new adaptive prompt surface and consistent side panel placement across Word, PowerPoint, and Excel.

product update

Mistral rebrands Le Chat to Vibe, launches autonomous coding agent and work automation platform

Mistral AI has rebranded Le Chat as Vibe, introducing two new agent modes: Work Mode for multi-step business tasks across connected apps, and Code Mode for autonomous coding from pull request to merge. The service includes a new VS Code extension and starts at $14.99/month for Pro tier.

changelog

OpenCode v1.15.13 Adds Session Metadata API, Fixes Anthropic Opus 4.7 Adaptive Reasoning Bug

OpenCode v1.15.13 introduces custom session metadata storage through its API and SDK. The release fixes a bug where Anthropic's Opus 4.7+ adaptive reasoning returned empty thinking blocks instead of summarized thinking.

Comments

Loading...