Claude Desktop v3.1623.4
Claude Desktop 3.1623.4 for macOS, published to Homebrew as the claude cask.
AI lab · founded 2021
Everything Anthropic ships that we track: 2 AI coding tools and 15 AI models. Last shipped 1h ago.
Photos and logos via Wikimedia Commons, GitHub and company websites; hover one for its credit.
Products
Models
Release history
Claude Desktop 3.1623.4 for macOS, published to Homebrew as the claude cask.
Claude Desktop 3.1623.3 for macOS, published to Homebrew as the claude cask.
What's changed Bug fixes and reliability improvements
What's changed Added /claude-api api-version to move Claude API code to API version 2026-10-21 Added the claude_code.safety_event OpenTelemetry event for each tool call a permission rule, auto mode, a safety check, a hook or the sandbox stopped, prompted or…
Claude Desktop 3.1623.1 for macOS, published to Homebrew as the claude cask.
What's changed Fixed claude -p inside cloud sessions reporting "Not logged in" when started without the session's environment variables Fixed an API error being replaced by "prompt is too long", and an unneeded compaction, in sessions with many MCP tools
What's changed Added sandbox.allowNestedUserNamespaces so sandboxed commands on Linux can create user namespaces (Chromium, rootless podman); this lets them get around the sandbox's file protections Added CLAUDE_CODE_RETRY_WATCHDOG_USAGE_LIMIT_RECHECK_MS so…
Claude Desktop 3.1623.0 for macOS, published to Homebrew as the claude cask.
What's changed Added a transcript line when a plugin that runs first skips one of your mod's hooks, naming the event and the plugin Added decider: "person" to a mod's tool.check answer: only the permission dialog or a host's callback can approve the ask, and…
Claude Desktop 2.42304.2 for macOS, published to Homebrew as the claude cask.
What's changed Bug fixes and reliability improvements
What's changed Added CLAUDE_CODE_AUTO_MODE_MODEL to choose the model the client-side auto mode classifier uses; it does not change the model for server-side auto mode Added an Idle compaction row to /config for turning idle compaction off or back on; the…
What's changed Added CLAUDE_CODE_RETRY_WATCHDOG_MAX_USAGE_LIMIT_WAIT_MS so unattended retry mode (CLAUDE_CODE_RETRY_WATCHDOG) ends a request at a usage limit that resets too far away instead of waiting Added OpenTelemetry tracing guidance to the claude-api…
Claude Desktop 2.42304.0 for macOS, published to Homebrew as the claude cask.
What's changed Added virtualText to a mod's prompt decorations: text drawn in the prompt box that never enters the draft or the submitted prompt Added cache_creation_5m_tokens and cache_creation_1h_tokens to the OpenTelemetry api_request event, splitting cache…
What's changed Added CLAUDE_CODE_DISABLE_FILE_MENTIONS environment variable: Claude gets the paths of @ file mentions to read with its file tools, not the files' contents Added idle compaction in the terminal: a 200K+ token conversation left idle for about 54…
Claude Desktop 2.37337.1 for macOS, published to Homebrew as the claude cask.
What's changed Added a code key to the Claude apps gateway's managed.policies[]: the same settings as cli, also applied in Claude Desktop's Code tab; beside desktop, it turns on Claude Desktop's gateway mode Added autoCompactWindow to subagent frontmatter and…
Claude Desktop 2.31226.1 for macOS, published to Homebrew as the claude cask.
What's changed Added onFailure: "block" for command and HTTP hooks: a hook that can't start, times out, or exits with an unexpected code blocks the action instead of letting it through Added Program Status Protocol (OSC 7501) support: terminals that implement…
In the news
Introducing 𝚍𝚞𝚛𝚊𝚋𝚕𝚎-𝚑𝚊𝚛𝚗𝚎𝚜𝚜. Run Pi, OpenCode, Codex, Claude Code, eve, fx, or your own harness durably on Vercel. With 𝚍𝚞𝚛𝚊𝚋𝚕𝚎-𝚑𝚊𝚛𝚗𝚎𝚜𝚜, agents automatically resume work after failures and run for hours, days, or months.
Devin Fusion has claimed a top score of 68 on the @ArtificialAnlys Coding Agent Index with an Opus 5.5 lead and GPT-6 Luna sidekick. Devin Fusion outperforms Claude Code with Opus 5.5 on both performance and price – earning a score of 68 at a 31% lower cost per task.
Directory