← All updates

DAILY RELEASE TRACKER

Claude Code

Anthropic’s terminal-native coding agent and developer workflow tool.

GitHub releasesLast checked: Nov 01, 2026Refreshes daily
v2.1.316Latest

v2.1.316

Explanation

Claude Code v2.1.316 focuses on model selection, reasoning, or inference behavior, developer workflow and CLI productivity, integrations, APIs, connectors, or MCP support. This note is useful as a direction signal for teams tracking AI agent tooling and production workflows.

Official highlights

  • Added `CLAUDE_CODE_DISABLE_ULTRATHINK`, which turns the `ultrathink` keyword off
  • Added pooled group budgets to the Claude apps gateway: one monthly budget that a group's members share, on top of each member's own limit, set with `pooled_budget` on the spend limits admin API
  • Added `CLAUDE_CODE_DISABLE_LOOPED_CROSS_CERT_DROP` to keep system cross-certificates that certify each other in a loop, for servers whose private CA needs one
  • Added `CLAUDE_CODE_SUBAGENT_EFFORT` to set the effort level subagents run at when nothing else names one, instead of inheriting the session's
Read original update →
v2.1.314

v2.1.314

Explanation

Claude Code v2.1.314 focuses on security, authentication, or permission flow changes, model selection, reasoning, or inference behavior, developer workflow and CLI productivity. This note is useful as a direction signal for teams tracking AI agent tooling and production workflows.

Official highlights

  • Added `permissions.blockWritesOutsideWorkingDirectories`: Write, Edit and NotebookEdit refuse paths outside the working directories in every permission mode
  • Added an optional `groups` list to Claude apps gateway upstreams: only developers in the listed IdP groups are sent to that upstream, on failover too
  • Added `guardrail_trace` to Claude apps gateway Bedrock upstreams, to log which Amazon Bedrock guardrail filter fired on a request, without the matched text
  • Added idle compaction to VS Code and Claude Desktop's Code tab: a 200K+ token conversation left idle is summarized, and the summary is used on your next message if the prompt cache has expired
Read original update →
v2.1.312

v2.1.312

Explanation

Claude Code v2.1.312 focuses on model selection, reasoning, or inference behavior, developer workflow and CLI productivity, memory, context handling, or conversation state. This note is useful as a direction signal for teams tracking AI agent tooling and production workflows.

Official highlights

  • Added `oidc.user_id_claim` to the Claude apps gateway, to identify people by an id_token claim other than `sub`, such as Microsoft Entra ID's `oid`
  • Added click to send: in fullscreen, clicking the "to send now" hint under a queued message sends it right away, as its key does
  • Fixed managed settings and organization policy not being fetched for the rest of the session after signing in from the VS Code extension
  • Fixed Claude overwriting a very large CLAUDE.md, rules file or @-included file in a subdirectory after seeing only its start; Write now asks Claude to read it all or edit in place
Read original update →
v2.1.311

v2.1.311

Explanation

Claude Code v2.1.311 focuses on model selection, reasoning, or inference behavior, developer workflow and CLI productivity, memory, context handling, or conversation state. This note is useful as a direction signal for teams tracking AI agent tooling and production workflows.

Official highlights

  • Added `--hold-idle-file` and `--max-hold-min` to `self-hosted-runner`, to keep an idle session while your host reports processes it left running
  • Added a tip for the Explanatory output style, shown when you ask Claude for explanations
  • Fixed long freezes at startup and after reading or editing files when a CLAUDE.md file holds a very long list item
  • Fixed interrupting Claude not taking effect until a timeout while an MCP server had not answered a resource read or a skill was still downloading
Read original update →
v2.1.310

v2.1.310

Explanation

This update enhances reliability by fixing request failures behind gateways that reject specific beta headers and resolving compaction issues that caused repeated 'Prompt is too long' errors with dense content like base64. It also improves operational stability by correcting background cleanup logic for large retention periods and fixing file permission prompts for symbolic links, ensuring smoother execution in complex development environments.

Official highlights

  • Added the Monitor tool and plugin monitors on Bedrock, Vertex, and Foundry, and when telemetry or nonessential traffic is disabled; long foreground sleeps are now blocked there too
  • Fixed requests failing behind some gateways and compatible servers that reject the `effort-2025-11-24` beta value or mid-conversation system messages; Claude Code now retries without them
  • Fixed background cleanup deleting some recent files, such as pasted images, when `cleanupPeriodDays` is set to a very large value
  • Fixed compaction after a "Prompt is too long" error keeping too much of a conversation with dense text, such as base64 or SVG, so the next request could fail again
Read original update →
v2.1.309

v2.1.309

Explanation

This update resolves critical security vulnerabilities in Claude Code's sandboxing and MCP integration, specifically addressing issues where startup files, symlinked paths, and configuration files could be modified outside intended restrictions. It also stabilizes worktree isolation and permission checks for Bash and Zsh, ensuring that operators and developers maintain strict control over AI agent actions and prevent unintended side effects in complex shell environments.

Official highlights

  • Fixed sandboxed Bash commands on macOS and Linux running the shell's startup files outside the sandbox before each command
  • Fixed macOS sandbox `denyWrite` glob patterns not applying at a path's real location when the pattern's folder is reached through a symlink
  • Fixed sandboxed commands and auto-accepted edits being able to modify the MCP config file passed with `--mcp-config`
  • Fixed a disabled MCP server being reconnected by a later permission prompt in print and SDK sessions
Read original update →
v2.1.308

v2.1.308

Explanation

The v2.1.308 release for Claude Code focuses exclusively on bug fixes and reliability improvements, addressing underlying stability issues without introducing new features. This update ensures a more consistent and dependable development environment for technical teams relying on the tool for automated coding tasks.

Official highlights

  • Bug fixes and reliability improvements
Read original update →
v2.1.307

v2.1.307

Explanation

This update introduces granular OpenTelemetry safety instrumentation and an explicit API versioning command, enhancing observability for AI product teams while resolving critical stability issues with MCP server authentication, retry logic, and context window handling on macOS and Linux.

Official highlights

  • 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 sent back
  • Fixed requests failing with a model-not-found error when `CLAUDE_CODE_DISABLE_1M_CONTEXT` is set and the model is an alias with the `[1m]` suffix, such as `opus[1m]`
  • Fixed the `prompt-caching-scope` beta header being sent behind custom `ANTHROPIC_BASE_URL` gateways and on Foundry, where it has no effect
Read original update →