← All updates

DAILY RELEASE TRACKER

Claude Code

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

GitHub releasesLast checked: Oct 05, 2026Refreshes daily
v2.1.289Latest

v2.1.289

Explanation

This update resolves critical stability and security issues, including terminal freezes from complex shell syntax, symlink bypasses in read deny rules, and sandbox auto-allow loopholes. It also fixes plugin rendering bugs and authentication regressions, ensuring reliable operation for managed enterprise environments.

Official highlights

  • Fixed a deny or ask rule on a nested part of a compound shell command not holding over a user-installed mod's approval on managed machines
  • Fixed the terminal freezing on short code blocks with many unclosed `<script>` tags or deeply nested `${` substitutions
  • Fixed `Read` deny rules not applying to files @-mentioned, changed, or selected in the IDE through a symlink
  • [VSCode] Reverted a 2.1.288 change to `claude auth status` that may have made sign-outs more frequent
Read original update →
v2.1.288

v2.1.288

Explanation

This update enhances mod development with $.ui.selection and improves cloud session reliability by adding a built-in gh api and fixing control character handling. It also resolves critical session continuity issues, including prompt recovery after Ctrl+C, auto-compaction for long conversations, and robust resume functionality for partial responses and thinking traces.

Official highlights

  • Added `$.ui.selection()` for mods: returns the text you last selected in fullscreen mode and, when the selection lies within one transcript row, that row
  • Added a built-in `gh api` to cloud sessions whose image has no GitHub CLI, and fixed the built-in sending control characters from file names, jq filters or GitHub errors to the terminal
  • Added recovery for a prompt cleared with Ctrl+C: pressing Up on the empty prompt brings the draft back, including pasted text and images
  • Added a re-authenticate prompt when an MCP server asks for more OAuth scope during a tool call
Read original update →
v2.1.287

v2.1.287

Explanation

Claude Code v2.1.287 introduces Claude Mods for deeper plugin behavior and a new 'You should know' side agent, while fixing critical remote session stability and OpenTelemetry instrumentation issues. These changes enhance observability and reliability for developers and operators managing complex AI workflows.

Official highlights

  • Added Claude Mods: plugins may now modify deeper behavior
  • Added You should know, a built-in mod where a side agent watches your back and flags things you or Claude might miss. Turn it on with `/plugin enable cc-plugin-you-should-know@builtin` (for first-party sessions with telemetry on)
  • Added an `n:<text>` filter to the agents view that matches session names and tasks; a filter now shows matches in collapsed sections and Enter opens the first match
  • Added `prompt_text` to the OpenTelemetry `user_prompt` event, a copy of `prompt` for backends that nest dotted keys; drop or mask it wherever you drop or mask `prompt` (anthropics/claude-code#70763)
Read original update →
v2.1.286

v2.1.286

Explanation

This update enhances UX with permission counters and mouse support, while critically fixing session stability issues like parallel tool call crashes and credential refresh loops. It also resolves API errors from non-text tool outputs and optimizes pricing logic for prompt caching and streamed server-side tools.

Official highlights

  • Added a count such as "2 of 5" to the permission prompt when several permission requests stack up
  • Added mouse support for the "N more" rows of lists in fullscreen mode: click one to jump to that end of the list, with hover and pressed states
  • Fixed several Claude Code processes and IDE extensions each opening a login browser when gcpAuthRefresh or awsAuthRefresh credentials expire
  • Fixed `claude --resume` and `--continue` sometimes losing every turn after a batch of parallel tool calls when the earlier session crashed or was killed
Read original update →
v2.1.285

v2.1.285

Explanation

This update enhances security and operational control by introducing the CLAUDE_CODE_DISABLE_WEB_FETCH environment variable and allowedProviders managed setting to restrict API usage. It also improves plugin management with new configuration commands and fixes critical bugs in SSH-based installations and subagent execution.

Official highlights

  • Added `CLAUDE_CODE_DISABLE_WEB_FETCH` environment variable to turn off the WebFetch tool
  • Added `claude --desktop` to open the Claude desktop app on the current directory, or on a session with `--continue` / `--resume <id>`
  • Added `claude plugin configure <plugin>` to show a plugin's options and which are unset, or save new values read from stdin with `--values-stdin`
  • Added `<server>.<key>=<value>` to `claude plugin install --config`, so a bundled `.mcpb` MCP server's own settings can be set at install time and it starts without visiting `/plugin` → Configure
Read original update →
v2.1.284

v2.1.284

Explanation

This update introduces Claude Sonnet 5.5 as the default model with 1M context and new pricing, while enhancing operational control via customizable effort keybindings and improved gateway telemetry and authentication features.

Official highlights

  • Added Claude Sonnet 5.5 (`claude-sonnet-5-5`), now the default Sonnet model on the Anthropic API — 1M context, $2/$10 per Mtok with $0.20/Mtok cache reads
  • Added a "Yes, but ask again next time" answer to auto mode's prompt before a read outside the working directories, so you can allow that one read and still be asked about later ones
  • Added `effortSlider:decreaseEffort`, `increaseEffort` and `toggleUltracode` keybinding actions, so the `/effort` slider's arrow and Tab keys can be rebound in `keybindings.json`
  • Added `/rate-limit-options` to `/help` and the command menu for claude.ai subscribers, so the usage-limit notices that mention it point to a command you can find
Read original update →
v2.1.283

v2.1.283

Explanation

This update enhances observability and governance by adding prompt grouping headers, OpenTelemetry span details, and granular model allow/deny settings. It also resolves critical SDK session persistence bugs and improves MCP server lifecycle management for more reliable agent operations.

Official highlights

  • Added `x-claude-code-prompt-id` to the gateway hint headers so LLM gateways can group the requests that serve one user prompt; opt in with `CLAUDE_CODE_GATEWAY_HINT_HEADERS=1`
  • Added `availableModelsMatch` managed setting: with `"exact"`, an `availableModels` entry allows only the model version it names, so new releases stay blocked until listed
  • Added `deniedModels` managed setting to block specific models, even when `availableModels` allows them
  • Added MCP tool, WebFetch and WebSearch outputs to the `tool.output` OpenTelemetry span event when `OTEL_LOG_TOOL_CONTENT=1`
Read original update →
v2.1.282

v2.1.282

Explanation

This update enhances terminal UX with configurable prose width and improves operational resilience by fixing session continuity issues, retrying failed compaction, and maintaining readiness during database failovers. It also resolves critical API errors related to web search decryption and extended thinking blocks, ensuring more stable long-running conversations.

Official highlights

  • Added a `maxProseWidth` setting that caps the width of Claude's prose in wide terminals while tables and code blocks keep the full width
  • Added a startup notice, and `/status` and `claude doctor` entries, listing telemetry variables in a project's settings files that were ignored or that turned telemetry off
  • Added the `allowClaudeInChromeWithManagedMcp` managed setting to let `claude --chrome` run alongside an exclusive `managed-mcp.json`; the error shown when Chrome is blocked now names it
  • Added `store.readiness_grace_seconds` to the Claude apps gateway so `/readyz` can stay ready through a short Postgres outage such as a database failover
Read original update →