Anthropic

**Full Changelog**: https://github.com/anthropics/claude-code-action/compare/v1.0.239...v1.0.240

## What's changed - 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 - Added `--max-findings <n>|all` to /code-review to report more or fewer findings than the usual limit; the choice is reused until you pass `--max-findings default` - Added Ctrl+F to find a session by name and Alt+↑/↓ to jump between groups in the agents view; both, and rename, can be rebound in keybindings.json - Added a screen reader mode announcement of the new permission mode when you approve a

**Full Changelog**: https://github.com/anthropics/claude-code-action/compare/v1.0.238...v1.0.239

## What's changed - 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) - Added URL prompts from MCP servers on the 2025-11-25 protocol, for example to sign in. If a server no longer connects after this update, add "bareElicitationCapability": true to its MCP config entry - Windows: Added a startup warning when denying the Bash tool also turns off the PowerShell tool, so Claude has no shell

Material Event filed 2026-10-01

## What's Changed * ci: security hardening for GitHub Actions workflows that call Claude by @qing-ant in https://github.com/anthropics/claude-code-action/pull/1867 ## New Contributors * @qing-ant made their first contribution in https://github.com/anthropics/claude-code-action/pull/1867 **Full Changelog**: https://github.com/anthropics/claude-code-action/compare/v1.0.237...v1.0.238

## What's changed - 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 - Fixed API 400 errors after a tool or hook returned an object, number or boolean instead of text, including in resumed sessions - Fixed cloud sessions with very large histories never waking up because the container was stopped while the transcript was still loading - Fixed the Claude apps gateway's spend meter pricing 1-hour prompt cache writes at the cheaper 5-minute rate, and counting only the first model call's input tokens on str

## What's Changed * Make nine tests able to fail, and cover globToRegex and the public export list by @ronleizrowice-ant in https://github.com/anthropics/sandbox-runtime/pull/570 * Correct five false statements, and remove dead and duplicated code by @ronleizrowice-ant in https://github.com/anthropics/sandbox-runtime/pull/571 * test: fix the typecheck of the seccomp suite that broke main by @ronleizrowice-ant in https://github.com/anthropics/sandbox-runtime/pull/583 * linux: exit status under zsh, and import zod/v3 by @ronleizrowice-ant in https://github.com/anthropics/sandbox-runtime/pull/590 * Write limits are judged by where a write lands: say so, and test it by @ronleizrowice-ant in https://github.com/anthropics/sandbox-runtime/pull/614 * linux: bind a deny path that another sandbox makes while the wrap is looking by @ronleizrowice-ant in https://github.com/anthropics/sandbox-runtime/pull/618 * ci: pin workflow inputs, use npm trusted publishing, pack on pull requests by @dylan-con

### Internal/Other Changes - Updated bundled Claude CLI to version 2.1.285 --- **PyPI:** https://pypi.org/project/claude-agent-sdk/0.2.162/ ```bash pip install claude-agent-sdk==0.2.162 ```

**Full Changelog**: https://github.com/anthropics/claude-code-action/compare/v1.0.236...v1.0.237

## What's changed - Added an optional `read.title` (the artifact's stored title) to the Artifact tool's structured read result - Added `provider_not_allowed` to `startup_failure_reason` and `allowedProviders` to the `Settings` type - Fixed sessions with `CLAUDE_CODE_FORK_SUBAGENT=1`: a subagent's own Agent call now runs in the foreground, so the subagent gets the child's result - Fixed `getSessionMessages()` leaving out a message sent while Claude was working when the process stopped before the reply, or when another prompt followed it with no reply in between - Fixed `toggleMcpServer(name, false)` leaving the connection open for a server that had not yet connected when the session started, or whose config was edited after it connected - Fixed `rewind_conversation` leaving a backgrounded MCP tool call running after the message that started it was removed - Changed Bash/PowerShell `timeout` to bound a `run_in_background` command (was ignored; default 30 min, max 2 h); the `stopped` task