This release introduces a new project purge command for comprehensive deletion of all project state, along with enhanced OAuth login capabilities, particularly for environments like WSL2 or SSH. Key changes include improved model listing from Anthropic-compatible gateways, broader bypassing of permission prompts via --dangerously-skip-permissions, and better Windows PowerShell detection and usage. Significant reliability improvements cover session stability, addressing timeouts during long thinking pauses and after system sleep, fixing large image paste issues, and resolving multiple OAuth login failures. A critical security fix prevents managed domain settings from being ignored, alongside numerous other quality-of-life and performance enhancements.
Changed12
- The `/model` picker now lists models from your gateway's `/v1/models` endpoint when `ANTHROPIC_BASE_URL` points at an Anthropic-compatible gateway
- - Added `claude project purge [path]` to delete all Claude Code state for a project (transcripts, tasks, file history, config entry) — supports `--dry-run`, `-y/--yes`, `-i/--interactive`, and `--all`
- `--dangerously-skip-permissions` now bypasses prompts for writes to `.claude/`, `.git/`, `.vscode/`, shell config files, and other previously-protected paths (catastrophic removal commands still prompt as a safety net)
- `claude auth login` now accepts the OAuth code pasted into the terminal when the browser callback can't reach localhost (WSL2, SSH, containers)
- `claude_code.skill_activated` OpenTelemetry event now fires for user-typed slash commands and carries a new `invocation_trigger` attribute (`"user-slash"`, `"claude-proactive"`, or `"nested-skill"`)
- Auto mode: the spinner now turns red when a permission check stalls, instead of looking like the tool is running
- Host-managed deployments (`CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST`) no longer auto-disable analytics on Bedrock/Vertex/Foundry
- Windows: PowerShell 7 installed via the Microsoft Store, MSI without PATH, or `.NET global tool` is now detected
- Windows: when the PowerShell tool is enabled, Claude now treats PowerShell as the primary shell instead of defaulting to Bash
- Read tool: removed the per-file malware-assessment reminder that could cause spurious refusals and "this is not malware" commentary on legacy models
- Bounded total size of file-modified reminders when a linter touches many files at once
- PowerShell tool: bare `--` (e.g. `git diff -- file`) is no longer mis-flagged as the `--%` stop-parsing token
Fixed20
- **Security:** Fixed `allowManagedDomainsOnly` / `allowManagedReadPathsOnly` being ignored when a higher-priority managed-settings source lacked a `sandbox` block
- Fixed pasting an image larger than 2000px breaking the session — images are now downscaled on paste, and oversized images in history are automatically removed and the request retried
- Fixed showing the login screen for "OAuth not allowed for organization" errors — now shows guidance to contact your admin
- Fixed OAuth login failing with timeout on slow or proxied connections, in IPv6-only devcontainers, and when the browser callback can't reach localhost
- Fixed a rare race where a concurrent credential write could clear a valid OAuth refresh token
- Fixed API retry countdown sticking at "0s" instead of counting down between attempts
- Fixed "Stream idle timeout" error after waking Mac from sleep mid-request
- Fixed background and remote sessions falsely aborting with "Stream idle timeout" during long model thinking pauses
- Fixed a hang where the assistant could finish thinking but show no output after a run of empty turns
- Fixed overly fast trackpad scrolling in Cursor and VS Code 1.92–1.104 integrated terminals
- Fixed claude.ai MCP connectors being suppressed by manual servers stuck in needs-auth state
- Fixed Japanese/Korean/Chinese text rendering as garbled characters on Windows in no-flicker mode
- Fixed `Ctrl+L` clearing the prompt input — it now only forces a screen redraw, matching readline behavior
- Fixed deferred tools (WebSearch, WebFetch, etc.) not being available to skills with `context: fork` and other subagents on their first turn
- Fixed plan-mode tools being unavailable in interactive sessions launched with `--channels`
- Fixed `/plugin` Uninstall reporting "Enabled" instead of "Uninstalled"
- Fixed `/remote-control` retries appearing stuck on "connecting…" — each retry now shows its result
- Fixed Remote Control failure notification not showing the error reason for initial connection failures
- Windows: clipboard writes no longer expose copied content in process command-line arguments visible to EDR/SIEM telemetry; also fixes >22KB selections not reaching the clipboard
- Fixed Agent SDK hang when the model emits a malformed tool name in a parallel tool call batch
Earlier 2.1.126 release · April 30, 2026
Changed12
- The `/model` picker now lists models from your gateway's `/v1/models` endpoint when `ANTHROPIC_BASE_URL` points at an Anthropic-compatible gateway
- - Added `claude project purge [path]` to delete all Claude Code state for a project (transcripts, tasks, file history, config entry) — supports `--dry-run`, `-y/--yes`, `-i/--interactive`, and `--all`
- `--dangerously-skip-permissions` now bypasses prompts for writes to `.claude/`, `.git/`, `.vscode/`, shell config files, and other previously-protected paths (catastrophic removal commands still prompt as a safety net)
- `claude auth login` now accepts the OAuth code pasted into the terminal when the browser callback can't reach localhost (WSL2, SSH, containers)
- `claude_code.skill_activated` OpenTelemetry event now fires for user-typed slash commands and carries a new `invocation_trigger` attribute (`"user-slash"`, `"claude-proactive"`, or `"nested-skill"`)
- Auto mode: the spinner now turns red when a permission check stalls, instead of looking like the tool is running
- Host-managed deployments (`CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST`) no longer auto-disable analytics on Bedrock/Vertex/Foundry
- Windows: PowerShell 7 installed via the Microsoft Store, MSI without PATH, or `.NET global tool` is now detected
- Windows: when the PowerShell tool is enabled, Claude now treats PowerShell as the primary shell instead of defaulting to Bash
- Read tool: removed the per-file malware-assessment reminder that could cause spurious refusals and "this is not malware" commentary on legacy models
- Bounded total size of file-modified reminders when a linter touches many files at once
- PowerShell tool: bare `--` (e.g. `git diff -- file`) is no longer mis-flagged as the `--%` stop-parsing token
Fixed21
- **Security:** Fixed `allowManagedDomainsOnly` / `allowManagedReadPathsOnly` being ignored when a higher-priority managed-settings source lacked a `sandbox` block
- Fixed pasting an image larger than 2000px breaking the session — images are now downscaled on paste, and oversized images in history are automatically removed and the request retried
- Fixed showing the login screen for "OAuth not allowed for organization" errors — now shows guidance to contact your admin
- Fixed OAuth login failing with timeout on slow or proxied connections, in IPv6-only devcontainers, and when the browser callback can't reach localhost
- Fixed a rare race where a concurrent credential write could clear a valid OAuth refresh token
- Fixed API retry countdown sticking at "0s" instead of counting down between attempts
- Fixed "Stream idle timeout" error after waking Mac from sleep mid-request
- Fixed background and remote sessions falsely aborting with "Stream idle timeout" during long model thinking pauses
- Fixed a hang where the assistant could finish thinking but show no output after a run of empty turns
- Fixed overly fast trackpad scrolling in Cursor and VS Code 1.92–1.104 integrated terminals
- Fixed claude.ai MCP connectors being suppressed by manual servers stuck in needs-auth state
- Fixed Japanese/Korean/Chinese text rendering as garbled characters on Windows in no-flicker mode
- Fixed `Ctrl+L` clearing the prompt input — it now only forces a screen redraw, matching readline behavior
- Fixed deferred tools (WebSearch, WebFetch, etc.) not being available to skills with `context: fork` and other subagents on their first turn
- Fixed plan-mode tools being unavailable in interactive sessions launched with `--channels`
- Fixed blank remote-session transcript when certain messaging tools are unavailable
- Fixed `/plugin` Uninstall reporting "Enabled" instead of "Uninstalled"
- Fixed `/remote-control` retries appearing stuck on "connecting…" — each retry now shows its result, and unenrolled trusted-device failures are caught up-front
- Fixed Remote Control failure notification not showing the error reason for initial connection failures
- Windows: clipboard writes no longer expose copied content in process command-line arguments visible to EDR/SIEM telemetry; also fixes >22KB selections not reaching the clipboard
- Fixed Agent SDK hang when the model emits a malformed tool name in a parallel tool call batch
Never miss a Claude Code release.
Get a push notification the moment the next version ships.
Get Claude DropsNew to the changelog? Read our guide to reading the Claude Code changelog or browse all releases.