Claude Code v2.1.126
Released May 1, 2026 (4 months ago).
⚠ Elevated report volume. This build drew 398 issue reports —
more than double the typical release (160 median). That can mean a regression, or simply
that many users happened to be on this build. Skim the reports below before deciding to upgrade.
398 issues reference this build
13 still open
385 resolved (97%)
"References this build" means the issue body mentions running 2.1.126 (from the
bug-report template). It reflects report volume, not a proven defect count — an issue may mention a
version without being caused by it. First-party data from the anthropics/claude-code tracker.
Top issues reported on v2.1.126
Ranked by community engagement (reactions and comments).
- [BUG] npm install now ships Bun binary (v2.1.126) — npm workaround for non-AVX VPS is dead, no upgrade path
- [BUG] .devcontainer/init-firewall.sh: statsig.anthropic.com fails DNS resolution, aborts container startup
- Korean outputs use informal/slang verb "박다" (bakda) at 18× baseline frequency
- /rewind says "conversation will be forked" but never creates a resumable fork
- [BUG] Single README.md edit burns entire 5-hour Max 5x window in 9m 39s (Opus 4.7 1M, resumed session, v2.1.126, JetBrains, Windows)
- [BUG] Sandbox fails with "bwrap: loopback: Failed RTM_NEWADDR: Operation not permitted" on Ubuntu 25.10 / kernel 6.17 (still broken, ref #14719)
- [BUG] Can't upgrade Pro → Max: payment authentication fails on every card/method
- [BUG] Remote MCP OAuth requests every scope from oauth-authorization-server.scopes_supported, causing invalid_scope on GitLab self-hosted
- PowerShell tool fails with exit code 1 on Windows when pwsh installed via winget
- [BUG] Agent Teams: Single teammate spawn creates 10-151 duplicate worker instances, each consuming full context and actively editing files
- ~/.claude/settings.json loads in sessions started with CLAUDE_CONFIG_DIR pointing elsewhere (hooks, statusLine, env, model, enabledPlugins all bleed)
- [BUG] Subagent permission cascade-failure when multiple Agent tool calls in one message (2.1.126)
- [BUG] Claude Code extension webview tab restoration hangs Cursor IDE on workspace startup
- [BUG] Answer to a queued mid-turn user message is written between tool calls and never displayed; model later insists it answered
- claude_code_cost_usage_USD_total OTEL counter collides across parallel processes sharing the same session_id, producing oscillating values and inflating increase() queries by 100×+
- [Bug] Process exits with code 127 (command not found)
- [BUG] Markdown auto-fix on numbered lists can change context/meaning
- [Bug] Claude Code performance degradation - slow response times
- [Bug] OTel: skill_activated masks skill.name to "custom_skill" while api_request events and cost/token metrics export it verbatim (regression since ~2.1.126)
- [BUG] PowerShell tool fails with "Command line is invalid" on Windows (Japanese locale) since v2.1.124
- [Bug] Plugin paths stored as absolute paths break cross-environment usage (devcontainers, multi-user setups)
- [BUG] Deterministic Bun startup segfault at USER32.dll+0xbe584 / address 0x3C on Windows 11 build 26200 (claude.exe 2.1.114+) — distinct from 0xFFFFFFFFFFFFFFFF family
- [Bug] Elevated error rate in API responses
- [Bug] /ultrareview GitHub authentication fails despite valid gh credentials
- [Bug] Hook subprocess cleanup causes 100% CPU freeze on task interruption
- You've hit your limit · resets 9:10pm (Europe/Kiev)
- /rewind picker accepts selection but main screen does not re-render (v2.1.126)
- [Bug] Permission allowlist and mode toggles not suppressing Read/Write/Edit prompts
- [BUG] Sub-agent dispatched via Agent tool stalls silently on MCP permission gate — no surface to parent CLI UI
- Wide-table fallback leaves stale bordered paint in scroll buffer alongside the key-value re-render
Changelog
What's changed
- The
/modelpicker now lists models from your gateway's/v1/modelsendpoint whenANTHROPIC_BASE_URLpoints 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-permissionsnow 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 loginnow accepts the OAuth code pasted into the terminal when the browser callback can't reach localhost (WSL2, SSH, containers)claude_code.skill_activatedOpenTelemetry event now fires for user-typed slash commands and carries a newinvocation_triggerattribute ("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 toolis 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
- Security: Fixed
allowManagedDomainsOnly/allowManagedReadPathsOnlybeing ignored when a higher-priority managed-settings source lacked asandboxblock - 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+Lclearing 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: forkand other subagents on their first turn - Fixed plan-mode tools being unavailable in interactive sessions launched with
--channels - Fixed
/pluginUninstall reporting "Enabled" instead of "Uninstalled" - Bounded total size of file-modified reminders when a linter touches many files at once
- Fixed
/remote-controlretries 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
- PowerShell tool: bare
--(e.g.git diff -- file) is no longer mis-flagged as the--%stop-parsing token - Fixed Agent SDK hang when the