Claude Code v2.1.162
Released Jun 3, 2026 (2 months ago).
148 issues reference this build
11 still open
137 resolved (93%)
"References this build" means the issue body mentions running 2.1.162 (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 v2.1.162
Ranked by community engagement (reactions and comments).
- [Bug] deep-research workflow aborts entire run (and burns millions of tokens) when any schema-bound subagent fails to emit StructuredOutput
- [BUG] effortLevel "max" in settings.json ignored at session start (downgrades to high) — v2.1.162, regression of #43322
- [BUG] Fullscreen renderer corrupts pasted multibyte UTF-8 (Korean/CJK) on Windows — bytes decoded as Latin-1; default renderer unaffected
- [BUG] Pressing Ctrl-O (scrollback) while an AskUserQuestion is pending dismisses it as "User declined to answer questions"
- Auto-compact fails to trigger on Sonnet 4.6, session grows past 200K limit and becomes unrecoverable
- [BUG] System prompt consumes ~9.3M tokens on every session after installing Claude Desktop on Windows (WSL setup)
- [Bug] API Error: Usage Policy violation on simple requests
- [BUG] Everything I do is a violation
- Prompt suggestions (grey ghost-text, Tab to accept) never appear in GUI app despite promptSuggestionEnabled: true
- opusplan downgrades plan mode to Sonnet past 200k — Claude Code regression (it previously auto-compacted at 200k and kept Opus)
- [BUG]Cannot authenticate Claude Code on headless remote server (VPS)
- Voice: "No audio detected" in long-running session after default input device changes (macOS)
- [BUG] Parallel sub-agents permanently wedge after completing work — unkillable, ignore queued input, "Tool result missing due to internal error", 8h+ zombies (Windows, 2.1.162)
- [BUG] Mouse-wheel/trackpad scroll far too fast in fullscreen TUI on Cursor (macOS), even at CLAUDE_CODE_SCROLL_SPEED=1
- [Feature Request] TUI fullscreen mode incompatible with tmux scroll history and customizable keybindings
- [Bug] Agent ignores repeated user instructions to stop actions
- [Bug] Bash tool output capture fails with false "disk full" (ENOSPC) error on macOS
- Worktree-relocated background agent sessions crash-loop on reopen from the agents view ("No conversation found with session ID")
- [BUG] 5 hour usage limit reached - but I have not used Claude in over a day
- [Feature Request] Add user:design OAuth scopes to Claude Code authentication
- [Bug] Unattributable prompt injection instruction detected in Claude Code session after plugin installation
- [BUG] Claude Desktop (macOS): file-attachment chip from agent file-delivery is not clickable (click is a no-op)
- [Bug] Claude Sonnet ignores user instructions and makes unauthorized code changes
- [Bug] Anthropic API Error: Usage credits required for 1M context window
- [Bug] `/exit` command not recognized or documented
- Background daemon sessions fail permanently on transient socket errors — no retry/reconnect
- [Bug] Approval prompt fails to render intermittently, causing session to hang
- [BUG] MCP stdio: tool result written by server in <100ms is never processed — 3-min stall, then "[Tool result missing due to internal error]" (Windows, 2.1.162)
- Permission rules should (optionally) evaluate against the original input when a PreToolUse hook returns updatedInput
- [Bug] Anthropic API Error: Server-side rate limiting without retry guidance
Changelog
What's changed
claude agents --jsonnow includeswaitingForshowing what a waiting session is blocked on (e.g. permission prompt)--tools: explicitly listing Grep/Glob now provides the dedicated search tools on native builds with embedded search (previously these names were silently ignored)/effortnow confirms when your chosen level will persist as the default for new sessions- Clicking a slash command in the autocomplete menu now fills it into your prompt instead of running it immediately; press Enter to run
- Remote Control now shows as a persistent footer pill (with a link to the session) instead of a startup message
- Renamed Windsurf to Devin Desktop in the
/idemenu,/terminal-setup, and/scroll-speed, following the editor's rebrand - Fixed a silent startup hang when the config directory is read-only or unwritable — Claude Code now starts with in-memory config and surfaces startup errors instead of showing a blank screen
- Fixed WebFetch permission rules not being applied to built-in preapproved domains; explicit
WebFetch(domain:...)deny/ask/allow rules now take precedence over the preapproved-host auto-allow - Fixed Windows permission rules never matching when spelled with backslashes (
~\,\\server\share) or case-variant paths, and Read deny rules not hiding files from Glob/Grep results - Fixed an interrupt (Esc) sent at the very start of a turn being silently dropped in stream-json/SDK sessions, leaving the turn running with no "Interrupted" feedback
- Fixed API 400
no low surrogate in stringerrors for classifier side-queries and MCP server descriptions containing emoji near a truncation boundary - Fixed MCP per-server
timeoutconfig values below 1000 ms being floored to a 1-second watchdog that aborted every tool call; sub-1000 ms values are now ignored (falling back toMCP_TOOL_TIMEOUTor default), andclaude mcp getannotates them accordingly - Fixed the LSP tool's
workspaceSymboloperation returning no results; it now accepts aqueryparameter and passes it to the language server - Fixed
claude agentscutting live status text (tool args, replies, prompts, exec output) at 60–120 columns on wide terminals; the status detail now uses the full terminal width - Fixed
claude agentstruncating long session names at 40 columns; the name column now grows with terminal width - Fixed
claude agentsattach occasionally bouncing straight back to the session list on the first try after a background-service restart - Fixed
claude agentsCtrl+V image paste doing nothing in the dispatch input and the session reply box; pasting with no image now shows a hint - Fixed backgrounding a session with ← silently losing the conversation when the background service cannot start; the session stays in the list as a failed row you can wake with Enter
- Fixed replies from the agents view that fail to send being lost; they are now queued for delivery on the next session start
- Fixed cross-session messaging (
SendMessage) silently breaking whenCLAUDE_CODE_TMPDIRor$TMPDIRpoints at a deep directory - Fixed opening a running background session from
claude agentsstalling for 5 seconds before attaching - Quieter startup: notices group by severity, and session info and announcements share a single line per launch
- Startup warnings rewritten to be shorter and clearer, each with a concrete fix
- Launch-prompt warnings (deep link/pre-filled prompt) now stay pinned below the input until you act instead of scrolling away
- Failed turns now show a compact warning line instead of a multi-line red error block
- Improved background service startup and
claude updateverification to wait out endpoint-security scanning of new binaries instead of failing after 5 seconds - Background dispatch spawn failures now report the error class name when no errno is available
- Removed the "Claude in Chrome enabled" and "marketplace installed" startup messages; model auto-updates and the team-onboarding tip n