Claude Code v2.1.225
Released Aug 8, 2026 (22 days ago).
28 issues reference this build
26 still open
2 resolved (7%)
"References this build" means the issue body mentions running 2.1.225 (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 v2.1.225
Ranked by community engagement (reactions and comments).
- [BUG] CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH=1 does not disable nesting on 2.1.225; effective depth is one level greater than configured
- Agent teams: per-agent autocompact control + a protocol to compact a context-exhausted teammate
- [BUG] Project-slug write path drops a repeated path segment; read-key ≠ write-key in one session → silent memory split
- macOS: Read of an image >~200KB deadlocks every subsequent API call (surfaces as ECONNRESET after retry ladder); session permanently poisoned incl. --resume
- [Feature Request] Support custom security review plugins without triggering API safety filters
- Desktop (Windows): file links are not clickable when the file is on a different drive than the session cwd
- [BUG] rate_limits absent from statusLine stdin for Team plan sessions — usage data exists server-side
- Agent tool description flips to its subagent variant in the main conversation while in-process teammates are alive — tools_changed cache miss on every fleet phase boundary
- Fullscreen TUI copies never reach the RDP/AVD client clipboard: spawned Set-Clipboard helper exits before the AVD clipboard broker samples the update
- Auto-compaction INCREASES real on-wire context when preTokens diverges (up to 6.34x) and compaction fires below the rebuild floor — 133 net-negative events across 5,180 boundaries, worst +167,519 tokens, 12.9% of subagent compactions affected
- [Bug] Misleading "Executable not found in $PATH" when a hook targets a Windows App Execution Alias (pwsh.exe, python.exe)
- [BUG] Text block streamed between two thinking blocks is never written to the session JSONL (silent loss of user-facing replies; 3,738 across two machines since v2.1.170)
- [BUG] SSHFS read/write issue
- asking something simiple
- [Bug] Opus 5 Safeguards Overly Aggressive: Blocking Legitimate Security Research and Benign Input
- [Model behavior] Code quality is optimized at write-time while its cost lands at maintain-time — request for a longer-horizon training/eval signal
- [Feature Request] Session cron / loop wakeups can only be listed and cancelled through the model — impossible to stop while rate-limited
- [Bug] Compact command message fails on initial submission, succeeds on resubmit
- [Bug] Authentication workflow interruption in project context
- [BUG] Native updater on Windows silently skips the binary swap when consecutive releases have identical file sizes, and reports success
- [BUG] security-guidance 2.0.6 registers five indistinguishable Bash handlers
- [Bug] Anthropic API Error: Overly broad content safety filter blocks legitimate security testing workflows
- [BUG] npm global update leaves a stub binary and no bin/claude symlink — no rollback, and the error message is unreachable
- [Bug] Unexpected redirect to legal page on API error
- [Bug] advisor server-tool 'overloaded' kills workflow-spawned subagents with a generic 'Connection closed mid-response' instead of a recoverable tool error (main loop degrades correctly)
- VS Code/code-server extension: resumed/new tabs silently ignore claudeCode.initialPermissionMode after extension update — permissionMode stuck undefined
- [Bug] Claude Code flags legitimate Bluetooth security analysis as policy violation
- Duplicate proactive auth-refresh scheduling corrupts OAuth token, requires re-login every ~6 hours
Changelog
What's changed
- Added gateway spend-limit support to Claude Code's usage warning; the limit-reached message now names the cap, its reset time, and the operator's message (requires the gateway on 2.1.225)
- Added a workspace trust prompt to
claude agentsfor untrusted directories, matching the behavior ofclaude - Fixed a transient 401 replacing a long-lived
CLAUDE_CODE_OAUTH_TOKENwith a stored login's short-lived token, breaking headless sessions until restart - Fixed MCP OAuth servers on macOS intermittently failing with a burst of 401 errors, as if never authenticated, after a keychain read timed out
- Fixed auto mode counting a safety-filter refusal of its own permission check toward the consecutive-block limit; the action is still denied, but the model is now told to move on rather than retry
- Fixed cross-session messages staying parked without a notice or expiry in headless sessions and during startup
- Fixed conversation history breaking on Remote Control session resume after very large conversations were compacted
- Fixed hovering over a session in another project in the agents list changing the directory the next agent starts in
- Fixed
claude self-hosted-runnerregistering and then failing every session when--base-dircannot be created or written; it now exits at startup with a clear error - Fixed Claude Code on the web sessions being misreported as stuck, re-sending a growing event backlog on every reconnect
- Improved Remote Control: photos attached from the Claude app are now shown to Claude directly instead of being read from disk with a separate tool call
- [VSCode] Fixed Focus view folding away the latest to-do list, a pending question's context, and settled answers; thinking-only folds show "Thought for Ns" and re-collapse when their turn completes
- SendMessage can now start a conversation with your Remote Control sessions on other machines by name (
ListAgentsshows them asname [ref]), instead of only replying after they message you first - SendMessage: a Remote Control recipient you already confirmed is never swapped for a same-named session on this machine when its own list couldn't be checked