Claude Code v2.1.292
Released Oct 6, 2026 (8 days ago).
106 issues reference this build
92 still open
14 resolved (13%)
"References this build" means the issue body mentions running 2.1.292 (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 v2.1.292
Ranked by community engagement (reactions and comments).
- [Bug] Docked plugin panes render opaque background, ignoring terminal transparency
- Transcript JSONL corruption; records spliced by unsynchronized writers
- Default spinner verbs should be opt-in (AND FIXED to a single "Thinking" word)
- [BUG] Windows: removing CLAUDE_CONFIG_DIR while claude.exe is running pins one CPU core indefinitely (no error, no backoff)
- Worktree-isolation Bash guard overrides an explicit PreToolUse `permissionDecision: allow`
- [FEATURE] Configurable token threshold for idle compaction (idleCompactMinTokens)
- [BUG] Remote Control: Projects threads on my computer fail with "CCR v2 worker registration failed ... 400"; self-started sessions on the same server register fine
- Marketplace clone recurses into git submodules, so marketplaces with large submodules can never refresh
- [BUG] VS Code/Cursor: Claude editor tabs vanish after a reload while the (remote) extension host is down, and panelTabSessions prunes them instead of restoring them
- macOS permission prompts and Privacy settings show Claude Code as a bare version number (e.g. "2.1.83")
- [MODEL] Safety classifier withholds responses during legitimate healthcare documentation work
- [BUG] Projects: Library needs more work in terms of file management. Claude cannot manipulate it properly either.
- [BUG] CVP access revoked without notice; identity verification (KYC) locked as "not approved" with no retry, so Claude Code keeps hitting cyber safeguard blocks
- [BUG] --max-budget-usd is checked after each call returns, so a $1 cap stops at $1.38 (3/3, 2.1.292)
- [Feature Request] Add option to disable classifier
- [Bug] Zellij integration: scrollback navigation breaks terminal input in Claude Code tab
- [Feature Request] Interactive companion pet with dynamic reactions and state awareness in Claude desktop app
- [BUG] --cloud: finished work stranded — session idles with background jobs pending, no push-access warning, held messages reported as sent
- [Bug] Anthropic API Error: Over-sensitive security detection for common crawler functions
- I'm Claude Code, Anthropic's CLI tool. I can only help with issues related to Claude Code itself. For Apple support, please visit Apple's official support website or contact them directly through the
- Desktop auto mode: pending Bash permission request resolved itself after 37 hours and ran unattended
- [BUG] Claude Pro 5-hour session limit exhausted within 4 minutes of auto-resume after reset (v2.1.292)
- [DOCS] Sub-agents page omits the Agent tool's per-invocation effort parameter and the values the per-invocation model parameter accepts
- [BUG] claude hangs silently on startup (all versions, clean config, empty env) — Debian 13, since 2026-10-07
- [BUG] enabledMcpjsonServers in settings.json changes from an array to a string without notice, then fails validation ("Invalid settings")
- [Bug] Out of Memory errors causing frequent crashes
- [Bug] Plan mode ignores MCP tool allow list permissions
- [Bug] TaskCreate inconsistently available across projects on same version
- [Bug] Agent fails to maintain conversation history after session close
- [Bug] Rebranding document breaks cybersecurity analysis functionality
Changelog
What's changed
- Added
--marketplace <source>toclaude plugin install: adds the marketplace if needed, under the same policy checks asclaude plugin marketplace add, then installs the plugin from it - Added an
effortparameter to the Agent tool, so Claude runs a sub-agent at the effort level you ask for - Added
CLAUDE_CODE_OVERLOADED_RETRY_BASE_DELAY_MSenvironment variable to set a longer base delay for the backoff when retrying an overloaded (529) request - Added
prompt.autocomplete, an event a mod hooks to add its own rows to the prompt box's autocomplete list - Added prompt caching to
$.model.completefor mods:promptandsystemtake blocks of text, andcache: trueon a block caches the request up to it - Added workflow agents to the
agent.spawnmod hook, with their run and index, so a mod can refuse them - Fixed subagent definitions with
permissionMode: autoentering auto mode when auto mode is unavailable (disabled by settings, circuit breaker, or a model that doesn't support it) - Fixed sandboxed commands being able to read the staged file copies of
/ultrareviewuploads under~/.claude/seed-admin - Fixed a managed sandbox read-deny path (and user ones beside it) that appears or re-points mid-session not dropping project grants inside it or ending credential injection from files it covers
- Fixed a notebook or PDF read on macOS and Windows being able to return a file outside what was approved, through a link swapped in mid-read
- Fixed a tampered on-disk cache of server-managed settings being able to switch off or unseat the built-in policy plugin while the settings fetch failed
- Fixed
rm -rfon the 8.3 short name or another alternate Windows spelling of the home folder or a drive not being treated as removing it - Security: Fixed PreToolUse hook approvals and auto mode bypassing the permission prompt for file reads from network (UNC) paths
- Fixed a skill's or slash command's
allowed-toolsrule coming back in a later turn when you leave auto mode or plan mode partway through that turn - Fixed
NO_PROXYbeing ignored for Claude Code's own API requests (sign-in, policy, feedback, artifacts) whenHTTPS_PROXYis set - Fixed an MCP tool with a name longer than 128 characters making every request fail; that tool is now left out and an MCP error names it
- Fixed
claude plugincommands such asmarketplace addandinstallrunning before an organization's managed settings had loaded on a first run - Fixed one-shot
claude -pand Agent SDK runs stopping a background command 5 seconds after the final result, and one-shotclaude -pruns dropping a scheduled wakeup; both are now waited for - Fixed plan mode not being restored when resuming a session from the
claude --resumesession picker or with/resume - Fixed saved scheduled tasks created after
/resume,/branchor/clearnever firing, and saved tasks ignoring later creates and deletes after two writes to the tasks file milliseconds apart - Fixed a background session's
/loopsilently stopping when the session's process restarted (for example after a crash), because its pending wakeup was lost - Fixed Grep and Glob reporting no matches when the file or folder they were given could not be read; Claude now retries once or tells you
- Fixed the Read tool returning only the first entry, with no error, when a PDF's
pageswas a list such as "6,9,15"; it now returns an error saying to read each page or range separately - Fixed @-mentioned text files over 256KB being left out silently: Claude is now told the file's size and to read it in portions
- Fixed the usage limit alert repeating once per background agent when agents failed on a limit that had already stopped the main conversation
- Fixed Remote Control viewers seeing an empty subagent pane for background subagents in sessions hosted by the desktop app or an IDE
- Fixed cross-session delivery notices showing two sessions with similar names as one recipient, and the expiry