Claude Code v2.1.235
Released Aug 18, 2026 (12 days ago).
133 issues reference this build
109 still open
24 resolved (18%)
"References this build" means the issue body mentions running 2.1.235 (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 v2.1.235
Ranked by community engagement (reactions and comments).
- [BUG] Claude abuses bash tools for reads, writes, and edits when running in Auto Mode
- bypass permissions mode steers agents off Read/Edit/Grep onto composed shell strings, reintroducing quoting and exit-code failures that the structured tools cannot have
- [BUG] Desktop remote/SSH: archive never cleans up worktrees since 2.1.235 — app requires hardened git.status(baseRepo) but only ships a 2026-07-06 daemon, so "reconnect to deploy the updated daemon" is a no-op
- [BUG] VSCode extension streaming errors: content_block_delta and message_stop without a current message (regression after v2.1.235)
- keybindings: ctrl+enter / shift+enter never reach the keybinding matcher on Windows Terminal; ctrl+j rebind ignored
- [BUG] MSIX in-place update leaks a container silo, making Claude Desktop unlaunchable until reboot (0x80070020)
- [Bug] False positive security risk flagging for non-cybersecurity code
- autoUpdates: false is not honoured on native installs — version pin silently reverted
- [Bug] Session history stale for days: sidebar and ccd_session_mgmt list_sessions omit all recent sessions (Windows desktop, 2.1.235)
- [BUG] Claude Code fails to authenticate on MacOS in certain environments.
- [BUG] auto mode can be remotely enabled by attacker
- Background-session git rule "Never push to main/master, force-push, or merge" has no precedence clause, so agents refuse merges their repo CLAUDE.md explicitly requires
- Ink UI leaves stale placeholder text when TERM_PROGRAM=ghostty and new content is shorter
- [BUG] Remote Control: ending a session from the app exits the child 1, so the bridge reports a crash and permanently leaks the worktree
- Worktree-isolation Bash guard refuses every compound command, even with no git usage at all
- [BUG] Subscription features are withdrawn when `ANTHROPIC_BASE_URL` isn't the official string, even when the proxy terminates at Anthropic
- [BUG] Bug report: assistant fabricated a user turn and system prompts inside its own response, then executed them
- [Feature Request] Add option to disable automatic message compaction
- [BUG] Multiple terminals attached to the same live session have locked/synced scroll position, and resizing one corrupts rendering in the other
- /cd changes the working directory but does not relocate the session to the new project storage
- [BUG] Background daemon never reaps stale workers or unclaimed spares — they are re-adopted on every restart (64 leaked processes / ~7.1 GB after six weeks)
- Non-fork subagents receive auto-memory (MEMORY.md) in full, contradicting docs; no per-agent way to trim CLAUDE.md inheritance
- [Bug] Claude Code artifact links return 404 page not found
- [BUG] Desktop (Windows/WSL): detached window's slash menu lists only bundled skills
- [Bug] Memory/Context not persisting user profile updates across sessions
- /mo[Bug] Consecutive API failures with Claude Opus and Claude 3.5 Sonnet models
- [Bug] Test submission - unable to process legitimate company test
- [Bug] Anthropic API: Claude 3.5 Opus high hallucination rate in code generation
- [MODEL] Claude autonomously launches costly subagents without explicit consent
- [Bug] Normal app workflows trigger Claude's safety guidelines
Changelog
What's changed
- Added an optional
spellchecksetting that underlines misspelled words in the prompt input as you type, using your installedaspell,hunspell, orispell - Fixed whole-prompt-cache invalidation when a language server disconnected or reconnected mid-session
- Fixed nested markdown list items misaligning at depth 3+ and added a hanging indent to wrapped list items in the terminal UI
- Fixed prompt input highlights (slash commands, keywords, mentions) appearing shifted by one or more characters in some multi-line prompts
- Fixed Shift+Tab inside the permission prompt's comment field approving the edit and granting session-wide edit permission instead of closing the field
- Fixed the Agent tool advertising a general-purpose default in sessions where that agent is unavailable: an omitted
subagent_typethere now gets a clear error listing the available agents - Fixed notebook cell delete/replace approval dialogs silently omitting the existing cell content when the notebook or cell could not be read; the dialog now says why
- Fixed slash commands run while Claude is responding showing HTML entities instead of the actual characters
- Fixed the prompt footer not showing the "Update installed" restart notice after a background auto-update
- Fixed the expanded task list (
ctrl+t) always starting collapsed when resuming or relaunching into a session that still has open tasks - Improved memory and CPU usage while cloud sessions such as
/ultrareviewor/autofix-prrun in the background — their event streams are no longer re-scanned and re-rendered on every update - Improved permission dialogs: display text and "don't ask again" options now always match what a grant would cover, and "don't ask again" is withheld when contents cannot be fully displayed
- Improved the embedded
grepin native macOS/Linux builds: pathological patterns now fail fast instead of exhausting memory, and-m Nwith-A/-Cprints correct context - Improved the context-limit error to say when auto-compact is off and point to
/configto re-enable it - Vim mode: NORMAL mode and cursor position are now preserved when toggling the detailed transcript (ctrl+o) or closing a panel
- Dialogs: arrow keys and Enter pressed in quick succession now select the option you navigated to instead of the previously highlighted one
SendMessagenow refuses messages too large for cross-session delivery up front instead of silently dropping them- Remote Control:
claude rcnow applies the same enterprise-gateway availability check as interactive startup - [VSCode] Fixed focus jumping between open Claude tabs on its own when a window with several Claude panels is restored or reloaded