Claude Code v2.1.247
Released Aug 26, 2026 (3 days ago).
113 issues reference this build
110 still open
3 resolved (3%)
"References this build" means the issue body mentions running 2.1.247 (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 v2.1.247
Ranked by community engagement (reactions and comments).
- [BUG] Shifted punctuation arrives unshifted in WezTerm (2.1.247 regression)
- Remote Control should be opt-in, not on by default
- Desktop: cycle sessions in most-recently-used (MRU) order, or a toggle-last-two-sessions shortcut
- Windows native CLI 2.1.250 launches embedded Bun instead of Claude Code
- You've hit your session limit · resets 1:40pm (Pacific/Auckland)
- [BUG] Auto Mode classifier the native tools like read and edit..
- Trusted Devices fails open on individual accounts: revoking devices doesn't re-verify an active session, and declining "Sign in again to verify your device" has no effect either
- Inconsistent usage percentage display between VS Code extension and claude.ai
- Desktop: every session switch spawns a throwaway Claude Code session — 950 unused sessions in 4 weeks, inflating claude_code.session.count and littering ~/.claude/projects
- Desktop: Expose the auto-compact window in the usage ring that already shows context usage
- macOS: TCC-protected folders unreadable — no consent prompt, no remediation in the error, and Read reports EISDIR instead of EPERM
- Desktop app's bundled CLI stuck at 2.1.247, Remote Control silently fails to connect (no error shown)
- Desktop app: prompt suggestions (Tab to accept) silently stopped — host gate off since ~Aug 14-20 while user setting is on
- [Bug] Subagent polling wake-ups consume excessive tokens for no-op status checkssu
- [Bug] Claude refuses to provide security vulnerability details citing safety guidelines during legitimate security testing
- [BUG] Opening a session with a large slash command makes the second request discard the entire prompt cache
- Self-hosted marketplace: desktop app rejects non-allowlisted git hosts, and authenticated marketplaces appear to require managed settings
- [BUG] Subagent goes idle without its final report ever reaching the parent session
- [BUG] Agent definitions are cached at startup: new files are invisible and edits are silently ignored, with no notice and no way to reload
- [Bug] Fan-out launches agents without stagger, causing correlated 529 failures
- [Bug] Compaction loses track of in-flight agents, causing duplicate work
- /config remoteControl=true confirmation is ambiguous about when it takes effect
- [BUG] Session and weekly usage limits jump to a high percentage with no activity
- Claude session hit 5h limit in less than 5min even when sonnet 5 model is used. You've hit your session limit · resets 4:30pm (Asia/Kolkata)
- Claude 5h usage limits hitting in 15 min of usage with simple 3 propmpts. You've hit your session limit · resets 3:40pm (Asia/Kolkata)
- security-guidance: stop-time review echoes raw ~/.claude/.credentials.json OAuth tokens into the transcript
- [BUG] Forking from unprimed post-compact context re-bills the full shared prefix twice (fork AND parent each pay full cache_creation)
- [BUG] Claude Code 2.1.247 in GitHub Actions (claude-code-action v1.0.207) fails right after init: is_error:true, no model response, no error message; last known-good is v1.0.206 (2.1.246)
- Desktop: no supported way to bring dormant sessions back into Remote Control after an app restart
- Bundled Claude Code binary at a version-numbered path re-triggers macOS TCC permission prompts on every desktop app update
Changelog
What's changed
- Added the
SendFeedbacktool: when something goes wrong in a session, Claude can draft a feedback report for you to review and send from/feedback(turn off with thefeedbackDraftssetting) - Added
{id, text, cooldownSessions, priority}entries,tipsFile, andlabeltospinnerTipsOverride, so organizations can rotate their own tips alongside the built-in ones - Added a tip on Bash permission prompts pointing to auto mode, with a one-keystroke "Yes, and switch to auto mode" option
- Added
/claude-api cost-optimizeto profile an existing project's Claude API spend and work through cost levers (caching, token hygiene, batch, effort, model choice) one measured change at a time - Updated the
/claude-apiskill with Admin API coverage (organization members, invites, workspaces, API keys, rate limit reports, workload identity federation, CMEK) - Fixed fast arrow-key + Enter sequences acting on the row above the one you navigated to in history search,
/config,/mcp,/skills, background tasks, and/model - Fixed sub-agents dying on a first-call model 404: they now use the session's fallback model chain, and the error returned to the parent includes the error type, status, request id, and model
- Fixed a hook or background agent that printed megabytes of error output being able to overflow the conversation and wedge the session on "Prompt is too long"
- Fixed Ctrl keyboard shortcuts not firing under non-Latin (e.g. Cyrillic) keyboard layouts in kitty-protocol terminals
- Fixed text like
<35;150;7Mbeing inserted into the prompt when a mouse report arrived split across reads right after the escape prefix - Fixed the Bash sandbox's after-command cleanup deleting a dotfile-managed
~/.claude/settings.jsonsymlink (nix/home-manager, stow) when it is repointed outside the sandbox's writable area - Fixed
/terminal-setupoverwriting your entire Zedkeymap.jsoninstead of merging in its keybinding - Fixed
/renamesilently confirming when the session registry could not be updated; it now says other sessions may still show the old name - Fixed
/compactand "Summarize from here" in sessions started with--agentsummarizing under the default system prompt instead of the conversation's own - Fixed a background session showing "opening…" forever in
claude agentsafter its terminal host process died; the row now fails within seconds with the reason, and Enter restarts it - Fixed unbounded memory growth when a hook's or background task's output file could not be written; the file now notes where output was lost
- Fixed
/install-github-appover SSH: the copy shortcut now says how the sign-in URL was copied instead of always claiming success, and the URL appears immediately when no browser can open - Fixed shell commands carried over from the foreground logging an internal error or showing a misleading
[exited with code -1]line when they finish in background sessions - Fixed a version-less marketplace plugin's live cache directory being deleted and recreated on a second-scope install, which could disrupt a running session using it
- Fixed Remote Control sessions started with
/remote-controlnot reporting the working-tree diff to connected clients - Fixed self-hosted runner sessions reporting
runningbefore Claude Code had started, which could trigger a premature "Claude is waiting for your input" notification from the Claude desktop app - Fixed first-run setup exiting with "Unable to connect to Anthropic services" when managed settings configure Claude apps gateway sign-in and Anthropic endpoints are unreachable
- Fixed cloud sessions (Claude Code on the web, desktop and mobile apps) sometimes showing the previous permission mode when you switch modes right after sending a message
- Fixed cloud sessions going silent when the session's container restarts between turns while a background agent, shell, or monitor is still running — the resumed session now reports the lost work
- Improved pl