Claude Code
Mon
Wed
Fri
JulAugSepOctNovDecJanFebMarAprMayJunJul
LessMore
Releases91Avg28/moVersionsv2.1.94 to v2.1.207
Last Checked
1h ago
Latest
v2.1.207
CLAUDE_CODE_ENABLE_AUTO_MODE opt-in on Bedrock, Vertex AI, and Foundry; disable via disableAutoMode in settingsclaude -p, the SDK) being permanently recorded as consented without ever showing the security consent dialog~/.local/bin/claude on every release; /doctor now reports an externally managed launchercd prompting for permission when the only output redirect was to /dev/nullextensions.worktreeConfig being left in the repo's .git/config (breaking go-git tools like tea) after the last worktree.sparsePaths worktree was removed.ignore, and .worktreeinclude breaking file reads, file suggestions, and worktree creation[Pasted text #N] placeholder instead of adding a second onewaiting 3m) instead of the same timestamp twiceautoMode from .claude/settings.local.json (repo-resident); use ~/.claude/settings.json insteadcredential_process): the 60-second stall guard now fires instead of waiting forever.${user_config.*} in shell-form commands is now rejected (shell-injection fix). Hooks: use exec form (args array) or $CLAUDE_PLUGIN_OPTION_<KEY>; monitors and headersHelper: read the value inside the script (config file or the server's env block).pluginConfigs) are no longer read from project-level .claude/settings.json; only user, --settings, and managed settings are honored/usage-credits amount inputs silently stripping malformed values (e.g. a pasted timestamp) to digits; malformed amounts are now rejected with an error, and amounts over $1,000 require a typed confirmation/cd, matching /add-dir behavior/doctor check that proposes trimming checked-in CLAUDE.md files by cutting content Claude could derive from the codebase/commit-push-pr now auto-allows git push to the repo's configured push remote (remote.pushDefault, or the sole remote when only one is configured) in addition to origin/login now supports Anthropic-operated public gateway endpointsEnterWorktree now asks for confirmation before entering a git worktree outside the project's .claude/worktrees/ directory/loginclaude --resume and --continue not responding to keyboard input on startup--mcp-config or .mcp.json ignoring a per-server request_timeout_ms, which caused long-running MCP tool calls to time out at the 60s default in fresh sessionsCLAUDE_CODE_EXTRA_BODY being silently ignored by claude agents / --bg background workers; the shell-exported override now follows the dispatching session--permission-prompt-tool pointing at an MCP server crashing with "MCP tool not found" on cold start before the server finishes connecting/model picker rows printing a price for a different model than the row named, and stopped quoting first-party list prices on providers that don't bill them/model picker when an entitlement or allowlist restriction drops the row they were positioned againstclaude --resume on Windowsclaude rm leaving the removed job in the daemon roster, causing the row to reappear in claude agents/remote-control showing "Unknown command" when logged out — it now explains how to sign in/status listing the same broken-install warning twice/doctor's update check to compare Homebrew installs against their cask's channel instead of the settings channelawsCredentialExport helper on networks with restricted egress/code-review findings quality on claude-opus-4-8 across all effort levels--json-schema silently producing unstructured output when the schema was invalid, and schemas using the format keyword being rejected--max-turns limitSendMessageclaude attach erroring when a background agent was mid-upgrade restart instead of waiting for it to come backclaude mcp add-from-claude-desktop getting stuck when a server name contains unsupported characters; invalid names are now reported and remaining servers still importrm -rf on a variable it can't resolve from contextclaude agents/doctor is now a full setup checkup that can diagnose and fix issues; /checkup is its aliasroots/list, with notifications/roots/list_changed sent when the set changesclaude agents silently stopping running subagents and re-running the prompt from scratch — their work now carries overPATH from the daemon instead of the dispatching shell, causing missing tools on WindowsANTHROPIC_BASE_URL, which sent API keys to the default endpoint and failed with 401TaskStop and TaskOutput failing to find background agents spawned by another agent — errors now list running agents by id and descriptionclaude agents composer discarding your typed message when a slash command isn't available thereeffortLevel changes in settings.json when forked through the daemonCLAUDE_CODE_DISABLE_MOUSE and CLAUDE_CODE_DISABLE_MOUSE_CLICKS opt-outs/exit incorrectly warning about running background agents after all named agents had completedWorktreeCreate hook was configured@ directory picker in claude agents not showing registered git worktrees/clear^[[I / ^[[O escape codes being printed when reattaching to a background sessionclaude agents view to always show the organized sections (Needs input / Working / Completed) with descriptions/doctor and /status insteadclaude agents footer/config for controlling how large Claude generally makes dynamic workflows (small/medium/large agent counts) — an advisory guideline, not an enforced capworkflow.run_id and workflow.name OpenTelemetry attributes to telemetry emitted by workflow-spawned agents, so a workflow run's activity can be reconstructed from OTel data/rename on background sessions being reverted when the job restarts, which broke addressing the session by its new nameclaude auth login and claude mcp login --no-browser not being reliably clickable when it wraps over SSH — it is now emitted as a single hyperlinkclaude agents sometimes failing with "currently running as a background agent" followed by a worker crash/respawn loop/remote-control sessions showing the wrong permission mode in the mobile and web apps/workflows agent list layout: wider titles, a dedicated time column, shorter model names, and no per-row tool-call countsurl but no type, suggesting "type": "http" instead of the misleading "command: expected string"/review <pr> back to a fast single-pass review; use /code-review <level> <pr#> for the multi-agent review at a chosen effort levelAskUserQuestion dialogs to no longer auto-continue by default; opt into an idle timeout via /config--help, VS Code, and JetBrains; --permission-mode manual and "defaultMode": "manual" are accepted alongside defaultdisabledMcpServers or enabledMcpServers in .claude.json is set to a non-array valuedaemon.lock whose PID the OS reusedclaude agents --plugin-dir <dir> not showing the plugin's agents and skills in the agent view when the flag is placed after agents/mcp server list not tracking focus for screen readers and magnifiersHeader: value. lines/skill-a /skill-b do XYZ now load all leading skills (up to 5), not just the firstNODE_EXTRA_CA_CERTS, expired certs) burning retries before showing actionable guidance — they now fail immediately with the fix hintclaude stop being silently undone when it raced a background-agent respawn — the respawn now honors the stop/model or /fast while viewing a subagent silently opening the lead's model picker — a notice now explains the command applies to the leadSessionStart, Setup, and SubagentStart hooks silently hiding stderr when exiting with code 2 — the error is now shown in the transcriptclaude --dangerously-skip-permissions daemon <subcommand> being treated as a chat prompt instead of running the subcommandSendMessage silently misrouting when a re-spawned agent reuses a previous agent's name — the tool now detects the mismatch and asks the caller to retarget← or /background dropping its /color from the agent view rowbrowser_batch calls are now correctly auto-allowedCLAUDE_CODE_RETRY_WATCHDOG now raises the default retry count for non-capacity transient errors to 300 and lifts the cap of 15 on CLAUDE_CODE_MAX_RETRIESclaude agents session rows now show pull-request links as bare #N without the redundant "PR" labelclaude agents — sessions that need input or finish now fire the Notification hook (agent_needs_input / agent_completed)/dataviz skill for chart and dashboard design guidance with a runnable color-palette validatorclaude agents now commit, push, and open a draft PR when they finish code work in a worktree, instead of stopping to ask/diff panel not refreshing when you switch branches or commit outside the sessionawsAuthRefresh now runs automatically/desktop failing with "Cannot determine working directory" after entering and exiting a worktree← inside claude attach <id> exiting to the shell instead of opening the agent viewclaude --bg silently creating an unattachable session when combined with --print/-p; the conflicting flags are now rejected up front.claude/rules/ conditional rules not loading when the target file is reached via a symlinked path/branch deriving its default fork name from the compaction summary instead of the first real prompt/login now opens the sign-in dialog from the claude agents view instead of saying it isn't available/agents wizard; ask Claude to create or manage subagents, or edit .claude/agents/ directly/model when you haven't picked one yourselfclaude mcp list/get no longer spawn .mcp.json servers that a repo self-approved via a committed .claude/settings.json; untrusted workspaces show ⏸ Pending approvalgit diff/git grep, egrep/fgrep, and quoted search patterns containing | being reported as failures when they exit 1, matching Bash behaviorclaude agents side panel issues: keyboard focus getting stuck when opening an agent, background jobs losing their subagent types on every open, and sessions showing incorrect status while actively runningclaude agents --dangerously-skip-permissions silently falling back to auto mode instead of showing the bypass disclaimer and applying bypass mode to spawned agents/cd reappearing in the old directory's resume list after a non-graceful exit when the old path contained special charactersclaude plugin validate skipping local plugins whose source is "." and stopping after the first error classscopes_supported catalog when no scope is specified, causing invalid_scope failures on GitLab self-hosted and other enterprise IdPs/context showing 0 tokens for all tool groups on Bedrock/deep-research misreporting verifier failures as "all claims refuted" instead of unverifiedclaude agents session status: completed rows no longer flip between "Done" and "Needs your input", stalled agents are now labeled "Needs attention", and results that mention a PR show a clickable link/code-review workflow: merged five cleanup finders into one, cutting token usage by roughly 25%CLAUDE_ENABLE_STREAM_WATCHDOG=0 to disable.ANTHROPIC_BASE_URL points at a non-Anthropic host, matching the existing behavior under CLAUDE_CODE_USE_BEDROCK/_VERTEX/_FOUNDRY← press instead of two, matching the behavior in background sessionsCLAUDE_CODE_DISABLE_MOUSE_CLICKS to disable mouse click/drag/hover in fullscreen mode while keeping wheel scrollcode-reviewer, mcp__brave-search) accidentally substring-matching — they now exact-match. Use mcp__brave-search__.* to match all tools from a hyphenated MCP server..claude/settings.json not requiring explicit install consent on every loader path/plugin Enable/Disable not working when a plugin's plugin.json name differs from its marketplace entry nameclaude agents or losing data when written by a newer Claude Code versionclaude agents completed list to fill available vertical space; on short terminals the header compacts so live sessions stay visibleautoMode.classifyAllShell setting to route all Bash/PowerShell commands through the auto-mode classifier instead of only arbitrary-code-execution patterns/permissions recent denialsclaude_code.assistant_response OpenTelemetry log event containing the model's response text. Redacted unless OTEL_LOG_ASSISTANT_RESPONSES=1; when that var is unset it follows OTEL_LOG_USER_PROMPTS, so deployments that already log prompt content will start receiving response content on upgrade — set OTEL_LOG_ASSISTANT_RESPONSES=0 to keep prompts-only.!)/mcpCLAUDE_CODE_DISABLE_BG_SHELL_PRESSURE_REAP=1)/model and other client-data-gated UI showing stale/empty state immediately after /loginheadersHelper auth: the helper now re-runs and reconnects automatically when a tool call returns 401/403renames maps are now followed automatically, updating your settings to the new name/add-dir message when the directory is already a working directory/rewind support for resuming a conversation from before /clear was run/voice showing a generic "not available" message when disabled by an organization's policy — it now explains the restriction/login URL opening truncated in Windows Terminal when it wraps across linesclaude agents sending builtin slash commands like /usage to background sessions as prompt text instead of showing a hintclaude agents job rows showing full filesystem paths for pasted images instead of the [Image #N] placeholder"Bash,PowerShell") silently never firing/permissions Recently-denied tab: approving a denial now persists on close instead of being silently discardedforceRemoteSettingsRefresh now takes effect when set via MDM or file policy, and the fetch sends Cache-Control: no-cache to prevent proxies from serving stale responsestools/list, prompts/list, resources/list) now retries transient network errors with short backoff/) to hint how to reach slash commandssandbox.credentials setting to block sandboxed commands from reading credential files and secret environment variables--model, /model, and ANTHROPIC_MODEL, with a "restricted by your organization's settings" message when a restricted model is selected/model, /config, etc.) in fullscreen mode--resume failing with "No conversation found" when the original -p run produced no model turns--json-schema and workflow agent({schema}) structured output: the model can no longer re-call StructuredOutput indefinitely after a successful call, and follow-up turns now reliably return structured outputCLAUDE_CODE_MCP_TOOL_IDLE_TIMEOUT)/update over Remote Control hanging when a startup trust dialog would have shown/bg, /tui, or /update.git/worktrees/ entries from killed agents are now cleaned up automaticallyclaude --help not listing the --bg/--background flag/share is uploading/install-github-app: GitHub Actions workflow setup is now optional — you can install just the GitHub App and skip the workflow/secret steps/btw with ←/→ arrow navigation to step through earlier answers/plugin to surface plugins you haven't used recently so you can clean them up