All updates from 6 AI coding tools at a glance
June 21, 2026
high and max thinking variants for GLM-5.2 across supported providers. (@imranshaiedi-byte)June 19, 2026
git reset --hard, git checkout -- ., git clean -fd, git stash drop) are now blocked when you didn't ask to discard local work, git commit --amend is blocked when the commit wasn't made by the agent this session, and terraform destroy/pulumi destroy/cdk destroy are blocked unless you asked for the specific stack-p) and now also covering models set in agent frontmatterattribution.sessionUrl setting to omit the claude.ai session link from commits and PRs in web and Remote Control sessions/config --help to list all available shorthand keys for /config key=value/config toggle behavior: Enter and Space both change the selected setting, and Esc now saves and closes instead of reverting/doctor to see configuration issues or use --debugthinking.disabled.display: Extra inputs are not permitted 400 errors on subagent spawns and session-title generation for affected configurationsJune 18, 2026
codex exec thread start and resume, while blocking PostToolUse hooks correctly reject code-mode tool calls. (#26434, #28365)wait_agent. (#28286, #28341)June 17, 2026
/config key=value syntax to set any setting from the prompt (e.g. /config thinking=false) — works in interactive, -p, and Remote Controlsandbox.allowAppleEvents opt-in setting that lets sandboxed commands send Apple Events on macOSCLAUDE_CLIENT_PRESENCE_FILE environment variable: point it at a marker file to suppress mobile push notifications while you're at the machineImproved N memories line to no longer list individual files outside verbose modeANTHROPIC_BASE_URL and on Foundry due to a per-request attestation token changing every turnopen, osascript, and browser-based auth flows failing with error -600 on macOS by adding the Apple Events entitlementTypeError: Cannot read properties of null) when .claude.json contains corrupted null project entries/recap and conversation forks using the previous model immediately after a model switchawsCredentialExport credentials with a short remaining lifetime causing credential refreshes every minute, and now accepts the JSON shape from aws configure export-credentialsclaude mcp get/list showing ✓ Connected when tools/list fails; they now show ! Connected · tools fetch failed with the error detail/remote-control leaving a stale "connecting…" line; it now confirms in the transcript once connectedgit cannot be resolved on Windows/effort or /model) failing with ENOENT when ~/.claude/settings.json is a relative symlink under a symlinked ~/.claude/stats "Most active day" and daily token chart dates showing one day early in UTC-negative timezones/copy and copy-on-select on Linux not detecting a clipboard utility installed after Claude Code startedJune 17, 2026
June 16, 2026
denyRead/allowRead glob over a large directory tree making the Bash tool description enormous and the session unusable on LinuxJune 16, 2026
June 15, 2026
TeamCreate and TeamDelete tools. With CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 set, every session now has one implicit team — spawn teammates directly with the Agent tool's name parameter, no setup step needed. The team_name parameter on the Agent tool is still accepted but ignored.Tool(param:value) syntax for permission rules to match a tool's input parameters (with * wildcard), e.g. Agent(model:opus) to block Opus subagents.claude/skills directories now load when working on files there; on a name clash, the nested skill appears as <dir>:<name> so both stay available.claude/ directories: the agent, workflow, and output-style closest to the working directory now wins when names collide; project-scope workflow saves now target the closest existing .claude/workflows//doctor with consistent flat tree layout across all sections, clearer section status icons, and highlighted command names/bug now requires a description before submitting, and no longer uses model-refusal text as the GitHub issue title.claude/skills skills with directory-qualified names being blocked by permission prompts in non-interactive runsclaude agents workers failing with 401 Invalid bearer token when the daemon was started from a shell with a custom API gateway via ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN--fallback-model: compaction now falls back to the configured fallback model chain on overload or model-availability errors/bg or ←← after a turn finished showing "Working" forever in the agents list.claude/skills or .claude/hooks is a symlinkCLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE=1 preventing fresh marketplace installs from cloningmcp__server, mcp__server__*, mcp__*) in subagent disallowedTools being silently ignoredu now steps through NORMAL/VISUAL-mode commands one at a time instead of merging commands in quick succession into a single undo stepvscode://) not opening when clicked in claude agentsJune 15, 2026
/usage views for daily, weekly, and cumulative account token activity. (#27925)/goal now preserves oversized text, large pasted blocks, and image attachments, including in remote app-server sessions. (#27508, #27509, #27510)codex delete, /delete, and app-server thread/delete, with confirmation safeguards and subagent cleanup. (#25018, #27476)/import for selectively importing setup, project configuration, and recent chats from Claude Code. (#27070, #27071, #27703)@ now opens the unified mentions menu for files, plugins, and skills by default. (#27499)/review from crashing when Esc is pressed with queued guidance, while preserving that guidance when the review is canceled. (#22879)/realtime voice controls and related audio dependencies from the TUI. (#27801)June 14, 2026
location.June 14, 2026
June 13, 2026
June 13, 2026
$ARGUMENTS so file contents are not injected twice (@verdverm)RunCommand fetch requests (@OpeOginni)Answers to the most important questions about our AI Coding Tools Changelog Hub