the latest updates to your ai tools, straight from their official changelogs.
+WebSocket Responses API mode is now available.
WebSocket Responses API mode is now available. Drive the Responses API over a single, long-lived WebSocket connection for lower end-to-end latency on tool-heavy agent workloads. For more details, see the WebSocket Mode docs.
continue reading on the release page →+Auto-review is a new run mode that allows Cursor to work for longer with fewer approval prompts and safer execution.
Auto-review is a new run mode that allows Cursor to work for longer with fewer approval prompts and safer execution.
Auto-review applies to Shell, MCP, and Fetch tool calls. Allowlisted calls run immediately, and calls that can be sandboxed run in the sandbox. All other agent actions go to a classifier subagent that decides whether to allow the call, try a different approach, or ask for your approval.
Configure your run mode in Settings > Cursor Settings > Agents > Approvals & Execution. You can also steer the classifier agent by giving it custom instructions.
Learn more in our docs.
continue reading on the release page →
/simplify now runs a cleanup-only review (reuse, simplification, efficiency, altitude) and applies the fixes, instead of running the full `/code-review --fix` bug-hunting review/effort slider labels from "Speed"/"Intelligence" to "Faster"/"Smarter" for clarityclaude agents: type `! <command>` to run a shell command as a background session you can attach to and detach from. Also available as `claude --bg --exec '<command>'`claude agents: `/logout` now signs you out instead of being sent to a background session←← to open the agents view now works on Bedrock, Vertex, Foundry, and with telemetry disabledCLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE (will be removed on 06/01). To use fast mode on Opus 4.6, switch with `/model claude-opus-4-6[1m]` and then `/fast on`rm -rf $HOME not being blocked as a dangerous path when `HOME` has a trailing slash$TMPDIR resolving to different directories in sandboxed vs unsandboxed Bash commands within the same sessionskipLfs option to `github`/`git` plugin marketplace sources to skip Git LFS downloads during clone and updateclaude agents: autocomplete in the dispatch input now suggests native slash commands and bundled skills, not just project skillsclaude agents: PR column now shows `PR #N` for a single PR or `N PRs` for multipleclaude doctor now shows the result of your last update attempt--strict-mcp-config no longer strips inline `mcpServers` from explicitly-passed agent definitions (`--agents` / SDK `agents`), and blocked subagent MCP servers now surface a visible warning/bg while Claude is responding now continues the response in the background session instead of dropping it/model now saves your selection as the default for new sessions (matching the IDE). Press `s` in the picker to switch models for the current session only.claude update installing the latest version instead of the configured release channel's version for npm installationsclaude agents and `claude --bg` running on a stale daemon started before binary-takeover support, even after upgrading+Web Search now supports explicitly searching for images.
Web Search now supports explicitly searching for images. Enable enable_image_search to let Grok search directly for relevant images; responses can include returned images as Markdown image embeds. For details, see Enable Image Search.
continue reading on the release page →/reload-skills command to re-scan skill directories without restarting the sessionMessageDisplay hook event that lets hooks transform or hide assistant message text as it is displayedpluginSuggestionMarketplaces managed setting: admins can allowlist org marketplaces whose plugins may be suggested via context-aware tips/code-review --fix now applies review findings to your working tree after the review, surfacing reuse, simplification, and efficiency suggestions; `/simplify` now invokes `/code-review --fix`SessionStart hooks can now return `reloadSkills: true` to re-scan skill directories, making skills installed by the hook available in the same sessionSessionStart hooks can now set the session title via `hookSpecificOutput.sessionTitle` on startup and resumeclaude plugin marketplace remove now accepts `--scope user|project|local` for symmetry with `marketplace add`, `install`, and `uninstall`/ in NORMAL mode now opens reverse history search (like Ctrl+R), matching bash/zsh vi-mode/doctor reporting "marketplace not found" or "plugin not found" for stale `enabledPlugins` entries referencing removed marketplaces or dropped plugins/usage now shows a per-category breakdown of what's driving your limits usage — skills, subagents, plugins, and per-MCP-server cost/diff detail view can now be scrolled with the keyboard (arrows, `j`/`k`, `PgUp`/`PgDn`, `Space`, `Home`/`End`)allowAllClaudeAiMcps managed setting to load claude.ai cloud MCP connectors alongside `managed-mcp.json`/feedback reports to include the conversation that happened before context compaction, making issues from earlier in long sessions easier to triagefind in the Bash tool exhausting the macOS system file/vnode table and crashing the host on large directory trees/ultraplan and remote session creation failing with "Could not capture uncommitted changes" when the working tree has no real changesotelHeadersHelper failing silently when the script path contains spaces; helper failures are now reported in `/doctor` and the debug log/simplify to `/code-review`. It now reports correctness bugs at a chosen effort level (e.g., `/code-review high`); pass `--comment` to post findings as inline GitHub PR comments. The old cleanup-and-fix behavior has been removed& in `!` command output displaying as `&`, which broke copy-pasting URLs from commands like `gcloud auth login` on headless machines/help rendering a broken tab header and showing only one command per page on small terminals when not in fullscreen modeif conditions like `PowerShell(git push*)` never matching — only `PowerShell(*)` worked+You can now share canvases from Cursor with your teammates.
You can now share canvases from Cursor with your teammates.
Canvases are interactive artifacts created by agents, like reports, dashboards, and custom interfaces. Instead of sharing a full chat thread, you can share a link to a live snapshot of a canvas for teammates to open in the browser.
Teammates open a shared canvas from its link with read-only access. The Shared Canvases page in the Cursor Dashboard lists the canvases you've published, so you can manage your own shares. Shared canvases are available on Pro, Teams, and Enterprise plans.
Learn more in our docs.
With /loop, Cursor can run a prompt repeatedly on a local schedule, until a certain outcome is achieved, or until you stop it. If you don't specify a fixed interval, the agent decides when or what event should wake it.
Use the /loop skill for local long-running agents. For example, you can ask it to “check deploy status every 5 minutes” or “work on this feature until tests pass.”
continue reading on the release page →claude agents --json to list live Claude sessions as JSON for scripting (tmux-resurrect, status bars, session pickers)agent_id and `parent_agent_id` attributes to `claude_code.tool` OTEL spans, and fixed trace parenting so background subagent spans nest under the dispatching Agent tool span/plugin Discover and Browse screens now show a plugin's commands, agents, skills, hooks, and MCP/LSP servers before installationclaude agents terminal tab title now shows the awaiting-input count so an alt-tabbed window tells you when an agent needs attention+Cursor is now available in Jira.
Cursor is now available in Jira.
Assign work items to Cursor, or mention @Cursor in a comment to kick off a cloud agent. Cursor uses the work item title, description, comments, and your team's repository settings to scope the task.
You can ask Cursor to fix bugs, add features, update tests, or investigate something described in the ticket. When the agent finishes, Jira shows completion updates and includes a link to the pull request.
Install the integration from Cursor integrations. You need Cursor admin access and Jira Commercial Cloud with Rovo enabled. Learn more in our docs.
continue reading on the release page →/resume support for background sessions — sessions started via `claude --bg` or agent view now appear alongside interactive ones, marked with `bg`/plugin browse and discover panes now show when a plugin was last updated/model now changes the model for the current session only; press `d` in the model picker to set a default for new sessions/bg and `←`-detach now preserve directories added via `/add-dir`claude agents / `--bg` rejection messages now name the specific gate (non-TTY, env var, or setting) instead of a generic messageclaude --bg --name <label> now echoes the name in the post-spawn confirmationclaude agents: renaming a background session with Ctrl+R now updates the attached session's banner immediately/branch failing with "No conversation to branch" after entering a worktree or in some background sessionsworktree.bgIsolation: "none" setting to let background sessions edit the working copy directly without `EnterWorktree`, for repos where worktrees are impracticalclaude agents now accepts `--add-dir`, `--settings`, `--mcp-config`, and `--plugin-dir` and applies them to the dashboard and to background sessions dispatched from itclaude agents accepts `--permission-mode`, `--model`, `--effort`, and `--dangerously-skip-permissions` to set defaults for sessions dispatched from the viewclaude --bg --dangerously-skip-permissions now persists across retire→wake.credentials.json with a non-array `scopes` value hanging the CLI on startup or silently aborting OAuth token refreshclaude agents on Windows Terminal and WSL/goal evaluator firing while background shells or delegated subagents are still runningNO_COLOR/`FORCE_COLOR` in settings.json `env` stripping Claude Code's own UI colors — they now apply to subprocesses only/bg without a prompt sending "continue" to the forked session — the fork now waits for inputclaude agents flags: `--add-dir`, `--settings`, `--mcp-config`, `--plugin-dir`, `--permission-mode`, `--model`, `--effort`, and `--dangerously-skip-permissions` to configure dispatched background sessions/plugin details pane and `claude plugin details` now show LSP servers a plugin provides/web-setup warns before replacing an existing GitHub App connection/model claude-sonnet-4-20250514 suggestion from Usage Policy refusal messagesMCP_TOOL_TIMEOUT not raising the per-request fetch timeout for remote HTTP and SSE MCP servers, which capped tool calls at 60 seconds regardless of the configured valueclaude agents "v to open in editor" using the daemon's default editor instead of your shell's `$EDITOR`/`$VISUAL`claude agents deadlocking on Windows with network-drive working directories; Ctrl+C now works during startupterminalSequence field to hook JSON output so hooks can emit desktop notifications, window titles, and bells without a controlling terminalCLAUDE_CODE_PLUGIN_PREFER_HTTPS to clone GitHub plugin sources over HTTPS instead of SSH, for environments without a GitHub SSH keyANTHROPIC_WORKSPACE_ID environment variable for workload identity federation — scopes the minted token to a specific workspace when the federation rule covers more than oneclaude agents --cwd <path> to scope the session list to a directory/feedback can now include recent sessions (last 24 hours or 7 days) for issues spanning more than the current sessionclaude agents: agents that finish work but leave a background shell running now move to Completed instead of staying under WorkingawsCredentialExport now always runs when configured instead of being skipped when ambient AWS credentials resolve, fixing auth for cross-account accessclaude daemon status and `/doctor` on Windows throwing when the daemon pipe key file is locked or unreadable — now shows the underlying error instead of an opaque failureclaude agents showing the agent-type list instead of the dashboard when launched through a wrapper that adds flagsclaude agents opening a crashed session firing redundant dispatches when the working directory was deleted/model in one session silently changing the autocompact threshold in other concurrent sessions