AWS Platform Adds Advisor Command to Bring In Experts for Suggestions
If you want a second opinion on Claude on AWS, you no longer need to switch between multiple chat windows. The platform has added an advisor feature.
Normally, no advisor runs quietly in the background until you explicitly enter /advisor, pass the --advisor flag at startup, or specify advisorModel in your configuration to launch one. If your team never uses this tool, you can disable it entirely using the environment variable CLAUDE_CODE_DISABLE_ADVISOR_TOOL=1.
FEATURE
Mods Expand Interface Capabilities with Virtual Text and History Change Hooks
Developing custom extension mods gives you more flexible control over input boxes and screen rendering.
Virtual text attributes let you display hint text inside the input box without ever polluting drafts or submitted prompts. An interface inspection function lets you review the activity history of a specific agent directly on the main screen, and passing an empty object returns you to the prior view. Text components now support right-to-left writing settings, displaying text direction correctly and aligning text to the right in Windows and VS Code terminals. A newly added input change hook triggers when retrieving history, clearing, undoing, or when plugins populate text. This also fixes an issue where entering a newline failed to trigger the edit hook.
FEATURE
Hooks Support Workflow Rewrites with Strict Validation for Inputs and Plugin Keys
When managing agent startup workflows through hooks, the biggest concern is external logic corrupting parameters or leaking secret keys.
Agent spawn hooks previously could only reject workflow agents, but they can now directly rewrite their prompts and models. When a hook returns updated inputs before tool execution or permission requests, the system filters unknown fields just like standard inputs, and inputs rejected by tools immediately block the call. Agent hooks now respect configured models, resolve aliases correctly, and cannot be overridden by subagents. If no model is found, they fall back to the caller's fallback model. When sharing modules, built-in skills actively scan for secret keys before opening files and ask for confirmation before scanning folders outside the project. Prompts rewritten or discarded by hooks, as well as module hot-reload notes, are no longer mistakenly logged to telemetry, session title requests, or conversation logs.
BUGFIX
Agent Lists and Task Views Fixed to Keep Sessions Open
Assigning multiple agents to work in parallel makes tracking progress and reviewing conversations more reliable. Previously, subagents that had just replied would quickly vanish from the task list after completing their work, leaving you with no way to revisit the conversation; they are now properly preserved.
When inspecting subagents, completed parent agents no longer drop from the top breadcrumb path, keeping hierarchical relationships clear. When typing quickly, if text contained arrow-key names, the agent screen previously misinterpreted them as keypresses, shifting the preview or even clearing drafts; this issue has been resolved. Agent commands no longer stall the entire update flow when encountering individual requests with incomplete data. Managed agent sessions within skills are now fully preserved unless you explicitly request archiving or deletion.
BUGFIX
Background Services Terminate Reliably Without Leaving Orphaned Processes
Running tests or builds in the background makes you worry about frozen terminals or leftover orphaned processes when exiting.
Previously, if background commands were still running when exiting the program, session-end hooks were sometimes skipped. Now, if a command does not close within 1.5 seconds after receiving a stop notification upon exit, the system forcibly terminates it. Stopping a daemon no longer creates the illusion that a frozen background service has stopped, and it returns error code 1 if cleanup fails. Stopping daemons when telemetry is disabled also no longer exits silently while leaving sessions stranded on the list. Executing background commands no longer polls output files repeatedly or falls into sleep. When background sessions resume workflows, they now resume execution through the workflow tool approval mechanism.
BUGFIX
Worktree Fixes Branch Resolution to Prevent Opening Wrong Versions on Tag Collisions
Large projects often require creating multiple Git worktrees to handle different features, and switching versions is now far more accurate.
Previously, if a branch or tag name resembled a commit hash, launching a worktree could check out the wrong version and display another branch name in the status; this identification issue is now resolved. In projects adopting modern storage backends, bugs causing abnormal branch name display and failures when reopening worktrees have been fixed. In worktrees for bare repositories unable to fetch the remote default branch, the system falls back to using the currently checked-out version as the baseline. When launching a worktree, corresponding plugin creation and removal hooks now run reliably.
BUGFIX
Remote Control Reconnection and Diff Views Fixed with Dead Sandbox Flags Removed
Connecting back to your computer from the web or desktop apps now offers better connection stability and file comparison for remote control.
When encountering brief credential issues, the server no longer abandons connection renewals immediately; it retries automatically and prompts you to log in again only when necessary. When a single computer hosts multiple connections simultaneously, active sessions are no longer mistakenly marked as stopped. Diff views across web and desktop clients now accurately distinguish between deleted and renamed files instead of labeling them all as modified, and conflict states display correctly. A previously ineffective sandbox command-line parameter has been removed; if you need sandbox protection, set sandbox.enabled to true in your configuration file.
BUGFIX
MCP Tool Fault Tolerance and Auto-Search Fixed to Survive Reconnections
Integrating external services poses risks when brief network reconnections or formatting errors interrupt an entire conversation. When auto tool search is enabled, if an MCP (Model Context Protocol) server reconnects halfway through, search previously shut down without warning; it now remains active after the fix.
When rejected external tool definitions trigger errors, subsequent turns transmit the tool without parameters, preventing every turn from getting stuck on 400 errors. For servers that finish connecting after session compaction, tools and descriptions update immediately. Resuming conversation history also avoids repeatedly searching for previously loaded deferred tools.
BUGFIX
Session Compaction and Record Retention Fixed to Protect Conversations Across Reboots
Deep, lengthy conversations and headless executions rely on scheduled summaries to prevent context from exceeding capacity limits. In headless mode or within the Agent SDK, if compaction triggered when answers hit length limits or during retries, reconnecting could drop recent pending messages or summaries; these scenarios have been thoroughly fixed.
When abnormal terminations truncate the final line of a conversation log, reopening no longer loses the very next log entry. Conversations containing unusual newline characters no longer cause branch commands to lose messages or cleanup commands to skip subprojects. Shrinking the auto-compaction window no longer causes compaction commands to emit false high-quota warnings. Local session logs now record system prompts and tool parameters for every request, allowing precise reproduction.
BUGFIX
Cloud Sessions Fix Freezes to Let Agents Resume After Container Resets
Long-running cloud tasks face risks when server reboots or policy fetch failures freeze progress for minutes at a time. Previously, if organization policies could not be retrieved, cloud sessions stalled for 5 minutes per turn; they now terminate the turn immediately and state the reason clearly.
When a session's own network configuration blocks the host, it reports this truthfully instead of misidentifying the cause as organization policy restrictions. After cloud containers are replaced, background agents that resumed once are no longer falsely reported as permanently lost, continuing execution normally. A bug where restarting during long responses caused completed messages to run a second time has also been resolved. Finally, command descriptions in the slash menu no longer vanish after sending a second message in a cloud conversation.
BUGFIX
Cowork Cloud Fixes Phantom File Writes, Improves Web Scraping and Permission Flexibility
When delegating tasks in the Cowork cloud environment, the system previously could misreport unreceived local files as successfully saved. Writing or editing files in the cloud with a specified local path used to show success even if the file never reached the machine; this false confirmation is now fixed.
The web scraping tool now explicitly explains the failure reason when encountering a freshly failed URL, rather than blindly fetching the same page again. When organizations disable allow-always, connector tool approval prompts previously missed the allow-for-this-task option, a regression that has been resolved. In cloud hooks, when an approval attempt tries to alter the mode, that modification is skipped while keeping the remaining approved items intact.
For enterprise environments navigating corporate security inspections and gateway controls, login credential and connection policy management is now much tighter.
When a login was previously rejected by a rule enforcing specific organizations, authorization tokens for the rejected organization used to linger; they are now wiped clean upon rejection. Behind proxy servers that perform TLS inspection through the operating system credential store, feature flags and staged rollouts update normally instead of getting stuck on older versions. Sessions in managed environments now ignore custom certificates and TLS variables in configuration files, preventing corporate policies from being overridden. The desktop Code tab applies managed settings when a gateway is specified, requiring a reachable gateway at launch. When encountering policy keys unsupported on desktop, gateway commands now name the offending key and abort on startup rather than merely issuing a warning.
FEATURE
Telemetry Records Break Down Cache Lifespans, Enabling Compression by Default on Large Requests
Monitoring API request costs and debugging traces now provides visibility into cache lifespans while conserving bandwidth through compression.
Large requests sent to the API now enable gzip compression by default to accelerate transfers, which remains effective even if telemetry is disabled; setting CLAUDE_CODE_GZIP_REQUEST_BODIES=0 disables it. Telemetry traces introduce breakdown fields for cache lifespan, explicitly separating 5-minute and 1-hour write units. Trace spans now populate standard generative AI attributes, including provider name, conversation ID, tool name, and error type. A bug was resolved where tool execution results omitted commit hashes during quiet commits in new-style repositories.
FEATURE
Artifact Tool Supports Single-Turn Publishing, Improving Draft and Document Paths
Asking Claude to write long reports or modify code deliverables is now cleaner and faster as Artifact generation and refinement improve.
When modifying an artifact, minor updates and republishing can now be merged in a single call, while larger edits can also be republished directly within the same response without staged delays. Detailed status lines during artifact tool execution previously displayed unprintable path codes when receiving input, but now clearly indicate waiting and running states just like terminal commands. Files recorded in session scratchpads now use full absolute paths instead of confusing standalone filenames or relative paths. When referencing PDF documents in a conversation, the model receives clearer prompts, reducing instances where it hallucinates answers before reading the content.
BUGFIX
Terminal Text Contrast and Menu Descriptions Fixed, Eliminating Duplicate Startup Calls
Display details across various terminals and integrated editor panels now render dim text clearly without duplicate startup checks. Under dark ANSI themes and 16-color terminals, secondary dim text previously appeared identical to standard text, making hierarchy hard to discern; contrast has now been adjusted.
When launching in the integrated terminal of VS Code, Cursor, or Devin Desktop, extension check commands previously ran 2 times, but are now streamlined to launch only 1 time. Option labels in the sandbox menu have been changed from misleading names to more intuitive command names. Documentation introducing restricted mode arguments was corrected after erroneously listing removed tools.
BUGFIX
Self-Hosted Runners Fix Output Freezes, Preserving Health Checks and Polling
Running automated tasks on self-hosted servers risks silent runner freezes whenever logs go unread. Previously, when output remained unread, runners and dispatchers stopped polling, health checks disconnected, and processes could not be shut down via signals.
Logs now retain the latest 256 KiB and track the count of discarded messages, excluding Windows systems, keeping services continuously operational.
BUGFIX
VS Code Adds Option to Disable Auto-Attaching Selected Text, Fixing Drag-and-Drop and Menus
Asking questions in VS Code can now prevent editor-selected text from being automatically inserted into the input box. The new claudeCode.attachSelection setting disables automatic attachment when set to false.
Holding Shift while dragging files into the input box on Windows no longer inserts unreadable drive paths, correctly generating references relative to the working directory instead. Dragging files across WSL, remote SSH, or container environments is no longer unresponsive. Pressing the up arrow to recall previous slash commands and hitting Enter no longer drops original arguments. Editing previously bookmarked prompts is no longer obstructed by unexpected file menu popups. Pressing Ctrl+Alt+F across File Explorer, other tree views, or the debug console on Windows and Linux now opens search instead of erroneously toggling Focus view.
BUGFIX
VS Code Intelligently Toggles Thinking and Quota States, Fixing Multi-Window Locks
Switching models or reloading windows in VS Code risks requests getting trapped in retry loops once quotas run out. Fast mode previously stayed on when quota was exhausted, causing requests to be repeatedly rejected and retried, but now displays an error prompt and turns off automatically.
For models that always perform deep thinking, the interface no longer displays a redundant thinking toggle. Conversation font size changes now apply immediately to diff views and plan previews without requiring a window reload, and are no longer overridden by theme changes. Reloading tabs or clicking to resume a session no longer loses branch conversations moved to worktrees. The system now calls tools directly when checking sessions in other windows, avoiding redundant processes from frequent path searches. After a crash and reboot, the system no longer falsely reports conversations as open elsewhere when process IDs are reused by other software.
Slack workspaces support cross-enterprise shared channels, enabling cross-company collaboration and authorization checks without switching tools. Administrators can now allow Claude to respond in shared Slack Connect channels, an option disabled by default for privacy; existing channel permission bundles also remain effective after upgrading to cross-organization channels.
When a connector tool requires authorization, an ephemeral card visible only to you appears in the thread to allow once or deny instead of throwing an error, while others only see that the system awaits your decision. Audio clip support is added, enabling Claude to read contents whenever Slack generates a transcript. A bug was fixed where other bots tagging Claude under messages sent by Claude itself went unanswered.
BUGFIX
Code Review Supports Triggers from Private Members, Linking Status Notes to Permission Settings
Summoning Claude to review code in pull requests now lets private members trigger the review workflow smoothly. Developers with write access whose GitHub organization membership was kept private previously found @claude review comments frequently ignored; the system now recognizes permissions accurately and launches reviews.
When repository review functionality is paused, comments no longer direct administrators to irrelevant settings landing pages, clearly naming authorized personnel instead and linking directly to the Git provider settings page.
Original changelog
Original changelogAWS Platform Adds Advisor Command to Bring In Experts for Suggestions
Added `/advisor` on Claude Platform on AWS; no advisor runs until you pick one with `/advisor`, `advisorModel` or `--advisor`, and `CLAUDE_CODE_DISABLE_ADVISOR_TOOL=1` turns it off
Original changelogMods Expand Interface Capabilities with Virtual Text and History Change Hooks
Added `virtualText` to a mod's prompt decorations: text drawn in the prompt box that never enters the draft or the submitted prompt
Added `$.ui.view({ agentId })` for mods: shows an agent's transcript in the main view when you ask, and `$.ui.view({})` goes back
Added a `dir` prop on a mod's `Text` for right-to-left text: on Windows and in VS Code's terminal its rows read in that direction and sit flush right
Added the `prompt.change` mod hook, raised when the prompt box's text changes without a typed edit: a recalled history entry, a clear, an undo, or a plugin's fill
Fixed a mod's `prompt.edit` hook not being raised for a newline entered with the `chat:newline` keybinding (Ctrl+J, or a rebound Enter)
Original changelogHooks Support Workflow Rewrites with Strict Validation for Inputs and Plugin Keys
Added support for rewriting a workflow agent's `prompt` and `model` in the `agent.spawn` mod hook, which could only refuse workflow agents before
Fixed a prompt that a mod's `prompt.submit` hook rewrote or dropped still being recorded as typed in the OpenTelemetry `user_prompt` event and interaction span, and in session title requests
Fixed a note meant for Claude about mod hot-reloading appearing in the transcript as if you had typed it
Fixed agent hooks ignoring their `model`: aliases like `haiku` now resolve, a subagent's model no longer overrides it, and an unavailable model falls back to the caller's instead of allowing the action
Improved mod sharing in the built-in `plugin-authoring` skill: Claude scans a mod's files for keys before opening them, and asks before scanning a folder outside the project
Changed hooks: `updatedInput` from PreToolUse and PermissionRequest hooks is now validated like Claude's own input: unknown keys are dropped, and input the tool rejects denies the call
Original changelogAgent Lists and Task Views Fixed to Keep Sessions Open
Fixed `claude agents` not refreshing any pull request's status when the data for one of them came back incomplete
Fixed subagents you had typed messages to disappearing from `/tasks` shortly after finishing, leaving no way back to the conversation
Fixed a completed parent agent dropping off the breadcrumb (its child shown re-rooted at top level) while you were viewing the child
Fixed the agents view taking a typed word such as "up", "down" or "escape" for that key when input arrived in a burst, which could move the peek mid-reply or clear a draft
Changed the `claude-api` skill to leave Managed Agents sessions in place unless you ask to archive or delete them
Original changelogBackground Services Terminate Reliably Without Leaving Orphaned Processes
Fixed SessionEnd hooks sometimes not running when you exit while a background command is still running
Fixed Claude polling a background command's output file or sleeping while it runs
Fixed `claude daemon stop --any` printing "stopped" while a stuck background service kept running: it now waits, force-kills the service, and says so with exit 1 if it is still there
Fixed `claude daemon stop` exiting with no output, and leaving sessions listed as running, when telemetry is turned off
Changed exit to force-kill background commands still running 1.5 seconds after being asked to stop; in fullscreen mode they could previously be left running
Changed background sessions to resume a carried workflow through the Workflow tool's approval instead of running it from the handoff file
Original changelogWorktree Fixes Branch Resolution to Prevent Opening Wrong Versions on Tag Collisions
Fixed plugin `WorktreeCreate` and `WorktreeRemove` hooks not running when Claude Code starts with `--worktree` (not yet with `--tmux`)
Fixed `--worktree` sessions sometimes starting from the wrong commit when a tag or branch was named like a commit ID, and their starting git status naming a branch other than the new worktree's
Fixed the branch showing as ".invalid" and `--worktree` failing to reopen a worktree in repositories using git's reftable ref storage
Fixed `--worktree` failing in a worktree of a bare repository when origin's default branch can't be fetched; the fallback base is now the current checkout's HEAD, not the main repository's
Original changelogRemote Control Reconnection and Diff Views Fixed with Dead Sandbox Flags Removed
Fixed the diff view in Claude Desktop and Remote Control sessions not noticing a conflicted cherry-pick or revert in reftable repositories
Fixed `claude remote-control` servers giving up on renewing their connection after a brief sign-in error, such as a locked keychain; they now retry, and warn when you need to run `claude /login`
Fixed Remote Control sessions being marked stopped while still running, on a computer serving several sessions at once
Removed the `--sandbox` and `--no-sandbox` flags from `claude remote-control`, which had no effect; passing either now exits with an error. Set `sandbox.enabled` in settings to sandbox sessions
[Remote Control] Fixed the diff view in Remote Control sessions on claude.ai and the desktop app showing deleted and renamed files as modified; requires Claude Code v2.1.296 or later on your machine
Original changelogMCP Tool Fault Tolerance and Auto-Search Fixed to Survive Reconnections
Fixed automatic tool search (`ENABLE_TOOL_SEARCH=auto`) turning off part-way through a conversation, for example while MCP servers reconnect after a resume
Fixed a conversation failing on every turn with a 400 error when the API rejected an MCP tool's input schema; Claude Code now sends that tool without parameters for the rest of the conversation
Fixed Claude not being told about an MCP server's tools and instructions until its next tool call, when the server finished connecting after a compaction
Fixed Claude searching for deferred tools already loaded earlier in the conversation when a session resumes a history that never listed them
Original changelogSession Compaction and Record Retention Fixed to Protect Conversations Across Reboots
Fixed `/autocompact` warning about high token usage when you choose a smaller auto-compact window
Fixed the first transcript entry written after resuming a session being lost when a crash had cut the transcript's last line short
Fixed `/branch` dropping messages, and `claude purge` skipping subfolder projects, when they contain a Unicode line or paragraph separator (U+2028, U+2029)
Fixed resuming a headless or Agent SDK session losing the recent messages a compaction had kept, when the compaction followed a reply cut at the output token limit (compactions from this version on)
Fixed resuming a headless or Agent SDK session losing its compaction summary or bringing back pre-compaction history, when the compaction followed a retried or unfinished reply in the same turn
Changed local session transcripts to also record each API request's system prompt, tools and parameters, so a transcript you choose to share can reproduce a request exactly
Original changelogCloud Sessions Fix Freezes to Let Agents Resume After Container Resets
Fixed cloud sessions telling Claude that an organization policy blocked a host when the session's own network settings did
Fixed Claude being told a background agent was lost, not resumable, after a cloud session's container was replaced, when the agent had already been resumed once
Fixed cloud sessions hanging 5 minutes per turn when the organization's policy can't be read; the turn now ends promptly and says why
Fixed a cloud session sometimes running an already answered message a second time after the session restarted during a long reply
[Cloud sessions] Fixed most commands in the / menu losing their descriptions in cloud sessions once you sent a second message
Original changelogCowork Cloud Fixes Phantom File Writes, Improves Web Scraping and Permission Flexibility
Fixed Write, Edit and NotebookEdit in Cowork cloud sessions reporting success for a path on your own computer, where the file never arrived
Improved WebFetch in Cowork cloud sessions to tell Claude that a page failed moments ago instead of fetching it again
Changed `PermissionRequest` hooks in Cowork cloud sessions: a `setMode` update in a hook's allow is now ignored; the rest of the approval still applies
[Cloud sessions] Fixed "Allow for this task" missing from Cowork's approval prompts for connector tools where an organization turns off "Always allow" (regression in 2.1.292)
Original changelogEnterprise Gateways Tighten Policy Controls, Fixing Proxies and Residual Login Credentials
Fixed a login refused by `forceLoginOrgUUID` leaving the refused organization's token stored, or live after `/login`
Fixed feature flags and staged rollouts staying stale behind a TLS-inspecting proxy whose certificate is trusted only through the OS certificate store
Changed `CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST` sessions to ignore CA-bundle, tool-proxy, git TLS and git config variables like `SSL_CERT_FILE` in settings; under Claude Desktop, only in project settings
Changed Claude Desktop's Code tab to apply managed settings when `forceLoginGatewayUrl` names an Anthropic-operated gateway that serves the session's hostname; that gateway must be reachable at start
Changed `claude gateway` to stop at start, naming the key, on a `desktop:` policy key that Claude Desktop cannot use from a gateway, where it earlier started with a warning
Original changelogTelemetry Records Break Down Cache Lifespans, Enabling Compression by Default on Large Requests
Added `cache_creation_5m_tokens` and `cache_creation_1h_tokens` to the OpenTelemetry `api_request` event, splitting cache writes by lifetime
Added OpenTelemetry GenAI semantic-convention attributes to trace spans, such as `gen_ai.provider.name`, `gen_ai.conversation.id`, `gen_ai.tool.name` and `error.type`
Fixed OpenTelemetry `tool_result` events missing `git_commit_id` after `git commit -q` in repositories using reftable ref storage
Changed large requests to api.anthropic.com to use gzip compression even when telemetry is disabled; set `CLAUDE_CODE_GZIP_REQUEST_BODIES=0` to turn it off
Original changelogArtifact Tool Supports Single-Turn Publishing, Improving Draft and Document Paths
Fixed the Artifact tool's verbose and ctrl+o line reading `Artifact("(unprintable path)")` while a call's input arrives; its row now shows "Waiting…" and "Running…" as Bash's does
Fixed Claude naming files in the session scratchpad by a bare filename or relative path instead of their full path
Improved the note Claude 3 models get about an @-mentioned PDF, so they less often answer without reading it
Improved artifact updates: Claude now applies a small change and republishes the artifact in one call, and makes larger edits and republishes within a single response
Original changelogTerminal Text Contrast and Menu Descriptions Fixed, Eliminating Duplicate Startup Calls
Fixed `claude --help` naming a removed tool in its description of `--restricted`
Fixed starting Claude Code in a VS Code, Cursor or Devin Desktop integrated terminal launching the editor's command-line tool twice to check for the extension; it now launches it once
Fixed secondary (dim) text looking the same as normal text under the dark ANSI theme and on 16-color terminals
Changed the `/sandbox` mode options to read "Sandbox commands" instead of "Sandbox BashTool"
Original changelogSelf-Hosted Runners Fix Output Freezes, Preserving Health Checks and Polling
Self-hosted runner: Fixed the runner and orchestrator freezing (no polls, `/healthz` or `SIGTERM` shutdown) while nobody reads their output; logs keep the latest 256 KiB and count drops (not on Windows)
Original changelogVS Code Adds Option to Disable Auto-Attaching Selected Text, Fixing Drag-and-Drop and Menus
[VSCode] Added the `claudeCode.attachSelection` setting to stop text selected in the editor from being added to your messages
[VSCode] Fixed "Edit prompt" on a flagged message opening the file or command menu over the restored prompt; Enter now sends it as written
[VSCode] Fixed Shift+dragging a file onto the prompt on Windows inserting an unreadable `/c:/…` path instead of a mention relative to the working directory
[VSCode] Fixed ↑ then Enter on a recalled slash command running it without its arguments; the command and file menus no longer open over a recalled prompt until you edit it
[VSCode] Fixed Shift+dragging a file from the Explorer or an editor tab onto the prompt inserting nothing in WSL, SSH and Dev Container windows
[VSCode] Fixed Ctrl+Alt+F toggling Focus view instead of opening Find in the Explorer, other tree views, or the Debug Console on Windows and Linux
Original changelogVS Code Intelligently Toggles Thinking and Quota States, Fixing Multi-Window Locks
[VSCode] Fixed fast mode staying on after usage credits ran out, which made each request be refused and re-sent; it now turns off until you turn it back on, with an error notice
[VSCode] Fixed the Thinking toggle switching to Off on models that always think; the toggle is no longer shown for those models
[VSCode] Fixed changes to VS Code's chat font size settings needing a window reload or being undone by a theme change; diffs and the plan preview now follow them too
[VSCode] Fixed "Resume session" and tabs restored after a reload opening an empty new conversation instead of one that had moved into a git worktree
[VSCode] Fixed the check for sessions open in other windows or terminals creating extra processes on macOS: it now starts `/bin/ps` directly instead of searching PATH for `ps` on every check
[VSCode] Windows: Fixed a conversation showing "still open somewhere else" after a crash or power loss, when Windows had since restarted and given the old process ID to another program
Original changelogSlack Supports Cross-Organization Channels, Adding Ephemeral Approval Cards and Audio Clip Reading
[Claude Tag] Added support for Slack Connect channels: an Owner or Claude Tag admin can let Claude in Slack answer in channels shared with another organization; it's off by default
[Claude Tag] Added a private Allow once / Deny card in Slack threads for connector actions that need your approval, so Claude asks instead of refusing; others only see that it's waiting on you
[Claude Tag] Added support for Slack voice clips in Claude in Slack: Claude reads Slack's transcript of a clip when Slack has one
[Claude Tag] Fixed Claude in Slack not answering another app that tags it in a thread under a message Claude itself posted to the channel
[Claude Tag] Changed access bundles an admin attached to a Slack channel to keep applying once the channel becomes a Slack Connect channel, with no need to remove and re-attach them
Original changelogCode Review Supports Triggers from Private Members, Linking Status Notes to Permission Settings
[Code Review] Fixed Code Review ignoring `@claude review` comments from people with write access whose GitHub organization membership is private; their comments now start a review
[Code Review] Fixed Code Review's "paused for this repository" comment sending admins to Code Review settings; it now says who can fix it and links the Git providers page