[renovate]

Note

This PR body was truncated due to platform limits.

This PR contains the following updates:

Package	Change	Age	Confidence	Type	Update	Pending
@aloth/olcli	0.13.0 → 0.15.2				minor	0.15.3
@anthropic-ai/claude-code	2.1.272 → 2.1.312				patch	2.1.318 (+4)
@ast-grep/cli (source)	0.45.3 → 0.51.0				minor	0.51.1
@drawio/mcp	1.5.0 → 1.10.0				minor	1.10.1
@eslint/js (source)	9.39.4 → 9.39.5			devDependencies	patch
@openai/codex (source)	0.154.0 → 0.166.0				minor
@playwright/mcp (source)	0.0.81 → 0.0.83				patch	0.0.84
@types/node (source)	22.20.0 → 22.20.5			devDependencies	patch
@vitest/coverage-v8 (source)	4.1.9 → 4.1.12			devDependencies	patch
astral-sh/uv	0.12.15 → 0.13.6				minor	0.13.7
cli/cli	v2.100.0 → v2.103.3				minor
esbuild	0.28.1 → 0.28.2			devDependencies	patch
eslint (source)	9.39.4 → 9.39.5			devDependencies	patch
github/github-mcp-server	v1.12.1 → v1.14.0				minor
go (source)	1.27.1 → 1.27.3				patch
golang.org/x/tools/gopls	v0.23.0 → v0.24.0				minor
jdx/mise	v2026.9.9 → v2026.10.23				minor	v2026.11.2 (+4)
mattpocock/skills	v1.2.3 → v1.3.2				minor
mattpocock/skills	v1.1.0 → v1.3.2				minor
n8n-mcp	2.92.1 → 2.99.2				minor	2.101.0 (+1)
node (source)	22.23.2 → 22.23.4				patch
npm (source)	10.9.4 → 10.9.9			packageManager	patch	10.9.10
prettier (source)	3.8.2 → 3.9.10			devDependencies	minor
skills	1.5.16 → 1.7.4				minor	1.7.6 (+1)
typescript-eslint (source)	8.62.1 → 8.72.1			devDependencies	minor
typescript-language-server	6.0.0 → 6.0.2				patch	6.0.3
vitest (source)	4.1.9 → 4.1.12			devDependencies	patch

---

Warning

Some dependencies could not be looked up. Check the Dependency Dashboard for more information.

Run the skills source sync command for provenance/skills-source.lock before merging so the adapted source stays aligned with this pin.

---

Release Notes

aloth/olcli (@​aloth/olcli)

v0.15.2

Compare Source

Fixed

• sync --verbose prints the file list again (#​7) - sync declared its own --verbose next to the global one, and the global one always took the flag, so the list of files deleted on the remote, skipped, or pushed never printed. sync now uses the global --verbose, and olcli sync --dry-run --verbose previews deletions as documented since 0.2.0. A test fails when a subcommand declares a flag that a parent command already declares
• Behavior change for scripts: diff --exit-code exits 2 when the run fails - without a credential, and on an unknown option or a missing option value, diff --exit-code exited 1, the status for "something differs", so a CI job could read an expired session as a changed paper. It now exits 2, as README.md and diff --help document. Without --exit-code, diff and every other command still exit 1 on failure
• Behavior change for scripts: whoami exits 1 when not authenticated - it printed "Not authenticated" or "Session invalid" and exited 0. It now exits 1 in both cases, so olcli whoami || olcli auth works
• The git remote helper names a command that exists - when no credential is found or the session is rejected, it said "Run 'olcli login'", which is not a command. It now says olcli auth or OVERLEAF_SESSION

Changed

• Package metadata for the MCP registry - package.json gains mcpName (io.github.aloth/olcli), and a server.json describes the MCP server for the official MCP registry: the olcli-mcp command of @aloth/olcli, with OVERLEAF_SESSION as a required secret and OVERLEAF_BASE_URL and OVERLEAF_COOKIE_NAME as optional. The author contact in package.json is now home@alexloth.com
• changes accept and changes reject help - --project no longer claims to default to the last used project, which no command reads. Without it both commands use the project in .olcli.json in the current directory, as before

Documentation

• MCP setup with npx - docs/MCP.md and SKILL.md started the server with npx -y @aloth/olcli-mcp, a package that does not exist. The examples now use npx -y --package @aloth/olcli olcli-mcp
• Git remote helper - docs/GIT-REMOTE.md says the helper reads .olauth from the current directory (the repository top level), not ~/.olauth. Its Limitations section now states that a push uploads your version of every file your commits changed, so an edit a coauthor made to one of those files on Overleaf after your last fetch is overwritten, and that running git pull right before git push avoids it
• Environment variables - README.md lists every variable olcli reads, including the previously undocumented OVERLEAF_COOKIE_NAME and OLCLI_CONCURRENCY. docs/MCP.md names both session cookie names, overleaf_session2 on overleaf.com and overleaf.sid on self-hosted instances, and shows OVERLEAF_COOKIE_NAME
• SKILL.md lists the accept_tracked_changes and reject_tracked_changes MCP tools and the project rename <newname> [project] signature. A test fails when a registered MCP tool is missing from SKILL.md or docs/MCP.md
• Contributor credits - the 0.6.0 entry credits @​Duccioo (#​31) and @​Littleor (#​32), and the 0.4.1 entry thanks @​Seauagain for #​26. CONTRIBUTING.md states that a pull request the maintainer reimplements instead of merging is credited with a Co-authored-by trailer in the commit and in the CHANGELOG

v0.15.1

Compare Source

Changed

• MCP tools that change an Overleaf project ask the user before writing - push_file, delete_entity, rename_entity, rename_project, create_project, add_comment, reply_to_comment, resolve_comment, accept_tracked_changes, and reject_tracked_changes with apply: true show a confirmation through MCP elicitation (form mode) and write only when the user checks "Confirm" and accepts. The dialog shows what will happen: for tracked changes each change with path, line, kind, author, and text plus a diff, for push_file the target path, size, and a diff against the current file, for comments and replies the exact text, for deletes and renames the resolved paths. Declining, dismissing, a timeout, or an error writes nothing, and the tool result says so. Previously accept_tracked_changes wrote immediately and reject_tracked_changes wrote as soon as the agent passed apply: true. Project content is written by collaborators and reaches the agent verbatim, so text in a comment or document could steer an agent into calling a write tool; the confirmation is answered by the user, not the agent. Input schemas are unchanged
• Behavior change for MCP clients without elicitation support - when the client does not declare the elicitation capability, the tools above no longer write. They return a preview, the olcli command that makes the same change from a terminal, and the opt-out. Setting OLCLI_MCP_UNCONFIRMED_WRITES=1 in the server environment restores the 0.15.0 behavior, writing without asking and relying on the client's own tool approval; it also skips the dialog in clients that support elicitation
• accept_tracked_changes writes only what was confirmed - it refuses if a selected change no longer has the kind and text shown in the confirmation. delete_entity and rename_entity act on the entity shown in the confirmation

Added

• MCP tool annotations - every tool declares readOnlyHint, destructiveHint, idempotentHint, and openWorldHint as applicable
• Untrusted-content notice - the MCP server sends instructions stating that project content (document text, comments, tracked changes, file and project names) is written by collaborators and is data, not instructions. Tools that return project content say so in their descriptions, and list_comments adds the notice as a second text block after the unchanged JSON block

Fixed

• The MCP server reported version 0.8.0 - it now reports the package version

v0.15.0

Compare Source

Added

• Tracked changes (#​58) - olcli comments list --changes lists suggested insertions and deletions next to comments, and olcli changes accept <ids...> and olcli changes reject <ids...> accept or reject them. reject shows a diff and writes nothing unless --yes is given. The MCP server gains include_changes on list_comments and the tools accept_tracked_changes and reject_tracked_changes. Track changes is an Overleaf premium feature: it is only available in projects whose owner has a premium plan, and invited collaborators on any plan can then use it

v0.14.0

Compare Source

Added

• olcli comments list --concurrency <n> and the OLCLI_CONCURRENCY environment variable set how many sockets fetch docs in parallel, from 1 to 8 (default 4). The option takes precedence over the variable, and 1 restores the previous one-socket behavior. Values outside the range are rejected with an error

Changed

• olcli comments list (and resolve, reopen, delete, which look the thread up first) joins docs over four sockets instead of one doc at a time - the command joined every doc in the project serially at about 0.25 s each, so a 43-doc project took around 14 s. One socket cannot overlap requests, since the long-poll gives an acknowledgment to whichever request polls first and the others time out, so the docs are spread across a small pool of sockets instead
• A failed doc join stops the socket pool cleanly - after the first failure no socket starts another join, and the error is reported only after every socket has been closed. Previously the remaining sockets kept joining docs in the background after the command had already failed
• Extra sockets that are rate limited fall back to fewer sockets - if Overleaf answers HTTP 429 when an additional socket opens, that socket is dropped and the remaining ones take over its docs, down to a single socket. A 429 on the first socket still fails the command

v0.13.1

Compare Source

Fixed

• git push through git-remote-overleaf no longer drops or corrupts files (#​59) - the fast-export parser counted data <N> blocks as latin1 bytes while Git counts UTF-8 bytes. Any file with non-ASCII characters left the parser short of the announced length, so it swallowed the following lines as file content: files after it were silently skipped, deletions were missed, and the content that did arrive was mangled, while the push still reported success
• Binary files such as images and PDFs now push byte for byte - the remote helper read the stream with readline, which decodes every payload as text and cannot give the original bytes back, so a pushed PNG or PDF arrived at the right size but corrupted. Commands are now read as lines and data <N> payloads as exactly N raw bytes, which also removes the text-decoding problem above at its root
  • Quoted paths, which Git emits for names with spaces or non-ASCII characters, are now unquoted before upload
  • parseFastExport moves to src/fast-export.ts; test/fast-export.test.ts covers all 256 byte values, UTF-8, CRLF, a quoted path, a deletion, and payloads split across chunk boundaries
  • git pull and git fetch were not affected. Overleaf itself normalizes CRLF line endings in text files to LF

Contributors

• @​am009 - found and fixed the UTF-8 byte counting in the remote helper (#​59)

anthropics/claude-code (@​anthropic-ai/claude-code)

v2.1.312

Compare Source

• Added oidc.user_id_claim to the Claude apps gateway, to identify people by an id_token claim other than sub, such as Microsoft Entra ID's oid
• Added click to send: in fullscreen, clicking the "to send now" hint under a queued message sends it right away, as its key does
• Fixed managed settings and organization policy not being fetched for the rest of the session after signing in from the VS Code extension
• Fixed Claude overwriting a very large CLAUDE.md, rules file or @​-included file in a subdirectory after seeing only its start; Write now asks Claude to read it all or edit in place
• Fixed per-directory and paths: skills not being found after a Bash cd deeper into a git repository
• Fixed a rare case where the first reply after resuming a session in the terminal could be missing the next time the session was resumed
• Fixed a command with an invalid name stopping all commands from loading, which could leave claude -p with no output
• Fixed the Read tool sometimes failing on PDF pages with "pdftoppm failed: Could not write image" when the clean-up of old session files ran at the same time
• Fixed the spinner, OpenTelemetry effort values and transcripts naming a newly picked effort level during a task before the model applied it; they now show the level in force
• Fixed the /model and /effort cache warning saying the re-read waits for your next message; a change made while Claude is working can trigger it sooner
• Fixed some sessions showing as waiting on you when the last message only mentioned items waiting on you mid-sentence
• Fixed agent view restoring input text on the next launch after it was cleared with Ctrl+C just before exiting
• Fixed agent view reopening in shell mode after exiting with Ctrl+D from an empty ! input
• Fixed vim mode d, c and y with a gj or gk count larger than the lines left deleting or copying text; like Vim, they now only move the cursor
• Fixed /verify showing a long description meant for Claude in /help and the / command menu instead of a short one
• Improved the prompt's effort indicator: a change made mid-task now says it may wait for your next message, and the note clears when it no longer applies
• Improved WebFetch errors in cloud sessions: a host that does not resolve is now explained as possibly outside the allowed network domains, so Claude names the host to allow
• Changed Bedrock, Vertex, Foundry and Mantle to use the shorter system prompt for model names Claude Code doesn't recognize, such as custom deployment names and inference profile ARNs, even when they front Sonnet or Haiku; set CLAUDE_CODE_SIMPLE_SYSTEM_PROMPT=0 to keep the full prompt
• Changed automatic model switches after a flagged message to also cover model names Claude Code doesn't recognize, such as custom deployment names; set CLAUDE_CODE_DISABLE_REFUSAL_FALLBACK=1 to turn them off
• Changed usage limit messages to call the 5-hour window the "5-hour limit" instead of the "session limit"
• Changed cloud sessions started from the CLI to get their names and branch names from the server
• Changed prompt and agent hooks to run at most 24 at a time per session, sub-agents included, plus at most 12 that have waited longer than their event's timeout; a timeout under 1 second now counts as 1 second
• Changed a subagent's autoCompactWindow to lower the window set by CLAUDE_CODE_AUTO_COMPACT_WINDOW, where it had no effect before; it still never raises that window
• Changed OpenTelemetry mcp_server.name to report the real name of fixed-URL remote MCP servers declared by plugins from the official Anthropic marketplace, instead of custom
• Changed Claude Code to stop sending the claude_code.safety_event OpenTelemetry event
• [VSCode] Fixed sessions ending on a bare exit code when your organization's settings couldn't be loaded or were refused at startup; the tab now says why and offers Retry or Sign in again
• [VSCode] Changed usage limit resets to show a clock time ("Resets at 3:10 PM") and to say "5-hour limit"
• [Cloud sessions] Added an effort level to the model picker when you create or edit a routine that runs in the cloud
• [Cloud sessions] Added a Bash editor with colors, line numbers and a Copy button to the setup script box in cloud environment settings
• [Cloud sessions] Improved the step shown when Claude adds a repository to a cloud session: opening it now shows a short table of what happened instead of raw JSON
• [Cloud sessions] Fixed resending an unchanged message after a failed send in a cloud session sometimes running it twice
• [Cloud sessions] Fixed a failed cloud environment creation showing its error only as a toast outside the open dialog; it now appears inside the dialog
• [Cloud sessions] Fixed Edit in a routine's menu on the Routines page going to the routine's page without opening its edit dialog
• [Remote Control] Fixed an unarchived Remote Control session showing as working until a computer reconnected; it now shows as idle
• [Claude Tag] Improved Claude Tag's retry notice in Slack to name the model in use, or say rate limits were hit, instead of a generic API error
• [Claude Tag] Fixed a Claude Tag channel's on/off switch and agent settings falling back to workspace defaults when an older private Slack channel goes public and gets a new ID
• [Claude Tag] Fixed Claude in Slack not replying in channels whose environment has network access set to None
• [Claude Tag] Fixed Claude in Slack sometimes posting a file in the wrong thread when it was answering in another thread of the same channel
• [Code Review] Fixed Code Review reviewing an outdated commit, or none at all, when GitHub delivered a push event late; it now reviews the pull request's current commit

v2.1.311

Compare Source

• Added --hold-idle-file and --max-hold-min to self-hosted-runner, to keep an idle session while your host reports processes it left running
• Added a tip for the Explanatory output style, shown when you ask Claude for explanations
• Fixed long freezes at startup and after reading or editing files when a CLAUDE.md file holds a very long list item
• Fixed interrupting Claude not taking effect until a timeout while an MCP server had not answered a resource read or a skill was still downloading
• Fixed standard-context sessions stopping with "Usage credits required for 1M context" when a request ran over 200K tokens; Claude Code now compacts the conversation and continues
• Fixed Write and Edit stalling for up to 5 seconds after they ran, and reporting 0 lines changed, when changing thousands of lines in a file
• Fixed subagents being unable to use MCP tools from servers that finish connecting after the subagent starts
• Fixed Claude seeing stale MEMORY.md and CLAUDE.md content right after automatic compaction when those files were edited earlier in the session
• Fixed claude -p and SDK sessions saving transcript messages out of order or keeping messages that were taken back
• Fixed SubagentStop hooks running about twice a minute for each running subagent instead of once when it finishes
• Fixed the @​ file picker ignoring .ignore/.rgignore negation rules that re-include git-ignored files
• Fixed a subagent's isolated worktree being removed while a background subagent it started was still working in it
• Fixed background agents in auto mode that wait on their own shells starting a new main conversation turn on every wake
• Fixed the Bash tool description claiming the working directory always persists between calls
• Fixed the environment block naming a shell commands don't run in, such as fish when the Bash tool uses zsh
• Fixed claude mcp add, claude mcp remove and /mcp naming the current folder instead of the project entry in ~/.claude.json that holds a local-scope server when run below a repository root
• Fixed claude mcp list and claude mcp get showing the error code twice on failed-connection lines (for example ENOENT: ENOENT: …)
• Fixed Remote Control sessions staying on "Connecting" for about two minutes when a network proxy blocks a startup request
• Fixed messages that Claude sends to a cloud or Remote Control session appearing as your own message in the Claude mobile apps
• Fixed Claude not being told the cause when a file attached to a message sent over Remote Control or to a cloud session could not be saved because the disk was full, or that a message's attachments past the first 20 were left out
• Fixed WebFetch and WebSearch hanging on a stalled response in Cowork cloud sessions; an unfinished request now fails after 300 seconds
• Fixed a background session that crashed between turns not being restarted while it was attached, pinned, or had a scheduled task or wake-up set
• Fixed the "background service did not respond" error suggesting the disabled claude daemon restart; it now suggests claude daemon stop --any and says it ends background sessions
• Fixed claude respawn <id> starting the background service before reporting that no background session matches the id
• Fixed /effort not warning about a prompt cache miss in plan mode when the plan model differs from the session model
• Fixed /ide saying the VS Code extension was installed before the install finished or when it failed
• Fixed the Write tool's file preview skipping rows and miscounting hidden lines when a line is wider than the terminal
• Fixed ↑ in an agent's chat tab recalling a message that was still waiting to be delivered, so resending it sent a second copy
• Fixed Cowork cloud sessions losing their connectors and most tools after a restart when a plugin or your settings named an agent; Cowork cloud sessions now ignore that setting
• Fixed agent teams sessions showing an empty task list when coming back with --resume, --continue, /resume or --session-id, including after /clear or a crash, and /branch writing to the original session's list
• Fixed pasting text that mentions an image file, such as ! open /tmp/shot.png or /review look at /tmp/shot.png, attaching the image and dropping its path from the prompt
• Fixed the feedback draft card showing its 1/2/0 and Esc shortcuts while the prompt has text, when those keys act on the prompt instead of the card
• Fixed a lone backslash in quotes or brackets, like "\" or (\), disappearing from Claude's responses
• Fixed agent teammates compacting their history when DISABLE_COMPACT is set
• Fixed the rewind menu offering "Summarize from here" and "Summarize up to here" when DISABLE_COMPACT is set
• Fixed a finished /code-review, or another skill that runs in a sub-agent, running a second time when a cloud or background session restarts
• Fixed long hidden thinking being cut off as idle on Google Vertex AI, Microsoft Foundry and Claude Platform on AWS, where the endpoint sends thinking progress updates
• Fixed /ide saying it had installed the JetBrains plugin when nothing was installed
• Fixed Claude Pro and Max subscribers being told to ask their admin when their subscription can't be used; the message now points to billing settings
• Fixed the diff pane opening by itself after an edit in wide fullscreen terminals when it had nothing to show
• Fixed /mcp showing a remote server as failed after "Clear authentication" when the server works without sign-in
• Fixed /mcp showing "authenticated" for a remote server that Claude Code sends no credentials to
• Fixed a --plugin-dir folder of plugins loading as one plugin when an empty .mcp.json was at its top
• Fixed /usage never showing large prompt-cache misses under "What's contributing to your limits usage?"
• Fixed status line links staying plain text in background sessions after you open them from a terminal that supports links
• Fixed the /rewind confirmation saying the conversation "will be forked" when the later messages are removed from the conversation
• Fixed the /rewind warning that wrongly said manual and Bash edits are never affected by a code restore
• Fixed plan approval in screen reader mode sending feedback you had dismissed with Escape
• Fixed Claude Code retrying requests the API marked not to retry, which could hold a turn for minutes or, in unattended retry mode (CLAUDE_CODE_RETRY_WATCHDOG), indefinitely
• Linux: Fixed sandboxed Bash commands failing with bwrap: Can't create file when a --plugin-dir folder was also an added directory and permissions.blockReadsOutsideWorkingDirectories was on
• Self-hosted runner: Fixed a session failing to start when a rate limit (HTTP 429, or a git wrapper that exits 75) blocks an added read-only repository; it now starts without that repository
• Improved startup time for Pro and Max accounts by skipping two network requests on launches within an hour of the last check
• Improved /teleport and claude --teleport to warn when a compacted cloud session loads from its last compaction, so the messages it summarized aren't in the local copy
• Improved the messages shown when a background session's process exits: they no longer promise a restart that isn't coming, and they say how to resume the session
• Improved artifacts with several views: Claude now routes each view on the link's #name and no longer says the address bar stays the same as you switch views
• Improved shell commands that reach their timeout: the result now shows the output so far and says the command is still running in the background
• Improved compaction: when the model's reply has no summary in it, Claude Code now usually asks for the summary once more before it replaces the conversation
• Improved the Artifact tool's choice between a page and a document: explainers and visual or interactive work become artifact pages; documents are for writing people keep editing or pass around
• Improved startup time for launches whose only arguments are options and their values, such as claude --model opus
• Improved the "Connection dropped" API error: it now says where to look first (the proxy or gateway in use, else VPN or firewall; Anthropic API only, Bedrock, Vertex and Foundry are unchanged)
• Improved screen reader mode: deleting a rule in /permissions says "Deleted allow rule …" right away
• Improved the message shown when a pasted sign-in code is refused: it now says the code may have expired or been used, and to sign in again
• Improved Slack connector sends: Claude now checks a channel's topic for posting rules before messaging a channel you didn't name
• Improved screen reader mode: Claude's questions are listed as "Questions: Color (answered), Pages", without arrows or symbols
• Changed ultrathink in the interactive terminal to run its turn at xhigh effort on Opus 5.5, Sonnet 5.5, Haiku 5.5 and Fable 5.1 through Anthropic's API; typed while Claude is working, it raises the rest of that turn
• Changed the ultrathink rainbow to appear only where the keyword can raise effort, and not when the word is quoted or part of a file path
• Changed Ctrl+D in agent view to match the prompt: on an empty input, pressing it twice exits
• Changed --output-format json and stream-json output to write DEL, C1 control and Unicode format characters inside strings as \uXXXX escapes; parsed values are unchanged
• Changed model names and IDs to drop the [1m] suffix and its label on models where the suffix has no effect; the suffix is still accepted
• Changed startup warnings about permission rules in settings files to show once per user until the rule changes
• Changed /code-review to tell Claude to put the effort level first and use max only when asked
• Changed DISABLE_COMPACT in settings files and in a mod's $.env.set so they can only turn compaction off, not back on
• Changed Claude Code on Bedrock, Mantle, Vertex, and Foundry to load model settings from a signed file on downloads.claude.ai; set CLAUDE_CODE_MODEL_CATALOG=off to turn this off
• Changed sessions that set CLAUDE_CODE_SYNC_SKILLS with feature-flag fetching off to reuse a claude.ai skills list up to 10 minutes old that another session on the machine fetched
• Changed clicks on scrollbar arrows and bars in fullscreen lists to act when the mouse button is released, so moving off the scrollbar before letting go cancels the click
• Changed claude purge to say it deletes data only on this computer, not anything stored by Anthropic
• [VSCode] Added syntax coloring to code blocks in Claude's replies, in light, dark and high contrast dark themes
• [VSCode] Added a "Running UserPromptSubmit hooks" spinner status and screen reader announcement for slow UserPromptSubmit hooks
• [VSCode] Fixed custom skills and custom slash commands sent from the VS Code or JetBrains panel leaving out the open file or selected lines that ordinary messages include (#​102799)
• [VSCode] Fixed the extension host freezing while the login shell ran its start-up files to read PATH on macOS and Linux
• [VSCode] Fixed clicking an image in a tool result, or closing its preview, also opening the result's text in an editor tab
• [VSCode] Fixed voice dictation continuing to record after a message was sent with the Send button; sending now stops dictation first, as pressing Enter already did
• [VSCode] Changed the extension to start Claude Code sessions with DISABLE_TELEMETRY set while VS Code's telemetry setting is off, so they send no usage metrics or error reports and fetch no feature flags
• [VSCode] Changed the session list side bar to load Web sessions when the Web tab is first opened, not at startup
• [Cloud sessions] Fixed routines in Anthropic-hosted environments staying locked after their owner left the organization and rejoined; the owner can now turn them back on
• [Cloud sessions] Fixed a failed routine API token delete or regenerate showing nothing if the edit dialog had already closed; it now shows an error toast
• [Cloud sessions] Fixed cloud environment dialogs, including the admin dialog, accepting duplicate names; they now refuse a name another listed environment already has
• [Claude Tag] Added a Skills view to Claude Tag analytics showing how often Claude runs each attached skill in Slack channels and which go unused, with Usage links in admin settings
• [Claude Tag] Improved Claude Tag routines that run in a new session: a run with nothing to report can now end without posting a throwaway message to the channel
• [Claude Tag] Changed Claude Tag admin settings to show a lock instead of # for private Slack channels that your own Slack account can see
• [Code Review] Improved Code Review's check run to say no further automatic review will start when the model still can't analyze a change on the automatic retry
• [Code Review] Improved Code Review reliability: a review whose session fails to start because of a transient server fault is now retried once automatically, and its check run says so

v2.1.310

Compare Source

• Added the Monitor tool and plugin monitors on Bedrock, Vertex, and Foundry, and when telemetry or nonessential traffic is disabled; long foreground sleeps are now blocked there too
• Fixed requests failing behind some gateways and compatible servers that reject the effort-2025-11-24 beta value or mid-conversation system messages; Claude Code now retries without them
• Fixed background cleanup deleting some recent files, such as pasted images, when cleanupPeriodDays is set to a very large value
• Fixed compaction after a "Prompt is too long" error keeping too much of a conversation with dense text, such as base64 or SVG, so the next request could fail again
• Fixed file read permission prompts not showing where a symbolic link leads
• Fixed a question's auto-continue timeout firing the moment the external editor closed after a long edit
• Windows: Fixed PreToolUse and PermissionRequest hooks letting a tool call through when Git Bash is missing and the hook's command is only quoted strings, such as a quoted path
• Improved auto mode's prompt before the first read outside the working directories: it now says when blocking those reads makes shell commands ask for permission
• Improved memory use of non-interactive sessions (-p, Agent SDK) during compaction when the transcript file is very large
• Improved a mod's Image to draw inside tmux with allow-passthrough and focus-events on, in kitty, Ghostty, and iTerm2 3.5+ with fullscreen rendering, where it showed only its alt text
• Linux: Improved /sandbox and the sandbox startup warning to name Ubuntu's AppArmor restriction on user namespaces, and how to lift it, when it keeps bubblewrap from starting the sandbox
• Changed the error for an MCP tool call that times out in a non-interactive session while the server's elicitation is unanswered: it now tells Claude that no answer came and not to repeat the call
• [VSCode] Fixed pressing Enter on the plan review card's "Send feedback and keep planning" button approving the plan instead of sending your comments back
• [VSCode] Fixed the panel showing "Something went wrong" after "Switch branch & continue" on a cloud session opened from Session history's Web tab
• [Cloud sessions] Added Claude Code cloud sessions and Remote Control permissions to Enterprise custom roles, so Owners can control access to each by role
• [Cloud sessions] Added a Choose file button to load a cloud environment's setup script from a file
• [Cloud sessions] Fixed failed saves and archives in the cloud environment edit dialog showing no error inside the dialog
• [Cloud sessions] Fixed failed routine API token actions showing only a toast; the error now appears in the routine edit dialog
• [Cloud sessions] Improved the session start checklist to show a cloud environment's setup script output in a scrolling box
• [Cloud sessions] Changed turning on Cloud sessions or Remote Control in admin settings to ask for confirmation and list the custom roles that have that permission
• [Cloud sessions] Changed the cloud environment dialog to open network access, setup script and environment variables from rows instead of listing every editor at once
• [Claude Tag] Fixed Claude Tag treating ! commands such as !restart and !help as ordinary messages when sent in bold, italic or strikethrough
• [Claude Tag] Fixed Claude Tag admin channel and workspace pages being replaced by a load error when a background refresh of the bundle list fails
• [Claude Tag] Fixed Claude Tag's spend limits page in admin settings reporting that no channels match a filter while channel names are still loading
• [Code Review] Fixed the Code Review admin section hiding its repositories and switches after a failed refresh of the repository list
• [Code Review] Improved the Code Review admin section to retry the first load and show one Try again banner when it still fails

v2.1.309

Compare Source

• Fixed sandboxed Bash commands on macOS and Linux running the shell's startup files outside the sandbox before each command
• Fixed macOS sandbox denyWrite glob patterns not applying at a path's real location when the pattern's folder is reached through a symlink
• Fixed sandboxed commands and auto-accepted edits being able to modify the MCP config file passed with --mcp-config
• Fixed a disabled MCP server being reconnected by a later permission prompt in print and SDK sessions
• Fixed the Bash permission check trusting a variable set by a command whose redirect can fail to open
• Fixed Bash permission checks not prompting for some compound commands that change directory before running git when the cd is wrapped or prefixed, as they do for a plain cd
• Fixed an Edit(path) deny rule not blocking a Bash redirect to that path in some commands that also held a subshell
• Fixed worktree-isolated sessions accepting some locale-prefixed commands the isolation guard should refuse
• Fixed worktree-isolated sessions on zsh accepting some arithmetic commands that the isolation guard should refuse
• Fixed worktrees and branch checkouts that Claude Code creates so they ignore git replace refs, as its other git operations already do
• Fixed profile store write protection not applying when the config directory is reached through a symlink
• Fixed sessions compacting repeatedly after reading files under a very large nested CLAUDE.md; a nested CLAUDE.md over the size limit now loads only its start
• Fixed ctrl+enter (send now) only queuing a message when pressed before the response had started, and restarting a prompt's hooks while leaving the message queued when pressed while those hooks were running
• Fixed key-bound slash commands running in the shell from ! mode
• Fixed ctrl+o not showing messages from other agents and sessions that are still waiting to be delivered; they now appear in full under the transcript, marked as waiting
• Fixed long tool output previews being cut through an emoji, leaving session transcripts that jq could not parse
• Fixed Read reporting "File does not exist" for PDF page ranges in Linux sandboxes that share the parent's /proc
• Fixed messages from a Claude Desktop-hosted session sometimes being lost when its connection refreshed
• Fixed features missing from Claude Code sessions in the Claude desktop app when the terminal on the same computer was signed in to a different account or organization
• Fixed the claude remote-control status line showing HEAD as the branch for a folder that is not in a git repository
• Fixed split-pane agent teammates not inheriting the tool deny and --tools rules given on the leader's command line
• Fixed sessions renamed with /rename appearing to other sessions under a generated name after a VS Code window reload or a non-interactive --resume
• Fixed the /rewind list showing "No code changes" for a turn that changed checkpointed files through /code-review --fix, a subagent or a shell command
• Fixed /privacy-settings showing an out-of-date "Help improve our AI models" value; it now also says when the setting can't be fetched
• Fixed feedback saying "try again later" when your organization does not accept feedback; it now shows the server's reason and where to report a bug
• Fixed oversized /feedback reports failing instead of being resent without the transcript
• Fixed a skill in an --add-dir folder being unreachable when another skill already held its name; it is now offered as <folder>:<name>
• Fixed /verify and /code-review not finding a nested package's own skill when its files were changed from the shell
• Fixed the /claude-api skill saying that ant beta:worker poll --on-work passes trace context to the command
• Fixed the /claude-api skill's C# tracing setup missing spans from the cloud platform clients
• Fixed the /claude-api skill saying that API spans for requests to Claude Platform on AWS can't join the caller's trace
• Fixed hooks that run in PowerShell not blocking when the hook's program exits with code 2, and on Windows PreToolUse and PermissionRequest hooks with "shell": "powershell" failing open when Git for Windows isn't installed
• Fixed a mod's turn.step hook that names a model by alias, such as haiku, failing every request with a model error: the alias now resolves to its model
• Fixed plugins and skills synced from claude.ai being removed, sometimes mid-session, after a disk read error
• Fixed artifact publishes and updates being refused for some ordinary pages, such as pages with certain minified scripts or artifacts Claude could not read first
• Fixed Claude asking for permission on each artifact update for the rest of a turn after the conversation was compacted in that turn
• Fixed fine-grained tool streaming

[!IMPORTANT]
✂ PR body was truncated to here.

[renovate]

⚠️ Artifact update problem

Renovate failed to update an artifact related to this branch. You probably do not want to merge this PR as-is.

♻ Renovate will retry this branch, including artifacts, only when one of the following happens:

• any of the package files in this branch needs updating, or
• the branch becomes conflicted, or
• you click the rebase/retry checkbox if found above, or
• you rename this PR's title to start with "rebase!" to trigger it manually

The artifact failure details are included below:

File name: council/ts/package-lock.json

npm error Cannot read properties of null (reading 'edgesOut')
npm error A complete log of this run can be found in: /runner/cache/others/npm/_logs/2026-11-05T23_52_25_759Z-debug-0.log

[renovate]

Edited/Blocked Notification

Renovate will not automatically rebase this PR, because it does not recognize the last commit author and assumes somebody else may have edited the PR.

You can manually request rebase by checking the rebase/retry box above.

⚠️ Warning: custom changes will be lost.