Upstream: Claude Code v2.1.309 Assessment

Start by reviewing the actionable Claude Code v2.1.309 changes and the listed affected files: templates/hooks/pre-tool.sh, plugin/hooks/hooks.json, and templates/settings.json. Check whether the PowerShell hook behavior or model alias change affects sequant, then record any concrete follow-up needed; the assessment already identifies the changes and their impact, but the payload does not name tests.

Upstream: Claude Code v2.1.309 Assessment

Release: v2.1.309
Released: 2026-10-22
Assessed: 2026-10-26

Summary

Category	Count	Action Required
Breaking Changes	0	None
Name Collisions	0	None
Deprecations	0	None
New Tools	1	Issue if it touches sequant
Hook Changes	2	Issue if it touches sequant
Opportunities	39	Noted for review
No Action	37	None

Actionable

Breaking changes, deprecations, and other items that affect sequant.

1. Hook change: Fixed hooks that run in PowerShell not blocking when the hook's program exits wi...

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

• Matched keywords: hook, PreToolUse
• Matched patterns: hook
• Affected files: templates/hooks/pre-tool.sh, plugin/hooks/hooks.json, templates/settings.json
• Impact: medium

2. Hook change: Fixed a mod's turn.step hook that names a model by alias, such as haiku, fai...

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

• Matched keywords: hook
• Matched patterns: hook
• Impact: medium

3. New tool: Self-hosted runner: Improved sessions that move to a new runner: Claude now sees...

Self-hosted runner: Improved sessions that move to a new runner: Claude now sees the tool call that was interrupted, marked as outcome unknown

• Matched keywords: tool
• Matched patterns: newTool
• Impact: low

Informational

Opportunities noted for human triage. No individual issues auto-created.

1. Fixed sandboxed Bash commands on macOS and Linux running the shell's startup fil...

Fixed sandboxed Bash commands on macOS and Linux running the shell's startup files outside the sandbox before each command

• Matched keywords: Bash
• Impact: low

2. Fixed macOS sandbox denyWrite glob patterns not applying at a path's real loca...

Fixed macOS sandbox denyWrite glob patterns not applying at a path's real location when the pattern's folder is reached through a symlink

• Matched keywords: Glob
• Impact: low

3. Fixed sandboxed commands and auto-accepted edits being able to modify the MCP co...

Fixed sandboxed commands and auto-accepted edits being able to modify the MCP config file passed with --mcp-config

• Matched keywords: MCP, config
• Matched patterns: mcp
• Impact: low

4. Fixed a disabled MCP server being reconnected by a later permission prompt in pr...

Fixed a disabled MCP server being reconnected by a later permission prompt in print and SDK sessions

• Matched keywords: MCP, permission
• Matched patterns: permission, mcp
• Impact: low

5. Fixed the Bash permission check trusting a variable set by a command whose redir...

Fixed the Bash permission check trusting a variable set by a command whose redirect can fail to open

• Matched keywords: Bash, permission
• Matched patterns: permission
• Impact: low

6. Fixed Bash permission checks not prompting for some compound commands that chang...

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

• Matched keywords: Bash, permission
• Matched patterns: permission
• Impact: low

7. Fixed an Edit(path) deny rule not blocking a Bash redirect to that path in som...

Fixed an Edit(path) deny rule not blocking a Bash redirect to that path in some commands that also held a subshell

• Matched keywords: Bash, Edit, deny
• Matched patterns: permission
• Impact: low

8. Fixed profile store write protection not applying when the config directory is r...

Fixed profile store write protection not applying when the config directory is reached through a symlink

• Matched keywords: Write, config
• Impact: low

9. Fixed long tool output previews being cut through an emoji, leaving session tran...

Fixed long tool output previews being cut through an emoji, leaving session transcripts that jq could not parse

• Matched keywords: tool
• Impact: low

10. Fixed Read reporting "File does not exist" for PDF page ranges in Linux sandboxe...

Fixed Read reporting "File does not exist" for PDF page ranges in Linux sandboxes that share the parent's /proc

• Matched keywords: Read
• Impact: low

11. Fixed split-pane agent teammates not inheriting the tool deny and --tools rule...

Fixed split-pane agent teammates not inheriting the tool deny and --tools rules given on the leader's command line

• Matched keywords: deny, tool, agent
• Matched patterns: permission
• Impact: low

12. Fixed the /rewind list showing "No code changes" for a turn that changed check...

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

• Matched keywords: subagent
• Impact: low

13. Fixed /privacy-settings showing an out-of-date "Help improve our AI models" va...

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

• Matched keywords: settings
• Impact: low

14. Fixed a skill in an --add-dir folder being unreachable when another skill alre...

Fixed a skill in an --add-dir folder being unreachable when another skill already held its name; it is now offered as <folder>:<name>

• Matched keywords: skill
• Impact: low

15. Fixed /verify and /code-review not finding a nested package's own skill when...

Fixed /verify and /code-review not finding a nested package's own skill when its files were changed from the shell

• Matched keywords: skill
• Impact: low

16. Fixed the /claude-api skill saying that ant beta:worker poll --on-work passes ...

Fixed the /claude-api skill saying that ant beta:worker poll --on-work passes trace context to the command

• Matched keywords: skill
• Impact: low

17. Fixed the /claude-api skill's C# tracing setup missing spans from the cloud plat...

Fixed the /claude-api skill's C# tracing setup missing spans from the cloud platform clients

• Matched keywords: skill
• Impact: low

18. Fixed the /claude-api skill saying that API spans for requests to Claude Platfor...

Fixed the /claude-api skill saying that API spans for requests to Claude Platform on AWS can't join the caller's trace

• Matched keywords: skill
• Impact: low

19. Fixed plugins and skills synced from claude.ai being removed, sometimes mid-sess...

Fixed plugins and skills synced from claude.ai being removed, sometimes mid-session, after a disk read error

• Matched keywords: Read
• Impact: low

20. Fixed artifact publishes and updates being refused for some ordinary pages, such...

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

• Matched keywords: Read
• Impact: low

21. Fixed Claude asking for permission on each artifact update for the rest of a tur...

Fixed Claude asking for permission on each artifact update for the rest of a turn after the conversation was compacted in that turn

• Matched keywords: permission
• Matched patterns: permission
• Impact: low

22. Fixed fine-grained tool streaming staying off on Amazon Bedrock when `ANTHROPIC_...

Fixed fine-grained tool streaming staying off on Amazon Bedrock when ANTHROPIC_BEDROCK_BASE_URL is set to the default bedrock-runtime.<region>.amazonaws.com endpoint

• Matched keywords: tool
• Impact: low

23. Linux: Fixed sandbox write denies lifting when a background command outlived the...

Linux: Fixed sandbox write denies lifting when a background command outlived the session

• Matched keywords: Write, background
• Impact: low

24. Windows: Fixed PowerShell permission checks auto-approving some Set-Location o...

Windows: Fixed PowerShell permission checks auto-approving some Set-Location or cd commands that target the current directory and carry extra arguments; these now prompt for approval

• Matched keywords: permission
• Matched patterns: permission
• Impact: low

25. Self-hosted runner: Fixed --startup-timeout-min stopping a session whose first...

Self-hosted runner: Fixed --startup-timeout-min stopping a session whose first prompt, such as /code-review, was still working in a subagent; a frozen process is still stopped

• Matched keywords: subagent
• Impact: low

26. Improved disk-full handling: a Bash command cut off by a full disk now says so a...

Improved disk-full handling: a Bash command cut off by a full disk now says so and names the folder to free up, and starting on a full temp volume prints a clear message, not a raw ENOSPC error

• Matched keywords: Bash
• Impact: low

27. Improved the /claude-api skill to check the live docs before saying a feature is...

Improved the /claude-api skill to check the live docs before saying a feature is unsupported

• Matched keywords: skill
• Impact: low

28. Updated the bundled dataviz skill to accept APCA as a text-contrast measure (kee...

Updated the bundled dataviz skill to accept APCA as a text-contrast measure (keeping WCAG 2 ratios where AA conformance is required), add an apca(text, background) function to its palette validator scripts, and say whether a label inside a colored chart fill should be white or near-black

• Matched keywords: background, skill
• Impact: low

29. Changed sed -i to get the standard Bash prompt and run as written, not a simul...

Changed sed -i to get the standard Bash prompt and run as written, not a simulated file-edit preview; like other Bash edits, it is no longer restored by /rewind

• Matched keywords: Bash, Edit
• Impact: low

30. Changed the dangerous rm and rmdir prompt in bypass permissions mode in the ...

Changed the dangerous rm and rmdir prompt in bypass permissions mode in the Desktop app and VS Code to deny the command at once with a rewrite hint, so unattended sessions keep going

• Matched keywords: deny
• Matched patterns: permission
• Impact: low

31. Changed commands the settings exclude from the sandbox to ask before writing to ...

Changed commands the settings exclude from the sandbox to ask before writing to its write-list paths while the sandbox is enabled but cannot run; the unsandboxed fallback is refused there

• Matched keywords: Write, ask, settings
• Matched patterns: permission
• Impact: low

32. Changed worktree creation and reuse so git no longer fetches objects on demand, ...

Changed worktree creation and reuse so git no longer fetches objects on demand, in ordinary clones and in partial clones with a Bash sandbox configured; such a partial clone fetches them first

• Matched keywords: Bash
• Impact: low

33. Changed the /claude-api skill to build Managed Agents subagent teams on `multi...

Changed the /claude-api skill to build Managed Agents subagent teams on multiagent_20261001 with dynamic workflows on by default, instead of coordinator

• Matched keywords: subagent, skill
• Impact: low

34. [VSCode] Fixed a mod's "From the … plugin" label above the prompt being drawn ov...

[VSCode] Fixed a mod's "From the … plugin" label above the prompt being drawn over the slash command and @-mention menus (anthropics/claude-code#102981)

• Matched keywords: plugin
• Impact: low

35. [VSCode] Improved Edit and Write speed in the chat panel: the wait for new probl...

[VSCode] Improved Edit and Write speed in the chat panel: the wait for new problems after each edit is now 0.75 seconds in most cases, down from 1 to 1.5 seconds

• Matched keywords: Write, Edit
• Impact: low

36. [Cloud sessions] Fixed the self-hosted environment details dialog in admin setti...

[Cloud sessions] Fixed the self-hosted environment details dialog in admin settings so its title, tabs and buttons stay in view while only the content scrolls

• Matched keywords: settings
• Impact: low

37. [Cloud sessions] Fixed the "read documentation" tool row in cloud sessions, whic...

[Cloud sessions] Fixed the "read documentation" tool row in cloud sessions, which showed escaped JSON instead of a readable page

• Matched keywords: Read, tool
• Impact: low

38. [Claude Tag] Fixed Allow and Deny on Claude's approval cards in Slack doing noth...

[Claude Tag] Fixed Allow and Deny on Claude's approval cards in Slack doing nothing when the session had stopped; your answer now restarts the session

• Matched keywords: allow, deny
• Matched patterns: permission
• Impact: low

39. [Claude Tag] Fixed the Slack page in Claude Tag admin settings saying no workspa...

[Claude Tag] Fixed the Slack page in Claude Tag admin settings saying no workspaces were connected when the list failed to load; it now shows an error with a Retry button

• Matched keywords: settings
• Impact: low

No Action Required

37 changes did not require action:

• 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 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 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 sessions renamed with /rename appearing to other sessions under a generated name after a VS Code window reload or a non-interactive --resume
• 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 the "Waiting for API response" hint flickering behind gateways that send only keepalive pings: routes off Anthropic's backend now wait 45 seconds
• Fixed Claude notifying unrelated GitHub users by writing role names and placeholders as mentions in PRs, issues and comments
• macOS: Fixed the "Install Command Line Developer Tools" dialog opening each time Claude Code starts on a Mac without Xcode or the Command Line Tools
• Improved the speed of many git commands Claude Code runs for itself on Windows; on every platform, errors from those commands now show in English even when git is set to another language
• Improved the error when a hooks module is nested too deep to load: it now names the file instead of showing a bare stack-overflow message
• Improved the /claude-api skill to offer API tracing alongside SDK tracing when asked to add OpenTelemetry
• Updated the /claude-api skill: service account keys and Workload Identity Federation tokens can now manage OpenTelemetry destinations
• Changed claude ultrareview to require workspace trust: it asks on a terminal, else refuses; scripts pass --trust-workspace, which takes no value (put a PR number or base branch before it), or set CLAUDE_CODE_DISABLE_ULTRAREVIEW_TRUST_CHECK=1
• [VSCode] Added a log warning that says what to do when dictation or the extension's own requests fail certificate verification, such as behind a TLS-inspecting proxy
• [VSCode] Fixed the Claude panel staying blank after the editor cached an incomplete copy of its files; it now recovers by itself, or says what went wrong and how to fix it
• [VSCode] Fixed Session history filling up with empty "Untitled" sessions each time you start a new session without sending a message
• [VSCode] Fixed long slash-command messages such as /goal filling the chat panel; they now fold behind Show more like other prompts (anthropics/claude-code#97469)
• [VSCode] Fixed long messages not folding behind Show more after the chat panel is made narrower
• [VSCode] Fixed Ctrl+J in the chat input always inserting a newline: it is now left to VS Code and the OS when "ctrl+j" is set to null in the Chat context of ~/.claude/keybindings.json
• [VSCode] Fixed an empty list item, paragraph or code block, and list items renumbered from 1, when pasting copied LaTeX math
• [VSCode] Fixed the feedback error showing only an HTTP status when your organization does not accept feedback
• [Cloud sessions] Fixed the Add connector list in routine forms saying no connectors were available while they were still loading
• [Cloud sessions] Fixed the cloud environment editor shuffling environment variables and adding backslashes to values that contain both kinds of quote
• [Cloud sessions] Improved a cloud session's Changes pane, which now says when it lists only pushed commits or only Claude's edits
• [Claude Tag] Fixed Claude in Slack posting a draft you approved for a channel into your DM by mistake; a post with no channel is now refused so it can go to the approved channel
• [Claude Tag] Fixed Claude ignoring untagged messages in a Slack channel after its workspace moved to a different Claude organization, including unshared channels on Enterprise Grid
• [Claude Tag] Fixed Claude in a Slack channel posting a threaded reply before reading a newer message someone had just added to that thread
• [Code Review] Fixed a finished review showing no check on the pull request when earlier tries to create it failed; a final try now adds a completed check
• [Code Review] Fixed a push queued behind a running review still starting a review after @claude review stop; its check now closes and says why

---

Generated by /upstream skill