Upstream: Claude Code v2.1.307 Assessment

Start by reading the /upstream skill and the release assessment workflow that generated this issue. The issue reports two upstream hook changes, but gives no specific change to make in sequant. Done means identifying whether either change affects the project and recording or filing any required follow-up.

Upstream: Claude Code v2.1.307 Assessment

Release: v2.1.307
Released: 2026-10-21
Assessed: 2026-10-26

Summary

Category	Count	Action Required
Breaking Changes	0	None
Name Collisions	0	None
Deprecations	0	None
New Tools	0	None
Hook Changes	2	Issue if it touches sequant
Opportunities	19	Noted for review
No Action	22	None

Actionable

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

1. Hook change: Self-hosted runner: Fixed archiving or requeueing a session, or stopping the run...

Self-hosted runner: Fixed archiving or requeueing a session, or stopping the runner, during its checkout hook leaving the hook's processes running and the runner's slot held

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

2. Hook change: Self-hosted runner: Changed checkout hooks to be stopped after 30 minutes by def...

Self-hosted runner: Changed checkout hooks to be stopped after 30 minutes by default, failing the session's setup; if yours needs longer, raise --checkout-hook-timeout-min or set it to 0

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

Informational

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

1. Fixed MCP servers showing "needs authentication" in claude -p on macOS while t...

Fixed MCP servers showing "needs authentication" in claude -p on macOS while the login keychain was locked; they now say why, and the next run after an unlock connects without a new sign-in

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

2. Fixed MCP servers being reported as timed out, and staying failed in headless ru...

Fixed MCP servers being reported as timed out, and staying failed in headless runs, when a macOS or Linux computer went to sleep while they were connecting

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

3. Fixed HTTP MCP tool calls being sent twice when the connection closed mid-call; ...

Fixed HTTP MCP tool calls being sent twice when the connection closed mid-call; only read-only or idempotent tools are now retried

• Matched keywords: Read, MCP, tool
• Matched patterns: mcp
• Impact: low

4. Fixed a turn sometimes starting without an SDK MCP server's latest tools when a ...

Fixed a turn sometimes starting without an SDK MCP server's latest tools when a background task was running

• Matched keywords: Task, MCP, background
• Matched patterns: mcp
• Impact: low

5. Fixed some "Autocompact is thrashing" errors in turns that read many PDF pages, ...

Fixed some "Autocompact is thrashing" errors in turns that read many PDF pages, images or other large tool results

• Matched keywords: Read, tool
• Impact: low

6. Fixed /permissions > Recently denied not showing the denied shell command, and...

Fixed /permissions > Recently denied not showing the denied shell command, and auto mode's local classifier ignoring an approval from there when it checks a retried command; approving a row now names the command, not its description

• Matched patterns: permission
• Impact: low

7. Fixed subagent transcripts recording placeholder token usage and an empty stop r...

Fixed subagent transcripts recording placeholder token usage and an empty stop reason for streamed responses

• Matched keywords: subagent
• Impact: low

8. Fixed model switches through the Agent SDK's setModel(), and apps built on it,...

Fixed model switches through the Agent SDK's setModel(), and apps built on it, being refused when the API took more than 5 seconds to confirm the model; Claude Code now waits up to 15 seconds

• Matched keywords: agent
• Impact: low

9. Fixed a background command stopped through a connected app (such as the desktop ...

Fixed a background command stopped through a connected app (such as the desktop app archiving an idle session) being reported to Claude as stopped by the user; the notice now names its output file

• Matched keywords: background
• Impact: low

10. Fixed WebFetch in Cowork cloud sessions reporting a tool error when a site answe...

Fixed WebFetch in Cowork cloud sessions reporting a tool error when a site answered with a 4xx status or a robots.txt refusal; it is now a normal result, as in local sessions

• Matched keywords: tool, WebFetch
• Impact: low

11. Fixed write tools on a directly configured GitHub MCP server showing a form that...

Fixed write tools on a directly configured GitHub MCP server showing a form that closed without creating anything in the desktop app's Code tab

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

12. Fixed Artifact tool reads failing with a connection reset when the server had cl...

Fixed Artifact tool reads failing with a connection reset when the server had closed a reused connection

• Matched keywords: tool
• Impact: low

13. Self-hosted runner: Fixed sessions with --use-anthropic-git-proxy committing a...

Self-hosted runner: Fixed sessions with --use-anthropic-git-proxy committing a .claude/settings.local.json left in the clone by an earlier session

• Matched keywords: settings
• Impact: low

14. Improved recovery from unparseable tool calls: Claude Code now retries the call ...

Improved recovery from unparseable tool calls: Claude Code now retries the call up to twice before ending the turn with an error

• Matched keywords: tool
• Impact: low

15. Improved the time to the first reply in cloud sessions when one of the desktop a...

Improved the time to the first reply in cloud sessions when one of the desktop app's MCP servers can't connect

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

16. Changed the notice Claude gets when the WebSearch budget is used up to also tell...

Changed the notice Claude gets when the WebSearch budget is used up to also tell it not to query search engines in a browser or through computer use

• Matched keywords: WebSearch
• Impact: low

17. Changed the axScreenReader setting and CLAUDE_AX_SCREEN_READER in a settings...

Changed the axScreenReader setting and CLAUDE_AX_SCREEN_READER in a settings env block to apply only from user, managed or --settings settings (since 2.1.305)

• Matched keywords: settings
• Impact: low

18. [VSCode] Fixed dictation failing behind a TLS-inspecting proxy when `NODE_EXTRA_...

[VSCode] Fixed dictation failing behind a TLS-inspecting proxy when NODE_EXTRA_CA_CERTS is set only in ~/.claude/settings.json; it now also follows CLAUDE_CODE_CERT_STORE

• Matched keywords: settings
• Impact: low

19. [VSCode] Changed the extension's own requests to filter their trusted certificat...

[VSCode] Changed the extension's own requests to filter their trusted certificates as the CLI does, and to trust the NODE_EXTRA_CA_CERTS file named in the environment or in user settings

• Matched keywords: settings
• Impact: low

No Action Required

22 changes did not require action:

• Added /claude-api api-version to move Claude API code to API version 2026-10-21
• Added the claude_code.safety_event OpenTelemetry event for each tool call a permission rule, auto mode, a safety check, a hook or the sandbox stopped, prompted or sent back
• Fixed requests failing with a model-not-found error when CLAUDE_CODE_DISABLE_1M_CONTEXT is set and the model is an alias with the [1m] suffix, such as opus[1m]
• Fixed the prompt-caching-scope beta header being sent behind custom ANTHROPIC_BASE_URL gateways and on Foundry, where it has no effect
• Fixed /autocompact in cloud sessions going back to the default window after the session restarted
• Fixed a conversation cleared with /clear sometimes coming back when a cloud or self-hosted runner session restarted
• Fixed CLAUDE_STREAM_FIRST_BYTE_TIMEOUT_MS being ignored in Claude apps gateway sessions
• Fixed telemetry from Claude Desktop sessions behind a Claude apps gateway being rejected when OTEL_EXPORTER_OTLP_HEADERS is set
• Fixed /help and the / command menu showing long model-facing descriptions for bundled skills such as /claude-api instead of their short descriptions
• Improved fork subagents launched together: each is now told which launch is its own, so forks are much less likely to try to start each other's work
• Improved browser sign-in: the success page now appears as soon as sign-in completes, without waiting for your account profile to load
• Improved web search errors in cloud and self-hosted runner sessions: a search refused with a 403 that gives a reason now shows that reason instead of a generic "Authentication error"
• Improved Remote Control connect time for sessions whose transcript contains large pasted images or PDF reads
• Self-hosted runner: Changed the certificate file built for Anthropic-managed git to filter its trusted certificates as the CLI does; a [runner:warn] line gives the number left out
• [VSCode] Added a notice on the microphone button when voice dictation stops by itself (15 seconds without recognized speech, or the 2-minute limit), saying why and that the text so far is kept
• [VSCode] Fixed a long prompt expanded with Show more covering the whole chat panel: a pinned prompt is now capped at 40% of the panel and scrolls
• [VSCode] Fixed part of a list item or table cell with LaTeX math pasting as a new list or table in rich text editors
• [VSCode] Changed the "still open somewhere else" notice to also cover a Claude process left over from an extension restart, which usually ends on its own within about 10 minutes
• [VSCode] Changed voice dictation to filter its trusted certificates as the CLI does
• [Cloud sessions] Fixed the repository picker saying "No repositories match" while a search was still running; it now shows "Searching…" until the results arrive
• [Cloud sessions] Fixed the "Waiting for a runner" status on self-hosted environments being cut off; with on-demand runners it now counts up from your last message and shows failed attempts
• [Code Review] Added @claude review stop (also off and pause) to Code Review, ending an @claude review always subscription on a pull request without starting a new review

---

Generated by /upstream skill