build(deps-dev): bump @anthropic-ai/claude-code from 2.1.259 to 2.1.266

[dependabot]

Bumps @anthropic-ai/claude-code from 2.1.259 to 2.1.266.

Release notes

Sourced from @​anthropic-ai/claude-code's releases.

v2.1.266

What's changed

• Fixed a 2.1.265 regression affecting LLM-gateway and proxy setups: the undocumented CLAUDE_CODE_USE_GATEWAY environment variable, previously ignored unless ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN were both set, began forcing Cloud-gateway sign-in on its own in 2.1.265, so configurations that set it alongside an API key, apiKeyHelper, or custom auth headers failed every request with "Not signed in to the Cloud gateway". The variable on its own is ignored again; no configuration change is needed

v2.1.265

What's changed

• Added user.email and user.groups to the telemetry Claude Desktop and Cowork send through a Claude apps gateway, matching terminal sessions
• Added support for pointing --plugin-dir at a folder of plugins: each child folder with a manifest loads, and children added or removed while running are picked up
• Added a 1 GB cap on tool results saved to disk; the in-conversation preview says when a saved file was truncated
• Fixed resuming a foreground-spawned subagent changing its tool list and system prompt prefix, which broke prompt-cache reuse for that agent
• Fixed agent teammates and resumed subagents moving SubagentStart hook context and preloaded skills out of the prompt prefix on later turns, which broke prompt-cache reuse
• Fixed resume after the previous process died while a tool was running: the last prompt is no longer rewritten, and the interrupted tool call is kept and marked interrupted
• Fixed /model opusplan[1m] being rejected with "Model not found"
• Fixed syntax-highlighted code in permission prompts and messages sometimes omitting a character after a Ruby ?, Erlang $, or Perl $ sigil
• Fixed the fullscreen transcript jumping by one row whenever the slash-command or @-file suggestion list opened or closed
• Fixed a plugin path containing a backslash bypassing the symlink containment check on macOS and Linux
• Fixed plugin directories whose names begin with two dots being wrongly refused as outside the plugin root
• Fixed VS Code and SDK sessions occasionally requiring re-login when a session was closed while refreshing its token
• Fixed Remote Control sessions sending the end-of-turn signal before the reply's last message, which could show a reply as finished in the Claude app before its last part arrived
• Fixed background (--bg) sessions occasionally being retired mid-turn when a message arrived just before the idle timeout
• Fixed Claude Code's own git status and diff probes running clean filters configured by a nested repository inside the working tree
• Fixed the advisor tool and its instructions being re-decided per request from the request's model; the decision is now made once and announced in the conversation when it changes
• Fixed artifact publish accepting connector tool names the connector doesn't expose; the publish is now refused when none of the declared tools exist, and warned when only some don't
• Fixed /add-dir <subdirectory> refusing to load a subdirectory's agents when managed settings lock only skills to plugins, and promising agents when only agents are locked
• Fixed two-key keyboard shortcuts cancelling silently when the second key arrived more than a second later, as happens inside tmux; they now wait 3 seconds and show a notice when they time out
• Fixed forked skills (context: fork) not streaming their kickoff prompt and, with --forward-subagent-text, their text turns as progress events in stream-json
• Fixed a plugin's default component folder that the OS cannot check, such as a symlink loop, being silently skipped; it is now reported in /plugin with the error code
• Fixed the Claude apps gateway's OTLP telemetry relay pausing all forwarding to a collector for 30 seconds after it rejected a few payloads as malformed or too large
• Fixed /plugin Discover/Browse and claude plugin list --json --available showing no description or display name for marketplace plugins whose metadata lives only in their plugin.json
• Fixed /login showing "no gateway URL is configured" when re-run in a session that signed in to a Claude apps gateway set by managed settings
• Fixed /model claiming a model was "saved as your default" when the settings file couldn't be written; it now says the save failed and why
• Fixed /clear from Remote Control waiting on SessionStart hooks and on open terminal dialogs before completing
• Fixed the /config dialog changing height when switching between its tabs
• Fixed resuming a workflow run after its container restarted; a resume whose run journal is missing now fails with a clear error instead of rerunning every agent
• Fixed the claude-api skill's error-code reference: model access failures return 404 and unavailable beta headers return 400, not 403
• Fixed non-interactive sessions (-p with stream-json input, Agent SDK, cloud sessions) resetting the shell working directory at each new user message; a cd now persists across turns
• Fixed MCP servers configured as http that only speak the legacy HTTP+SSE transport never connecting; Claude Code now falls back to SSE as the MCP spec describes
• Fixed some claude.ai connectors in cloud sessions showing as needing authentication even though they are connected in claude.ai (servers that answer an unsupported request with HTTP 401)
• Fixed remote sessions keeping their sandbox container alive while a connector approval or sign-in link waits for you
• Fixed resumed sessions showing long model-facing recovery instructions in "background task didn't finish" notices instead of a short status line
• Windows: Fixed Read, Write and Edit refusing every file ("symlink resolution changed after permission was checked") when running inside an AppContainer or restricted-token sandbox
• Improved --worktree startup on large repositories: the new worktree is now checked out in parallel (git 2.32+)
• Improved /workflows agent detail: tool calls are marked running, failed or done, the subagent's task list is shown when it has one, and Enter unfolds the listed calls with their inputs and results
• Improved slash commands typed mid-prompt: matches now show in a list (Tab opens it outside fullscreen) instead of a single suggestion, and a plugin skill is now found by its bare name
• Improved remote MCP servers that need sign-in: Claude Code no longer registers an OAuth client with them until you actually authenticate
• Improved the time to resume long sessions that read many files
• Improved the error shown when an image over the size limits cannot be decoded: it now names the cause and how to fix it instead of only citing the limit
• Improved the Artifact tool's read of an artifact someone else wrote: the summary now treats the page as untrusted content and flags embedded instructions rather than relaying them

... (truncated)

Changelog

Sourced from @​anthropic-ai/claude-code's changelog.

2.1.266

• Fixed a 2.1.265 regression affecting LLM-gateway and proxy setups: the undocumented CLAUDE_CODE_USE_GATEWAY environment variable, previously ignored unless ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN were both set, began forcing Cloud-gateway sign-in on its own in 2.1.265, so configurations that set it alongside an API key, apiKeyHelper, or custom auth headers failed every request with "Not signed in to the Cloud gateway". The variable on its own is ignored again; no configuration change is needed

2.1.265

• Added user.email and user.groups to the telemetry Claude Desktop and Cowork send through a Claude apps gateway, matching terminal sessions
• Added support for pointing --plugin-dir at a folder of plugins: each child folder with a manifest loads, and children added or removed while running are picked up
• Added a 1 GB cap on tool results saved to disk; the in-conversation preview says when a saved file was truncated
• Fixed resuming a foreground-spawned subagent changing its tool list and system prompt prefix, which broke prompt-cache reuse for that agent
• Fixed agent teammates and resumed subagents moving SubagentStart hook context and preloaded skills out of the prompt prefix on later turns, which broke prompt-cache reuse
• Fixed resume after the previous process died while a tool was running: the last prompt is no longer rewritten, and the interrupted tool call is kept and marked interrupted
• Fixed /model opusplan[1m] being rejected with "Model not found"
• Fixed syntax-highlighted code in permission prompts and messages sometimes omitting a character after a Ruby ?, Erlang $, or Perl $ sigil
• Fixed the fullscreen transcript jumping by one row whenever the slash-command or @-file suggestion list opened or closed
• Fixed a plugin path containing a backslash bypassing the symlink containment check on macOS and Linux
• Fixed plugin directories whose names begin with two dots being wrongly refused as outside the plugin root
• Fixed VS Code and SDK sessions occasionally requiring re-login when a session was closed while refreshing its token
• Fixed Remote Control sessions sending the end-of-turn signal before the reply's last message, which could show a reply as finished in the Claude app before its last part arrived
• Fixed background (--bg) sessions occasionally being retired mid-turn when a message arrived just before the idle timeout
• Fixed Claude Code's own git status and diff probes running clean filters configured by a nested repository inside the working tree
• Fixed the advisor tool and its instructions being re-decided per request from the request's model; the decision is now made once and announced in the conversation when it changes
• Fixed artifact publish accepting connector tool names the connector doesn't expose; the publish is now refused when none of the declared tools exist, and warned when only some don't
• Fixed /add-dir <subdirectory> refusing to load a subdirectory's agents when managed settings lock only skills to plugins, and promising agents when only agents are locked
• Fixed two-key keyboard shortcuts cancelling silently when the second key arrived more than a second later, as happens inside tmux; they now wait 3 seconds and show a notice when they time out
• Fixed forked skills (context: fork) not streaming their kickoff prompt and, with --forward-subagent-text, their text turns as progress events in stream-json
• Fixed a plugin's default component folder that the OS cannot check, such as a symlink loop, being silently skipped; it is now reported in /plugin with the error code
• Fixed the Claude apps gateway's OTLP telemetry relay pausing all forwarding to a collector for 30 seconds after it rejected a few payloads as malformed or too large
• Fixed /plugin Discover/Browse and claude plugin list --json --available showing no description or display name for marketplace plugins whose metadata lives only in their plugin.json
• Fixed /login showing "no gateway URL is configured" when re-run in a session that signed in to a Claude apps gateway set by managed settings
• Fixed /model claiming a model was "saved as your default" when the settings file couldn't be written; it now says the save failed and why
• Fixed /clear from Remote Control waiting on SessionStart hooks and on open terminal dialogs before completing
• Fixed the /config dialog changing height when switching between its tabs
• Fixed resuming a workflow run after its container restarted; a resume whose run journal is missing now fails with a clear error instead of rerunning every agent
• Fixed the claude-api skill's error-code reference: model access failures return 404 and unavailable beta headers return 400, not 403
• Fixed non-interactive sessions (-p with stream-json input, Agent SDK, cloud sessions) resetting the shell working directory at each new user message; a cd now persists across turns
• Fixed MCP servers configured as http that only speak the legacy HTTP+SSE transport never connecting; Claude Code now falls back to SSE as the MCP spec describes
• Fixed some claude.ai connectors in cloud sessions showing as needing authentication even though they are connected in claude.ai (servers that answer an unsupported request with HTTP 401)
• Fixed remote sessions keeping their sandbox container alive while a connector approval or sign-in link waits for you
• Fixed resumed sessions showing long model-facing recovery instructions in "background task didn't finish" notices instead of a short status line
• Windows: Fixed Read, Write and Edit refusing every file ("symlink resolution changed after permission was checked") when running inside an AppContainer or restricted-token sandbox
• Improved --worktree startup on large repositories: the new worktree is now checked out in parallel (git 2.32+)
• Improved /workflows agent detail: tool calls are marked running, failed or done, the subagent's task list is shown when it has one, and Enter unfolds the listed calls with their inputs and results
• Improved slash commands typed mid-prompt: matches now show in a list (Tab opens it outside fullscreen) instead of a single suggestion, and a plugin skill is now found by its bare name
• Improved remote MCP servers that need sign-in: Claude Code no longer registers an OAuth client with them until you actually authenticate
• Improved the time to resume long sessions that read many files
• Improved the error shown when an image over the size limits cannot be decoded: it now names the cause and how to fix it instead of only citing the limit
• Improved the Artifact tool's read of an artifact someone else wrote: the summary now treats the page as untrusted content and flags embedded instructions rather than relaying them
• Updated the .claude folder permission option to say what it actually allows: editing files in the project's .claude folder (or ~/.claude) for the session
• Changed machines with forceLoginGatewayUrl in managed settings to be Claude apps gateway sessions from startup, like forceLoginMethod: "gateway"; a leftover claude.ai login or API key is not used

... (truncated)

Commits

• 347b38e chore: Update CHANGELOG.md and feed.xml
• 8e02f6d chore: Update CHANGELOG.md and feed.xml
• ab9b2cf chore: Update CHANGELOG.md and feed.xml
• d7dbd9a chore: Update CHANGELOG.md and feed.xml
• b3f0e50 chore: Update CHANGELOG.md and feed.xml
• ee2a058 Merge pull request #91894 from williamqian12/frontend-design-skill-update
• dbdd79c Update /frontend-design SKILL.md
• See full diff in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

[github-actions]

❌ Claude's run did not complete (outcome: failure). View job run

[github-actions]

🟠 Should fix [policy]

This bumps @anthropic-ai/claude-code to 2.1.266, but the version-pinned allowScripts entry below (line 43) still names the old version:

"allowScripts": {
  "@anthropic-ai/claude-code@2.1.259": true
}

npm 12's lifecycle-script gate keys allowScripts approvals by exact name@version. Since that key no longer matches the installed version, @anthropic-ai/claude-code@2.1.266's postinstall script will be silently blocked on the next npm ci/npm install — non-fatally (a log.warn, not a failed install), so CI stays green while the script quietly stops running.

This isn't a hypothetical stack default: the allowScripts entry was deliberately added in 2d35b3f specifically because .github/workflows/dependabot.yml's investigate job invokes this CLI directly via npx claude, so the postinstall script "genuinely needs to run." This PR reintroduces the exact gap that commit closed.

Suggested fix — update line 43 to:

Suggested change

	"@anthropic-ai/claude-code": "2.1.266",
	"@anthropic-ai/claude-code": "2.1.266",

(and separately bump "@anthropic-ai/claude-code@2.1.259": true → "@anthropic-ai/claude-code@2.1.266": true on line 43, outside this diff's hunk)

Since the automatic-fix pass is off for this run: @claude please update the allowScriptskey on line 43 of package.json from"@anthropic-ai/claude-code@2.1.259": trueto"@anthropic-ai/claude-code@2.1.266": true to match this bump.

Superseded by re-review on the latest commit.

[github-actions]

Verdict: requesting changes. This is a clean, routine Dependabot patch bump (@anthropic-ai/claude-code 2.1.259 → 2.1.266). Verified the diff line by line: package.json:20 and every one of the 8 platform-specific optional dependencies in package-lock.json (darwin-arm64, darwin-x64, linux-arm64, linux-arm64-musl, linux-x64, linux-x64-musl, win32-arm64, win32-x64) bump consistently to 2.1.266 with matching integrity hashes, and no line in the diff is unaccounted for. Title/description are accurate as-is — left untouched.

One finding carries over from my prior review on this exact commit. Restating it here rather than duplicating the still-open inline thread on package.json:20, which I'm leaving unresolved since it still applies:

🟠 Should fix [policy] — package.json:43: the allowScripts entry is still pinned to the old version:

"allowScripts": {
  "@anthropic-ai/claude-code@2.1.259": true
}

npm 12's lifecycle-script gate keys approval by exact name@version, so 2.1.266's postinstall script will now silently no-op (a warning, not a failed npm ci, so this won't be caught by CI). This gate was added deliberately in 2d35b3f, and its own commit message explains why: .github/workflows/dependabot.yml's investigate job invokes this CLI directly via npx claude, which depends on that postinstall step having run. Fix:

"allowScripts": {
  "@anthropic-ai/claude-code@2.1.266": true
}

Note the suggestion block on the existing open thread doesn't actually apply this fix — it shows line 20 unchanged rather than editing line 43 — so don't apply it as-is; the corrected key above is the actual fix needed.

No other issues found.

Housekeeping: cleared and dismissed my own prior review on this same commit (superseded by this one) before submitting.

[github-actions]

🗜️ Headroom context compression

Metric	Value
Requests proxied	79
Tokens saved	135015
Aggregate savings	1.5% of all tokens sent
Average per-request compression	3.9%

[dependabot]

Superseded by #74.