@anthropic-ai/claude-agent-sdk
0.3.330 · 20 Nov 2026SEE LICENSE IN README.md20.7M / weekRepositorynpmAtom feed
Upgrading @anthropic-ai/claude-agent-sdk From 0.3.327 to 0.3.328
1 release in betweenevery note read
Reading releases, release notes and advisories…
Release by release
- New
Added
onFailuretomcp_toolhooks in theSettingstype: with"block", a hook whose call fails blocks the action it guards - New
Added
CLAUDE_CODE_DISABLE_DEFERRED_TOOL_RESUME: set it in theenvoption to stopresumeandcontinuefrom running a tool call that a hook deferred; settings can't set it - New
Added support for the policy plugin's
allowManagedModsOnlyoption in host-suppliedmanagedSettings; an admin's managed settings still win - Fixed
Fixed the
agentoption: an inline definition inagentsnow wins over a user, project, plugin or built-in agent of the same name for model, prompt and hooks - Fixed
Fixed the
agentoption: an agent from an agents directory now keeps its system prompt whensystemPromptis not set - Fixed
Fixed the model saying background agents were still running after an SDK interrupt had stopped them
- New
4 other lines we could not sort, mostly version bumps
- 0.3.328
Changed subagents to wait for their own subagents by default when
CLAUDE_CODE_FORK_SUBAGENT=0is set - 0.3.328
Changed a shell command rewritten by a
PermissionRequesthook: the rewrite's own permission check now decides the sandbox, so a sandbox-excluded rewrite runs outside it;canUseToolis unchanged - 0.3.328
Changed
resolveSettings()on Windows to re-read registry policy every 6 hours while none is set (was 30 minutes) - 0.3.328
Updated to parity with Claude Code v2.1.328
A whole project to check? Paste its package.json in the dependency check: every deprecated, outdated or vulnerable dependency, with what to upgrade to. Free, no account.