Host-supplied managedSettings previously dropped disableAllHooks and disableSkillShellExecution, so a host could believe hooks or shell execution were disabled when they were not. The update restores them and hardens CLI extraction.
Key takeaways · AI-distilled
Before this release, host-supplied managedSettings dropped disableAllHooks and disableSkillShellExecution, along with empty allowedHttpHookUrls and httpHookAllowedEnvVars lists, so those host restrictions were not carried through.
extractFromBunfs() now extracts the embedded CLI into its own per-user temp directory (claude-AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition →-sdk-<uid>, or claude-agent-sdk on Windows) instead of Claude Code's temp root.
An already-extracted CLI file is now reused only when its bytes match the embedded binary; otherwise it is replaced. The release also brings the SDK to parity with Claude Code v2.1.309.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
agent hook — A script the harness runs automatically at a fixed point in an agent's loop — before a tool call, after an edit, on session start.
agent skill — A reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.
