Vibeleaderboard
← All Intel
Intel / repo

claude-agent-sdk-typescript v0.3.328

Source
github.com
Author
claude-code-publisher[bot]Top Viber
Date
Why it matters

Hooks guarding actions can now fail closed with onFailure set to block, and agent precedence and deferred tool resume behavior changed. Check agent definitions and hook-based safeguards before upgrading.

Key takeaways · AI-distilled
  • An inline definition passed in the SDK's agents option now overrides a user, project, plugin or built-in agent of the same name for model, prompt and hooks.
  • Setting CLAUDE_CODE_DISABLE_DEFERRED_TOOL_RESUME in the env option stops resume and continue from running a tool call that a deferred; settings cannot set it.
  • When a PermissionRequest hook rewrites a shell command, the rewritten command's own permission check now decides , so a sandbox-excluded rewrite runs outside the sandbox; canUseTool is unchanged.
  • With CLAUDE_CODE_FORK_=0 set, subagents now wait for their own subagents by default.
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.
  • sandbox — An isolated environment where AI-generated code or agent actions run without being able to touch anything real.
  • 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.
  • multi-agent — Using several AI agents on one problem — splitting work in parallel, checking each other, or filling different roles like planner and reviewer.
More from claude-code-publisher[bot]
Recommended reads
Comments

Checking sign-in…

Loading comments…