claude-agent-sdk

Package : @anthropic-ai/claude-agent-sdk@0.2.12 Breaking Changes : v0.1.45 - Structured outputs (Nov 2025), v0.1.0 - No default system prompt, settingSources required Major Features: Example: Zod Compatibility (v0.1.71+): SDK supports both Zod v3.24.1+ and Zod v4.0.0+ as peer dependencies. Import remains import { z } from "zod" for either version. All 12 Hook Events: Hook Configuration: 📚 Docs : Key signature: Critical Options: Enable 1 million token context window: Two forms of systemPrompt: Use preset form when you want Claude Code's default behaviors plus custom additions. Tool Control: Built-in Tools: Read, Write, Edit, Bash, Grep, Glob, WebSearch, WebFetch, Task, NotebookEdit, BashOutput, KillBash, ListMcpResources, ReadMcpResource, AskUserQuestion Enable user interaction during agent execution: Use cases: Three forms of tool configuration: Note: allowedTools and disallowedTools still work but tools provides more flexibility. Server Types: Tool Definition: Handler Return: Format : mcp__ __ CRITICAL: Examples: mcp__weather-service__get_weather , mcp__filesystem__read_file Field Details: Usage: Known Issue : Subagents don't stop when parent agent stops ( Issue #132 ) When a parent agent is stopped (via cancellation or error), spawned subagents continue running as orphaned processes. This can lead to: Workaround : Implement cleanup in Stop hooks: Enhancement Tracking :...