Claude Opus 5.5 tool_choice 400: 3 SDKs Tested (2026)
September 25, 2026
Claude Opus 5.5 rejects forced tool_choice with a 400. I captured what the AI SDK, LangChain and the raw SDK actually send, and built a preflight check.
#tool-use
Give an AI Agent Long-Term Memory with pgvector (2026)
July 17, 2026
Build a Claude agent with long-term memory: Postgres + pgvector store facts, cosine-similarity recall injects them back — verified across a process restart.
Trace Claude Agent Tool Calls with OpenTelemetry (2026)
July 15, 2026
Instrument a Claude tool-calling agent with OpenTelemetry GenAI semantic conventions in TypeScript: real spans, nested tool calls, cost tracking. 2026.
Add Human-in-the-Loop Approval to Claude Agent SDK (2026)
July 13, 2026
Build a human-in-the-loop approval gate for the Claude Agent SDK in TypeScript: canUseTool prompts, PreToolUse hooks, and a full audit log for every tool call.
Build an MCP Client in TypeScript: A 2026 Tutorial
June 3, 2026
Build a Model Context Protocol (MCP) client in TypeScript with @modelcontextprotocol/sdk: connect over stdio, list and call tools, and handle errors correctly.
Claude Tool Use in TypeScript: Agentic Loop Tutorial (2026)
May 29, 2026
Hands-on Claude Sonnet 4.6 tool use tutorial: build a typed agentic loop in TypeScript with the Anthropic SDK 0.98, parallel tool calls, and JSON Schema.