Tag: anthropic-sdk

A step-by-step checklist for retiring a hand-rolled while-loop agent and running the same job on @cursor/sdk 1.0.26. The tool bodies survive, the loop does not, and three things you probably rely on have no equivalent: a system prompt string, a tool allowlist, and per-turn control.

A step-by-step checklist for lifting a hand-rolled Anthropic tool-calling loop onto a standalone MCP server. The tool bodies move almost verbatim; what changes is where the schema comes from, how results are wrapped, and how errors cross the process boundary.

Use CodeAct (the agent writes executable code as its action) when your tasks chain many tools, loop, or move large data, and you can afford a sandbox. Use the JSON tool-calling loop for a handful of discrete, high-stakes actions where a code interpreter is overkill or unsafe. CodeAct wins on token cost and multi-step success rate; tool calling wins on safety and simplicity.

Use stdio for a local server one client launches, use Streamable HTTP for anything remote or multi-client, and do not build new HTTP+SSE servers -- that transport was deprecated in the 2025-03-26 MCP spec. Here is the decision, the wire-level differences, and the code for each.

Rule-based checks are your floor and they are non-negotiable; LLM-as-judge is the ceiling you add when code quality, not just correctness, is what you ship. Here is the decision, with cost, latency, and the SWE-bench gap that proves why.

Claude subagents give you orchestration-level parallelism out of the box: one agent spawns isolated sub-contexts that run concurrently. OpenAI Assistants never had that, and it shuts down August 26, 2026, so new parallel work belongs on the Responses API plus your own fan-out. Here is how the two models actually differ and which to reach for.

The cache read and write multipliers are identical on both models, so the break-even point is the same. What differs is the minimum cacheable prefix (1,024 vs 4,096 tokens), the per-token dollar savings, and a new Opus 4.7 tokenizer that counts up to 35% more tokens. With claude-sonnet-4-6 and claude-opus-4-7 pricing math.

Two ways to call Claude from C#: the official Anthropic .NET SDK directly, or the provider-neutral Microsoft.Extensions.AI IChatClient that wraps it. When each wins, what you lose at the abstraction boundary, and why it is not actually either/or. With claude-opus-4-8 and claude-sonnet-4-6 examples.

Use custom tool calling for one app you own end to end, MCP for any integration you want reused across Claude Code, Cursor, and ChatGPT, and OpenAPI plugins only as a bridge when you already have a spec. MCP is the cross-client standard in 2026; plugins are legacy.

This banner is a pause, not a failure. It maps to the API's pause_turn stop reason (default 10 server-tool iterations). Click Continue, or in code re-send the assistant response. Full fix here.