@intentqa/llm-anthropic

Anthropic planner adapter for intentqa.

pnpm add -D @intentqa/llm-anthropic
export ANTHROPIC_API_KEY=...            # or run `ant auth login`
npx intentqa generate --intent "a premium user can apply a coupon"

Bring your own key, always. This package never proxies through a key the project owns: a testing tool that quietly spends someone else's money is a tool nobody can adopt at work. Plans are cached on disk against the intent, the catalog hash and the prompt version, so unchanged intent against an unchanged vocabulary costs nothing to re-run.

Defaults to claude-opus-5 with adaptive thinking at high effort. Override per project:

import { anthropicPlanner } from "@intentqa/llm-anthropic";

export const planner = anthropicPlanner({ model: "claude-sonnet-5", effort: "medium" });

The prompt and the plan schema live in intentqa, not here, so swapping providers cannot silently change what the model is asked to do — and a cross-provider comparison stays meaningful.

The model gets a strict output schema, no tools, and no way to emit code. The worst it can do is pick the wrong step from the catalog, which the compiler catches and the reviewer sees. Its reply is re-validated against the schema rather than trusted: strict output modes are a strong constraint, not a guarantee.