# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
description: |
  Run evals against Claude via a local Claude Code session (no Anthropic
  Console API key needed). Requires `claude /login` to have been run on the
  same machine.

prompts:
  - |
    You are a careful technical writer. Rewrite the following sentence for
    clarity without changing its meaning:

    "{{sentence}}"

providers:
  - id: anthropic:messages:claude-sonnet-4-6
    config:
      # Skip the API key preflight and authenticate via the local Claude Code
      # OAuth credential (macOS keychain or ~/.claude/.credentials.json).
      apiKeyRequired: false
      max_tokens: 512

# Use the same Claude Code session to run the llm-rubric grader. This lets
# Claude Pro / Max subscribers use semantic model-graded evals without a
# separate Anthropic Console API key.
defaultTest:
  options:
    provider:
      id: anthropic:messages:claude-sonnet-4-6
      config:
        apiKeyRequired: false

tests:
  - vars:
      sentence: 'Utilizing these tools, we can facilitate the optimization of the process.'
    assert:
      - type: llm-rubric
        value: |
          The rewrite is concise, uses plain English, and preserves the
          original meaning (improving a process using the tools). It should
          not invent new details.
  - vars:
      sentence: 'The aforementioned refactor exhibits suboptimal efficiency characteristics.'
    assert:
      - type: llm-rubric
        value: |
          The rewrite is clearer and less jargon-heavy while still saying the
          refactor is inefficient or slow. It must not add unrelated claims.