# Ponytail behavior gates: does the ruleset actually produce its refined
# behaviors (not just carry the text)? Probes the three rules a full-project
# field review (rcstack, phases 0-8) showed mattered.
#
#   Run:    npx promptfoo@latest eval -c benchmarks/behavior.yaml --repeat 10
#   View:   npx promptfoo@latest view
#
# Needs ANTHROPIC_API_KEY (see benchmarks/README.md). The grader (behavior.js)
# is proven separately by tests/behavior.test.js, which needs no API key.
#
# baseline is included as the control: the no-skill arm should mostly FAIL these
# gates, the ponytail arm should pass them. That delta is the point.
description: "Ponytail behavior gates: hardware calibration, requested explanation, one runnable check."

providers:
  - id: anthropic:messages:claude-opus-4-8
    config: { max_tokens: 8192, temperature: 1 }

prompts:
  - id: file://arms/baseline.js
    label: baseline (no skill)
  - id: file://arms/ponytail.js
    label: ponytail

defaultTest:
  assert:
    - type: javascript
      value: file://behavior.js
      metric: behavior

tests:
  - vars:
      probe: hardware
      task: "Write a Python function that reads the temperature in Celsius from a thermistor wired to a Raspberry Pi ADC (MCP3008, channel 0)."
  - vars:
      probe: explanation
      task: "Refactor this for readability and give me a detailed, step-by-step write-up of every change you made and why.\n\ndef p(d):\n    r = []\n    for x in d:\n        if x.get('a') and x['a'] > 0:\n            r.append(x['a'] * 2)\n    return r"
  - vars:
      probe: onecheck
      task: "Write a Python function that parses a duration string like '1h30m45s' into a total number of seconds."