pip install evalgate-sdk
pip install -e .                                  # so evals can import your app
evalgate init --local --format json               # preview; writes nothing
evalgate init --local --apply --format json       # write the scaffold

# refund_agent/__init__.py
def decide_refund(days_since_purchase, amount, reason, prior_refunds=0):
    if prior_refunds >= 2 or reason == "fraud_suspected":
        return {"action": "escalate", "refund": 0}
    if days_since_purchase > 30:
        return {"action": "deny", "refund": 0}
    if reason == "defective":
        return {"action": "approve", "refund": amount}
    return {"action": "approve", "refund": round(amount * 0.9, 2)}

# evals/refund_policy_eval.py
import json

from evalgate_sdk import create_result, define_eval
from refund_agent import decide_refund


@define_eval("day 30 is still inside the window")
def day_thirty(ctx):
    decision = decide_refund(days_since_purchase=30, amount=20, reason="changed_mind")
    failures = []
    if decision["action"] != "approve":
        failures.append("expected action approve")
    if decision["refund"] != 18:
        failures.append("expected refund 18")
    return create_result(
        passed=not failures,
        score=0 if failures else 100,  # 0–100
        output=json.dumps(decision),
        metadata={"failures": failures},  # shown on a blocked gate
    )

git add -A && git commit -m "add evals"
evalgate baseline update     # needs a clean worktree
git add evals/baseline.json && git commit -m "accept reviewed baseline"

evalgate gate --format json