bb220

{
  "messages": [
    {
      "type": "human",
      "content": "Start my push workout"
    },
    {
      "type": "ai",
      "content": "Let's crush this Push Day workout! Here's what we'll be doing:\n\n1. **Bench Press:** 4 sets x 8-10 reps\n2. **Overhead Press:** 3 sets x 8-10 reps\n3. **Incline Dumbbell Press:** 3 sets x 10-12 reps\n4. **Lateral Raises:** 3 sets x 12-15 reps\n5. **Tricep Dips:** 3 sets x 10-12 reps\n\n💪 Start with the **Bench Press**! Aim for 4 sets of 8-10 reps. Let me know when you complete a set."
    }

bb220

def log_exercise_set_execution_evaluator(inputs: dict, outputs: dict, reference_outputs: dict) -> bool:
    """
    Evaluator for record_exercise_sets tool execution.
    Verifies that record_exercise_sets tool is called successfully.

    Args:
        inputs: Test input (user message)
        outputs: Agent output including tool_calls, tool_results, and final state
        reference_outputs: Expected behavior ("record_exercise_sets_called")

bb220

# LLM-as-judge instructions
grader_instructions = """You are a teacher grading a quiz.

You will be given the GROUND TRUTH (correct) RESPONSE and the STUDENT RESPONSE.

Here is the grade criteria to follow:
(1) Grade the student responses based ONLY on their factual accuracy relative to the ground truth response.
(2) Ensure that the student response does not contain any conflicting statements with the ground truth response.
(3) It is OK if the student response contains additional information or is more general than the ground truth response, as long as it does not conflict with the ground truth response.

bb220

import { useEffect, useMemo, useRef, useState } from "react";
import { AnimatePresence, motion } from "framer-motion";

const ROTATIONS = [
  {
    label: "Fashion",
    image:
      "https://cdn.prod.website-files.com/64d0cb3600efdc84fa51b372/6790236a8462d40a62534a48_Hero%201.webp",
    focal: "center",
  },