"""
Streamlit UI for ShopManagerEng — Interactive Jewelry Shop Demo.
An AI heuristic agent automatically plays through each episode.
Users press "New Episode" and watch the agent navigate all 3 phases.
"""
import os
import sys
import random
import time
from pathlib import Path
import streamlit as st
# ── Ensure imports resolve ──────────────────────────────────────────────────
ROOT = Path(__file__).resolve().parent
if str(ROOT) not in sys.path:
sys.path.insert(0, str(ROOT))
os.environ.setdefault("SHOPMANAGER_MARKET_MODE", "synthetic")
from server.ShopManagerEng_environment import JewelryShopEnvironment
from models import JewelryAction, PRODUCT_CATALOG
# ── Page config ─────────────────────────────────────────────────────────────
st.set_page_config(
page_title="ShopManagerEng — Jewelry Shop RL",
page_icon="💎",
layout="wide",
initial_sidebar_state="expanded",
)
# ── CSS: clean light-theme styling ──────────────────────────────────────────
st.markdown("""
""", unsafe_allow_html=True)
# ── Heuristic Agent ─────────────────────────────────────────────────────────
def heuristic_action(obs):
"""Simple rule-based agent that plays through all 3 phases."""
if obs.phase == "market":
price = float(obs.gold_price or 300)
# Buy if we have enough cash for at least 1 oz
if obs.cash >= price + 10:
return JewelryAction(
market_action="buy",
gold_qty=1.0,
target_price_usd=obs.gold_price,
)
return JewelryAction(market_action="wait")
if obs.phase == "warehouse":
# Pick the highest-demand product we can afford
demand = obs.demand or {"ring": 0.5, "necklace": 0.3, "bracelet": 0.2}
for name in sorted(demand, key=lambda k: demand.get(k, 0), reverse=True):
spec = PRODUCT_CATALOG[name]
if obs.gold_oz + 1e-8 >= spec["gold_oz"] and obs.cash >= spec["labor"]:
return JewelryAction(product_choice=name)
return JewelryAction(product_choice="ring")
if obs.phase == "showroom":
# Accept if margin > 15% or after round 3
if (
obs.current_offer
and obs.cost_basis > 0
and float(obs.current_offer) / float(obs.cost_basis) >= 1.15
) or (obs.negotiation_round and int(obs.negotiation_round) >= 3):
return JewelryAction(message="I accept")
offer = float(obs.current_offer or 0)
if offer:
return JewelryAction(message=f"How about ${offer * 1.08:.2f}?")
return JewelryAction(message="I need a better offer")
return JewelryAction()
# ── Session state ───────────────────────────────────────────────────────────
if "episode_steps" not in st.session_state:
st.session_state.episode_steps = None
st.session_state.final_reward = None
st.session_state.episode_count = 0
def run_episode(task_id):
"""Run a full episode with the heuristic agent and return step logs."""
env = JewelryShopEnvironment()
seed = random.randint(0, 99999)
obs = env.reset(seed=seed, market_mode="synthetic", task_id=task_id)
steps = [{
"step": 0, "phase": obs.phase, "action": "reset",
"msg": obs.message, "reward": 0.0,
"cash": obs.cash, "gold_oz": obs.gold_oz,
"gold_price": obs.gold_price,
"cumulative": float(obs.cumulative_reward),
}]
for i in range(1, 20):
if obs.done:
break
action = heuristic_action(obs)
# Describe the action in human terms
if obs.phase == "market":
act_str = f"BUY {action.gold_qty} oz" if action.market_action == "buy" else "WAIT"
elif obs.phase == "warehouse":
act_str = f"CRAFT {action.product_choice}"
else:
act_str = action.message or "..."
obs = env.step(action)
steps.append({
"step": i, "phase": obs.phase, "action": act_str,
"msg": obs.message, "reward": float(obs.reward),
"cash": obs.cash, "gold_oz": obs.gold_oz,
"gold_price": getattr(obs, "gold_price", 0),
"product": getattr(obs, "product_for_sale", None),
"offer": float(obs.current_offer) if obs.current_offer else None,
"cost_basis": float(obs.cost_basis) if obs.cost_basis else None,
"cumulative": float(obs.cumulative_reward),
})
return steps, float(obs.cumulative_reward)
# ── Sidebar ─────────────────────────────────────────────────────────────────
with st.sidebar:
st.markdown("### 💎 ShopManagerEng")
st.markdown("---")
task = st.selectbox(
"🎯 Task Profile",
["profit_negotiator", "market_timing", "demand_crafter"],
index=0,
)
weights = {
"profit_negotiator": "Showroom 60% · Market 20% · Warehouse 20%",
"market_timing": "Market 60% · Warehouse 20% · Showroom 20%",
"demand_crafter": "Warehouse 60% · Market 20% · Showroom 20%",
}
st.caption(f"**Weights:** {weights[task]}")
st.markdown("---")
if st.button("🚀 New Episode", use_container_width=True, type="primary"):
steps, reward = run_episode(task)
st.session_state.episode_steps = steps
st.session_state.final_reward = reward
st.session_state.episode_count += 1
st.rerun()
st.markdown("---")
st.markdown("#### How It Works")
st.markdown("""
An AI **heuristic agent** automatically plays
through all 3 phases of the jewelry shop:
1. 📈 **Market** — Buy gold at the right price
2. 🏭 **Warehouse** — Craft the most demanded product
3. 🤝 **Showroom** — Negotiate the best sale price
Press **🚀 New Episode** to watch the agent play!
""")
if st.session_state.final_reward is not None:
st.markdown("---")
reward = st.session_state.final_reward
color = "#10b981" if reward >= 0.6 else "#f59e0b" if reward >= 0.4 else "#ef4444"
st.markdown(f"**Final Score:** :{'green' if reward >= 0.6 else 'orange' if reward >= 0.4 else 'red'}[{reward:.4f}]")
st.metric("Episodes Played", st.session_state.episode_count)
# ── Main area ───────────────────────────────────────────────────────────────
st.markdown('💎 Jewelry Shop Manager
', unsafe_allow_html=True)
st.markdown('An RL environment for training LLMs on multi-step business decisions
', unsafe_allow_html=True)
# ── No episode yet — show welcome ──────────────────────────────────────────
if st.session_state.episode_steps is None:
st.info("👋 **Welcome!** Press **🚀 New Episode** in the sidebar to watch the AI agent play through the jewelry shop simulation.")
st.markdown("### 📦 Product Catalog")
cols = st.columns(3)
items = [("💍 Ring", "ring"), ("📿 Necklace", "necklace"), ("⌚ Bracelet", "bracelet")]
for i, (icon_name, key) in enumerate(items):
spec = PRODUCT_CATALOG[key]
with cols[i]:
st.markdown(f"""
{icon_name}
🪙 Gold: {spec['gold_oz']} oz
🔧 Labor: ${spec['labor']:.0f}
📊 Base demand: {spec['base_demand']:.0%}
""", unsafe_allow_html=True)
st.markdown("### 🧠 Three Business Phases")
c1, c2, c3 = st.columns(3)
with c1:
st.markdown("""
📈 Phase 1: Market
Buy raw gold at the best price. Prices fluctuate — time your purchase wisely!
""", unsafe_allow_html=True)
with c2:
st.markdown("""
🏭 Phase 2: Warehouse
Craft a product (ring, necklace, bracelet) that matches market demand.
""", unsafe_allow_html=True)
with c3:
st.markdown("""
🤝 Phase 3: Showroom
Negotiate with a customer over 5 rounds to maximize your selling price.
""", unsafe_allow_html=True)
# ── Episode results ─────────────────────────────────────────────────────────
else:
steps = st.session_state.episode_steps
reward = st.session_state.final_reward
# ── Score banner ────────────────────────────────────────────────────────
if reward >= 0.8:
grade, grade_emoji = "Excellent", "🏆"
elif reward >= 0.6:
grade, grade_emoji = "Good", "👍"
elif reward >= 0.4:
grade, grade_emoji = "Fair", "😐"
else:
grade, grade_emoji = "Poor", "😬"
st.markdown(f"""
{grade_emoji} Episode #{st.session_state.episode_count} — {grade}
{reward:.4f}
cumulative reward (out of 1.0)
""", unsafe_allow_html=True)
st.markdown("")
# ── Summary metrics ─────────────────────────────────────────────────────
last = steps[-1]
m1, m2, m3, m4 = st.columns(4)
with m1:
st.markdown(f"""""", unsafe_allow_html=True)
with m2:
st.markdown(f"""Final Cash
${last['cash']:,.0f}
Gold Price
${gold_price:,.0f}/oz
Product
{(product or 'N/A').title()}