diff --git a/tests/test_full_stack_contract.py b/tests/test_full_stack_contract.py
index 59cee34..3973991 100644
--- a/tests/test_full_stack_contract.py
+++ b/tests/test_full_stack_contract.py
@@ -1,10 +1,24 @@
-from pathlib import Path
+from __future__ import annotations
 
+import asyncio
+import os
+from pathlib import Path
+from unittest.mock import patch
+
+from a2a_pack import LocalRunContext, PlatformUserAuth
 from a2a_pack.cli.local import load_local_project
 
+from agent import QuoteInput, QuoteJudgeStudioV1, QuoteWeights, _build_comparison_result
+
 
 ROOT = Path(__file__).resolve().parents[1]
 
+SUCCESS_QUOTES = [
+    QuoteInput(vendor="Acme Bearings", unit_price=10.75, quantity=500, delivery_days=12, warranty_months=12),
+    QuoteInput(vendor="Beta Industrial", unit_price=9.1, quantity=500, delivery_days=8, warranty_months=18),
+]
+SUCCESS_WEIGHTS = QuoteWeights(price=50, delivery=30, warranty=20)
+
 
 def test_full_stack_product_contract():
     manifest = (ROOT / "a2a.yaml").read_text(encoding="utf-8")
@@ -12,17 +26,79 @@ def test_full_stack_product_contract():
     frontend = (ROOT / "frontend" / "src" / "App.jsx").read_text(encoding="utf-8")
 
     assert "frontend:" in manifest and "mount: /app" in manifest
+    assert "public: false" in manifest
     assert "resources:" in manifest and "databases:" in manifest
     assert "migrations:" in manifest and "db/migrations" in manifest
     assert "PlatformUserAuth" in source
     assert "AgentPlatformResources" in source and "AgentDatabase(" in source
+    assert "LLMProvisioning" not in source
+    assert "ctx.llm" not in source
     assert "Skill runner" not in frontend, "replace the generic scaffold with the product workflow"
+    forbidden = ["A2A_LITELLM_KEY", "OPENAI_API_KEY", "svc.cluster.local", "DATABASE_URL"]
+    assert not any(secret in frontend for secret in forbidden)
 
     migrations = list((ROOT / "db" / "migrations").glob("*.sql"))
     assert migrations and all(path.read_text(encoding="utf-8").strip() for path in migrations)
 
     card = load_local_project(ROOT).agent_cls().card()
+    skill_names = {skill.name for skill in card.skills}
+    assert {"compare_quotes", "get_comparison", "compare_quotes_from_browser_upload", "compare_quotes_from_upload"}.issubset(skill_names)
     databases = card.runtime.platform_resources.databases
     assert databases, "live Agent Card must declare its managed database"
+    assert databases[0].scope == "user"
     assert databases[0].migrations is not None
     assert databases[0].migrations.path == "db/migrations"
+    assert card.runtime.pricing.caller_pays_llm is False
+
+
+def test_scoring_success_fixture_is_deterministic():
+    result = _build_comparison_result("studio-quote-v1", SUCCESS_QUOTES, SUCCESS_WEIGHTS)
+    assert result["ok"] is True
+    assert result["comparison_id"] == "studio-quote-v1"
+    assert result["recommendation"]["vendor"] == "Beta Industrial"
+    beta = result["comparison_table"][0]
+    assert beta["vendor"] == "Beta Industrial"
+    assert beta["total_price"] == 4550.0
+    assert beta["scores"]["weighted_total"] == 100.0
+
+
+def test_failure_fixture_returns_actionable_validation():
+    result = _build_comparison_result(
+        "studio-quote-invalid",
+        [QuoteInput(vendor="Only Vendor", unit_price=10, quantity=1, delivery_days=5, warranty_months=6)],
+        SUCCESS_WEIGHTS,
+    )
+    assert result["ok"] is False
+    assert result["code"] == "at_least_two_quotes_required"
+    assert result["validation_errors"]
+
+
+def test_success_and_reload_persist_with_receipt():
+    saved: dict[tuple[str, str], dict] = {}
+    receipts: list[dict] = []
+
+    async def fake_save(tenant_key, comparison_id, result):
+        saved[(tenant_key, comparison_id)] = result
+
+    async def fake_load(tenant_key, comparison_id):
+        return saved.get((tenant_key, comparison_id))
+
+    async def fake_receipt(ctx, tenant_key, comparison_id, tool_name, status, inputs, result):
+        receipt = {"persisted": True, "receipt_id": f"receipt-{tool_name}-{comparison_id}", "input_hash": "abc"}
+        receipts.append({"tenant_key": tenant_key, "comparison_id": comparison_id, "tool_name": tool_name, "status": status})
+        return receipt
+
+    async def run():
+        agent = QuoteJudgeStudioV1()
+        ctx = LocalRunContext(auth=PlatformUserAuth(sub="user-1", user_id=1, email="u@example.com"))
+        with patch("agent._save_comparison", fake_save), patch("agent._load_comparison", fake_load), patch("agent._persist_receipt", fake_receipt):
+            success = await agent.invoke("compare_quotes", ctx, comparison_id="studio-quote-v1", quotes=SUCCESS_QUOTES, weights=SUCCESS_WEIGHTS)
+            reload = await agent.invoke("get_comparison", ctx, comparison_id="studio-quote-v1")
+        assert success["ok"] is True
+        assert success["recommendation"]["vendor"] == "Beta Industrial"
+        assert success["receipt"]["persisted"] is True
+        assert reload["ok"] is True
+        assert reload["recommendation"]["vendor"] == "Beta Industrial"
+        assert len(receipts) >= 2
+
+    asyncio.run(run())