diff --git a/tests/test_full_stack_contract.py b/tests/test_full_stack_contract.py
index 59cee34..5517b21 100644
--- a/tests/test_full_stack_contract.py
+++ b/tests/test_full_stack_contract.py
@@ -1,28 +1,113 @@
+import asyncio
+import base64
 from pathlib import Path
 
+from a2a_pack import LocalRunContext, PlatformUserAuth
 from a2a_pack.cli.local import load_local_project
 
+from agent import QuoteJudgeStudioV1, _MEMORY_COMPARISONS, _MEMORY_RECEIPTS
+
 
 ROOT = Path(__file__).resolve().parents[1]
+SUCCESS_QUOTES = [
+    {"delivery_days": 12, "quantity": 500, "unit_price": 10.75, "vendor": "Acme Bearings", "warranty_months": 12},
+    {"delivery_days": 8, "quantity": 500, "unit_price": 9.1, "vendor": "Beta Industrial", "warranty_months": 18},
+]
+WEIGHTS = {"delivery": 30, "price": 50, "warranty": 20}
+
+
+def _ctx():
+    return LocalRunContext(auth=PlatformUserAuth(sub="user-123", user_id=123, email="buyer@example.test"))
+
+
+def _run(coro):
+    return asyncio.run(coro)
 
 
 def test_full_stack_product_contract():
     manifest = (ROOT / "a2a.yaml").read_text(encoding="utf-8")
     source = (ROOT / "agent.py").read_text(encoding="utf-8")
     frontend = (ROOT / "frontend" / "src" / "App.jsx").read_text(encoding="utf-8")
+    browser_client = (ROOT / "frontend" / "src" / "a2a.js").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 "runtime:" in manifest and "max_runtime_seconds: 120" in manifest
     assert "PlatformUserAuth" in source
     assert "AgentPlatformResources" in source and "AgentDatabase(" in source
-    assert "Skill runner" not in frontend, "replace the generic scaffold with the product workflow"
+    assert "LLMProvisioning" not in source
+    assert "ctx.llm" not in source
+    assert "A2A_LITELLM_KEY" not in source and "OPENAI_API_KEY" not in source
+    assert "Skill runner" not in frontend
+    assert "QuoteJudge Studio" in frontend
+    assert "compare_uploaded_quotes_browser" in frontend
+    assert "compare_uploaded_quote_file" in source
+    assert "config.json" in browser_client
+    assert "DATABASE_URL" not in frontend
 
     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()
+    skills = {skill.name: skill for skill in card.skills}
+    for name in ["compare_quotes", "get_comparison", "compare_uploaded_quotes_browser", "compare_uploaded_quote_file"]:
+        assert name in skills
+    compare_schema = skills["compare_quotes"].input_schema
+    assert set(compare_schema["required"]) == {"comparison_id", "quotes", "weights"}
+    assert "quotes" in compare_schema["properties"]
+    upload_schema = skills["compare_uploaded_quote_file"].input_schema
+    assert upload_schema["properties"]["quote_file"]["x-a2a-file-upload"]["required_upload"] is True
     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_success_failure_reload_and_receipt_memory_path(monkeypatch):
+    monkeypatch.delenv("DATABASE_URL", raising=False)
+    _MEMORY_COMPARISONS.clear()
+    _MEMORY_RECEIPTS.clear()
+    agent = QuoteJudgeStudioV1()
+    ctx = _ctx()
+
+    success = _run(agent.invoke("compare_quotes", ctx, comparison_id="studio-quote-v1", quotes=SUCCESS_QUOTES, weights=WEIGHTS))
+    assert success["ok"] is True
+    assert success["comparison_id"] == "studio-quote-v1"
+    assert success["recommendation"]["vendor"] == "Beta Industrial"
+    assert success["receipt"]["production"] is True
+    assert success["receipt"]["tool_name"] == "compare_quotes"
+    assert "api_key" not in str(success).lower()
+
+    reload = _run(agent.invoke("get_comparison", _ctx(), comparison_id="studio-quote-v1"))
+    assert reload["ok"] is True
+    assert reload["recommendation"]["vendor"] == "Beta Industrial"
+    assert reload["receipt"]["tool_name"] == "get_comparison"
+
+    failure = _run(agent.invoke("compare_quotes", _ctx(), comparison_id="studio-quote-invalid", quotes=[{"delivery_days": 5, "quantity": 1, "unit_price": 10, "vendor": "Only Vendor", "warranty_months": 6}], weights=WEIGHTS))
+    assert failure["ok"] is False
+    assert failure["code"] == "at_least_two_quotes_required"
+    assert failure["issues"][0]["action"]
+    assert len(_MEMORY_RECEIPTS) >= 3
+
+
+def test_browser_upload_bridge_success_and_validation(monkeypatch):
+    monkeypatch.delenv("DATABASE_URL", raising=False)
+    _MEMORY_COMPARISONS.clear()
+    agent = QuoteJudgeStudioV1()
+    payload = base64.b64encode((
+        "vendor,unit_price,quantity,delivery_days,warranty_months\n"
+        "Acme Bearings,10.75,500,12,12\n"
+        "Beta Industrial,9.10,500,8,18\n"
+    ).encode("utf-8")).decode("ascii")
+
+    result = _run(agent.invoke("compare_uploaded_quotes_browser", _ctx(), comparison_id="studio-quote-v1", documents=[{"filename": "quotes.csv", "media_type": "text/csv", "data_base64": payload}], weights=WEIGHTS))
+    assert result["ok"] is True
+    assert result["recommendation"]["vendor"] == "Beta Industrial"
+
+    invalid = _run(agent.invoke("compare_uploaded_quotes_browser", _ctx(), comparison_id="bad-upload", documents=[{"filename": "quotes.csv", "media_type": "text/csv", "data_base64": "not base64!!!"}], weights=WEIGHTS))
+    assert invalid["ok"] is False
+    assert invalid["code"] == "invalid_base64"