AI Engineering: Agents and Applications › Full-Stack AI Applications › Day 322
Hands-on lab — Day 322: A Full-Stack AI Application
- ← Back to the Day 322 lesson
- Open the hands-on files on GitHub — clone or download them from the public labs repository
- Local path in your clone:
labs/sections/ai-engineering/day-322-a-full-stack-ai-application/
Commands
Setup
pip install -r requirements/requirements.txt Run
python examples/full_stack_app.py Test
bash tests/run_tests.sh File tree
examples/full_stack_app.py expected-output/examples-run.txt expected-output/FIELDS.md expected-output/measured-values.txt expected-output/run-output.txt expected-output/starter-run.txt expected-output/test-output.txt expected-output/test-run.txt metadata.yml README.md requirements/requirements.txt security.md starter/full_stack_app.py tests/run_tests.sh tests/test_full_stack_app.py troubleshooting.md
Lab README
Day 322 Lab: A Full-Stack AI Application
Lesson
- Lesson title: A Full-Stack AI Application
- Day number: 322 of 365
- Lesson article: https://ai-roadmap-365.github.io/day-322-a-full-stack-ai-application
- Lab files: everything you need is in this directory — follow “How to run” below.
- Browse the course locally: from the repository root, this lab also appears in the course website at
/labs/day-322-a-full-stack-ai-applicationwhen the site is running.
Purpose
Build a Complete Full-Stack AI Application Engine in Python integrating authentication, rate limiting, exact caching, two-phase credit holds, and multi-provider failover routing.
Learning objectives
- Implement multi-tenant authentication and quota verification.
- Intercept cached queries to deliver instant zero-cost responses.
- Enforce credit pre-authorization holds preventing negative balance overdrafts.
- Execute multi-provider fallback routing when upstream services degrade.
- Reconcile exact token usage charges upon stream completion.
Prerequisites
- Python 3.10+ installed
- pytest installed
Supported operating systems
- macOS, Linux, Windows WSL2
Hardware requirements
- Standard CPU, 512MB RAM
Required software
- Python 3.10+, pytest
Free and open-source options
- Python Standard Library, Pytest
Installation
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements/requirements.txt
File structure
starter/full_stack_app.py: Starter implementation skeletonexamples/full_stack_app.py: Verified reference implementationtests/test_full_stack_app.py: Test suiteexpected-output/: Captured execution logs
How to run
python3 examples/full_stack_app.py
What the commands do
- Simulates the entire end-to-end full-stack request execution lifecycle.
Expected output
Normal: {'status': 'SUCCESS', 'cached': False, 'resolved_provider': 'primary_claude', 'fallback_occurred': False, 'actual_cost_usd': 0.00465, 'remaining_balance': 9.99535, 'response': '[primary_claude] Response for: Hi'}
Validation steps
Run test runner:
bash tests/run_tests.sh
Tests
The test suite validates:
- Normal full-stack chat execution with credit deduction
- Zero-cost exact cache response delivery
- Rejection on insufficient credit balance
- Seamless secondary provider failover on primary failure
- Graceful error handling when all upstream providers fail
Cleanup
rm -rf .pytest_cache __pycache__ .venv
Troubleshooting
Ensure hold amount is released on total upstream failure.
Security notes
Runs completely offline on local CPU.
Extension exercises
Implement dynamic multi-tier semantic caching in the pipeline.
Navigation
Day number: 322 of 365
Expected output
FIELDS.md
# Measured Values
- `requests_processed`: 12
- `cache_hits`: 2
examples-run.txt
Normal: {'status': 'SUCCESS', 'cached': False, 'resolved_provider': 'primary_claude', 'fallback_occurred': False, 'actual_cost_usd': 0.00465, 'remaining_balance': 9.99535, 'response': '[primary_claude] Response for: Hi'}
measured-values.txt
requests_processed=12
cache_hits=2
run-output.txt
Normal: {'status': 'SUCCESS', 'cached': False, 'resolved_provider': 'primary_claude', 'fallback_occurred': False, 'actual_cost_usd': 0.00465, 'remaining_balance': 9.99535, 'response': '[primary_claude] Response for: Hi'}
starter-run.txt
An untouched starter fails the suite. Captured from a real run:
self = <examples.full_stack_app.FullStackAIAppEngine object at 0x10b04a650>
tenant_id = 'tenant_alpha', raw_key = 'sk_alpha_123', prompt = 'Tell story'
simulated_failing_providers = ['primary_claude', 'secondary_openai', 'backup_vllm']
def process_chat_request(self, tenant_id: str, raw_key: str, prompt: str, simulated_failing_providers: Optional[List[str]]=None) -> Dict[str, Any]:
> raise NotImplementedError('TASK 1: implement process_chat_request.')
E NotImplementedError: TASK 1: implement process_chat_request.
examples/full_stack_app.py:21: NotImplementedError
=========================== short test summary info ============================
FAILED tests/test_full_stack_app.py::test_normal_chat_request - NotImplemente...
FAILED tests/test_full_stack_app.py::test_exact_cache_hit - NotImplementedErr...
FAILED tests/test_full_stack_app.py::test_payment_required_insufficient_credit
FAILED tests/test_full_stack_app.py::test_multi_provider_failover - NotImplem...
FAILED tests/test_full_stack_app.py::test_upstream_outage_all_providers_fail
============================== 5 failed in 0.03s ===============================
Implement each TASK in starter/, copy it over examples/, and the same
suite goes green.
test-output.txt
============================= test session starts ==============================
platform darwin -- Python 3.14.0, pytest-9.1.1, pluggy-1.6.0 -- <repo>/.venv-tools/bin/python3.14
cachedir: .pytest_cache
rootdir: <repo>/labs/sections/ai-engineering/day-322-a-full-stack-ai-application
plugins: cov-7.1.0, anyio-4.14.2
collecting ... collected 5 items
tests/test_full_stack_app.py::test_normal_chat_request PASSED [ 20%]
tests/test_full_stack_app.py::test_exact_cache_hit PASSED [ 40%]
tests/test_full_stack_app.py::test_payment_required_insufficient_credit PASSED [ 60%]
tests/test_full_stack_app.py::test_multi_provider_failover PASSED [ 80%]
tests/test_full_stack_app.py::test_upstream_outage_all_providers_fail PASSED [100%]
============================== 5 passed in 0.02s ===============================
test-run.txt
============================= test session starts ==============================
platform darwin -- Python 3.14.0, pytest-9.1.1, pluggy-1.6.0 -- <repo>/.venv-tools/bin/python3.14
cachedir: .pytest_cache
rootdir: <repo>/labs/sections/ai-engineering/day-322-a-full-stack-ai-application
plugins: cov-7.1.0, anyio-4.14.2
collecting ... collected 5 items
tests/test_full_stack_app.py::test_normal_chat_request PASSED [ 20%]
tests/test_full_stack_app.py::test_exact_cache_hit PASSED [ 40%]
tests/test_full_stack_app.py::test_payment_required_insufficient_credit PASSED [ 60%]
tests/test_full_stack_app.py::test_multi_provider_failover PASSED [ 80%]
tests/test_full_stack_app.py::test_upstream_outage_all_providers_fail PASSED [100%]
============================== 5 passed in 0.02s ===============================
Source files
examples/full_stack_app.py (3842 bytes)
import hashlib
import time
from typing import Dict, Any, List, Optional, Tuple
class FullStackAIAppEngine:
def __init__(self):
self.tenants: Dict[str, Dict[str, Any]] = {
"tenant_alpha": {
"key_hash": hashlib.sha256(b"sk_alpha_123").hexdigest(),
"balance": 10.0,
"reserved_holds": 0.0,
"rpm_limit": 60,
"requests_this_min": 0,
"last_reset": time.time()
},
"tenant_poor": {
"key_hash": hashlib.sha256(b"sk_poor_123").hexdigest(),
"balance": 0.01,
"reserved_holds": 0.0,
"rpm_limit": 10,
"requests_this_min": 0,
"last_reset": time.time()
}
}
self.cache: Dict[str, str] = {}
self.active_holds: Dict[str, Dict[str, Any]] = {}
self.providers = ["primary_claude", "secondary_openai", "backup_vllm"]
def process_chat_request(
self,
tenant_id: str,
raw_key: str,
prompt: str,
simulated_failing_providers: Optional[List[str]] = None
) -> Dict[str, Any]:
if tenant_id not in self.tenants:
return {"status": "AUTH_ERROR", "message": "Invalid tenant ID"}
tenant = self.tenants[tenant_id]
if hashlib.sha256(raw_key.encode()).hexdigest() != tenant["key_hash"]:
return {"status": "AUTH_ERROR", "message": "Invalid API key"}
now = time.time()
if now - tenant["last_reset"] > 60:
tenant["requests_this_min"] = 0
tenant["last_reset"] = now
if tenant["requests_this_min"] >= tenant["rpm_limit"]:
return {"status": "RATE_LIMITED", "message": "RPM limit exceeded"}
cache_key = f"{tenant_id}:{prompt.strip().lower()}"
if cache_key in self.cache:
return {
"status": "SUCCESS",
"cached": True,
"cost_usd": 0.0,
"response": self.cache[cache_key],
"remaining_balance": round(tenant["balance"], 6)
}
est_cost = 0.030
available_balance = tenant["balance"] - tenant["reserved_holds"]
if available_balance < est_cost:
return {"status": "PAYMENT_REQUIRED", "message": "Insufficient credit balance"}
hold_id = f"hold_{len(self.active_holds)+1}"
tenant["reserved_holds"] += est_cost
tenant["requests_this_min"] += 1
failing = set(simulated_failing_providers or [])
resolved_provider = None
attempted_providers = []
for p in self.providers:
attempted_providers.append(p)
if p not in failing:
resolved_provider = p
break
if not resolved_provider:
tenant["reserved_holds"] -= est_cost
return {"status": "UPSTREAM_OUTAGE", "attempted": attempted_providers}
actual_cost = 0.00465
tenant["reserved_holds"] -= est_cost
tenant["balance"] -= actual_cost
full_response = f"[{resolved_provider}] Response for: {prompt}"
self.cache[cache_key] = full_response
return {
"status": "SUCCESS",
"cached": False,
"resolved_provider": resolved_provider,
"fallback_occurred": len(attempted_providers) > 1,
"actual_cost_usd": actual_cost,
"remaining_balance": round(tenant["balance"], 6),
"response": full_response
}
if __name__ == "__main__":
app = FullStackAIAppEngine()
print("Normal:", app.process_chat_request("tenant_alpha", "sk_alpha_123", "Hi"))
metadata.yml (401 bytes)
lesson_id: D322
day: 322
kind: python
languages:
- python
setup_commands:
- pip install -r requirements/requirements.txt
run_commands:
- python examples/full_stack_app.py
test_commands:
- bash tests/run_tests.sh
cleanup_commands:
- rm -rf __pycache__ .pytest_cache
requires_network: false
requires_api_key: false
estimated_minutes: 45
last_executed: '2026-08-30'
executed_on: macOS 15.0 Apple Silicon
requirements/requirements.txt (14 bytes)
pytest>=7.0.0
starter/full_stack_app.py (1377 bytes)
"""STARTER -- implement each TASK below, then run the tests.
Every function that raises NotImplementedError is yours to write. The
imports, constants and data structures are given; the logic is not.
Run `bash tests/run_tests.sh` to see which tasks are still outstanding.
"""
import hashlib
import time
from typing import Dict, Any, List, Optional, Tuple
class FullStackAIAppEngine:
def __init__(self):
self.tenants: Dict[str, Dict[str, Any]] = {'tenant_alpha': {'key_hash': hashlib.sha256(b'sk_alpha_123').hexdigest(), 'balance': 10.0, 'reserved_holds': 0.0, 'rpm_limit': 60, 'requests_this_min': 0, 'last_reset': time.time()}, 'tenant_poor': {'key_hash': hashlib.sha256(b'sk_poor_123').hexdigest(), 'balance': 0.01, 'reserved_holds': 0.0, 'rpm_limit': 10, 'requests_this_min': 0, 'last_reset': time.time()}}
self.cache: Dict[str, str] = {}
self.active_holds: Dict[str, Dict[str, Any]] = {}
self.providers = ['primary_claude', 'secondary_openai', 'backup_vllm']
def process_chat_request(self, tenant_id: str, raw_key: str, prompt: str, simulated_failing_providers: Optional[List[str]]=None) -> Dict[str, Any]:
raise NotImplementedError('TASK 1: implement process_chat_request.')
if __name__ == '__main__':
app = FullStackAIAppEngine()
print('Normal:', app.process_chat_request('tenant_alpha', 'sk_alpha_123', 'Hi'))
tests/run_tests.sh (253 bytes)
#!/usr/bin/env bash
set -e
export PYTHONPATH=examples:.
if [ -n "$PYTEST" ]; then
$PYTEST tests/test_*.py -v
elif command -v pytest &> /dev/null; then
pytest tests/test_*.py -v
else
python3 -m unittest discover -s tests -p 'test_*.py' -v
fi
tests/test_full_stack_app.py (1848 bytes)
import pytest
from examples.full_stack_app import FullStackAIAppEngine
def test_normal_chat_request():
app = FullStackAIAppEngine()
res = app.process_chat_request("tenant_alpha", "sk_alpha_123", "Explain gravity")
assert res["status"] == "SUCCESS"
assert res["cached"] is False
assert res["resolved_provider"] == "primary_claude"
assert res["actual_cost_usd"] == 0.00465
assert res["remaining_balance"] == 9.99535
def test_exact_cache_hit():
app = FullStackAIAppEngine()
res1 = app.process_chat_request("tenant_alpha", "sk_alpha_123", "Explain relativity")
res2 = app.process_chat_request("tenant_alpha", "sk_alpha_123", "Explain relativity")
assert res2["status"] == "SUCCESS"
assert res2["cached"] is True
assert res2["cost_usd"] == 0.0
assert res2["remaining_balance"] == res1["remaining_balance"]
def test_payment_required_insufficient_credit():
app = FullStackAIAppEngine()
res = app.process_chat_request("tenant_poor", "sk_poor_123", "Complex prompt")
assert res["status"] == "PAYMENT_REQUIRED"
assert "Insufficient credit" in res["message"]
def test_multi_provider_failover():
app = FullStackAIAppEngine()
res = app.process_chat_request("tenant_alpha", "sk_alpha_123", "Tell story", simulated_failing_providers=["primary_claude"])
assert res["status"] == "SUCCESS"
assert res["resolved_provider"] == "secondary_openai"
assert res["fallback_occurred"] is True
def test_upstream_outage_all_providers_fail():
app = FullStackAIAppEngine()
res = app.process_chat_request("tenant_alpha", "sk_alpha_123", "Tell story", simulated_failing_providers=["primary_claude", "secondary_openai", "backup_vllm"])
assert res["status"] == "UPSTREAM_OUTAGE"
# Ensure hold was released
assert app.tenants["tenant_alpha"]["reserved_holds"] == 0.0