validate_project.py

#!/usr/bin/env python3
"""Comprehensive project validation script"""

import os
import sys
from pathlib import Path

print("="*70)
print("COMPREHENSIVE PROJECT VALIDATION")
print("="*70)

issues = []
warnings = []

# 1. Check all required files exist
print("\n[CHECK 1] Required Files")
required_files = [
    "environment/__init__.py",
    "environment/types.py",
    "environment/env.py",
    "environment/data_generator.py",
    "environment/graders.py",
    "app.py",
    "Dockerfile",
    "requirements.txt",
    "inference.py",
    "openenv.yaml",
    "README.md"
]

for file in required_files:
    if Path(file).exists():
        size = Path(file).stat().st_size
        print(f"  [OK] {file:35} ({size:>6} bytes)")
    else:
        print(f"  [ERROR] {file:35} MISSING")
        issues.append(f"Missing file: {file}")

# 2. Check Python syntax
print("\n[CHECK 2] Python Syntax")
python_files = [
    "environment/types.py",
    "environment/env.py",
    "environment/data_generator.py",
    "environment/graders.py",
    "app.py",
    "inference.py"
]

for file in python_files:
    try:
        with open(file, 'r') as f:
            code = f.read()
        compile(code, file, 'exec')
        print(f"  [OK] {file:35} syntax valid")
    except SyntaxError as e:
        print(f"  [ERROR] {file:35} {e}")
        issues.append(f"Syntax error in {file}")

# 3. Check imports
print("\n[CHECK 3] Import Validation")
try:
    from environment.types import Observation, Action, Reward, State
    print(f"  [OK] environment.types imports")
except ImportError as e:
    print(f"  [ERROR] environment.types: {e}")
    issues.append(f"Import error in types")

try:
    from environment.env import EmailTriageEnv
    print(f"  [OK] environment.env imports")
except ImportError as e:
    print(f"  [ERROR] environment.env: {e}")
    issues.append(f"Import error in env")

try:
    from environment.data_generator import DataGenerator
    print(f"  [OK] environment.data_generator imports")
except ImportError as e:
    print(f"  [ERROR] environment.data_generator: {e}")
    issues.append(f"Import error in data_generator")

try:
    from environment.graders import SpamDetectionGrader
    print(f"  [OK] environment.graders imports")
except ImportError as e:
    print(f"  [ERROR] environment.graders: {e}")
    issues.append(f"Import error in graders")

# 4. Check environment functionality
print("\n[CHECK 4] Environment Functionality")
try:
    from environment import EmailTriageEnv, Action, EmailCategory, Team

    for task in ["spam_detection", "multi_class_routing", "context_aware_triage"]:
        env = EmailTriageEnv(task)
        obs = env.reset()
        assert obs is not None

        action = Action(classification=EmailCategory.NORMAL, team=Team.SUPPORT, priority=1)
        obs, reward, done, info = env.step(action)

        assert 0 <= reward.value <= 1
        print(f"  [OK] {task:30} works")
except Exception as e:
    print(f"  [ERROR] {e}")
    issues.append(f"Environment error: {str(e)[:50]}")

# 5. Check Flask app
print("\n[CHECK 5] Flask App")
try:
    from app import app
    print(f"  [OK] Flask app loads")

    routes = [rule.rule for rule in app.url_map.iter_rules()]
    required = ['/health', '/reset', '/step', '/state', '/tasks']

    for route in required:
        if route in routes:
            print(f"  [OK] {route:20} endpoint")
        else:
            warnings.append(f"Missing route: {route}")
except Exception as e:
    print(f"  [ERROR] Flask: {e}")
    issues.append(f"Flask error")

# 6. Check openenv.yaml
print("\n[CHECK 6] openenv.yaml")
try:
    import yaml
    with open('openenv.yaml', 'r') as f:
        spec = yaml.safe_load(f)

    if 'tasks' in spec and len(spec['tasks']) >= 3:
        print(f"  [OK] {len(spec['tasks'])} tasks defined")
    else:
        warnings.append("Less than 3 tasks")

    if 'action_space' in spec:
        print(f"  [OK] action_space defined")
    if 'observation_space' in spec:
        print(f"  [OK] observation_space defined")
    if 'reward' in spec:
        print(f"  [OK] reward defined")
except Exception as e:
    print(f"  [ERROR] openenv.yaml: {e}")
    issues.append(f"YAML error")

# 7. Check inference.py format
print("\n[CHECK 7] Inference Format")
try:
    with open('inference.py', 'r') as f:
        code = f.read()

    if '[START]' in code and '[STEP]' in code and '[END]' in code:
        print(f"  [OK] Logging format correct")

    if 'OpenAI' in code:
        print(f"  [OK] Uses OpenAI client")

    if all(x in code for x in ['OPENAI_API_KEY', 'MODEL_NAME', 'API_BASE_URL']):
        print(f"  [OK] All env vars handled")
except Exception as e:
    print(f"  [ERROR] inference.py: {e}")
    issues.append(f"Inference error")

# 8. Check Dockerfile
print("\n[CHECK 8] Dockerfile")
try:
    with open('Dockerfile', 'r') as f:
        df = f.read()

    if 'python:3.11' in df:
        print(f"  [OK] Python 3.11 base")
    if '7860' in df:
        print(f"  [OK] Port 7860 exposed")
    if 'HEALTHCHECK' in df:
        print(f"  [OK] Health check set")
except Exception as e:
    print(f"  [ERROR] Dockerfile: {e}")
    issues.append(f"Dockerfile error")

# 9. Check requirements.txt
print("\n[CHECK 9] requirements.txt")
try:
    with open('requirements.txt', 'r') as f:
        reqs = f.read().lower()

    for pkg in ['pydantic', 'flask', 'openai', 'pyyaml']:
        if pkg in reqs:
            print(f"  [OK] {pkg:20} listed")
except Exception as e:
    print(f"  [ERROR] requirements.txt: {e}")
    issues.append(f"Requirements error")

# 10. Check documentation
print("\n[CHECK 10] Documentation")
doc_files = {
    "README.md": 5000,
    "DEPLOYMENT_CHECKLIST.md": 2000,
    "START_HERE.md": 1000,
    "SUBMISSION_CHECKLIST.md": 5000,
}

docs_ok = 0
for doc, min_size in doc_files.items():
    if Path(doc).exists():
        size = Path(doc).stat().st_size
        if size >= min_size:
            print(f"  [OK] {doc:35}")
            docs_ok += 1
        else:
            warnings.append(f"{doc} too small ({size} bytes)")
    else:
        warnings.append(f"Missing: {doc}")

# Summary
print("\n" + "="*70)
print("VALIDATION RESULTS")
print("="*70)
print(f"\nCritical Issues: {len(issues)}")
print(f"Warnings: {len(warnings)}")

if issues:
    print(f"\nCRITICAL ISSUES TO FIX:")
    for issue in issues:
        print(f"  - {issue}")
    sys.exit(1)
else:
    print(f"\n[SUCCESS] All critical checks passed!")
    if warnings:
        print(f"\nMinor warnings ({len(warnings)}):")
        for w in warnings:
            print(f"  - {w}")

print("\n[READY] Project is ready for deployment!")