tfm_ainventory/backend/main.py

import os
from . import config_loader  # This triggers the automatic environment loading
from fastapi import FastAPI
from fastapi.middleware.cors import CORSMiddleware
from slowapi import Limiter
from slowapi.util import get_remote_address
from . import models
from .database import engine
from .routers import items, operations, users, auth, sync, categories
from .routers.admin import backups, ai_config, db_config
from .logger import log
from .scheduler import scheduler, sync_scheduler_config
from .services.image_storage import ensure_image_directories

# Create the database tables
from .database import DATA_DIR, db_path
log.info(f"Using DATA_DIR: {DATA_DIR}")
log.info(f"Database path: {db_path}")
models.Base.metadata.create_all(bind=engine)
log.info("Database tables verified.")

app = FastAPI(title="TFM aInventory API", version="1.1.0")
log.info("TFM aInventory API process started.")

# [SECURITY FIX M-01] CORS Configuration
# We dynamically build allowed origins from environment variables to simplify deployment.
_raw_origins = os.environ.get("ALLOWED_ORIGINS", "")
ALLOWED_ORIGINS = [o.strip() for o in _raw_origins.split(",") if o.strip()]

# Automatically add origins based on network_config.env variables if present
server_ip = os.environ.get("SERVER_IP")
front_port = os.environ.get("FRONTEND_PORT", "8917")
front_ssl_port = os.environ.get("FRONTEND_SSL_PORT", "8919")
back_ssl_port = os.environ.get("BACKEND_SSL_PORT", "8918")

# Always allow localhost
defaults = [
    f"http://localhost:{front_port}",
    f"https://localhost:{front_ssl_port}",
    f"https://localhost:{back_ssl_port}",
]
for d in defaults:
    if d not in ALLOWED_ORIGINS:
        ALLOWED_ORIGINS.append(d)

# Add IP-based origins if SERVER_IP is set
if server_ip and server_ip != "localhost":
    ip_origins = [
        f"http://{server_ip}:{front_port}",
        f"https://{server_ip}:{front_ssl_port}",
        f"https://{server_ip}:{back_ssl_port}",
    ]
    for ip_o in ip_origins:
        if ip_o not in ALLOWED_ORIGINS:
            ALLOWED_ORIGINS.append(ip_o)

# [NEW] Add Extra Allowed Origins (Tailscale, VPN, etc.)
extra_origins_raw = os.environ.get("EXTRA_ALLOWED_ORIGINS", "")
if extra_origins_raw:
    for extra_ip in [o.strip() for o in extra_origins_raw.split(",") if o.strip()]:
        # Generate standard combinations for this extra origin
        ext_combos = [
            f"http://{extra_ip}:{front_port}",
            f"https://{extra_ip}:{front_ssl_port}",
            f"https://{extra_ip}:{back_ssl_port}",
        ]
        for combo in ext_combos:
            if combo not in ALLOWED_ORIGINS:
                ALLOWED_ORIGINS.append(combo)

log.info("🔒 [SECURITY] CORS configuration initialized.")
for origin in ALLOWED_ORIGINS:
    log.info(f"   -> Allowed: {origin}")

# Add CORS middleware FIRST (before rate limiter)
app.add_middleware(
    CORSMiddleware,
    allow_origins=ALLOWED_ORIGINS,
    allow_credentials=True,
    allow_methods=["GET", "POST", "PUT", "PATCH", "DELETE", "OPTIONS"],
    allow_headers=["*"],
)

# [H-02] Rate limiting on API
limiter = Limiter(key_func=get_remote_address)
app.state.limiter = limiter

app.include_router(items.router)
app.include_router(operations.router)
app.include_router(users.router)
app.include_router(auth.router)
app.include_router(sync.router)
app.include_router(categories.router)
app.include_router(backups.router)
app.include_router(ai_config.router)
app.include_router(db_config.router)

@app.on_event("startup")
def startup_event():
    log.info("[STARTUP] Initializing image storage directories...")
    ensure_image_directories()
    log.info("[STARTUP] Starting background scheduler...")
    scheduler.start()
    sync_scheduler_config()

    # [NEW] Initialize default system settings
    from .database import SessionLocal
    db = SessionLocal()
    try:
        # Default AI Prompt from User Request
        default_prompt = (
            "Extract hardware specifications with PRECISE formatting.\n"
            "For any field, do not add comments in parenthesis or measurement units in Item name.\n\n"
            "SIZE CONVERSION RULES (CRITICAL - Apply to all size fields):\n"
            "  Convert sizes to HUMAN-READABLE format:\n"
            "  • Storage ≥1600GB: convert to TB (e.g., '1600GB' → '1.6TB', '2048GB' → '2TB', '8192GB' → '8TB')\n"
            "  • Storage 512GB-1599GB: keep as GB (e.g., '512GB', '1TB' if labeled as 1000GB)\n"
            "  • Memory ≥1024MB: convert to GB (e.g., '1024MB' → '1GB')\n"
            "  • Cables/length: express in meters (e.g., '5m', '30m')\n"
            "  Apply this rule to: Item field size prefix, Size field, and OCR key sizes.\n\n"
            "ITEM FIELD FORMAT (Critical):\n"
            "[<size_or_length>] <type> <vendor> <connector> <part_number>\n"
            "  <size_or_length>: HUMAN-READABLE format - GB/TB for storage, meters for cables (e.g., '2m', '256GB', '1.6TB'). Omit diameter/mm measurements.\n"
            "  <type>: DDR3/DDR4/DDR5/SSD/HDD/NVMe/SAS/SATA/Patchcord/Fiber/Cable/Transceiver etc.\n"
            "  <vendor>: HP/HPE/Dell/Samsung/Cisco/Lenovo/Hynix etc.\n"
            "  <connector>: RJ45/LC-LC/MPO/U.3/SATA/SAS/LC/ST etc. Omit if N/A.\n"
            "  <part_number>: PN only if visible on label. Omit serial numbers.\n"
            "Examples: '5m Patchcord LC-LC' / '256GB SSD Samsung SAS' / '128GB DDR4 Hynix SK-234' / '1.6TB NVMe HP U.3' / '8TB HDD Seagate SATA'\n\n"
            "TYPE: Item asset class (DDR3/SSD/NVMe/Patchcord/SFP etc.)\n"
            "DESCRIPTION: Technical details max 5 words (e.g., 'High speed fiber optic cable'). Omit size/length here.\n"
            "CATEGORY: Broad ecosystem (Memory, Storage, Network, Cabling, etc.)\n"
            "CONNECTOR: Physical interface type (e.g., 'LC', 'RJ45', 'U.3')\n"
            "SIZE: HUMAN-READABLE capacity or length ONLY (e.g., '256GB', '1.6TB', '2m'). No serial numbers or comments.\n"
            "COLOR: Physical color if distinguishing.\n"
            "PartNr: Part number only (no serial numbers)\n"
            "OCR: Robust matching key. Include: core type + vendor + key identifiers + HUMAN-READABLE size + common variations.\n"
            "     Examples: 'PATCHCORD 5M LC LC CAT6 FIBER' / '256GB SSD SAMSUNG' / '1.6TB NVME HP' / '128GB DDR4 HYNIX'\n"
            "     Include abbreviations: 'DDR4'/'DDR' or 'SSD'/'SSDS' or 'HP'/'HPE' or 'NVMe'/'NVME'\n"
            "     Format: ALL UPPERCASE, space-separated tokens, NO special chars. Skip serial numbers. Use human-readable sizes."
        )
        
        # Wrap in JSON instructions for reliable parsing
        final_prompt = f"IMAGE ANALYSIS INSTRUCTIONS:\n{default_prompt}\n\nIMPORTANT: Return ONLY a valid JSON object with the keys: Item, Type, Description, Category, Connector, Size, Color, PartNr, OCR."

        existing = db.query(models.SystemSetting).filter(models.SystemSetting.key == "ai_extraction_prompt").first()
        if not existing:
            db.add(models.SystemSetting(key="ai_extraction_prompt", value=final_prompt))
            db.commit()
            log.info("Initialized default AI prompt in database.")
            # Refresh existing after commit
            existing = db.query(models.SystemSetting).filter(models.SystemSetting.key == "ai_extraction_prompt").first()

        # [NEW] Sync/Initialize AI prompt file in /config
        from .database import BASE_DIR
        PROJECT_ROOT = os.path.dirname(BASE_DIR)
        PROMPT_FILE_PATH = os.path.join(PROJECT_ROOT, "config", "ai_prompt.md")
        
        if not os.path.exists(PROMPT_FILE_PATH):
            try:
                os.makedirs(os.path.dirname(PROMPT_FILE_PATH), exist_ok=True)
                # Use DB value (which we just ensured exists)
                current_val = existing.value if existing else final_prompt
                with open(PROMPT_FILE_PATH, 'w', encoding='utf-8') as f:
                    f.write(current_val)
                log.info(f"✅ Initialized AI prompt configuration file: {PROMPT_FILE_PATH}")
            except Exception as fe:
                log.error(f"❌ Failed to initialize AI prompt file: {fe}")

        defaults = {
            "backup_retention_count": "10",
            "backup_schedule_hour": "3",
            "backup_schedule_freq_days": "1",
            "ai_provider": "gemini"
        }
        for key, val in defaults.items():
            if not db.query(models.SystemSetting).filter(models.SystemSetting.key == key).first():
                db.add(models.SystemSetting(key=key, value=val))
                log.info(f"Initialized default setting: {key}")
        db.commit()
    except Exception as e:
        log.error(f"Failed to initialize settings: {e}")
    finally:
        db.close()

@app.get("/")
def read_root():
    return {"message": "Inventory API is running"}