#!/usr/bin/env python3
"""Check shonuff@germainebrown.com inbox. Outputs JSON for LLM summary.
Silent if nothing new. Skips trusted senders (Germaine, mailer-daemon).
"""
import imaplib, email, json, os, hashlib
from email.utils import parsedate_to_datetime

HOST = "mail.germainebrown.com"
PORT = 993
USER = "shonuff@germainebrown.com"
PW = "Catches.bullets1985"
SEEN_FILE = "/root/.hermes/scripts/.shonuff-processed.json"
TRUSTED = ["g@germainebrown.com"]

def load_seen():
    if os.path.exists(SEEN_FILE):
        return set(json.load(open(SEEN_FILE)))
    return set()

def save_seen(seen):
    json.dump(list(seen), open(SEEN_FILE, "w"))

def safe_str(val):
    if val is None: return ""
    if isinstance(val, str): return val
    try: return str(val)
    except: return ""

def get_text_body(msg):
    body = ""
    # Try text/plain first
    if msg.is_multipart():
        for part in msg.walk():
            if part.get_content_type() == "text/plain":
                payload = part.get_payload(decode=True)
                if payload:
                    body += payload.decode("utf-8", errors="replace")
        # Fallback: extract text from text/html if no plain text found
        if not body.strip():
            for part in msg.walk():
                if part.get_content_type() == "text/html":
                    payload = part.get_payload(decode=True)
                    if payload:
                        import html
                        text = payload.decode("utf-8", errors="replace")
                        text = re.sub(r'<[^>]+>', ' ', text)
                        text = html.unescape(text)
                        body = text
                    break
    else:
        payload = msg.get_payload(decode=True)
        if payload:
            ct = msg.get_content_type()
            text = payload.decode("utf-8", errors="replace")
            if ct == "text/html":
                text = re.sub(r'<[^>]+>', ' ', text)
                import html
                text = html.unescape(text)
            body = text
    import re
    body = re.sub(r'\s+', ' ', body).strip()
    return body[:500]

def main():
    seen = load_seen()
    new_msgs = []
    try:
        conn = imaplib.IMAP4_SSL(HOST, PORT)
        conn.login(USER, PW)
        conn.select("INBOX")
        status, data = conn.search(None, "UNSEEN")
        if status == "OK" and data[0]:
            for num in data[0].split():
                status, msg_data = conn.fetch(num, "(RFC822)")
                if status != "OK": continue
                raw = email.message_from_bytes(msg_data[0][1])
                sender = safe_str(raw.get("From", "")).strip()
                subj = safe_str(raw.get("Subject", "(no subject)"))
                mid = safe_str(raw.get("Message-ID", str(num)))
                date = safe_str(raw.get("Date", ""))
                if any(t.lower() in sender.lower() for t in TRUSTED): continue
                h = hashlib.md5(mid.encode()).hexdigest()
                if h in seen: continue
                seen.add(h)
                new_msgs.append({"from": sender, "subject": subj, "date": date, "body_preview": get_text_body(raw)[:500], "uid": num.decode()})
                conn.store(num, "+FLAGS", "\\Seen")
        conn.logout()
        save_seen(seen)
    except Exception as e:
        print(json.dumps({"error": str(e)}))
        return
    if new_msgs:
        print(json.dumps({"messages": new_msgs}, indent=2))

if __name__ == "__main__":
    main()