4ventures-client-portal/scripts/sync_clientify_tenant.py

#!/usr/bin/env python3
"""Sync Clientify contacts → leads and deals → deals for one tenant.

Requires in .env.local:
  CLIENTIFY_API_KEY (or CLIENTIFY_API_KEY_<SLUG>)
  NEXT_PUBLIC_SUPABASE_URL
  SUPABASE_SERVICE_ROLE_KEY

Usage:
  python3 scripts/sync_clientify_tenant.py --tenant-id a7a6eb49-... --label agua-miia
"""
from __future__ import annotations

import argparse
import json
import os
import sys
import urllib.error
import urllib.parse
import urllib.request
import uuid
from datetime import datetime, timezone
from pathlib import Path
from typing import Any

ROOT = Path(__file__).resolve().parents[1]
CFY = "https://api.clientify.com/v1"

# Clientify deal status_desc → warehouse stage
STAGE_MAP = {
    "won": "won",
    "lost": "lost",
    "open": "open",
}


def load_env() -> None:
    for line in (ROOT / ".env.local").read_text().splitlines():
        if "=" in line and not line.startswith("#"):
            k, v = line.split("=", 1)
            k = k.strip()
            if k and k not in os.environ:
                os.environ[k] = v.strip().strip('"').strip("'")


def env_key(label: str) -> str:
    slug = label.upper().replace("-", "_").replace(" ", "_")
    return (
        os.environ.get(f"CLIENTIFY_API_KEY_{slug}")
        or os.environ.get("CLIENTIFY_API_KEY")
        or ""
    )


def sb_headers() -> dict[str, str]:
    key = os.environ["SUPABASE_SERVICE_ROLE_KEY"]
    return {
        "apikey": key,
        "Authorization": f"Bearer {key}",
        "Content-Type": "application/json",
    }


def sb(method: str, path: str, body: Any = None, prefer: str = "return=minimal"):
    url = os.environ["NEXT_PUBLIC_SUPABASE_URL"].rstrip("/") + path
    headers = dict(sb_headers())
    if prefer:
        headers["Prefer"] = prefer
    data = None if body is None else json.dumps(body).encode()
    req = urllib.request.Request(url, data=data, headers=headers, method=method)
    try:
        with urllib.request.urlopen(req, timeout=120) as r:
            raw = r.read().decode()
            return r.status, (json.loads(raw) if raw.strip() else None)
    except urllib.error.HTTPError as e:
        return e.code, e.read().decode()[:500]


def cfy_get(token: str, path: str) -> dict:
    req = urllib.request.Request(
        CFY + path,
        headers={"Authorization": f"Token {token}", "Accept": "application/json"},
    )
    with urllib.request.urlopen(req, timeout=60) as r:
        return json.loads(r.read())


def cfy_paginate(token: str, path: str, page_size: int = 100) -> list[dict]:
    out: list[dict] = []
    # path may already have query
    sep = "&" if "?" in path else "?"
    url_path = f"{path}{sep}page_size={page_size}"
    page = 1
    while True:
        q = f"{url_path}&page={page}" if "page=" not in url_path else url_path
        # rebuild clean
        base, _, query = path.partition("?")
        params = urllib.parse.parse_qs(query)
        params["page_size"] = [str(page_size)]
        params["page"] = [str(page)]
        q = base + "?" + urllib.parse.urlencode({k: v[0] for k, v in params.items()})
        j = cfy_get(token, q)
        batch = j.get("results") or []
        out.extend(batch)
        print(f"  {path} page={page} +{len(batch)} total={len(out)}/{j.get('count')}", flush=True)
        if not j.get("next") or not batch:
            break
        page += 1
    return out


def first_email(c: dict) -> str | None:
    emails = c.get("emails") or []
    if isinstance(emails, list) and emails:
        e = emails[0]
        if isinstance(e, dict):
            return (e.get("email") or e.get("value") or "").strip() or None
        return str(e).strip() or None
    return None


def first_phone(c: dict) -> str | None:
    phones = c.get("phones") or []
    if isinstance(phones, list) and phones:
        p = phones[0]
        if isinstance(p, dict):
            return (p.get("phone") or p.get("value") or "").strip() or None
        return str(p).strip() or None
    return None


def contact_id_from_url(url: str | None) -> str | None:
    if not url:
        return None
    # https://api.clientify.com/v1/contacts/12345/
    parts = url.rstrip("/").split("/")
    return parts[-1] if parts else None


def map_stage(deal: dict) -> str:
    desc = (deal.get("status_desc") or "").strip().lower()
    if desc in STAGE_MAP:
        return STAGE_MAP[desc]
    st = deal.get("status")
    # Observed: 1 open-ish, 3 won, 4 lost (API filter unreliable)
    if st == 3 or desc == "won":
        return "won"
    if st == 4 or desc == "lost":
        return "lost"
    return "open"


def parse_date(s: str | None) -> str | None:
    if not s:
        return None
    # date-only or iso
    try:
        if "T" in s:
            return datetime.fromisoformat(s.replace("Z", "+00:00")).astimezone(timezone.utc).isoformat()
        return datetime.fromisoformat(s + "T12:00:00+00:00").astimezone(timezone.utc).isoformat()
    except Exception:
        return None


def main() -> int:
    load_env()
    ap = argparse.ArgumentParser()
    ap.add_argument("--tenant-id", required=True)
    ap.add_argument("--label", default="tenant")
    ap.add_argument("--contacts-only", action="store_true")
    ap.add_argument("--deals-only", action="store_true")
    args = ap.parse_args()

    token = env_key(args.label)
    if not token:
        print("missing CLIENTIFY_API_KEY", file=sys.stderr)
        return 2

    tid = args.tenant_id
    print(f"Sync Clientify → warehouse tenant={tid} label={args.label}", flush=True)

    do_contacts = not args.deals_only
    do_deals = not args.contacts_only

    contact_to_lead: dict[str, str] = {}

    if do_contacts:
        print("Fetching contacts…", flush=True)
        contacts = cfy_paginate(token, "/contacts/")
        # wipe previous clientify leads for tenant
        st, _ = sb(
            "DELETE",
            f"/rest/v1/leads?tenant_id=eq.{tid}&crm=eq.clientify",
        )
        print(f"DELETE leads → {st}", flush=True)

        rows = []
        for c in contacts:
            cid = str(c["id"])
            lid = str(uuid.uuid5(uuid.NAMESPACE_URL, f"clientify-lead:{tid}:{cid}"))
            contact_to_lead[cid] = lid
            source = (
                (c.get("contact_source") or c.get("channel") or c.get("medium") or "clientify")
            )
            if isinstance(source, str):
                source = source.strip().lower()[:80] or "clientify"
            else:
                source = "clientify"
            status = (c.get("status") or "new")
            if isinstance(status, str):
                status = status.strip().lower()[:40] or "new"
            else:
                status = "new"
            rows.append(
                {
                    "id": lid,
                    "tenant_id": tid,
                    "first_name": (
                        " ".join(
                            x
                            for x in [(c.get("first_name") or "").strip(), (c.get("last_name") or "").strip()]
                            if x
                        )
                        or None
                    ),
                    "email": first_email(c),
                    "phone": first_phone(c),
                    "source": source,
                    "medium": (c.get("medium") or None),
                    "crm": "clientify",
                    "crm_contact_id": cid,
                    "status": status,
                    "created_at": parse_date(c.get("created"))
                    or datetime.now(timezone.utc).isoformat(),
                }
            )

        ok = 0
        for i in range(0, len(rows), 200):
            chunk = rows[i : i + 200]
            st, err = sb("POST", "/rest/v1/leads", chunk)
            if st not in (200, 201):
                print("FAIL leads", st, err, flush=True)
                return 1
            ok += len(chunk)
            print(f"  INSERT leads {ok}/{len(rows)}", flush=True)
        print(f"OK contacts→leads {ok}", flush=True)

    if do_deals:
        if not contact_to_lead and do_contacts is False:
            # load existing map
            st, data = sb(
                "GET",
                f"/rest/v1/leads?tenant_id=eq.{tid}&crm=eq.clientify&select=id,crm_contact_id&limit=20000",
                prefer="",
            )
            if st == 200 and isinstance(data, list):
                for r in data:
                    if r.get("crm_contact_id"):
                        contact_to_lead[str(r["crm_contact_id"])] = r["id"]

        print("Fetching deals…", flush=True)
        deals = cfy_paginate(token, "/deals/")
        st, _ = sb(
            "DELETE",
            f"/rest/v1/deals?tenant_id=eq.{tid}&crm_deal_id=like.clientify:*",
        )
        print(f"DELETE deals → {st}", flush=True)

        rows = []
        by_stage = {"won": 0, "lost": 0, "open": 0}
        for d in deals:
            did = str(d["id"])
            stage = map_stage(d)
            by_stage[stage] = by_stage.get(stage, 0) + 1
            cid = contact_id_from_url(d.get("contact"))
            lead_id = contact_to_lead.get(cid) if cid else None
            amount = float(d.get("amount") or d.get("amount_user") or 0)
            closed = parse_date(d.get("actual_closed_date"))
            pipe_url = str(d.get("pipeline") or "")
            pipe_id = ""
            if "/pipelines/" in pipe_url:
                pipe_id = pipe_url.rstrip("/").split("/")[-1]
            raw_src = (
                d.get("deal_source")
                or d.get("contact_source")
                or ""
            )
            if isinstance(raw_src, str):
                raw_src = raw_src.strip()[:80]
            else:
                raw_src = ""
            tags = d.get("tags") or []
            tag_blob = " ".join(str(t) for t in tags).lower() if isinstance(tags, list) else ""
            name = (d.get("name") or "")[:200]
            if not raw_src:
                if any(x in tag_blob for x in ("facebook", "instagram", "meta", " fb ")):
                    raw_src = "meta"
                elif "google" in tag_blob:
                    raw_src = "google"
                elif "woocommerce" in tag_blob or name.lower().startswith("order "):
                    raw_src = "ecommerce"
            row = {
                "id": str(uuid.uuid5(uuid.NAMESPACE_URL, f"clientify-deal:{tid}:{did}")),
                "tenant_id": tid,
                "lead_id": lead_id,
                "crm_deal_id": f"clientify:{did}",
                "stage": stage,
                "amount": amount,
                "won_at": closed if stage == "won" else None,
                "lost_at": closed if stage == "lost" else None,
                "pipeline_id": pipe_id or None,
                "pipeline_name": (d.get("pipeline_desc") or None),
                "source": raw_src.lower() if raw_src else None,
                "name": name or None,
            }
            rows.append(row)

        ok = 0
        for i in range(0, len(rows), 200):
            chunk = rows[i : i + 200]
            st, err = sb("POST", "/rest/v1/deals", chunk)
            if st not in (200, 201):
                print("FAIL deals", st, err, flush=True)
                return 1
            ok += len(chunk)
            print(f"  INSERT deals {ok}/{len(rows)}", flush=True)
        won_amt = sum(r["amount"] for r in rows if r["stage"] == "won")
        print(f"OK deals {ok} by_stage={by_stage} won_amount={won_amt:.2f}", flush=True)

    # touch integration
    now = datetime.now(timezone.utc).isoformat()
    sb(
        "PATCH",
        f"/rest/v1/integrations?tenant_id=eq.{tid}&provider=eq.clientify",
        {"status": "connected", "last_sync_at": now, "error_message": None},
    )
    print("DONE", flush=True)
    return 0


if __name__ == "__main__":
    raise SystemExit(main())