GTI_GERENCIADOR_FISCAL/scripts/enrichment_placeholder_e2e.py

"""COPY-ONLY E2E of the TECHNICAL_PLACEHOLDER case found by the operator: the SGV refuses a product without NCM, so it was saved with CLASSIFICACAO_FISCAL = '00000000'.

    python scripts/enrichment_placeholder_e2e.py

Real Firebird COPY + the real Agent worker + the real Hub resolver (in-process, fake providers, no internet). Proves: placeholder detected and classified (DRY_RUN = zero writes), replaced under ENABLED,
CEST/IPI filled only when safe, cClassTrib typed by the operator untouched, a real NCM (or an unlisted filler such as 99999999) preserved even when the KB disagrees, second run = 0 writes.
"""
import json
import sys
import threading
import time
from pathlib import Path

ROOT = Path(__file__).resolve().parents[1]
sys.path.insert(0, str(ROOT)); sys.path.insert(0, str(ROOT / "scripts")); sys.path.insert(0, str(ROOT / "agent" / "src"))
from dotenv import load_dotenv  # noqa: E402

load_dotenv(ROOT / ".env")
import enrichment_copy_e2e as ce  # noqa: E402
from gti_fiscal_agent import enrichment as E  # noqa: E402

base = ce.base


def insert(code, ncm, ean, cclasstrib=None, name="COCA-COLA ORIGINAL LATA 350 ML"):
    conn = base.connect(True); cur = conn.cursor()
    cur.execute("INSERT INTO C000025 (CODIGO, PRODUTO, CODBARRA, CLASSIFICACAO_FISCAL, CCLASSTRIB) VALUES (?, ?, ?, ?, ?)", (code, name, ean, ncm, cclasstrib))
    conn.commit(); conn.close()


def row(code):
    conn = base.connect(False); cur = conn.cursor()
    cur.execute("SELECT CLASSIFICACAO_FISCAL, CEST, IPI, CCLASSTRIB FROM C000025 WHERE CODIGO=?", (code,))
    r = cur.fetchone(); conn.close()
    return tuple(None if v is None else (v if isinstance(v, float) else str(v).strip()) for v in r) if r else None


def main():
    checks = {}
    base.restore_copy()
    hub = ce.InProcessHub()
    from central.app.models import CestEntry
    for entry in hub.session.query(CestEntry).all():
        entry.description = "COCA-COLA ORIGINAL LATA 350 ML"                     # official CEST text close enough to the product for the (conservative) description match
    hub.session.commit()
    for suffix in ("", "-wal", "-shm"):
        try:
            (ROOT / "scratch_enrich" / f"enrich_ph_e2e.db{suffix}").unlink()
        except FileNotFoundError:
            pass
    store = E.EnrichmentStore(ROOT / "scratch_enrich" / "enrich_ph_e2e.db")
    worker = E.EnrichmentWorker(hub=hub, store=store, read_conn=lambda: base.connect(False), write_conn=lambda: base.connect(True), create_reprocess=lambda codes: None)

    class Stop:
        stop = False
    stop = Stop()
    threading.Thread(target=worker.run_forever, args=(stop,), daemon=True).start()
    ean = ce.gtin("789700000001")
    hub.features = {"features_configured": True, "corrector_enabled": True, "enrichment_mode": "DRY_RUN"}
    worker._features_at = -999
    time.sleep(6)                                                                 # baseline taken while the function is active
    insert("PH001", "00000000", ean, cclasstrib="200009")
    time.sleep(9)
    checks["PLACEHOLDER_PRODUCT_DETECTED_DRY_RUN"] = store.get("PH001") is not None and hub.calls >= 1
    checks["DRY_RUN_ZERO_WRITES"] = row("PH001") == ("00000000", None, None, "200009")
    decisions = [it for rep in hub.reports for it in rep["fields"] if rep["product_code"] == "PH001"]
    checks["DRY_RUN_DECISION_GENERATED_FOR_NCM"] = any(d["field"] == "CLASSIFICACAO_FISCAL" and d["outcome"] == "DRY_RUN" and d["old"] == "00000000" and d["new"] == "22021000" for d in decisions)
    hub.features = {"features_configured": True, "corrector_enabled": True, "enrichment_mode": "ENABLED"}
    worker._features_at = -999
    worker._auth_cache = (None, 0.0)
    insert("PH002", "00000000", ean, cclasstrib="200009")                          # same real scenario, function already ENABLED
    t0 = time.monotonic()
    while time.monotonic() - t0 < 25 and row("PH002")[0] == "00000000":
        time.sleep(0.2)
    time.sleep(4)                                                                 # remaining fields + audit report follow the NCM write
    r2 = row("PH002")
    checks["ENABLED_PLACEHOLDER_REPLACED"] = r2[0] == "22021000"
    checks["CEST_IPI_ONLY_WHEN_SAFE"] = r2[2] == 0.0 and r2[1] == "0300700"
    checks["CCLASSTRIB_OPERATOR_VALUE_UNTOUCHED"] = r2[3] == "200009"
    applied = [it for rep in hub.reports for it in rep["fields"] if rep["product_code"] == "PH002" and it["outcome"] == "APPLIED"]
    checks["AUDIT_RECORDS_THE_REPLACED_PLACEHOLDER"] = any(a["field"] == "CLASSIFICACAO_FISCAL" and a["old"] == "00000000" for a in applied)
    # negative: real NCM / unlisted filler are preserved even though the KB says 22021000
    insert("PH003", "19059090", ean); insert("PH004", "99999999", ean); insert("PH005", "22021000", ean)
    time.sleep(12)
    checks["EXISTING_REAL_VALUE_PRESERVED"] = row("PH003")[0] == "19059090" and row("PH005")[0] == "22021000"
    checks["UNLISTED_FILLER_NOT_OVERWRITTEN"] = row("PH004")[0] == "99999999"
    calls_before, writes_before = hub.calls, sum(1 for rep in hub.reports for it in rep["fields"] if it["outcome"] == "APPLIED")
    time.sleep(14)
    writes_after = sum(1 for rep in hub.reports for it in rep["fields"] if it["outcome"] == "APPLIED")
    checks["SECOND_RUN_WRITES_0"] = writes_after == writes_before and row("PH002")[0] == "22021000"
    stop.stop = True
    result = {"copy_only": True, "checks": checks, "ALL_PASS": all(checks.values()), "PH002": row("PH002")}
    (ROOT / "docs" / "runs" / "enrichment_placeholder_e2e.json").write_text(json.dumps(result, indent=1), encoding="utf-8")
    print(json.dumps(result, indent=1))
    sys.exit(0 if result["ALL_PASS"] else 1)


if __name__ == "__main__":
    main()