ERP/bot/tools/test_matching.py

"""Phase 3-5 tests for entity matching (mock by default; live with RUN_LIVE=1).

    docker compose exec bot python tools/test_matching.py            # mock only
    docker compose exec -e RUN_LIVE=1 bot python tools/test_matching.py   # + real NLU + Jev

The live section calls DeepSeek (NLU) and TypeSafe (Jev) with the REAL keys
from bot/.env — it never sends anything to Bale and never creates drafts.
"""
import asyncio
import os
import sys
from types import SimpleNamespace
from pathlib import Path

sys.path.insert(0, str(Path(__file__).resolve().parents[1]))

from app import matching
from app.config import settings
from app.nlu import normalize_text
from app.resolve import Candidate

PASSED: list[str] = []
FAILED: list[str] = []


def check(name: str, ok: bool, extra: str = "") -> None:
    (PASSED if ok else FAILED).append(name)
    print(f"{'PASS' if ok else 'FAIL'}  {name}{'  — ' + str(extra) if extra else ''}")


class FakeResolver:
    async def projects(self):
        return [Candidate(id="p1", name="دفتر"), Candidate(id="p2", name="منشانه")]

    async def all_suppliers(self):
        return [Candidate(id="s1", name="بازرگانی مصطفوی",
                          extra={"location": "اصفهان", "category_name": "مصالح"})]

    async def all_materials(self):
        return [Candidate(id="m1", name="گچ و خاک", extra={"canonical_unit_id": 2})]

    async def brands(self):
        return [Candidate(id="b1", name="سیمان تهران")]

    async def specs(self):
        return [Candidate(id="سایز ۱۴", name="سایز ۱۴")]

    async def units(self):
        return [Candidate(id="u1", name="کیسه"), Candidate(id="u2", name="عدد")]


def make_fake_ask(answers_by_mention: dict, model: str = "jev-1.13.0"):
    async def fake_ask(state, questions):
        if fake_ask.fail:
            return None
        return {"answers": answers_by_mention, "usage": {"input_tokens": 1, "output_tokens": 1},
                "model": model, "latency_ms": 7}
    fake_ask.fail = False
    return fake_ask


async def mock_tests() -> None:
    ctx = SimpleNamespace(resolver=FakeResolver())
    orig_ask = matching.jev_ask

    # 1) routing bands: exact / ambiguity / low-trust / new + variant grouping
    matching.jev_ask = make_fake_ask({
        "mention_0": {"choice": "منشانه", "confidence": 0.9,
                      "probabilities": {"منشانه": 0.95, "_none": 0.05}},
        "mention_1": {"choice": "دفتر", "confidence": 0.7,
                      "probabilities": {"دفتر": 0.73, "منشانه": 0.15, "_none": 0.12}},
        "mention_2": {"choice": "_none", "confidence": 0.9,
                      "probabilities": {"_none": 0.94}},
        "mention_3": {"choice": "دفتر", "confidence": 0.5,
                      "probabilities": {"دفتر": 0.52, "_none": 0.48}},
    })
    mentions = [
        {"field": "project", "variants": ["منشیانه"]},
        {"field": "project", "variants": ["دفتر", "دفر"]},
        {"field": "project", "variants": ["چیز عجیب"]},
        {"field": "project", "variants": ["دفر دو"]},
    ]
    res = await matching.resolve_mentions(ctx, {"items": []}, mentions, None)
    r0 = matching.lookup(res, "منشیانه")
    r1 = matching.lookup(res, "دفر")          # variant key resolves too
    r2 = matching.lookup(res, "چیز عجیب")
    check("exact band -> status exact + id", r0 and r0["status"] == "exact" and r0["id"] == "p2")
    check("mid band -> ambiguity + candidates", r1 and r1["status"] == "ambiguity"
          and r1["candidates"][0]["name"] == "دفتر")
    check("variant of same mention shares one result", r1 is r0 if False else
          (r1 and matching.lookup(res, "دفتر") is r1))
    check("_none / low conf -> new", r2 and r2["status"] == "new")
    check("below-floor pick -> NO result (difflib fallback keeps its chance)",
          matching.lookup(res, "دفر دو") is None)
    check("below-floor pick did not pollute other mentions", r1 and r1["status"] == "ambiguity")

    # 2) Jev failure -> empty map (callers fall back to difflib)
    matching.jev_ask = make_fake_ask({})
    matching.jev_ask.fail = True
    res_fail = await matching.resolve_mentions(ctx, {"items": []}, mentions, None)
    check("jev failure -> empty results (difflib fallback path)", res_fail == {})

    # 3) apply_exact writes supplier/project ids into a payload
    payload = {"items": []}
    matching.apply_exact(payload, {"field": "project", "id": "p2", "name": "منشانه",
                                   "variants": ["منشیانه"], "scores": {}})
    matching.apply_exact(payload, {"field": "supplier", "id": "s1", "name": "بازرگانی مصطفوی",
                                   "extra": {"location": "اصفهان"}, "variants": ["مستفدی"]})
    check("apply_exact -> project_id/resolved_projects/project_ids",
          payload.get("project_id") == "p2"
          and payload["resolved_projects"].get("منشیانه") == "p2")
    check("apply_exact -> supplier_id/name/extra",
          payload.get("supplier_id") == "s1" and payload.get("supplier_location") == "اصفهان")

    # 4) material/unit/brand/spec application on items
    payload2 = {"items": [{"material_name": "مصطفی", "unit_name": "کیسه",
                           "brand_name": "سیمان تهران", "specs": ["سایز 14"]}]}
    matching.apply_choice(payload2, "material", {"id": "m1", "name": "گچ و خاک",
                                                 "extra": {"canonical_unit_id": 2}},
                          ["مصطفی"])
    matching.apply_choice(payload2, "unit", {"id": "u1", "name": "کیسه"}, ["کیسه"])
    matching.normalize_brand_spec(payload2, {normalize_text("سایز 14"): {
        "field": "spec", "status": "exact", "name": "سایز ۱۴", "id": "سایز ۱۴",
        "variants": ["سایز 14"]}})
    it = payload2["items"][0]
    check("material/unit applied on matching items",
          it["material_id"] == "m1" and it["unit_id"] == "u1" and it["unit_explicit"] is True)
    check("spec normalization (spelling only)", it["specs"][0] == "سایز ۱۴")

    # 5) create_ambiguities builds an entity_match entry with percentages
    payload3 = {"items": [], "ambiguities": []}
    jev_map = {normalize_text("منشیانه"): {
        "field": "project", "status": "ambiguity", "variants": ["منشیانه"],
        "candidates": [{"id": "p2", "name": "منشانه", "prob": 0.8},
                       {"id": "p1", "name": "دفتر", "prob": 0.02}]}}
    matching.create_ambiguities(payload3, jev_map)
    ambs = payload3["ambiguities"]
    check("entity_match ambiguity created with candidates + details",
          len(ambs) == 1 and ambs[0]["kind"] == "entity_match"
          and len(ambs[0]["candidates"]) == 2 and "۸۰٪" in ambs[0]["details"])
    matching.create_ambiguities(payload3, jev_map)   # idempotent
    check("create_ambiguities is deduped", len(payload3["ambiguities"]) == 1)

    matching.jev_ask = orig_ask


# ---------------------------------------------------------------------------
# live section (real NLU + real Jev) — opt-in and Bale-free
# ---------------------------------------------------------------------------

HARNESS_TRANSCRIPT = (
    "مدل 1 (Whisper): الان شبت بخیر می خواستیم که بیست و پنج تا کیسه گچ و خاک از مصطفوی بخریم "
    "و کنارش هم یه پنجاه تا کیسه سیمان پنجاه کیلویی. خریدمون هم عمدتا برای منشیانه و دفتر. "
    "پیش فاکتورم گفته تا حدودا بیست روزی اوکیه.\n"
    "مدل 2 (Vosk): میخواستیم 25 تا کیسه گچ و خاک از مستفدی بخریم و کنارشم یه 50 تا کیسه سیمان "
    "50 کیلویی، خریدمون هم برای منشیانه و دفتر."
)


async def live_tests() -> None:
    from app.api.client import ErpClient
    from app.resolve import Resolver
    from app.nlu import understand

    api = ErpClient(settings.API_BASE_URL, settings.API_TIMEOUT_SECONDS, settings.SERVICE_TOKEN)
    ctx = SimpleNamespace(resolver=Resolver(api))

    print("\n--- LIVE: NLU entity_mentions ---")
    result = await understand(settings, HARNESS_TRANSCRIPT)
    mentions = result.get("entity_mentions") or []
    print("intent:", result.get("intent"), "| mentions:", mentions)
    check("live NLU produced entity_mentions", len(mentions) >= 2, f"{len(mentions)} mentions")
    sup = next((m for m in mentions if m["field"] == "supplier"), None)
    check("voice spellings grouped into ONE supplier mention",
          bool(sup) and len(sup["variants"]) >= 2, str(sup))

    print("\n--- LIVE: Jev per-field matching (real data) ---")
    jev_map = await matching.resolve_mentions(ctx, result.get("patch") or {}, mentions, None)
    for key, r in sorted(jev_map.items()):
        print(f"  {key!r}: {r['status']} -> {r.get('name')!r} conf={r.get('confidence')}")
    check("live matching returned results", len(jev_map) > 0, f"{len(jev_map)} variants")


async def main() -> None:
    await mock_tests()
    if os.environ.get("RUN_LIVE") == "1":
        if not settings.TYPESAFE_API_KEY:
            check("live section requires TYPESAFE_API_KEY", False, "bot/.env not mounted?")
        else:
            await live_tests()
    else:
        print("\n(live section skipped — run with RUN_LIVE=1 to hit real NLU + Jev)")

    total = len(PASSED) + len(FAILED)
    print(f"\n{len(PASSED)}/{total} passed")
    if FAILED:
        print("FAILED:", FAILED)
        raise SystemExit(1)


if __name__ == "__main__":
    asyncio.run(main())