gustavosantos/GTI_GERENCIADOR_FISCAL
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: OSCBR optional provider, re-baseline after inactivity, field audit, provider UI/feature matrix tests, benchmark chain; 1.3.1

Browse Source 
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
gti
2026-09-26 00:48:18 -03:00
co-authored by Claude Sonnet 5
parent c3c9d1b4e0
commit e6bcf12d53
27 changed files with 1015 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/enrichment_benchmark.py
+10 -4
View File
@@ -17,13 +17,13 @@ ROOT = Path(__file__).resolve().parents[1]
sys.path.insert(0, str(ROOT))
import httpx # noqa: E402
from central.app.enrichment.providers import Cosmos, OpenBeautyFacts, OpenFoodFacts, OpenProductsFacts, ProviderError, UpcItemDb, USER_AGENT # noqa: E402
from central.app.enrichment.providers import Cosmos, Oscbr, OpenBeautyFacts, OpenFoodFacts, OpenProductsFacts, ProviderError, UpcItemDb, USER_AGENT # noqa: E402
PACE = {"upcitemdb": 2.6, "openfoodfacts": 5.2, "openproductsfacts": 5.2, "openbeautyfacts": 5.2, "cosmos": 1.0} # seconds between calls: comfortably under the documented burst / per-minute limits
PACE = {"oscbr": 3.2, "upcitemdb": 2.6, "openfoodfacts": 5.2, "openproductsfacts": 5.2, "openbeautyfacts": 5.2, "cosmos": 1.0} # seconds between calls: comfortably under the documented burst / per-minute limits
def bench(provider, items):
out = {"provider": provider.name, "configured": provider.configured, "sample_size": 0, "found": 0, "not_found": 0, "with_description": 0, "with_brand": 0, "with_ncm": 0, "with_cest": 0, "errors": 0, "error_kinds": {}, "latencies_ms": []}
out = {"provider": provider.name, "configured": provider.configured, "sample_size": 0, "found": 0, "not_found": 0, "with_description": 0, "with_brand": 0, "with_ncm": 0, "with_cest": 0, "errors": 0, "error_kinds": {}, "latencies_ms": [], "per_gtin": {}}
if not provider.configured:
out["status"] = "NOT_CONFIGURED"
return out
@@ -40,6 +40,7 @@ def bench(provider, items):
continue
out["sample_size"] += 1
out["latencies_ms"].append(int((time.monotonic() - started) * 1000))
out["per_gtin"][item["gtin"]] = {"found": product.found, "description": bool(product.title), "ncm": bool(product.ncm), "cest": bool(product.cest)}
if product.found:
out["found"] += 1
out["with_description"] += bool(product.title)
@@ -65,12 +66,17 @@ def main():
args = ap.parse_args()
items = json.loads(Path(args.sample).read_text(encoding="utf-8"))[: args.limit]
client = httpx.Client(timeout=8.0, headers={"User-Agent": USER_AGENT})
providers = [Cosmos(client, os.environ.get("COSMOS_TOKEN")), UpcItemDb(client), OpenFoodFacts(client), OpenProductsFacts(client), OpenBeautyFacts(client)]
providers = [Cosmos(client, os.environ.get("COSMOS_TOKEN")), Oscbr(client, None, os.environ.get("OSCBR_USER"), os.environ.get("OSCBR_PASSWORD")), UpcItemDb(client), OpenFoodFacts(client), OpenProductsFacts(client), OpenBeautyFacts(client)]
only = {n for n in args.only.split(",") if n}
out = Path(args.out)
result = json.loads(out.read_text(encoding="utf-8")) if only and out.exists() else {"measured_at": time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime()), "sample_source": "lab ERP databases (read-only), valid GTINs only", "limit_per_provider": args.limit, "providers": []}
measured = [bench(p, items) for p in providers if not only or p.name in only]
result["providers"] = [p for p in result["providers"] if p["provider"] not in {m["provider"] for m in measured}] + measured
per = [p.get("per_gtin", {}) for p in result["providers"]]
tested = sorted({g for d in per for g in d})
def rate(key):
return round(sum(1 for g in tested if any(d.get(g, {}).get(key) for d in per)) / len(tested), 3) if tested else None
result["chain"] = {"gtins_tested": len(tested), "ANY_PROVIDER_FOUND_RATE": rate("found"), "ANY_PROVIDER_NCM_RATE": rate("ncm"), "ANY_PROVIDER_CEST_RATE": rate("cest"), "ANY_PROVIDER_DESCRIPTION_RATE": rate("description")}
Path(args.out).write_text(json.dumps(result, ensure_ascii=False, indent=1), encoding="utf-8")
print(json.dumps(result, ensure_ascii=False, indent=1))