fix: site/ with __init__.py — proper Python package, no stdlib conflict

site/services/metrics.py

@@ -0,0 +1,88 @@
+"""Metrics — quality signals without golden dataset.
+
+Checks that work immediately:
+- Arithmetic: sum == price * qty (free signal of LLM/data errors)
+- JSON fix rate: how often _safe_json_parse has to repair LLM output
+"""
+from decimal import Decimal, InvalidOperation
+
+
+def check_arithmetic(ops: list) -> list[dict]:
+    """Check sum == price * qty for ADD/UPDATE operations.
+    Returns list of mismatches: [{action, name, price, qty, expected_sum, actual_sum, diff}]
+    """
+    mismatches = []
+    for op in ops:
+        action = op.get("action", "")
+        if action not in ("ADD", "UPDATE"):
+            continue
+
+        row = op.get("new_row") or op.get("new_values") or {}
+        price = _to_decimal(row.get("price"))
+        qty = _to_decimal(row.get("qty"))
+        actual_sum = _to_decimal(row.get("sum"))
+
+        if price is None or qty is None or actual_sum is None:
+            continue  # can't check without all three
+
+        expected = price * qty
+        if expected != actual_sum:
+            mismatches.append({
+                "action": action,
+                "name": row.get("name", "")[:100],
+                "price": float(price),
+                "qty": float(qty),
+                "expected_sum": float(expected),
+                "actual_sum": float(actual_sum),
+                "diff": float(actual_sum - expected),
+            })
+    return mismatches
+
+
+class ClassifyMetrics:
+    """Track _safe_json_parse fix rate per batch."""
+    def __init__(self):
+        self.total = 0
+        self.fixes = 0  # how many times JSON needed repair
+
+    def record(self, needed_fix: bool):
+        self.total += 1
+        if needed_fix:
+            self.fixes += 1
+
+    @property
+    def fix_rate(self) -> float:
+        return self.fixes / self.total if self.total else 0.0
+
+    def summary(self) -> dict:
+        return {
+            "total_classifications": self.total,
+            "json_fixes": self.fixes,
+            "json_fix_rate": round(self.fix_rate, 3),
+        }
+
+
+def _to_decimal(val) -> Decimal | None:
+    """Safe conversion to Decimal with number normalization."""
+    if val is None or val == "":
+        return None
+    try:
+        s = str(val).replace("\xa0", "").replace(" ", "").replace(",", ".")
+        return Decimal(s)
+    except (InvalidOperation, ValueError):
+        return None
+
+
+def normalize_date(ds: str) -> str | None:
+    """Normalize date to YYYY-MM-DD. Handles DD.MM.YYYY, YYYY-MM-DD, etc."""
+    if not ds:
+        return None
+    import re
+    # DD.MM.YYYY → YYYY-MM-DD
+    m = re.match(r"(\d{2})\.(\d{2})\.(\d{4})", ds)
+    if m:
+        return f"{m.group(3)}-{m.group(2)}-{m.group(1)}"
+    # YYYY-MM-DD — already canonical
+    if re.match(r"\d{4}-\d{2}-\d{2}", ds):
+        return ds
+    return ds  # return as-is if unrecognized format