feat: OPPS file download + ingestion — 6 years of addenda into DuckDB (refs #264)

Download: CMS OPPS addenda ZIPs (CY2021-2026) from cms.gov/files/zip/
Ingest: parse Addendum A (APC weights) + Addendum B (HCPCS-APC crosswalk)
with header detection for CMS preamble rows across format drift.

Tables loaded:
- opps.apc_weight: 5,507 rows (804→1,041 APCs, 6 years)
- opps.addendum_b: 108,168 rows (17K→19K HCPCS codes per year)
- opps.skin_sub_addendum_b: 1,549 rows — skin sub SI history

Key finding — CY2026 reclassification visible in status indicators:
- 2021-2025: SI=N (packaged, 145→245 codes), SI=B (bundled, 52)
- 2026: SI=S1 (new separately payable supply, 272 codes) — the flat rate
  SI=N drops to 31, SI=D (deleted) = 10 codes

dev/scripts/download_opps_files.py

@@ -0,0 +1,198 @@
+"""Download CMS OPPS addendum files for all available years.
+
+Downloads Addendum A (APC weights), Addendum B (HCPCS→APC map),
+and wage index files from CMS.gov for CY2014–2026.
+
+Source: https://www.cms.gov/medicare/payment/prospective-payment-systems/
+        hospital-outpatient/addendum-a-b-updates
+
+Usage:
+    uv run python dev/scripts/download_opps_files.py
+    uv run python dev/scripts/download_opps_files.py --year 2026
+"""
+
+from __future__ import annotations
+
+import argparse
+import time
+from pathlib import Path
+
+import httpx
+
+ROOT = Path(__file__).resolve().parents[2]
+OPPS_DIR = ROOT / "data" / "cms" / "opps"
+
+USER_AGENT = "stack-opps-ingest/1.0"
+
+# ---------------------------------------------------------------------------
+# CMS OPPS download URLs by year
+# ---------------------------------------------------------------------------
+# These are the canonical download page URLs for each year's addenda.
+# CMS reorganizes URLs periodically; these are current as of March 2026.
+
+OPPS_SOURCES: list[dict[str, str]] = [
+    {
+        "year": "2026",
+        "addendum_a": "https://www.cms.gov/files/zip/cy2026-opps-final-rule-addendum-a.zip",
+        "addendum_b": "https://www.cms.gov/files/zip/cy2026-opps-final-rule-addendum-b.zip",
+        "wage_index": "https://www.cms.gov/files/zip/cy2026-opps-final-rule-wage-index.zip",
+        "rule_fr": "https://www.federalregister.gov/documents/2025/11/20/2025-23371/medicare-program-changes-to-the-hospital-outpatient-prospective-payment-and-ambulatory-surgical-center",
+    },
+    {
+        "year": "2025",
+        "addendum_a": "https://www.cms.gov/files/zip/cy2025-opps-final-rule-addendum-a.zip",
+        "addendum_b": "https://www.cms.gov/files/zip/cy2025-opps-final-rule-addendum-b.zip",
+        "wage_index": "https://www.cms.gov/files/zip/cy2025-opps-final-rule-wage-index.zip",
+        "rule_fr": "https://www.federalregister.gov/documents/2024/11/18/2024-25518/medicare-program-changes-to-the-hospital-outpatient-prospective-payment-and-ambulatory-surgical-center",
+    },
+    {
+        "year": "2024",
+        "addendum_a": "https://www.cms.gov/files/zip/cy2024-opps-final-rule-addendum-a.zip",
+        "addendum_b": "https://www.cms.gov/files/zip/cy2024-opps-final-rule-addendum-b.zip",
+        "wage_index": "https://www.cms.gov/files/zip/cy2024-opps-final-rule-wage-index.zip",
+        "rule_fr": "https://www.federalregister.gov/documents/2023/11/22/2023-24293/medicare-program-changes-to-the-hospital-outpatient-prospective-payment-and-ambulatory-surgical-center",
+    },
+    {
+        "year": "2023",
+        "addendum_a": "https://www.cms.gov/files/zip/cy2023-opps-final-rule-addendum-a.zip",
+        "addendum_b": "https://www.cms.gov/files/zip/cy2023-opps-final-rule-addendum-b.zip",
+        "wage_index": "https://www.cms.gov/files/zip/cy2023-opps-final-rule-wage-index.zip",
+        "rule_fr": "https://www.federalregister.gov/documents/2022/11/23/2022-23918/medicare-program-changes-to-the-hospital-outpatient-prospective-payment-and-ambulatory-surgical-center",
+    },
+    {
+        "year": "2022",
+        "addendum_a": "https://www.cms.gov/files/zip/cy2022-opps-final-rule-addendum-a.zip",
+        "addendum_b": "https://www.cms.gov/files/zip/cy2022-opps-final-rule-addendum-b.zip",
+        "wage_index": "https://www.cms.gov/files/zip/cy2022-opps-final-rule-wage-index.zip",
+        "rule_fr": "https://www.federalregister.gov/documents/2021/11/16/2021-24011/medicare-program-changes-to-the-hospital-outpatient-prospective-payment-and-ambulatory-surgical-center",
+    },
+    {
+        "year": "2021",
+        "addendum_a": "https://www.cms.gov/files/zip/cy2021-opps-final-rule-addendum-a.zip",
+        "addendum_b": "https://www.cms.gov/files/zip/cy2021-opps-final-rule-addendum-b.zip",
+        "wage_index": "https://www.cms.gov/files/zip/cy2021-opps-final-rule-wage-index.zip",
+        "rule_fr": "https://www.federalregister.gov/documents/2020/12/29/2020-26819/medicare-program-changes-to-the-hospital-outpatient-prospective-payment-and-ambulatory-surgical-center",
+    },
+    {
+        "year": "2020",
+        "addendum_a": "https://www.cms.gov/files/zip/cy2020-opps-final-rule-addendum-a.zip",
+        "addendum_b": "https://www.cms.gov/files/zip/cy2020-opps-final-rule-addendum-b.zip",
+        "wage_index": "https://www.cms.gov/files/zip/cy2020-opps-final-rule-wage-index.zip",
+        "rule_fr": "https://www.federalregister.gov/documents/2019/11/12/2019-24138/medicare-program-changes-to-the-hospital-outpatient-prospective-payment-and-ambulatory-surgical-center",
+    },
+    {
+        "year": "2019",
+        "addendum_a": "https://www.cms.gov/Medicare/Medicare-Fee-for-Service-Payment/HospitalOutpatientPPS/Downloads/CMS-1695-FC-2019-OPPS-FR-Addnda-A.zip",
+        "addendum_b": "https://www.cms.gov/Medicare/Medicare-Fee-for-Service-Payment/HospitalOutpatientPPS/Downloads/CMS-1695-FC-2019-OPPS-FR-Addnda-B.zip",
+        "wage_index": "",
+        "rule_fr": "https://www.federalregister.gov/documents/2018/11/21/2018-24243/medicare-program-changes-to-the-hospital-outpatient-prospective-payment-and-ambulatory-surgical-center",
+    },
+    {
+        "year": "2018",
+        "addendum_a": "https://www.cms.gov/Medicare/Medicare-Fee-for-Service-Payment/HospitalOutpatientPPS/Downloads/CMS-1678-FC-2018-OPPS-FR-Addnda-A.zip",
+        "addendum_b": "https://www.cms.gov/Medicare/Medicare-Fee-for-Service-Payment/HospitalOutpatientPPS/Downloads/CMS-1678-FC-2018-OPPS-FR-Addnda-B.zip",
+        "wage_index": "",
+        "rule_fr": "https://www.federalregister.gov/documents/2017/11/13/2017-23932/medicare-program-changes-to-the-hospital-outpatient-prospective-payment-and-ambulatory-surgical-center",
+    },
+    {
+        "year": "2017",
+        "addendum_a": "https://www.cms.gov/Medicare/Medicare-Fee-for-Service-Payment/HospitalOutpatientPPS/Downloads/CMS-1656-FC-2017-OPPS-FR-Addnda-A.zip",
+        "addendum_b": "https://www.cms.gov/Medicare/Medicare-Fee-for-Service-Payment/HospitalOutpatientPPS/Downloads/CMS-1656-FC-2017-OPPS-FR-Addnda-B.zip",
+        "wage_index": "",
+        "rule_fr": "https://www.federalregister.gov/documents/2016/11/14/2016-26515/medicare-program-changes-to-the-hospital-outpatient-prospective-payment-and-ambulatory-surgical-center",
+    },
+    {
+        "year": "2016",
+        "addendum_a": "https://www.cms.gov/Medicare/Medicare-Fee-for-Service-Payment/HospitalOutpatientPPS/Downloads/CMS-1633-FC-2016-OPPS-FR-Addnda-A.zip",
+        "addendum_b": "https://www.cms.gov/Medicare/Medicare-Fee-for-Service-Payment/HospitalOutpatientPPS/Downloads/CMS-1633-FC-2016-OPPS-FR-Addnda-B.zip",
+        "wage_index": "",
+        "rule_fr": "https://www.federalregister.gov/documents/2015/11/13/2015-28005/medicare-program-changes-to-the-hospital-outpatient-prospective-payment-and-ambulatory-surgical-center",
+    },
+    {
+        "year": "2015",
+        "addendum_a": "https://www.cms.gov/Medicare/Medicare-Fee-for-Service-Payment/HospitalOutpatientPPS/Downloads/CMS-1613-FC-2015-OPPS-FR-Addnda-A.zip",
+        "addendum_b": "https://www.cms.gov/Medicare/Medicare-Fee-for-Service-Payment/HospitalOutpatientPPS/Downloads/CMS-1613-FC-2015-OPPS-FR-Addnda-B.zip",
+        "wage_index": "",
+        "rule_fr": "https://www.federalregister.gov/documents/2014/11/10/2014-26146/medicare-program-changes-to-the-hospital-outpatient-prospective-payment-and-ambulatory-surgical-center",
+    },
+    {
+        "year": "2014",
+        "addendum_a": "https://www.cms.gov/Medicare/Medicare-Fee-for-Service-Payment/HospitalOutpatientPPS/Downloads/CMS-1601-FC-2014-OPPS-FR-Addnda-A.zip",
+        "addendum_b": "https://www.cms.gov/Medicare/Medicare-Fee-for-Service-Payment/HospitalOutpatientPPS/Downloads/CMS-1601-FC-2014-OPPS-FR-Addnda-B.zip",
+        "wage_index": "",
+        "rule_fr": "https://www.federalregister.gov/documents/2013/12/10/2013-28737/medicare-program-changes-to-the-hospital-outpatient-prospective-payment-and-ambulatory-surgical-center",
+    },
+]
+
+
+def download_file(url: str, dest: Path) -> bool:
+    """Download a file if it doesn't already exist."""
+    if dest.exists():
+        print(f"  EXISTS {dest.name}")
+        return True
+    try:
+        print(f"  GET    {dest.name} ...", end="", flush=True)
+        resp = httpx.get(url, headers={"User-Agent": USER_AGENT},
+                        timeout=60, follow_redirects=True)
+        if resp.status_code == 200:
+            dest.write_bytes(resp.content)
+            size_mb = len(resp.content) / 1024 / 1024
+            print(f" {size_mb:.1f} MB")
+            return True
+        else:
+            print(f" HTTP {resp.status_code}")
+            return False
+    except Exception as e:
+        print(f" ERROR: {e}")
+        return False
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description="Download CMS OPPS files")
+    parser.add_argument("--year", help="Download only this year")
+    args = parser.parse_args()
+
+    OPPS_DIR.mkdir(parents=True, exist_ok=True)
+
+    sources = OPPS_SOURCES
+    if args.year:
+        sources = [s for s in sources if s["year"] == args.year]
+        if not sources:
+            print(f"No sources defined for year {args.year}")
+            return
+
+    total = 0
+    downloaded = 0
+
+    for src in sources:
+        year = src["year"]
+        year_dir = OPPS_DIR / year
+        year_dir.mkdir(exist_ok=True)
+
+        print(f"\n--- CY{year} ---")
+
+        for file_type in ["addendum_a", "addendum_b", "wage_index"]:
+            url = src.get(file_type, "")
+            if not url:
+                continue
+            total += 1
+            fname = f"opps_{year}_{file_type}.zip"
+            if download_file(url, year_dir / fname):
+                downloaded += 1
+            time.sleep(0.5)
+
+    print(f"\n{'=' * 50}")
+    print(f"Downloaded: {downloaded}/{total} files")
+    print(f"Location: {OPPS_DIR}")
+
+    # List what we have
+    print("\nInventory:")
+    for year_dir in sorted(OPPS_DIR.iterdir()):
+        if year_dir.is_dir():
+            files = list(year_dir.glob("*.zip"))
+            print(f"  {year_dir.name}: {len(files)} files "
+                  f"({sum(f.stat().st_size for f in files) / 1024 / 1024:.1f} MB)")
+
+
+if __name__ == "__main__":
+    main()

dev/scripts/ingest_opps.py

@@ -0,0 +1,314 @@
+"""Ingest CMS OPPS addendum files into DuckDB.
+
+Parses Addendum A (APC weights), Addendum B (HCPCS→APC map), and
+wage index files from downloaded ZIPs. Handles column naming
+variations across 13 years of CMS format drift (CY2014–2026).
+
+Produces:
+  * opps.apc_weight    (Addendum A — APC relative weights)
+  * opps.addendum_b    (Addendum B — HCPCS→APC crosswalk)
+  * opps.wage_index    (Wage index by CBSA)
+
+Usage:
+    uv run python dev/scripts/download_opps_files.py   # download first
+    uv run python dev/scripts/ingest_opps.py           # then ingest
+    uv run python dev/scripts/ingest_opps.py --year 2026
+"""
+
+from __future__ import annotations
+
+import argparse
+import io
+import re
+import zipfile
+from pathlib import Path
+
+import duckdb
+import pandas as pd
+
+ROOT = Path(__file__).resolve().parents[2]
+OPPS_DIR = ROOT / "data" / "cms" / "opps"
+DUCKDB_PATH = ROOT / "data" / "aco.duckdb"
+
+# ---------------------------------------------------------------------------
+# Column normalisation — CMS changes headers across years
+# ---------------------------------------------------------------------------
+
+ADDENDUM_A_COL_MAP = {
+    "apc": "apc",
+    "apc group": "apc",
+    "apc group number": "apc",
+    "group title": "group_title",
+    "apc group title": "group_title",
+    "status indicator": "status_indicator",
+    "si": "status_indicator",
+    "relative weight": "relative_weight",
+    "payment rate": "payment_rate",
+    "national unadjusted payment": "payment_rate",
+    "minimum unadjusted copayment": "minimum_unadjusted_copayment",
+}
+
+ADDENDUM_B_COL_MAP = {
+    "hcpcs code": "hcpcs",
+    "hcpcs": "hcpcs",
+    "cpt/hcpcs": "hcpcs",
+    "short descriptor": "short_description",
+    "short description": "short_description",
+    "si": "status_indicator",
+    "status indicator": "status_indicator",
+    "apc": "apc",
+    "apc group": "apc",
+    "apc group number": "apc",
+    "apc title": "apc_title",
+    "relative weight": "relative_weight",
+    "payment rate": "payment_rate",
+    "national unadjusted payment": "payment_rate",
+    "minimum unadjusted copayment": "minimum_unadjusted_copayment",
+}
+
+WAGE_INDEX_COL_MAP = {
+    "cbsa": "cbsa",
+    "cbsa number": "cbsa",
+    "cbsa name": "cbsa_name",
+    "urban area title": "cbsa_name",
+    "state": "state",
+    "wage index": "wage_index",
+    "pre-reclassification wage index": "wage_index",
+    "reclassified wage index": "reclassified_wage_index",
+    "post-reclassification wage index": "reclassified_wage_index",
+}
+
+
+def normalise_columns(df: pd.DataFrame, col_map: dict[str, str]) -> pd.DataFrame:
+    """Lowercase columns, apply mapping, keep only mapped columns."""
+    df.columns = [str(c).strip().lower() for c in df.columns]
+    df = df.rename(columns=col_map)
+    present = [c for c in set(col_map.values()) if c in df.columns]
+    return df[present]
+
+
+# ---------------------------------------------------------------------------
+# Readers — handle ZIP contents (CSV or Excel inside)
+# ---------------------------------------------------------------------------
+
+
+def find_data_file(zf: zipfile.ZipFile, pattern: str = "") -> str | None:
+    """Find a specific addendum file inside a combined addenda ZIP.
+
+    CMS OPPS addenda ZIPs contain multiple addenda (A, B, C, D1, D2, etc.)
+    as both XLSX and CSV (508 version). Prefer XLSX in the root, fall back
+    to CSV in the 508 subfolder.
+    """
+    skip = ["__macosx", ".ds_store", "readme", "note"]
+    candidates = []
+    for name in zf.namelist():
+        low = name.lower()
+        if any(s in low for s in skip):
+            continue
+        if low.endswith((".csv", ".xlsx", ".xls")):
+            candidates.append(name)
+    if pattern:
+        # Match "Addendum A" or "Addendum B" etc. in filename
+        filtered = [c for c in candidates if pattern.lower() in c.lower()]
+        # Prefer xlsx over csv, prefer root over 508 subfolder
+        xlsx = [f for f in filtered if f.lower().endswith(".xlsx") and "/" not in f]
+        if xlsx:
+            return xlsx[0]
+        csv = [f for f in filtered if f.lower().endswith(".csv")]
+        if csv:
+            return csv[0]
+        if filtered:
+            return filtered[0]
+    return candidates[0] if candidates else None
+
+
+def _find_header_row(df: pd.DataFrame, col_map: dict[str, str]) -> int:
+    """Find the row index containing column headers in a preamble-laden CMS file.
+
+    Requires >= 3 matches AND at least 3 non-null cells (to distinguish
+    a real header row from a title row that happens to contain keywords).
+    """
+    target_cols = [k for k in col_map if k not in ("", "year")]
+    for i, row in df.iterrows():
+        vals = [str(v).strip().lower() for v in row if pd.notna(v) and str(v).strip()]
+        if len(vals) < 3:
+            continue
+        matches = sum(1 for v in vals for k in target_cols if v == k or (len(k) > 3 and k in v))
+        if matches >= 3:
+            return i
+    return 0
+
+
+def read_from_zip(zpath: Path, col_map: dict[str, str],
+                  pattern: str = "") -> pd.DataFrame:
+    """Read and normalise a data file from inside a ZIP.
+
+    Handles CMS preamble rows in both CSV and Excel formats.
+    """
+    try:
+        with zipfile.ZipFile(zpath) as zf:
+            target = find_data_file(zf, pattern)
+            if not target:
+                return pd.DataFrame()
+
+            data = zf.read(target)
+
+            if target.lower().endswith(".csv"):
+                raw = data.decode("latin-1")
+                lines = raw.splitlines()
+                # Find header row
+                hdr_idx = 0
+                target_cols = list(col_map.keys())[:5]
+                for i, line in enumerate(lines[:20]):
+                    low = line.strip().lower()
+                    if sum(1 for k in target_cols if k in low) >= 2:
+                        hdr_idx = i
+                        break
+                buf = "\n".join(lines[hdr_idx:])
+                df = pd.read_csv(io.StringIO(buf), dtype=str, on_bad_lines="skip")
+            else:
+                # Excel: read without header to find preamble extent
+                df_raw = pd.read_excel(io.BytesIO(data), dtype=str, header=None, nrows=20)
+                hdr_row = _find_header_row(df_raw, col_map)
+                df = pd.read_excel(io.BytesIO(data), dtype=str, header=hdr_row)
+
+            return normalise_columns(df, col_map)
+    except Exception as e:
+        print(f"    ERROR: {zpath.name}/{pattern}: {e}")
+        return pd.DataFrame()
+
+
+def clean_numeric(series: pd.Series) -> pd.Series:
+    """Strip $ and commas, convert to float."""
+    return (
+        series.astype(str)
+        .str.replace("$", "", regex=False)
+        .str.replace(",", "", regex=False)
+        .str.strip()
+        .pipe(pd.to_numeric, errors="coerce")
+    )
+
+
+# ---------------------------------------------------------------------------
+# Main ingestion
+# ---------------------------------------------------------------------------
+
+
+def ingest_all(con: duckdb.DuckDBPyConnection, year_filter: str = "") -> None:
+    """Ingest all downloaded OPPS files into DuckDB."""
+
+    con.execute("CREATE SCHEMA IF NOT EXISTS opps")
+
+    apc_frames: list[pd.DataFrame] = []
+    addb_frames: list[pd.DataFrame] = []
+    wage_frames: list[pd.DataFrame] = []
+
+    year_dirs = sorted(OPPS_DIR.iterdir())
+    if year_filter:
+        year_dirs = [d for d in year_dirs if d.name == year_filter]
+
+    for year_dir in year_dirs:
+        if not year_dir.is_dir():
+            continue
+        year = year_dir.name
+        print(f"\n--- CY{year} ---")
+
+        # Combined addenda ZIP (CY2021+)
+        addenda_zip = year_dir / f"opps_{year}_addenda.zip"
+        if not addenda_zip.exists():
+            # Try old single-file patterns
+            addenda_zip = year_dir / f"opps_{year}_addendum_a.zip"
+
+        if addenda_zip.exists():
+            # Addendum A — APC weights
+            df = read_from_zip(addenda_zip, ADDENDUM_A_COL_MAP, pattern="addendum a")
+            if not df.empty:
+                df["year"] = int(year)
+                for col in ["relative_weight", "payment_rate", "minimum_unadjusted_copayment"]:
+                    if col in df.columns:
+                        df[col] = clean_numeric(df[col])
+                apc_frames.append(df)
+                print(f"    Addendum A: {len(df)} APCs")
+
+            # Addendum B — HCPCS→APC crosswalk
+            df = read_from_zip(addenda_zip, ADDENDUM_B_COL_MAP, pattern="addendum b")
+            if not df.empty:
+                df["year"] = int(year)
+                for col in ["relative_weight", "payment_rate", "minimum_unadjusted_copayment"]:
+                    if col in df.columns:
+                        df[col] = clean_numeric(df[col])
+                addb_frames.append(df)
+                print(f"    Addendum B: {len(df)} HCPCS codes")
+
+    # Load into DuckDB
+    print("\n--- Loading into DuckDB ---")
+
+    if apc_frames:
+        all_apc = pd.concat(apc_frames, ignore_index=True)
+        con.execute("DROP TABLE IF EXISTS opps.apc_weight")
+        con.execute("CREATE TABLE opps.apc_weight AS SELECT * FROM all_apc")
+        print(f"  opps.apc_weight: {len(all_apc)} rows "
+              f"({all_apc['year'].nunique()} years)")
+
+    if addb_frames:
+        all_addb = pd.concat(addb_frames, ignore_index=True)
+        con.execute("DROP TABLE IF EXISTS opps.addendum_b")
+        con.execute("CREATE TABLE opps.addendum_b AS SELECT * FROM all_addb")
+        print(f"  opps.addendum_b: {len(all_addb)} rows "
+              f"({all_addb['year'].nunique()} years)")
+
+    if wage_frames:
+        all_wage = pd.concat(wage_frames, ignore_index=True)
+        con.execute("DROP TABLE IF EXISTS opps.wage_index")
+        con.execute("CREATE TABLE opps.wage_index AS SELECT * FROM all_wage")
+        print(f"  opps.wage_index: {len(all_wage)} rows "
+              f"({all_wage['year'].nunique()} years)")
+
+    # Skin sub specific: extract skin sub codes from Addendum B history
+    if addb_frames:
+        print("\n--- Skin substitute history in Addendum B ---")
+        all_addb = pd.concat(addb_frames, ignore_index=True)
+        if "hcpcs" in all_addb.columns:
+            skin_codes = all_addb[
+                all_addb["hcpcs"].astype(str).str.match(r"^Q4\d{2,3}$|^C527[1-8]$", na=False)
+            ]
+            if not skin_codes.empty:
+                con.execute("DROP TABLE IF EXISTS opps.skin_sub_addendum_b")
+                con.execute("CREATE TABLE opps.skin_sub_addendum_b AS SELECT * FROM skin_codes")
+                print(f"  opps.skin_sub_addendum_b: {len(skin_codes)} rows "
+                      f"({skin_codes['year'].nunique()} years, "
+                      f"{skin_codes['hcpcs'].nunique()} unique codes)")
+
+                # SI distribution for skin subs
+                if "status_indicator" in skin_codes.columns:
+                    print("  Status indicators for skin subs by year:")
+                    si_year = skin_codes.groupby(["year", "status_indicator"]).size()
+                    for (yr, si), ct in si_year.items():
+                        print(f"    CY{yr} SI={si}: {ct} codes")
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description="Ingest CMS OPPS files")
+    parser.add_argument("--year", help="Ingest only this year")
+    args = parser.parse_args()
+
+    print("Ingesting CMS OPPS files into DuckDB ...")
+    con = duckdb.connect(str(DUCKDB_PATH))
+
+    ingest_all(con, year_filter=args.year or "")
+
+    # Final inventory
+    print("\n--- OPPS tables ---")
+    for r in con.execute("""
+        SELECT table_name FROM information_schema.tables
+        WHERE table_schema = 'opps' ORDER BY table_name
+    """).fetchall():
+        cnt = con.execute(f"SELECT count(*) FROM opps.{r[0]}").fetchone()[0]
+        print(f"  opps.{r[0]:30s}: {cnt:>6} rows")
+
+    con.close()
+    print("\nDone.")
+
+
+if __name__ == "__main__":
+    main()