opencode-skills-collection 2.0.0-beta.3 → 2.0.2

package/bundled-skills/monte-carlo-push-ingestion/scripts/templates/bigquery-iceberg/push_query_logs.py

@@ -0,0 +1,208 @@
+"""
+BigQuery Iceberg — Query Log Push (push only)
+=============================================
+Reads a JSON manifest produced by collect_query_logs.py and pushes query
+log entries to Monte Carlo using the pycarlo SDK's IngestionService.
+
+Uses dateutil.isoparse() to convert ISO8601 strings back to datetime
+objects (QueryLogEntry requires datetime, not str).
+
+Can be run standalone via CLI or imported (use the ``push()`` function).
+
+Substitution points (search for "← SUBSTITUTE"):
+  - MCD_INGEST_ID      : Monte Carlo Ingestion API key ID
+  - MCD_INGEST_TOKEN   : Monte Carlo Ingestion API key token
+  - MCD_RESOURCE_UUID  : Monte Carlo warehouse resource UUID
+
+Prerequisites:
+  pip install pycarlo>=0.12.251 python-dateutil>=2.8.0
+"""
+
+from __future__ import annotations
+
+import argparse
+import json
+import logging
+import os
+from concurrent.futures import ThreadPoolExecutor, as_completed
+from datetime import datetime, timezone
+
+from dateutil.parser import isoparse
+
+from pycarlo.core import Client, Session
+from pycarlo.features.ingestion import IngestionService
+from pycarlo.features.ingestion.models import QueryLogEntry
+
+logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s")
+log = logging.getLogger(__name__)
+
+LOG_TYPE = "bigquery"
+
+# Query logs include full SQL text — keep batches small to stay under the
+# 1 MB compressed payload limit.
+_BATCH_SIZE = 100
+
+# Truncate very long SQL to prevent 413 errors.
+_MAX_QUERY_TEXT_LEN = 10_000
+
+_ENDPOINT = "https://integrations.getmontecarlo.com"
+
+
+def _build_query_log_entries(queries: list[dict]) -> list[QueryLogEntry]:
+    """Convert manifest query dicts into QueryLogEntry objects."""
+    entries = []
+    truncated = 0
+    for q in queries:
+        query_text = q.get("query_text") or ""
+
+        if len(query_text) > _MAX_QUERY_TEXT_LEN:
+            query_text = query_text[:_MAX_QUERY_TEXT_LEN] + "... [TRUNCATED]"
+            truncated += 1
+
+        extra = {}
+        if q.get("total_bytes_billed") is not None:
+            extra["total_bytes_billed"] = q["total_bytes_billed"]
+        if q.get("statement_type") is not None:
+            extra["statement_type"] = q["statement_type"]
+
+        start_time = q.get("start_time")
+        end_time = q.get("end_time")
+
+        entry = QueryLogEntry(
+            query_id=q.get("query_id"),
+            query_text=query_text,
+            start_time=isoparse(start_time) if start_time else None,
+            end_time=isoparse(end_time) if end_time else None,
+            user=q.get("user"),
+            extra=extra or None,
+        )
+        entries.append(entry)
+
+    if truncated:
+        log.info("Truncated %d query text(s) exceeding %d chars", truncated, _MAX_QUERY_TEXT_LEN)
+    return entries
+
+
+def push(
+    input_file: str,
+    resource_uuid: str,
+    key_id: str,
+    key_token: str,
+    batch_size: int = _BATCH_SIZE,
+    output_file: str = "query_logs_push_result.json",
+) -> dict:
+    """Read a query log manifest and push entries to Monte Carlo in batches."""
+    endpoint = _ENDPOINT
+    log.info("Using endpoint: %s", endpoint)
+
+    with open(input_file) as fh:
+        manifest = json.load(fh)
+
+    queries = manifest.get("queries", [])
+    log_type = manifest.get("log_type", LOG_TYPE)
+    entries = _build_query_log_entries(queries)
+    log.info("Loaded %d query log entry/entries from %s", len(entries), input_file)
+
+    if not entries:
+        log.info("No query log entries to push.")
+        push_result = {
+            "resource_uuid": resource_uuid,
+            "log_type": log_type,
+            "invocation_ids": [],
+            "pushed_at": datetime.now(timezone.utc).isoformat(),
+            "total_entries": 0,
+            "batch_count": 0,
+            "batch_size": batch_size,
+        }
+        with open(output_file, "w") as fh:
+            json.dump(push_result, fh, indent=2)
+        return push_result
+
+    batches = [entries[i : i + batch_size] for i in range(0, len(entries), batch_size)]
+    total_batches = len(batches)
+
+    def _push_batch(batch: list[QueryLogEntry], batch_num: int) -> str | None:
+        client = Client(session=Session(
+            mcd_id=key_id, mcd_token=key_token, scope="Ingestion", endpoint=endpoint,
+        ))
+        service = IngestionService(mc_client=client)
+        result = service.send_query_logs(
+            resource_uuid=resource_uuid,
+            log_type=log_type,
+            events=batch,
+        )
+        invocation_id = service.extract_invocation_id(result)
+        log.info(
+            "Pushed batch %d/%d (%d entries) — invocation_id=%s",
+            batch_num, total_batches, len(batch), invocation_id,
+        )
+        return invocation_id
+
+    max_workers = min(4, total_batches)
+    invocation_ids: list[str | None] = [None] * total_batches
+
+    with ThreadPoolExecutor(max_workers=max_workers) as pool:
+        futures = {
+            pool.submit(_push_batch, batch, i + 1): i
+            for i, batch in enumerate(batches)
+        }
+        for future in as_completed(futures):
+            idx = futures[future]
+            try:
+                invocation_ids[idx] = future.result()
+            except Exception as exc:
+                log.error("ERROR pushing batch %d: %s", idx + 1, exc)
+                raise
+
+    log.info("All %d batch(es) pushed.", total_batches)
+
+    push_result = {
+        "resource_uuid": resource_uuid,
+        "log_type": log_type,
+        "invocation_ids": invocation_ids,
+        "pushed_at": datetime.now(timezone.utc).isoformat(),
+        "total_entries": len(entries),
+        "batch_count": total_batches,
+        "batch_size": batch_size,
+    }
+    with open(output_file, "w") as fh:
+        json.dump(push_result, fh, indent=2)
+    log.info("Push result written to %s", output_file)
+
+    return push_result
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(
+        description="Push BigQuery query logs from a manifest to Monte Carlo",
+    )
+    parser.add_argument("--resource-uuid", default=os.getenv("MCD_RESOURCE_UUID"))
+    parser.add_argument("--key-id", default=os.getenv("MCD_INGEST_ID"))
+    parser.add_argument("--key-token", default=os.getenv("MCD_INGEST_TOKEN"))
+    parser.add_argument("--input-file", default="query_logs_output.json")
+    parser.add_argument("--output-file", default="query_logs_push_result.json")
+    parser.add_argument(
+        "--batch-size",
+        type=int,
+        default=_BATCH_SIZE,
+        help=f"Max entries per push batch (default: {_BATCH_SIZE})",
+    )
+    args = parser.parse_args()
+
+    required = ["resource_uuid", "key_id", "key_token"]
+    missing = [k for k in required if getattr(args, k) is None]
+    if missing:
+        parser.error(f"Missing required arguments/env vars: {missing}")
+
+    push(
+        input_file=args.input_file,
+        resource_uuid=args.resource_uuid,
+        key_id=args.key_id,
+        key_token=args.key_token,
+        batch_size=args.batch_size,
+        output_file=args.output_file,
+    )
+
+
+if __name__ == "__main__":
+    main()

package/bundled-skills/monte-carlo-push-ingestion/scripts/templates/databricks/collect_and_push_lineage.py

@@ -0,0 +1,83 @@
+"""
+Databricks — Lineage Collect & Push (combined)
+================================================
+Collects table-level and (optionally) column-level lineage from Databricks Unity
+Catalog system tables, then pushes them to Monte Carlo via the push ingestion API.
+
+This script imports and calls collect() from collect_lineage and push() from
+push_lineage, running both in sequence.
+
+Substitution points (search for "← SUBSTITUTE"):
+  - DATABRICKS_HOST       : workspace hostname
+  - DATABRICKS_HTTP_PATH  : SQL warehouse HTTP path
+  - DATABRICKS_TOKEN      : PAT or service-principal secret
+  - LOOKBACK_DAYS         : how many days back to collect lineage (default 30)
+  - MCD_INGEST_ID / MCD_INGEST_TOKEN : Monte Carlo API credentials
+  - MCD_RESOURCE_UUID      : UUID of the Databricks connection in Monte Carlo
+  - PUSH_BATCH_SIZE       : number of events per API call (default 500)
+
+Use the --column-lineage flag to also push column-level lineage (disabled by default).
+
+Prerequisites:
+  pip install databricks-sql-connector pycarlo
+"""
+
+from __future__ import annotations
+
+import argparse
+import logging
+import os
+
+from collect_lineage import LOOKBACK_DAYS, collect
+from push_lineage import DEFAULT_BATCH_SIZE, push
+
+logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s")
+log = logging.getLogger(__name__)
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description="Collect and push Databricks lineage to Monte Carlo")
+    parser.add_argument("--host", default=os.getenv("DATABRICKS_HOST"))           # ← SUBSTITUTE
+    parser.add_argument("--http-path", default=os.getenv("DATABRICKS_HTTP_PATH")) # ← SUBSTITUTE
+    parser.add_argument("--token", default=os.getenv("DATABRICKS_TOKEN"))         # ← SUBSTITUTE
+    parser.add_argument("--resource-uuid", default=os.getenv("MCD_RESOURCE_UUID"))
+    parser.add_argument("--key-id", default=os.getenv("MCD_INGEST_ID"))
+    parser.add_argument("--key-token", default=os.getenv("MCD_INGEST_TOKEN"))
+    parser.add_argument("--lookback-days", type=int, default=LOOKBACK_DAYS)
+    parser.add_argument(
+        "--column-lineage", action="store_true",
+        help="Also collect column-level lineage (requires system.access.column_lineage access)",
+    )
+    parser.add_argument("--batch-size", type=int, default=DEFAULT_BATCH_SIZE)
+    parser.add_argument("--manifest", default="manifest_lineage.json")
+    args = parser.parse_args()
+
+    required = ["host", "http_path", "token", "resource_uuid", "key_id", "key_token"]
+    missing = [k for k in required if getattr(args, k) is None]
+    if missing:
+        parser.error(f"Missing required arguments/env vars: {missing}")
+
+    log.info("Step 1: Collecting lineage …")
+    collect(
+        host=args.host,
+        http_path=args.http_path,
+        token=args.token,
+        manifest_path=args.manifest,
+        include_column_lineage=args.column_lineage,
+        lookback_days=args.lookback_days,
+    )
+
+    log.info("Step 2: Pushing lineage to Monte Carlo …")
+    push(
+        manifest_path=args.manifest,
+        resource_uuid=args.resource_uuid,
+        key_id=args.key_id,
+        key_token=args.key_token,
+        batch_size=args.batch_size,
+    )
+
+    log.info("Done — collect and push complete.")
+
+
+if __name__ == "__main__":
+    main()

package/bundled-skills/monte-carlo-push-ingestion/scripts/templates/databricks/collect_and_push_metadata.py

@@ -0,0 +1,77 @@
+"""
+Databricks — Metadata Collect & Push (combined)
+=================================================
+Collects table schemas, row counts, and byte sizes from Databricks Unity Catalog,
+then pushes them to Monte Carlo via the push ingestion API.
+
+This script imports and calls collect() from collect_metadata and push() from
+push_metadata, running both in sequence.
+
+Substitution points (search for "← SUBSTITUTE"):
+  - DATABRICKS_HOST       : workspace hostname (e.g. adb-1234.azuredatabricks.net)
+  - DATABRICKS_HTTP_PATH  : SQL warehouse HTTP path (e.g. /sql/1.0/warehouses/abc123)
+  - DATABRICKS_TOKEN      : personal access token or service-principal secret
+  - DATABRICKS_CATALOG    : catalog to collect from (default: "hive_metastore" or "main")
+  - SCHEMA_EXCLUSIONS     : schemas to skip
+  - MCD_INGEST_ID / MCD_INGEST_TOKEN : Monte Carlo API credentials
+  - MCD_RESOURCE_UUID      : UUID of the Databricks connection in Monte Carlo
+  - PUSH_BATCH_SIZE       : number of assets per API call (default 500)
+
+Prerequisites:
+  pip install databricks-sql-connector pycarlo
+"""
+
+from __future__ import annotations
+
+import argparse
+import logging
+import os
+
+from collect_metadata import collect
+from push_metadata import DEFAULT_BATCH_SIZE, push
+
+logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s")
+log = logging.getLogger(__name__)
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description="Collect and push Databricks metadata to Monte Carlo")
+    parser.add_argument("--host", default=os.getenv("DATABRICKS_HOST"))           # ← SUBSTITUTE
+    parser.add_argument("--http-path", default=os.getenv("DATABRICKS_HTTP_PATH")) # ← SUBSTITUTE
+    parser.add_argument("--token", default=os.getenv("DATABRICKS_TOKEN"))         # ← SUBSTITUTE
+    parser.add_argument("--catalog", default=os.getenv("DATABRICKS_CATALOG", "hive_metastore"))
+    parser.add_argument("--resource-uuid", default=os.getenv("MCD_RESOURCE_UUID"))
+    parser.add_argument("--key-id", default=os.getenv("MCD_INGEST_ID"))
+    parser.add_argument("--key-token", default=os.getenv("MCD_INGEST_TOKEN"))
+    parser.add_argument("--batch-size", type=int, default=DEFAULT_BATCH_SIZE)
+    parser.add_argument("--manifest", default="manifest_metadata.json")
+    args = parser.parse_args()
+
+    required = ["host", "http_path", "token", "resource_uuid", "key_id", "key_token"]
+    missing = [k for k in required if getattr(args, k) is None]
+    if missing:
+        parser.error(f"Missing required arguments/env vars: {missing}")
+
+    log.info("Step 1: Collecting metadata …")
+    collect(
+        host=args.host,
+        http_path=args.http_path,
+        token=args.token,
+        catalog=args.catalog,
+        manifest_path=args.manifest,
+    )
+
+    log.info("Step 2: Pushing metadata to Monte Carlo …")
+    push(
+        manifest_path=args.manifest,
+        resource_uuid=args.resource_uuid,
+        key_id=args.key_id,
+        key_token=args.key_token,
+        batch_size=args.batch_size,
+    )
+
+    log.info("Done — collect and push complete.")
+
+
+if __name__ == "__main__":
+    main()

package/bundled-skills/monte-carlo-push-ingestion/scripts/templates/databricks/collect_and_push_query_logs.py

@@ -0,0 +1,83 @@
+"""
+Databricks — Query Log Collect & Push (combined)
+==================================================
+Collects finished query execution records from the Databricks system table
+system.query.history and pushes them to Monte Carlo for query-pattern analysis,
+lineage derivation, and usage attribution.
+
+This script imports and calls collect() from collect_query_logs and push() from
+push_query_logs, running both in sequence.
+
+Substitution points (search for "← SUBSTITUTE"):
+  - DATABRICKS_HOST       : workspace hostname
+  - DATABRICKS_HTTP_PATH  : SQL warehouse HTTP path
+  - DATABRICKS_TOKEN      : PAT or service-principal secret
+  - LOOKBACK_HOURS        : hours back from [now - LAG_HOURS] to collect (default 25)
+  - LOOKBACK_LAG_HOURS    : hours to lag behind now to avoid in-flight queries (default 1)
+  - MAX_ROWS              : maximum query rows to collect per run (default 10000)
+  - MCD_INGEST_ID / MCD_INGEST_TOKEN : Monte Carlo API credentials
+  - MCD_RESOURCE_UUID      : UUID of the Databricks connection in Monte Carlo
+  - PUSH_BATCH_SIZE       : number of entries per API call (default 250)
+
+Prerequisites:
+  pip install databricks-sql-connector pycarlo
+"""
+
+from __future__ import annotations
+
+import argparse
+import logging
+import os
+
+from collect_query_logs import LOOKBACK_HOURS, LOOKBACK_LAG_HOURS, MAX_ROWS, collect
+from push_query_logs import DEFAULT_BATCH_SIZE, push
+
+logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s")
+log = logging.getLogger(__name__)
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description="Collect and push Databricks query logs to Monte Carlo")
+    parser.add_argument("--host", default=os.getenv("DATABRICKS_HOST"))           # ← SUBSTITUTE
+    parser.add_argument("--http-path", default=os.getenv("DATABRICKS_HTTP_PATH")) # ← SUBSTITUTE
+    parser.add_argument("--token", default=os.getenv("DATABRICKS_TOKEN"))         # ← SUBSTITUTE
+    parser.add_argument("--resource-uuid", default=os.getenv("MCD_RESOURCE_UUID"))
+    parser.add_argument("--key-id", default=os.getenv("MCD_INGEST_ID"))
+    parser.add_argument("--key-token", default=os.getenv("MCD_INGEST_TOKEN"))
+    parser.add_argument("--lookback-hours", type=int, default=LOOKBACK_HOURS)
+    parser.add_argument("--lookback-lag-hours", type=int, default=LOOKBACK_LAG_HOURS)
+    parser.add_argument("--max-rows", type=int, default=MAX_ROWS)
+    parser.add_argument("--batch-size", type=int, default=DEFAULT_BATCH_SIZE)
+    parser.add_argument("--manifest", default="manifest_query_logs.json")
+    args = parser.parse_args()
+
+    required = ["host", "http_path", "token", "resource_uuid", "key_id", "key_token"]
+    missing = [k for k in required if getattr(args, k) is None]
+    if missing:
+        parser.error(f"Missing required arguments/env vars: {missing}")
+
+    log.info("Step 1: Collecting query logs …")
+    collect(
+        host=args.host,
+        http_path=args.http_path,
+        token=args.token,
+        manifest_path=args.manifest,
+        lookback_hours=args.lookback_hours,
+        lookback_lag_hours=args.lookback_lag_hours,
+        max_rows=args.max_rows,
+    )
+
+    log.info("Step 2: Pushing query logs to Monte Carlo …")
+    push(
+        manifest_path=args.manifest,
+        resource_uuid=args.resource_uuid,
+        key_id=args.key_id,
+        key_token=args.key_token,
+        batch_size=args.batch_size,
+    )
+
+    log.info("Done — collect and push complete.")
+
+
+if __name__ == "__main__":
+    main()

package/bundled-skills/monte-carlo-push-ingestion/scripts/templates/databricks/collect_lineage.py

@@ -0,0 +1,240 @@
+"""
+Databricks — Lineage Collection (collect-only)
+================================================
+Collects table-level and (optionally) column-level lineage from Databricks Unity
+Catalog system tables (system.access.table_lineage and system.access.column_lineage).
+No SQL parsing required — Databricks provides first-class lineage metadata.
+
+Writes a JSON manifest file that can be consumed by push_lineage.py.
+
+Substitution points (search for "← SUBSTITUTE"):
+  - DATABRICKS_HOST       : workspace hostname
+  - DATABRICKS_HTTP_PATH  : SQL warehouse HTTP path
+  - DATABRICKS_TOKEN      : PAT or service-principal secret
+  - LOOKBACK_DAYS         : how many days back to collect lineage (default 30)
+
+Use the --column-lineage flag to also collect column-level lineage (disabled by default).
+
+Prerequisites:
+  pip install databricks-sql-connector
+"""
+
+from __future__ import annotations
+
+import argparse
+import json
+import logging
+import os
+from datetime import datetime, timezone
+from typing import Any
+
+from databricks import sql
+
+logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s")
+log = logging.getLogger(__name__)
+
+RESOURCE_TYPE = "databricks"
+LOOKBACK_DAYS: int = int(os.getenv("LOOKBACK_DAYS", "30"))  # ← SUBSTITUTE
+
+
+def _check_available_memory(min_gb: float = 2.0) -> None:
+    """Warn if available memory is below the threshold."""
+    try:
+        if hasattr(os, "sysconf"):  # Linux / macOS
+            page_size = os.sysconf("SC_PAGE_SIZE")
+            avail_pages = os.sysconf("SC_AVPHYS_PAGES")
+            avail_gb = (page_size * avail_pages) / (1024 ** 3)
+        else:
+            return  # Windows — skip check
+    except (ValueError, OSError):
+        return
+    if avail_gb < min_gb:
+        log.warning(
+            "Only %.1f GB of memory available (minimum recommended: %.1f GB). "
+            "Consider reducing the collection scope or increasing available memory.",
+            avail_gb,
+            min_gb,
+        )
+
+
+def _query(cursor: Any, sql_text: str) -> list[dict[str, Any]]:
+    cursor.execute(sql_text)
+    cols = [d[0] for d in cursor.description]
+    rows = []
+    while True:
+        chunk = cursor.fetchmany(1000)
+        if not chunk:
+            break
+        rows.extend(dict(zip(cols, row)) for row in chunk)
+    return rows
+
+
+def _parse_full_name(full_name: str) -> tuple[str, str, str]:
+    """Split 'catalog.schema.table' into (catalog, schema, table)."""
+    parts = (full_name or "").split(".")
+    if len(parts) == 3:
+        return parts[0], parts[1], parts[2]
+    if len(parts) == 2:
+        return "", parts[0], parts[1]
+    return "", "", full_name
+
+
+def collect_table_lineage(cursor: Any, lookback_days: int) -> list[dict[str, Any]]:
+    rows = _query(
+        cursor,
+        f"""
+        SELECT DISTINCT
+            source_table_full_name,
+            target_table_full_name,
+            created_by,
+            MAX(event_time) AS last_seen
+        FROM system.access.table_lineage
+        WHERE event_time >= DATEADD(DAY, -{lookback_days}, CURRENT_TIMESTAMP())
+          AND source_table_full_name IS NOT NULL
+          AND target_table_full_name IS NOT NULL
+        GROUP BY source_table_full_name, target_table_full_name, created_by
+        LIMIT 50000
+        """,  # ← SUBSTITUTE: adjust lookback_days, LIMIT, or add catalog/schema filters
+    )
+
+    events: list[dict[str, Any]] = []
+    for row in rows:
+        src_catalog, src_schema, src_table = _parse_full_name(row["source_table_full_name"])
+        dst_catalog, dst_schema, dst_table = _parse_full_name(row["target_table_full_name"])
+
+        if not src_table or not dst_table:
+            continue
+
+        events.append({
+            "sources": [{"database": src_catalog, "schema": src_schema, "asset_name": src_table}],
+            "destination": {"database": dst_catalog, "schema": dst_schema, "asset_name": dst_table},
+            "lineage_type": "table",
+        })
+    return events
+
+
+def collect_column_lineage(cursor: Any, lookback_days: int) -> list[dict[str, Any]]:
+    rows = _query(
+        cursor,
+        f"""
+        SELECT DISTINCT
+            source_table_full_name,
+            source_column_name,
+            target_table_full_name,
+            target_column_name
+        FROM system.access.column_lineage
+        WHERE event_time >= DATEADD(DAY, -{lookback_days}, CURRENT_TIMESTAMP())
+          AND source_table_full_name IS NOT NULL
+          AND target_table_full_name IS NOT NULL
+        LIMIT 50000
+        """,  # ← SUBSTITUTE: adjust LIMIT or add catalog/schema filters if needed
+    )
+
+    # Group by destination table so we can build one event per destination
+    grouped: dict[str, dict[str, Any]] = {}
+    for row in rows:
+        dst_key = row["target_table_full_name"]
+        if dst_key not in grouped:
+            grouped[dst_key] = {"dst_full": dst_key, "columns": []}
+        grouped[dst_key]["columns"].append(row)
+
+    events: list[dict[str, Any]] = []
+    for dst_key, group in grouped.items():
+        dst_catalog, dst_schema, dst_table = _parse_full_name(group["dst_full"])
+        if not dst_table:
+            continue
+
+        col_fields: list[dict[str, Any]] = []
+        for row in group["columns"]:
+            src_catalog, src_schema, src_table = _parse_full_name(row["source_table_full_name"])
+            col_fields.append({
+                "destination_field": row["target_column_name"],
+                "sources": [{
+                    "database": src_catalog,
+                    "schema": src_schema,
+                    "asset_name": src_table,
+                    "field": row["source_column_name"],
+                }],
+            })
+
+        events.append({
+            "sources": [],  # column lineage carries source refs inside col_fields
+            "destination": {"database": dst_catalog, "schema": dst_schema, "asset_name": dst_table},
+            "column_lineage": col_fields,
+            "lineage_type": "column",
+        })
+    return events
+
+
+def collect(
+    host: str,
+    http_path: str,
+    token: str,
+    manifest_path: str = "manifest_lineage.json",
+    include_column_lineage: bool = False,
+    lookback_days: int = LOOKBACK_DAYS,
+) -> list[dict[str, Any]]:
+    """Connect to Databricks, collect lineage, write a JSON manifest, and return events."""
+    _check_available_memory(min_gb=2.0)
+    collected_at = datetime.now(timezone.utc).isoformat()
+
+    with sql.connect(
+        server_hostname=host,    # ← SUBSTITUTE
+        http_path=http_path,     # ← SUBSTITUTE
+        access_token=token,      # ← SUBSTITUTE
+    ) as conn:
+        with conn.cursor() as cursor:
+            table_events = collect_table_lineage(cursor, lookback_days)
+            col_events = collect_column_lineage(cursor, lookback_days) if include_column_lineage else []
+
+    all_events = table_events + col_events
+    log.info(
+        "Collected %d lineage events (%d table, %d column)",
+        len(all_events), len(table_events), len(col_events),
+    )
+
+    manifest = {
+        "resource_type": RESOURCE_TYPE,
+        "collected_at": collected_at,
+        "lookback_days": lookback_days,
+        "table_lineage_events": len(table_events),
+        "column_lineage_events": len(col_events),
+        "events": all_events,
+    }
+    with open(manifest_path, "w") as fh:
+        json.dump(manifest, fh, indent=2)
+    log.info("Manifest written to %s (%d events)", manifest_path, len(all_events))
+
+    return all_events
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description="Collect Databricks lineage to a manifest file")
+    parser.add_argument("--host", default=os.getenv("DATABRICKS_HOST"))           # ← SUBSTITUTE
+    parser.add_argument("--http-path", default=os.getenv("DATABRICKS_HTTP_PATH")) # ← SUBSTITUTE
+    parser.add_argument("--token", default=os.getenv("DATABRICKS_TOKEN"))         # ← SUBSTITUTE
+    parser.add_argument("--lookback-days", type=int, default=LOOKBACK_DAYS)
+    parser.add_argument(
+        "--column-lineage", action="store_true",
+        help="Also collect column-level lineage (requires system.access.column_lineage access)",
+    )
+    parser.add_argument("--manifest", default="manifest_lineage.json")
+    args = parser.parse_args()
+
+    required = ["host", "http_path", "token"]
+    missing = [k for k in required if getattr(args, k) is None]
+    if missing:
+        parser.error(f"Missing required arguments/env vars: {missing}")
+
+    collect(
+        host=args.host,
+        http_path=args.http_path,
+        token=args.token,
+        manifest_path=args.manifest,
+        include_column_lineage=args.column_lineage,
+        lookback_days=args.lookback_days,
+    )
+
+
+if __name__ == "__main__":
+    main()