opencode-skills-collection 2.0.0 → 2.0.2

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

@@ -0,0 +1,196 @@
+"""
+Redshift — Query Log Push (push-only)
+=======================================
+Reads a JSON manifest file produced by collect_query_logs.py and pushes the query
+log entries to Monte Carlo via the push ingestion API, with configurable batching
+to keep compressed payloads under 1 MB.
+
+Substitution points (search for "← SUBSTITUTE"):
+  - MCD_INGEST_ID / MCD_INGEST_TOKEN : Monte Carlo API credentials
+  - MCD_RESOURCE_UUID      : UUID of the Redshift connection in Monte Carlo
+  - PUSH_BATCH_SIZE       : number of entries per API call (default 100)
+
+Prerequisites:
+  pip install pycarlo
+"""
+
+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 typing import Any
+
+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 = "redshift"
+DEFAULT_BATCH_SIZE = 100  # ← SUBSTITUTE: conservative default to stay under 1 MB compressed
+
+# Truncate query_text longer than this to prevent 413 errors.
+# Some SQL statements (e.g., generated by BI tools) can be 100KB+ and blow up
+# compressed payloads even at small batch sizes.
+_MAX_QUERY_TEXT_LEN = 10_000
+
+
+def _build_query_log_entries(entry_dicts: list[dict[str, Any]]) -> list[QueryLogEntry]:
+    """Convert manifest query dicts into QueryLogEntry objects."""
+    entries = []
+    truncated = 0
+    for d in entry_dicts:
+        query_text = d.get("query_text") or ""
+
+        # Truncate very long SQL to prevent 413 Request Too Large
+        if len(query_text) > _MAX_QUERY_TEXT_LEN:
+            query_text = query_text[:_MAX_QUERY_TEXT_LEN] + "... [TRUNCATED]"
+            truncated += 1
+
+        extra = {}
+        if d.get("database_name") is not None:
+            extra["database_name"] = d["database_name"]
+        if d.get("elapsed_time_us") is not None:
+            extra["elapsed_time_us"] = d["elapsed_time_us"]
+
+        start_time = d.get("start_time")
+        end_time = d.get("end_time")
+
+        entries.append(
+            QueryLogEntry(
+                query_id=d.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=d.get("user"),
+                extra=extra or None,
+            )
+        )
+    if truncated:
+        log.info("Truncated %d query text(s) exceeding %d chars", truncated, _MAX_QUERY_TEXT_LEN)
+    return entries
+
+
+def push(
+    manifest_path: str,
+    resource_uuid: str,
+    key_id: str,
+    key_token: str,
+    batch_size: int = DEFAULT_BATCH_SIZE,
+) -> dict[str, Any]:
+    """Read a collect manifest and push query log entries to Monte Carlo in batches.
+
+    Returns a summary dict with invocation IDs and counts.
+    """
+    with open(manifest_path) as fh:
+        manifest = json.load(fh)
+
+    entry_dicts: list[dict[str, Any]] = manifest["entries"]
+    entries = _build_query_log_entries(entry_dicts)
+    log.info("Loaded %d query log entries from %s", len(entries), manifest_path)
+
+    if not entries:
+        log.info("No query log entries to push.")
+        summary = {
+            "resource_uuid": resource_uuid,
+            "log_type": LOG_TYPE,
+            "invocation_ids": [],
+            "pushed_at": datetime.now(timezone.utc).isoformat(),
+            "query_log_count": 0,
+            "batch_count": 0,
+            "batch_size": batch_size,
+        }
+        push_manifest_path = manifest_path.replace(".json", "_push_result.json")
+        with open(push_manifest_path, "w") as fh:
+            json.dump(summary, fh, indent=2)
+        return summary
+
+    # Split into batches
+    batches = []
+    for i in range(0, len(entries), batch_size):
+        batches.append(entries[i : i + batch_size])
+    total_batches = len(batches)
+
+    def _push_batch(batch: list, batch_num: int) -> str | None:
+        """Push a single batch using a dedicated Session (thread-safe)."""
+        client = Client(session=Session(mcd_id=key_id, mcd_token=key_token, scope="Ingestion"))
+        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
+
+    # Push batches in parallel (each thread gets its own pycarlo Session)
+    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 batches pushed (%d workers)", total_batches, max_workers)
+
+    summary = {
+        "resource_uuid": resource_uuid,
+        "log_type": LOG_TYPE,
+        "invocation_ids": invocation_ids,
+        "pushed_at": datetime.now(timezone.utc).isoformat(),
+        "query_log_count": len(entries),
+        "batch_count": total_batches,
+        "batch_size": batch_size,
+        "lookback_hours": manifest.get("lookback_hours"),
+        "lookback_lag_hours": manifest.get("lookback_lag_hours"),
+    }
+
+    push_manifest_path = manifest_path.replace(".json", "_push_result.json")
+    with open(push_manifest_path, "w") as fh:
+        json.dump(summary, fh, indent=2)
+    log.info("Push result written to %s", push_manifest_path)
+
+    return summary
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description="Push Redshift query logs to Monte Carlo from manifest")
+    parser.add_argument("--manifest", default="manifest_query_logs.json")
+    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)
+    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(
+        manifest_path=args.manifest,
+        resource_uuid=args.resource_uuid,
+        key_id=args.key_id,
+        key_token=args.key_token,
+        batch_size=args.batch_size,
+    )
+
+
+if __name__ == "__main__":
+    main()

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

@@ -0,0 +1,154 @@
+#!/usr/bin/env python3
+"""
+Collect lineage from Snowflake and push it to Monte Carlo — combined.
+
+Imports ``collect()`` from ``collect_lineage`` and ``push()`` from
+``push_lineage``, runs both in sequence.
+
+Substitution points
+-------------------
+- SNOWFLAKE_ACCOUNT    (env) / --account    (CLI) : Snowflake account identifier
+- SNOWFLAKE_USER       (env) / --user       (CLI) : Snowflake username
+- SNOWFLAKE_PASSWORD   (env) / --password   (CLI) : Snowflake password
+- SNOWFLAKE_WAREHOUSE  (env) / --warehouse  (CLI) : Snowflake virtual warehouse
+- MCD_INGEST_ID     (env) / --key-id     (CLI) : Monte Carlo ingestion key ID
+- MCD_INGEST_TOKEN  (env) / --key-token  (CLI) : Monte Carlo ingestion key token
+- MCD_RESOURCE_UUID     (env) / --resource-uuid (CLI) : MC resource UUID for this connection
+
+Prerequisites
+-------------
+    pip install pycarlo snowflake-connector-python
+
+Usage (table-level):
+    python collect_and_push_lineage.py \\
+        --account  <SNOWFLAKE_ACCOUNT> \\
+        --user     <SNOWFLAKE_USER> \\
+        --password <SNOWFLAKE_PASSWORD> \\
+        --warehouse <SNOWFLAKE_WAREHOUSE> \\
+        --key-id  <MCD_INGEST_ID> \\
+        --key-token <MCD_INGEST_TOKEN> \\
+        --resource-uuid <MCD_RESOURCE_UUID>
+
+Usage (column-level):
+    python collect_and_push_lineage.py ... --column-lineage
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+
+from collect_lineage import collect, _LOOKBACK_HOURS
+from push_lineage import push, _BATCH_SIZE
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(
+        description="Collect Snowflake lineage from ACCOUNT_USAGE and push to Monte Carlo",
+    )
+    parser.add_argument(
+        "--account",
+        default=os.environ.get("SNOWFLAKE_ACCOUNT"),
+        help="Snowflake account identifier (env: SNOWFLAKE_ACCOUNT)",
+    )
+    parser.add_argument(
+        "--user",
+        default=os.environ.get("SNOWFLAKE_USER"),
+        help="Snowflake username (env: SNOWFLAKE_USER)",
+    )
+    parser.add_argument(
+        "--password",
+        default=os.environ.get("SNOWFLAKE_PASSWORD"),
+        help="Snowflake password (env: SNOWFLAKE_PASSWORD)",
+    )
+    parser.add_argument(
+        "--warehouse",
+        default=os.environ.get("SNOWFLAKE_WAREHOUSE"),
+        help="Snowflake virtual warehouse (env: SNOWFLAKE_WAREHOUSE)",
+    )
+    parser.add_argument(
+        "--key-id",
+        default=os.environ.get("MCD_INGEST_ID"),
+        help="Monte Carlo ingestion key ID (env: MCD_INGEST_ID)",
+    )
+    parser.add_argument(
+        "--key-token",
+        default=os.environ.get("MCD_INGEST_TOKEN"),
+        help="Monte Carlo ingestion key token (env: MCD_INGEST_TOKEN)",
+    )
+    parser.add_argument(
+        "--resource-uuid",
+        default=os.environ.get("MCD_RESOURCE_UUID"),
+        help="Monte Carlo resource UUID for this Snowflake connection (env: MCD_RESOURCE_UUID)",
+    )
+    parser.add_argument(
+        "--lookback-hours",
+        type=int,
+        default=_LOOKBACK_HOURS,
+        help=f"Hours of QUERY_HISTORY to scan (default: {_LOOKBACK_HOURS})",
+    )
+    parser.add_argument(
+        "--column-lineage",
+        action="store_true",
+        help="Push column-level lineage instead of table-level",
+    )
+    parser.add_argument(
+        "--output-file",
+        default="lineage_output.json",
+        help="Path for the intermediate collect manifest (default: lineage_output.json)",
+    )
+    parser.add_argument(
+        "--push-result-file",
+        default="lineage_push_result.json",
+        help="Path to write the push result (default: lineage_push_result.json)",
+    )
+    parser.add_argument(
+        "--batch-size",
+        type=int,
+        default=_BATCH_SIZE,
+        help=f"Max events per push batch (default: {_BATCH_SIZE})",
+    )
+    args = parser.parse_args()
+
+    missing = [
+        name
+        for name, val in [
+            ("--account", args.account),
+            ("--user", args.user),
+            ("--password", args.password),
+            ("--warehouse", args.warehouse),
+            ("--key-id", args.key_id),
+            ("--key-token", args.key_token),
+            ("--resource-uuid", args.resource_uuid),
+        ]
+        if not val
+    ]
+    if missing:
+        parser.error(f"Missing required arguments: {', '.join(missing)}")
+
+    # Step 1: Collect
+    collect(
+        account=args.account,
+        user=args.user,
+        password=args.password,
+        warehouse=args.warehouse,
+        lookback_hours=args.lookback_hours,
+        column_lineage=args.column_lineage,
+        output_file=args.output_file,
+    )
+
+    # Step 2: Push
+    push(
+        input_file=args.output_file,
+        resource_uuid=args.resource_uuid,
+        key_id=args.key_id,
+        key_token=args.key_token,
+        batch_size=args.batch_size,
+        output_file=args.push_result_file,
+    )
+
+    print("Done.")
+
+
+if __name__ == "__main__":
+    main()

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

@@ -0,0 +1,137 @@
+#!/usr/bin/env python3
+"""
+Collect table metadata from Snowflake and push it to Monte Carlo — combined.
+
+Imports ``collect()`` from ``collect_metadata`` and ``push()`` from
+``push_metadata``, runs both in sequence.
+
+Substitution points
+-------------------
+- SNOWFLAKE_ACCOUNT    (env) / --account    (CLI) : Snowflake account identifier (e.g. xy12345.us-east-1)
+- SNOWFLAKE_USER       (env) / --user       (CLI) : Snowflake username
+- SNOWFLAKE_PASSWORD   (env) / --password   (CLI) : Snowflake password
+- SNOWFLAKE_WAREHOUSE  (env) / --warehouse  (CLI) : Snowflake virtual warehouse
+- MCD_INGEST_ID     (env) / --key-id     (CLI) : Monte Carlo ingestion key ID
+- MCD_INGEST_TOKEN  (env) / --key-token  (CLI) : Monte Carlo ingestion key token
+- MCD_RESOURCE_UUID     (env) / --resource-uuid (CLI) : MC resource UUID for this connection
+
+Prerequisites
+-------------
+    pip install pycarlo snowflake-connector-python
+
+Usage
+-----
+    python collect_and_push_metadata.py \\
+        --account  <SNOWFLAKE_ACCOUNT> \\
+        --user     <SNOWFLAKE_USER> \\
+        --password <SNOWFLAKE_PASSWORD> \\
+        --warehouse <SNOWFLAKE_WAREHOUSE> \\
+        --key-id  <MCD_INGEST_ID> \\
+        --key-token <MCD_INGEST_TOKEN> \\
+        --resource-uuid <MCD_RESOURCE_UUID>
+"""
+
+import argparse
+import os
+
+from collect_metadata import collect
+from push_metadata import push, _BATCH_SIZE
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(
+        description="Collect Snowflake table metadata and push to Monte Carlo",
+    )
+    parser.add_argument(
+        "--account",
+        default=os.environ.get("SNOWFLAKE_ACCOUNT"),
+        help="Snowflake account identifier, e.g. xy12345.us-east-1 (env: SNOWFLAKE_ACCOUNT)",  # ← SUBSTITUTE
+    )
+    parser.add_argument(
+        "--user",
+        default=os.environ.get("SNOWFLAKE_USER"),
+        help="Snowflake username (env: SNOWFLAKE_USER)",  # ← SUBSTITUTE
+    )
+    parser.add_argument(
+        "--password",
+        default=os.environ.get("SNOWFLAKE_PASSWORD"),
+        help="Snowflake password (env: SNOWFLAKE_PASSWORD)",  # ← SUBSTITUTE
+    )
+    parser.add_argument(
+        "--warehouse",
+        default=os.environ.get("SNOWFLAKE_WAREHOUSE"),
+        help="Snowflake virtual warehouse (env: SNOWFLAKE_WAREHOUSE)",  # ← SUBSTITUTE
+    )
+    parser.add_argument(
+        "--key-id",
+        default=os.environ.get("MCD_INGEST_ID"),
+        help="Monte Carlo ingestion key ID (env: MCD_INGEST_ID)",
+    )
+    parser.add_argument(
+        "--key-token",
+        default=os.environ.get("MCD_INGEST_TOKEN"),
+        help="Monte Carlo ingestion key token (env: MCD_INGEST_TOKEN)",
+    )
+    parser.add_argument(
+        "--resource-uuid",
+        default=os.environ.get("MCD_RESOURCE_UUID"),
+        help="Monte Carlo resource UUID for this Snowflake connection (env: MCD_RESOURCE_UUID)",
+    )
+    parser.add_argument(
+        "--output-file",
+        default="metadata_output.json",
+        help="Path for the intermediate collect manifest (default: metadata_output.json)",
+    )
+    parser.add_argument(
+        "--push-result-file",
+        default="metadata_push_result.json",
+        help="Path to write the push result (default: metadata_push_result.json)",
+    )
+    parser.add_argument(
+        "--batch-size",
+        type=int,
+        default=_BATCH_SIZE,
+        help=f"Max assets per push batch (default: {_BATCH_SIZE})",
+    )
+    args = parser.parse_args()
+
+    missing = [
+        name
+        for name, val in [
+            ("--account", args.account),
+            ("--user", args.user),
+            ("--password", args.password),
+            ("--warehouse", args.warehouse),
+            ("--key-id", args.key_id),
+            ("--key-token", args.key_token),
+            ("--resource-uuid", args.resource_uuid),
+        ]
+        if not val
+    ]
+    if missing:
+        parser.error(f"Missing required arguments: {', '.join(missing)}")
+
+    # Step 1: Collect
+    collect(
+        account=args.account,
+        user=args.user,
+        password=args.password,
+        warehouse=args.warehouse,
+        output_file=args.output_file,
+    )
+
+    # Step 2: Push
+    push(
+        input_file=args.output_file,
+        resource_uuid=args.resource_uuid,
+        key_id=args.key_id,
+        key_token=args.key_token,
+        batch_size=args.batch_size,
+        output_file=args.push_result_file,
+    )
+
+    print("Done.")
+
+
+if __name__ == "__main__":
+    main()

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

@@ -0,0 +1,137 @@
+#!/usr/bin/env python3
+"""
+Collect query logs from Snowflake and push them to Monte Carlo — combined.
+
+Imports ``collect()`` from ``collect_query_logs`` and ``push()`` from
+``push_query_logs``, runs both in sequence.
+
+Substitution points
+-------------------
+- SNOWFLAKE_ACCOUNT    (env) / --account    (CLI) : Snowflake account identifier
+- SNOWFLAKE_USER       (env) / --user       (CLI) : Snowflake username
+- SNOWFLAKE_PASSWORD   (env) / --password   (CLI) : Snowflake password
+- SNOWFLAKE_WAREHOUSE  (env) / --warehouse  (CLI) : Snowflake virtual warehouse
+- MCD_INGEST_ID     (env) / --key-id     (CLI) : Monte Carlo ingestion key ID
+- MCD_INGEST_TOKEN  (env) / --key-token  (CLI) : Monte Carlo ingestion key token
+- MCD_RESOURCE_UUID     (env) / --resource-uuid (CLI) : MC resource UUID for this connection
+
+Prerequisites
+-------------
+    pip install pycarlo snowflake-connector-python
+
+Usage
+-----
+    python collect_and_push_query_logs.py \\
+        --account  <SNOWFLAKE_ACCOUNT> \\
+        --user     <SNOWFLAKE_USER> \\
+        --password <SNOWFLAKE_PASSWORD> \\
+        --warehouse <SNOWFLAKE_WAREHOUSE> \\
+        --key-id  <MCD_INGEST_ID> \\
+        --key-token <MCD_INGEST_TOKEN> \\
+        --resource-uuid <MCD_RESOURCE_UUID>
+"""
+
+import argparse
+import os
+
+from collect_query_logs import collect
+from push_query_logs import push, _BATCH_SIZE
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(
+        description="Collect Snowflake query logs from ACCOUNT_USAGE and push to Monte Carlo",
+    )
+    parser.add_argument(
+        "--account",
+        default=os.environ.get("SNOWFLAKE_ACCOUNT"),
+        help="Snowflake account identifier, e.g. xy12345.us-east-1 (env: SNOWFLAKE_ACCOUNT)",  # ← SUBSTITUTE
+    )
+    parser.add_argument(
+        "--user",
+        default=os.environ.get("SNOWFLAKE_USER"),
+        help="Snowflake username (env: SNOWFLAKE_USER)",
+    )
+    parser.add_argument(
+        "--password",
+        default=os.environ.get("SNOWFLAKE_PASSWORD"),
+        help="Snowflake password (env: SNOWFLAKE_PASSWORD)",
+    )
+    parser.add_argument(
+        "--warehouse",
+        default=os.environ.get("SNOWFLAKE_WAREHOUSE"),
+        help="Snowflake virtual warehouse (env: SNOWFLAKE_WAREHOUSE)",  # ← SUBSTITUTE
+    )
+    parser.add_argument(
+        "--key-id",
+        default=os.environ.get("MCD_INGEST_ID"),
+        help="Monte Carlo ingestion key ID (env: MCD_INGEST_ID)",
+    )
+    parser.add_argument(
+        "--key-token",
+        default=os.environ.get("MCD_INGEST_TOKEN"),
+        help="Monte Carlo ingestion key token (env: MCD_INGEST_TOKEN)",
+    )
+    parser.add_argument(
+        "--resource-uuid",
+        default=os.environ.get("MCD_RESOURCE_UUID"),
+        help="Monte Carlo resource UUID for this Snowflake connection (env: MCD_RESOURCE_UUID)",
+    )
+    parser.add_argument(
+        "--output-file",
+        default="query_logs_output.json",
+        help="Path for the intermediate collect manifest (default: query_logs_output.json)",
+    )
+    parser.add_argument(
+        "--push-result-file",
+        default="query_logs_push_result.json",
+        help="Path to write the push result (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()
+
+    missing = [
+        name
+        for name, val in [
+            ("--account", args.account),
+            ("--user", args.user),
+            ("--password", args.password),
+            ("--warehouse", args.warehouse),
+            ("--key-id", args.key_id),
+            ("--key-token", args.key_token),
+            ("--resource-uuid", args.resource_uuid),
+        ]
+        if not val
+    ]
+    if missing:
+        parser.error(f"Missing required arguments: {', '.join(missing)}")
+
+    # Step 1: Collect
+    collect(
+        account=args.account,
+        user=args.user,
+        password=args.password,
+        warehouse=args.warehouse,
+        output_file=args.output_file,
+    )
+
+    # Step 2: Push
+    push(
+        input_file=args.output_file,
+        resource_uuid=args.resource_uuid,
+        key_id=args.key_id,
+        key_token=args.key_token,
+        batch_size=args.batch_size,
+        output_file=args.push_result_file,
+    )
+
+    print("Done.")
+
+
+if __name__ == "__main__":
+    main()