feat(reports): store and browse report artifacts

app/db/repositories.py

@@ -10,6 +10,7 @@ from __future__ import annotations
 
 import json
 import sqlite3
+import base64
 from contextlib import contextmanager
 from datetime import datetime, timedelta, timezone
 import ipaddress
@@ -233,6 +234,109 @@ def count_scans(conn: sqlite3.Connection) -> int:
     return int(conn.execute("SELECT COUNT(*) FROM scans").fetchone()[0])
 
 
+# ---------------------------------------------------------------------------
+# Report artifacts
+# ---------------------------------------------------------------------------
+
+def insert_report_artifact(conn: sqlite3.Connection, *, source: str,
+                           report_type: str, generated_at: str,
+                           payload: Any, original_path: str,
+                           content_sha256: str, scan_id: int | None = None,
+                           schema_version: int = 1) -> int:
+    """Insert a structured report artifact, idempotent by path and hash."""
+    with transaction(conn):
+        conn.execute(
+            "INSERT OR IGNORE INTO report_artifacts "
+            "(source, scan_id, report_type, generated_at, schema_version, "
+            "payload_json, original_path, content_sha256, created_at) "
+            "VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)",
+            (source, scan_id, report_type, generated_at, schema_version,
+             json.dumps(payload, ensure_ascii=False), original_path,
+             content_sha256, utcnow()),
+        )
+        row = conn.execute(
+            "SELECT id FROM report_artifacts "
+            "WHERE original_path=? AND content_sha256=?",
+            (original_path, content_sha256),
+        ).fetchone()
+    return int(row["id"])
+
+
+def list_report_artifacts(conn: sqlite3.Connection, *,
+                          source: str | None = None,
+                          report_type: str | None = None,
+                          since: str | None = None,
+                          until: str | None = None,
+                          limit: int = 50,
+                          cursor: str | None = None) -> dict[str, Any]:
+    """List report metadata using bounded keyset pagination."""
+    limit = min(max(int(limit), 1), 200)
+    clauses: list[str] = []
+    args: list[Any] = []
+    if source:
+        clauses.append("source=?")
+        args.append(source)
+    if report_type:
+        clauses.append("report_type=?")
+        args.append(report_type)
+    if since:
+        clauses.append("generated_at>=?")
+        args.append(since)
+    if until:
+        clauses.append("generated_at<=?")
+        args.append(until)
+    if cursor:
+        generated_at, artifact_id = _decode_report_cursor(cursor)
+        clauses.append("(generated_at<? OR (generated_at=? AND id<?))")
+        args.extend((generated_at, generated_at, artifact_id))
+
+    sql = (
+        "SELECT id, source, scan_id, report_type, generated_at, "
+        "schema_version, original_path, content_sha256 "
+        "FROM report_artifacts"
+    )
+    if clauses:
+        sql += " WHERE " + " AND ".join(clauses)
+    sql += " ORDER BY generated_at DESC, id DESC LIMIT ?"
+    rows = [dict(row) for row in conn.execute(sql, (*args, limit + 1))]
+    has_more = len(rows) > limit
+    rows = rows[:limit]
+    next_cursor = (
+        _encode_report_cursor(rows[-1]["generated_at"], rows[-1]["id"])
+        if has_more and rows else None
+    )
+    return {"items": rows, "next_cursor": next_cursor}
+
+
+def get_report_artifact(conn: sqlite3.Connection,
+                        artifact_id: int) -> dict[str, Any] | None:
+    """Fetch one artifact and decode its structured payload."""
+    row = conn.execute(
+        "SELECT id, source, scan_id, report_type, generated_at, "
+        "schema_version, payload_json, original_path, content_sha256, created_at "
+        "FROM report_artifacts WHERE id=?", (artifact_id,)).fetchone()
+    if row is None:
+        return None
+    artifact = dict(row)
+    artifact["payload"] = json.loads(artifact.pop("payload_json"))
+    return artifact
+
+
+def _encode_report_cursor(generated_at: str, artifact_id: int) -> str:
+    raw = f"{generated_at}\n{artifact_id}".encode("utf-8")
+    return base64.urlsafe_b64encode(raw).decode("ascii").rstrip("=")
+
+
+def _decode_report_cursor(cursor: str) -> tuple[str, int]:
+    try:
+        padded = cursor + "=" * (-len(cursor) % 4)
+        generated_at, artifact_id = base64.urlsafe_b64decode(
+            padded.encode("ascii")).decode("utf-8").split("\n", 1)
+        return generated_at, int(artifact_id)
+    except (ValueError, UnicodeError) as exc:
+        raise ValueError("invalid report cursor") from exc
+
+
 def correlate_across_sources(conn: sqlite3.Connection,
                              limit: int = 100) -> list[dict[str, Any]]:
     """IPs seen in more than one log source, with per-source counts."""