Implement durable event ingestion service

audit_core/ingestion.py

@@ -0,0 +1,126 @@
+"""Authenticated, idempotent HTTP ingestion for user-engine outbox events."""
+
+from __future__ import annotations
+
+import hashlib
+import hmac
+import json
+import os
+import sqlite3
+from datetime import datetime
+from http import HTTPStatus
+from typing import Any
+from wsgiref.simple_server import make_server
+
+from audit_core.interface import AuditEvent
+
+MAX_BODY_BYTES = 256 * 1024
+_SECRET_FRAGMENTS = ("password", "secret", "token", "credential", "private_key")
+
+
+class SQLiteEventStore:
+    def __init__(self, path: str) -> None:
+        self.db = sqlite3.connect(path, check_same_thread=False)
+        self.db.execute("""
+            CREATE TABLE IF NOT EXISTS events (
+              event_id TEXT PRIMARY KEY, payload_hash TEXT NOT NULL,
+              accepted_at TEXT NOT NULL, record TEXT NOT NULL
+            )
+        """)
+        self.db.commit()
+
+    def accept(self, event: AuditEvent, payload_hash: str) -> tuple[bool, str]:
+        existing = self.db.execute(
+            "SELECT payload_hash FROM events WHERE event_id = ?", (event.event_id,)
+        ).fetchone()
+        if existing:
+            if existing[0] != payload_hash:
+                raise ValueError("event_id_conflict")
+            return True, f"audit:{event.event_id}"
+        with self.db:
+            self.db.execute(
+                "INSERT INTO events VALUES (?, ?, ?, ?)",
+                (event.event_id, payload_hash, datetime.now().astimezone().isoformat(),
+                 json.dumps(event.as_record(), sort_keys=True)),
+            )
+        return False, f"audit:{event.event_id}"
+
+
+class IngestionApplication:
+    def __init__(self, store: SQLiteEventStore, bearer_token: str) -> None:
+        if not bearer_token:
+            raise ValueError("bearer token is required")
+        self.store = store
+        self.token = bearer_token
+
+    def __call__(self, environ, start_response):
+        path = environ.get("PATH_INFO", "")
+        if path in ("/healthz", "/readyz"):
+            return self._json(start_response, HTTPStatus.OK, {"status": "ok"})
+        if path != "/v1/events" or environ.get("REQUEST_METHOD") != "POST":
+            return self._json(start_response, HTTPStatus.NOT_FOUND, {"error": "not_found"})
+        supplied = str(environ.get("HTTP_AUTHORIZATION", ""))
+        if not hmac.compare_digest(supplied, f"Bearer {self.token}"):
+            return self._json(start_response, HTTPStatus.UNAUTHORIZED, {"error": "unauthorized"})
+        try:
+            length = int(environ.get("CONTENT_LENGTH") or 0)
+            if length <= 0 or length > MAX_BODY_BYTES:
+                raise ValueError("invalid_size")
+            raw = environ["wsgi.input"].read(length)
+            payload = json.loads(raw)
+            event = normalize(payload, environ.get("HTTP_IDEMPOTENCY_KEY"))
+            duplicate, reference = self.store.accept(
+                event, hashlib.sha256(raw).hexdigest()
+            )
+        except (ValueError, TypeError, KeyError, json.JSONDecodeError) as exc:
+            return self._json(start_response, HTTPStatus.BAD_REQUEST, {"error": str(exc)})
+        return self._json(start_response, HTTPStatus.OK if duplicate else HTTPStatus.ACCEPTED,
+                          {"status": "duplicate" if duplicate else "accepted",
+                           "reference": reference})
+
+    @staticmethod
+    def _json(start_response, status: HTTPStatus, payload: dict[str, Any]):
+        body = json.dumps(payload).encode()
+        start_response(f"{status.value} {status.phrase}", [
+            ("Content-Type", "application/json"), ("Content-Length", str(len(body)))
+        ])
+        return [body]
+
+
+def normalize(payload: dict[str, Any], idempotency_key: str | None) -> AuditEvent:
+    required = ("id", "type", "source", "subject", "tenant", "correlation_id", "occurred_at", "data")
+    if not isinstance(payload, dict) or any(not payload.get(key) for key in required):
+        raise ValueError("invalid_event")
+    if idempotency_key != payload["id"]:
+        raise ValueError("idempotency_key_mismatch")
+    if payload["source"] != "user-engine":
+        raise ValueError("source_not_allowed")
+    datetime.fromisoformat(str(payload["occurred_at"]).replace("Z", "+00:00"))
+    if _contains_secret(payload["data"]):
+        raise ValueError("secret_shaped_field")
+    return AuditEvent(
+        event_id=str(payload["id"]), observed_at=str(payload["occurred_at"]),
+        tenant=str(payload["tenant"]), scope="tenant", source="user-engine",
+        action=str(payload["type"]), resource=str(payload["subject"]),
+        outcome="recorded", actor=None,
+        details={"correlation_id": str(payload["correlation_id"]), "data": payload["data"]},
+    )
+
+
+def _contains_secret(value: Any) -> bool:
+    if isinstance(value, dict):
+        return any(any(fragment in str(key).lower() for fragment in _SECRET_FRAGMENTS)
+                   or _contains_secret(item) for key, item in value.items())
+    if isinstance(value, list):
+        return any(_contains_secret(item) for item in value)
+    return False
+
+
+def main() -> None:
+    app = IngestionApplication(
+        SQLiteEventStore(os.environ.get("AUDIT_CORE_DATABASE_PATH", "/data/audit-core.db")),
+        os.environ["AUDIT_CORE_INGEST_TOKEN"].strip(),
+    )
+    with make_server(os.environ.get("AUDIT_CORE_HOST", "0.0.0.0"),
+                     int(os.environ.get("AUDIT_CORE_HTTP_PORT", "8080")), app) as server:
+        server.serve_forever()