AUDIT-WP-0004 T01, T02, T07. T01 - ingestion wrote to SQLite directly and never called the AuditBackend contract, so a 202 meant a row existed rather than that a backend with a declared retention policy had accepted the event. Adds IdempotentAuditBackend to the contract: duplicate detection lives inside the backend so custody and idempotency state share a transaction and cannot diverge. SQLiteAuditBackend implements it with WAL, synchronous=FULL and a busy timeout. Ingestion now refuses any backend declaring durable=False, so the development file backend cannot silently become the production sink. The atomicity claim was tested rather than asserted, and the first attempt failed: with a single shared connection, 16 racing submissions of one event told two callers they were first. Storage was correct but the response was not. Fixed with per-thread connections and BEGIN IMMEDIATE around the insert/read pair, and locked in by a test. T02 - storage errors previously escaped the handler with start_response never called, and the auth check sat outside the try block so a non-ASCII Authorization header crashed the request. Adds a catch-all, maps conflict to 409, backend unavailability to 503 and unexpected faults to 500, and documents the full response contract with the retry semantics each status implies, since senders key their behaviour off it. T07 - ingestion tests 2 -> 23, suite 15 -> 36. accepted_at is now UTC rather than local time, and naive timestamps are rejected instead of silently assumed. Remaining in WP-0004: T03 tenant/source binding, T04 redaction policy, T05 operator read surface, T06 production serving layer. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
177 lines
6.2 KiB
Python
177 lines
6.2 KiB
Python
"""Durable SQLite audit backend.
|
|
|
|
Implements the idempotent backend contract for single-node deployments and for
|
|
development. Production custody moves to PostgreSQL under AUDIT-WP-0005; this
|
|
backend stays the development and test implementation and defines the
|
|
behaviour the Postgres backend must match.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import sqlite3
|
|
import threading
|
|
from datetime import datetime, timezone
|
|
|
|
from audit_core.interface import (
|
|
AcceptResult,
|
|
AuditEvent,
|
|
BackendUnavailableError,
|
|
EventConflictError,
|
|
EventValidationError,
|
|
RetentionPolicy,
|
|
validate_event,
|
|
)
|
|
|
|
_SCHEMA = """
|
|
CREATE TABLE IF NOT EXISTS events (
|
|
event_id TEXT PRIMARY KEY,
|
|
payload_hash TEXT NOT NULL,
|
|
accepted_at TEXT NOT NULL,
|
|
correlation_id TEXT,
|
|
tenant TEXT NOT NULL,
|
|
record TEXT NOT NULL
|
|
);
|
|
CREATE INDEX IF NOT EXISTS events_correlation_idx ON events (correlation_id);
|
|
CREATE INDEX IF NOT EXISTS events_tenant_idx ON events (tenant);
|
|
"""
|
|
|
|
|
|
class SQLiteAuditBackend:
|
|
"""Store audit events in SQLite with idempotent accept semantics.
|
|
|
|
Configured for durability rather than speed: WAL journalling, ``synchronous
|
|
= FULL`` so an acknowledged write has reached disk, and a busy timeout so
|
|
concurrent writers wait instead of raising immediately.
|
|
"""
|
|
|
|
def __init__(self, path: str, retention_days: int | None = None, busy_timeout_ms: int = 5000) -> None:
|
|
self.path = path
|
|
self.retention_days = retention_days
|
|
self.busy_timeout_ms = int(busy_timeout_ms)
|
|
# One connection per thread. A shared connection lets concurrent
|
|
# statements interleave, which was observed to let two callers both
|
|
# believe they were the first to accept the same event.
|
|
self._local = threading.local()
|
|
with self._connect_raw() as setup:
|
|
setup.executescript(_SCHEMA)
|
|
|
|
def _connect_raw(self) -> sqlite3.Connection:
|
|
try:
|
|
db = sqlite3.connect(self.path, isolation_level=None)
|
|
db.execute("PRAGMA journal_mode = WAL")
|
|
db.execute("PRAGMA synchronous = FULL")
|
|
db.execute(f"PRAGMA busy_timeout = {self.busy_timeout_ms}")
|
|
return db
|
|
except sqlite3.Error as exc:
|
|
raise BackendUnavailableError(f"cannot open audit store: {exc}") from exc
|
|
|
|
@property
|
|
def db(self) -> sqlite3.Connection:
|
|
conn = getattr(self._local, "conn", None)
|
|
if conn is None:
|
|
conn = self._local.conn = self._connect_raw()
|
|
return conn
|
|
|
|
@property
|
|
def retention_policy(self) -> RetentionPolicy:
|
|
return RetentionPolicy(
|
|
custody_class="development",
|
|
retention_days=self.retention_days,
|
|
immutable=False,
|
|
tamper_evidence=False,
|
|
durable=True,
|
|
)
|
|
|
|
def emit(self, event: AuditEvent) -> str:
|
|
"""Persist an event, generating no idempotency guarantee."""
|
|
return self.accept(event, payload_hash=_record_hash(event)).reference
|
|
|
|
def accept(self, event: AuditEvent, payload_hash: str) -> AcceptResult:
|
|
try:
|
|
validate_event(event)
|
|
except EventValidationError:
|
|
raise
|
|
reference = f"audit:{event.event_id}"
|
|
details = event.details if isinstance(event.details, dict) else {}
|
|
db = self.db
|
|
try:
|
|
# BEGIN IMMEDIATE takes the write lock up front, so the insert and
|
|
# the follow-up read are one atomic pair. Without it, two callers
|
|
# racing on the same event id can both be told they were first.
|
|
db.execute("BEGIN IMMEDIATE")
|
|
except sqlite3.Error as exc:
|
|
raise BackendUnavailableError(str(exc)) from exc
|
|
|
|
try:
|
|
inserted = db.execute(
|
|
"""
|
|
INSERT INTO events
|
|
(event_id, payload_hash, accepted_at, correlation_id, tenant, record)
|
|
VALUES (?, ?, ?, ?, ?, ?)
|
|
ON CONFLICT(event_id) DO NOTHING
|
|
RETURNING event_id
|
|
""",
|
|
(
|
|
event.event_id,
|
|
payload_hash,
|
|
datetime.now(timezone.utc).replace(microsecond=0).isoformat(),
|
|
str(details.get("correlation_id") or "") or None,
|
|
event.tenant,
|
|
json.dumps(event.as_record(), sort_keys=True),
|
|
),
|
|
).fetchone()
|
|
existing = None
|
|
if inserted is None:
|
|
existing = db.execute(
|
|
"SELECT payload_hash FROM events WHERE event_id = ?", (event.event_id,)
|
|
).fetchone()
|
|
db.execute("COMMIT")
|
|
except sqlite3.Error as exc:
|
|
_rollback(db)
|
|
raise BackendUnavailableError(str(exc)) from exc
|
|
except BaseException:
|
|
_rollback(db)
|
|
raise
|
|
|
|
if inserted is not None:
|
|
return AcceptResult(duplicate=False, reference=reference)
|
|
if existing is None:
|
|
# The row vanished between the insert and the read inside one
|
|
# transaction, which should be impossible. Retryable rather than
|
|
# guessed at.
|
|
raise BackendUnavailableError("event disappeared during accept")
|
|
if existing[0] != payload_hash:
|
|
raise EventConflictError(
|
|
f"event_id {event.event_id} already held with a different payload"
|
|
)
|
|
return AcceptResult(duplicate=True, reference=reference)
|
|
|
|
def health(self) -> None:
|
|
"""Raise :class:`BackendUnavailableError` if the store is unusable."""
|
|
try:
|
|
self.db.execute("SELECT 1 FROM events LIMIT 1").fetchone()
|
|
except sqlite3.Error as exc:
|
|
raise BackendUnavailableError(str(exc)) from exc
|
|
|
|
def close(self) -> None:
|
|
"""Close this thread's connection, if it has one."""
|
|
conn = getattr(self._local, "conn", None)
|
|
if conn is not None:
|
|
conn.close()
|
|
self._local.conn = None
|
|
|
|
|
|
def _rollback(db: sqlite3.Connection) -> None:
|
|
try:
|
|
db.execute("ROLLBACK")
|
|
except sqlite3.Error:
|
|
pass
|
|
|
|
|
|
def _record_hash(event: AuditEvent) -> str:
|
|
import hashlib
|
|
|
|
return hashlib.sha256(
|
|
json.dumps(event.as_record(), sort_keys=True).encode("utf-8")
|
|
).hexdigest()
|