fix(6848): auto-cleanup for telemetry tables causing OOM (#6988)

* fix(6848): add auto-cleanup for telemetry tables that grow without bound

Add retention-based cleanup for 4 tables that had no prune policy:
- domain_cost_history (timestamp INTEGER, unix epoch)
- compression_cache_stats (created_at DATETIME)
- xp_audit_log (created_at TEXT)
- compression_run_telemetry (timestamp INTEGER, unix epoch)

All default to 30-day retention, integrated into runAutoCleanup()
which runs on startup + every 6h via startCleanupScheduler().
Also runs VACUUM after startup cleanup to reclaim disk space.

6 unit tests covering retention boundary, no-op on recent data,
and DEFAULT_DATABASE_SETTINGS key existence.

Closes #6848

* ci: retrigger CI for Electron Package Smoke flaky test

* ci: retrigger flaky integration test (batch-e2e timeout)

* test(#6848): rewrite tests to call real cleanup functions with seeded DB data

Replace mock-only assertions with integration-style tests that seed data
into the isolated test DB, call the actual cleanup functions from
src/lib/db/cleanup.ts, and verify rows are correctly deleted.

All 6 tests now exercise real code paths:
- cleanupDomainCostHistory: verify old rows deleted, recent preserved
- cleanupCompressionCacheStats: verify old rows deleted, recent preserved
- cleanupXpAuditLog: verify old rows deleted, recent preserved
- cleanupCompressionRunTelemetry: ensure table + verify cleanup
- Combined: all 4 functions return 0 deletions when data is within retention
- DEFAULT_DATABASE_SETTINGS: verify new retention keys exist with value 30

* test(#6848): self-contained DATA_DIR isolation for the cleanup test

Builds on the existing rewrite (already correctly importing and calling
the real cleanupDomainCostHistory/cleanupCompressionCacheStats/
cleanupXpAuditLog/cleanupCompressionRunTelemetry from src/lib/db/cleanup.ts
with real seeded-row assertions instead of re-implementing the DELETE
inline) and closes the remaining gap: DATA_DIR isolation relied entirely
on the test:unit harness's `--import ./tests/_setup/isolateDataDir.ts`,
which is invisible from the test file itself.

Per CONTRIBUTING.md/CLAUDE.md, a single test file is documented to run
directly as `node --import tsx/esm --test tests/unit/<file>.test.ts` —
without the harness's isolation import, getDbInstance() resolves to the
developer's real ~/.omniroute/storage.sqlite, and this file's DELETE-based
cleanup calls operate on real rows, not test rows. Confirmed by running it
that way before this fix: it deleted 238 real compression_cache_stats rows
and 53 real xp_audit_log rows (assertions failed on the row counts, which
is how the gap surfaced) instead of the 2/3 rows the test itself inserted.

Fix: mkdtempSync + DATA_DIR override before the first src/lib/db/* import
(self-contained, matches the pattern in
tests/unit/duckduckgo-vqd-429-misclassification-6996.test.ts), plus
test.after() calling resetDbInstance() and removing the temp dir — the
repo's DB-test-cleanup rule (a dangling handle can hang the native test
runner). Re-ran after the fix: same 6/6 pass, now against an isolated
/tmp DB with the expected 3/2/3/2 row counts, in ~3s instead of ~15s.

Red-first proof: reset cleanupDomainCostHistory's cutoff to a no-op
(`cutoffEpoch = 0`, never matches a real row) — the dedicated
"cleanupDomainCostHistory: deletes rows older than retention window" test
failed as expected; restored and reran clean (6/6).

Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>

---------

Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
This commit is contained in:
Rafael Dias Zendron
2026-07-18 15:14:41 -03:00
committed by GitHub
parent 1843b34866
commit d415baa026
4 changed files with 318 additions and 9 deletions

View File

@@ -244,6 +244,66 @@ export async function cleanupMemoryEntries(): Promise<CleanupResult> {
return result;
}
/**
* Clean up old domain_cost_history based on retention settings. (#6848)
* Uses unix-epoch `timestamp` column (INTEGER).
*/
export async function cleanupDomainCostHistory(): Promise<CleanupResult> {
const db = getDbInstance();
const retention = getRetentionSettings();
const retentionDays = retention.domainCostHistory;
const cutoffEpoch = Math.floor(Date.now() / 1000) - retentionDays * 86_400;
const result: CleanupResult = { deleted: 0, errors: 0 };
try {
const stmt = db.prepare("DELETE FROM domain_cost_history WHERE timestamp < ?");
const runResult = stmt.run(cutoffEpoch);
result.deleted = runResult.changes;
console.log(
`[Cleanup] Deleted ${result.deleted} domain_cost_history older than ${retentionDays} days`
);
} catch (err: unknown) {
console.error("[Cleanup] Error cleaning domain_cost_history:", err);
result.errors++;
}
return result;
}
/**
* Clean up old compression_cache_stats based on retention settings. (#6848)
* Uses `created_at` column (DATETIME string).
*/
export async function cleanupCompressionCacheStats(): Promise<CleanupResult> {
const db = getDbInstance();
const retention = getRetentionSettings();
const retentionDays = retention.compressionCacheStats;
const cutoffDate = new Date();
cutoffDate.setDate(cutoffDate.getDate() - retentionDays);
const cutoffISO = cutoffDate.toISOString();
const result: CleanupResult = { deleted: 0, errors: 0 };
try {
const stmt = db.prepare("DELETE FROM compression_cache_stats WHERE created_at < ?");
const runResult = stmt.run(cutoffISO);
result.deleted = runResult.changes;
console.log(
`[Cleanup] Deleted ${result.deleted} compression_cache_stats older than ${retentionDays} days`
);
} catch (err: unknown) {
console.error("[Cleanup] Error cleaning compression_cache_stats:", err);
result.errors++;
}
return result;
}
/**
* Clean up old xp_audit_log based on retention settings.
*/
@@ -274,6 +334,35 @@ export async function cleanupXpAuditLog(): Promise<CleanupResult> {
return result;
}
/**
* Clean up old compression_run_telemetry based on retention settings. (#6848)
* Uses unix-epoch `timestamp` column (INTEGER).
*/
export async function cleanupCompressionRunTelemetry(): Promise<CleanupResult> {
const db = getDbInstance();
const retention = getRetentionSettings();
const retentionDays = retention.compressionRunTelemetry;
const cutoffEpoch = Math.floor(Date.now() / 1000) - retentionDays * 86_400;
const result: CleanupResult = { deleted: 0, errors: 0 };
try {
const stmt = db.prepare("DELETE FROM compression_run_telemetry WHERE timestamp < ?");
const runResult = stmt.run(cutoffEpoch);
result.deleted = runResult.changes;
console.log(
`[Cleanup] Deleted ${result.deleted} compression_run_telemetry older than ${retentionDays} days`
);
} catch (err: unknown) {
console.error("[Cleanup] Error cleaning compression_run_telemetry:", err);
result.errors++;
}
return result;
}
/**
* Run all cleanup functions if auto-cleanup is enabled.
*/
@@ -300,7 +389,10 @@ export async function runAutoCleanup(): Promise<{
mcpAudit: await cleanupMcpAudit(),
a2aEvents: await cleanupA2aEvents(),
memoryEntries: await cleanupMemoryEntries(),
domainCostHistory: await cleanupDomainCostHistory(),
compressionCacheStats: await cleanupCompressionCacheStats(),
xpAuditLog: await cleanupXpAuditLog(),
compressionRunTelemetry: await cleanupCompressionRunTelemetry(),
proxyLogs: await cleanupProxyLogs(),
};
@@ -523,9 +615,7 @@ export async function cleanupProxyLogs(): Promise<CleanupResult> {
const runResult = stmt.run(cutoffISO);
result.deleted = runResult.changes;
console.log(
`[Cleanup] Deleted ${result.deleted} proxy_logs older than ${retentionDays} days`
);
console.log(`[Cleanup] Deleted ${result.deleted} proxy_logs older than ${retentionDays} days`);
} catch (err: unknown) {
console.error("[Cleanup] Error cleaning proxy_logs:", err);
result.errors++;
@@ -557,9 +647,7 @@ export function startCleanupScheduler(): void {
const proxyResult = await cleanupProxyLogs();
const totalDeleted = result.totalDeleted + proxyResult.deleted;
if (totalDeleted > 0) {
console.log(
`[Cleanup] Startup cleanup freed ${totalDeleted} rows. Running VACUUM...`
);
console.log(`[Cleanup] Startup cleanup freed ${totalDeleted} rows. Running VACUUM...`);
try {
const db = getDbInstance();
db.exec("VACUUM");
@@ -580,9 +668,7 @@ export function startCleanupScheduler(): void {
const proxyResult = await cleanupProxyLogs();
const totalDeleted = result.totalDeleted + proxyResult.deleted;
if (totalDeleted > 0) {
console.log(
`[Cleanup] Periodic cleanup freed ${totalDeleted} rows. Running VACUUM...`
);
console.log(`[Cleanup] Periodic cleanup freed ${totalDeleted} rows. Running VACUUM...`);
try {
const db = getDbInstance();
db.exec("VACUUM");

View File

@@ -49,7 +49,10 @@ const LEGACY_FLAT_KEYS: {
callLogs: ["callLogs"],
usageHistory: ["usageHistory"],
memoryEntries: ["memoryEntries"],
domainCostHistory: ["domainCostHistory"],
compressionCacheStats: ["compressionCacheStats"],
xpAuditLog: ["xpAuditLog"],
compressionRunTelemetry: ["compressionRunTelemetry"],
autoCleanupEnabled: ["autoCleanupEnabled"],
},
aggregation: {

View File

@@ -46,7 +46,10 @@ export interface DatabaseSettings {
callLogs: number;
usageHistory: number;
memoryEntries: number;
domainCostHistory: number;
compressionCacheStats: number;
xpAuditLog: number;
compressionRunTelemetry: number;
autoCleanupEnabled: boolean;
};
@@ -107,7 +110,10 @@ export const DEFAULT_DATABASE_SETTINGS: Omit<DatabaseSettings, "location" | "sta
callLogs: 30,
usageHistory: 30,
memoryEntries: 30,
domainCostHistory: 30,
compressionCacheStats: 30,
xpAuditLog: 30,
compressionRunTelemetry: 30,
autoCleanupEnabled: true,
},
aggregation: {