wip(sync): merge main into next with combined resolutions

This commit is contained in:
coder-mos2
2026-08-02 23:11:22 -05:00
628 changed files with 126796 additions and 4189 deletions
+12 -121
View File
@@ -1,4 +1,4 @@
import { Inject, Injectable, Logger, Optional, type OnModuleInit } from '@nestjs/common';
import { Inject, Injectable, Optional } from '@nestjs/common';
import type { QueueHandle } from '@mosaicstack/queue';
import type { LogService } from '@mosaicstack/log';
import { LOG_SERVICE } from '../log/log.tokens.js';
@@ -13,64 +13,26 @@ export interface GCResult {
};
}
export interface GCSweepResult {
orphanedSessions: number;
totalCleaned: GCResult[];
duration: number;
}
export interface FullGCResult {
valkeyKeys: number;
logsDemoted: number;
jobsPurged: number;
tempFilesRemoved: number;
duration: number;
/** Escape Redis glob metacharacters so a session identifier is always literal. */
function escapeRedisGlobLiteral(value: string): string {
return value.replace(/[\\*?\[\]]/g, '\\$&');
}
@Injectable()
export class SessionGCService implements OnModuleInit {
private readonly logger = new Logger(SessionGCService.name);
export class SessionGCService {
constructor(
// On Local tier there is no Redis — the GC module provides null for this token.
// NOTE: if a future feature stores Redis-backed state on Local tier, this guard
// would silently skip GC for those keys. Revisit when that happens.
// Local tier has no Redis; lifecycle cleanup still demotes this session's logs.
@Optional()
@Inject(REDIS)
private readonly redis: QueueHandle['redis'] | null,
@Inject(LOG_SERVICE) private readonly logService: LogService,
) {}
onModuleInit(): void {
if (!this.redis) {
// Local tier: no Valkey — skip cold-start GC entirely (correct no-op).
this.logger.log('SessionGCService: Valkey GC skipped on local tier (no Redis configured)');
return;
}
// Fire-and-forget: run full GC asynchronously so it does not block the
// NestJS bootstrap chain. Cold-start GC typically takes 100500 ms
// depending on Valkey key count; deferring it removes that latency from
// the TTFB of the first HTTP request.
this.fullCollect()
.then((result) => {
this.logger.log(
`Full GC complete: ${result.valkeyKeys} Valkey keys, ` +
`${result.logsDemoted} logs demoted, ` +
`${result.jobsPurged} jobs purged, ` +
`${result.tempFilesRemoved} temp dirs removed ` +
`(${result.duration}ms)`,
);
})
.catch((err: unknown) => {
this.logger.error('Cold-start GC failed', err instanceof Error ? err.stack : String(err));
});
}
/**
* Scan Valkey for all keys matching a pattern using SCAN (non-blocking).
* KEYS is avoided because it blocks the Valkey event loop for the full scan
* duration, which can cause latency spikes under production key volumes.
* Returns empty array when Redis is not available (Local tier).
* Returns an empty population on the Local tier where Redis is disabled.
*/
private async scanKeys(pattern: string): Promise<string[]> {
if (!this.redis) return [];
@@ -90,9 +52,9 @@ export class SessionGCService implements OnModuleInit {
async collect(sessionId: string): Promise<GCResult> {
const result: GCResult = { sessionId, cleaned: {} };
// 1. Valkey: delete all session-scoped keys (skipped on Local tier)
// 1. Valkey: delete all session-scoped keys (skipped on Local tier).
if (this.redis) {
const pattern = `mosaic:session:${sessionId}:*`;
const pattern = `mosaic:session:${escapeRedisGlobLiteral(sessionId)}:*`;
const valkeyKeys = await this.scanKeys(pattern);
if (valkeyKeys.length > 0) {
await this.redis.del(...valkeyKeys);
@@ -100,84 +62,13 @@ export class SessionGCService implements OnModuleInit {
}
}
// 2. PG: demote hot-tier agent_logs for this session to warm
const cutoff = new Date(); // demote all hot logs for this session
const logsDemoted = await this.logService.logs.promoteToWarm(cutoff);
// 2. PG: demote hot-tier agent logs for this session only.
const cutoff = new Date();
const logsDemoted = await this.logService.logs.promoteSessionToWarm(sessionId, cutoff);
if (logsDemoted > 0) {
result.cleaned.logsDemoted = logsDemoted;
}
return result;
}
/**
* Sweep GC — find orphaned artifacts from dead sessions.
* System-wide operation: only call from admin-authorized paths or internal
* scheduled jobs. Individual session cleanup is handled by collect().
*/
async sweepOrphans(): Promise<GCSweepResult> {
const start = Date.now();
const cleaned: GCResult[] = [];
// 1. Find all session-scoped Valkey keys (non-blocking SCAN)
// Returns empty on Local tier — no Valkey session keys exist there.
const allSessionKeys = await this.scanKeys('mosaic:session:*');
// Extract unique session IDs from keys
const sessionIds = new Set<string>();
for (const key of allSessionKeys) {
const match = key.match(/^mosaic:session:([^:]+):/);
if (match) sessionIds.add(match[1]!);
}
// 2. For each session ID, collect stale keys
for (const sessionId of sessionIds) {
const gcResult = await this.collect(sessionId);
if (Object.keys(gcResult.cleaned).length > 0) {
cleaned.push(gcResult);
}
}
return {
orphanedSessions: cleaned.length,
totalCleaned: cleaned,
duration: Date.now() - start,
};
}
/**
* Full GC — aggressive collection for cold start.
* Assumes no sessions survived the restart.
*/
async fullCollect(): Promise<FullGCResult> {
const start = Date.now();
let valkeyKeysCount = 0;
if (this.redis) {
// 1. Valkey: delete ALL session-scoped keys (non-blocking SCAN)
const sessionKeys = await this.scanKeys('mosaic:session:*');
if (sessionKeys.length > 0) {
await this.redis.del(...sessionKeys);
}
valkeyKeysCount = sessionKeys.length;
}
// 2. NOTE: channel keys are NOT collected on cold start
// (discord/telegram plugins may reconnect and resume)
// 3. PG: demote stale hot-tier logs older than 24h to warm
const hotCutoff = new Date(Date.now() - 24 * 60 * 60 * 1000);
const logsDemoted = await this.logService.logs.promoteToWarm(hotCutoff);
// 4. No summarization job purge API available yet
const jobsPurged = 0;
return {
valkeyKeys: valkeyKeysCount,
logsDemoted,
jobsPurged,
tempFilesRemoved: 0,
duration: Date.now() - start,
};
}
}