MythEclipseandClaude Opus 4.8
07032ab521
- Split llmModerationClient.ts (2170 lines) into 5 focused sub-modules - Split aiAnalyzer.ts (1282 lines) into 4 modular pipelines - Split messages.db.ts (826 lines) into 5 domain-specific modules - Moved shared schema to @bete/shared, eliminated backend duplication - Added createChildLogger to all voice-recording and AI moderation modules - Extracted tryCommandThenFallback, normalizeMediaState, DEFAULT_VOICE_STATUS - Created shared pagination.ts utility, eliminated 5+ cursor-pagination duplications - Created shared messageMapper.ts for row mapping - Standardized backend error handling with asyncHandler - Added frontend createLogger utility and useAsyncAction hook - Added structured logging to frontend hooks, socket, and API client Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
54 lines
1.4 KiB
TypeScript
54 lines
1.4 KiB
TypeScript
import { createChildLogger } from "@bete/shared/logger";
|
|
import pLimit from "p-limit";
|
|
import { config } from "../../shared/config/config.js";
|
|
|
|
const logger = createChildLogger("concurrencyLimiter");
|
|
|
|
/**
|
|
* Concurrency limiter for LLM API calls.
|
|
*
|
|
* Prevents rate-limit (429) errors by capping simultaneous requests
|
|
* to the configured maximum (default: 5).
|
|
*/
|
|
const llmSemaphore = pLimit(config.AI_LLM_MAX_CONCURRENT ?? 5);
|
|
|
|
let activeCount = 0;
|
|
let pendingCount = 0;
|
|
|
|
// Track queue state changes for logging
|
|
function updateCounts(): void {
|
|
// p-limit exposes queueSize and activeCount via constructor internals,
|
|
// but we track via our wrapper to avoid depending on internals.
|
|
}
|
|
|
|
export async function withLlmConcurrency<T>(fn: () => Promise<T>): Promise<T> {
|
|
const queuedAt = activeCount + pendingCount;
|
|
pendingCount++;
|
|
logger.debug(
|
|
{ activeCount, pendingCount, maxConcurrent: config.AI_LLM_MAX_CONCURRENT },
|
|
"Queuing LLM request",
|
|
);
|
|
|
|
return llmSemaphore(async () => {
|
|
pendingCount--;
|
|
activeCount++;
|
|
|
|
if (activeCount >= (config.AI_LLM_MAX_CONCURRENT ?? 5)) {
|
|
logger.warn(
|
|
{ activeCount, maxConcurrent: config.AI_LLM_MAX_CONCURRENT },
|
|
"LLM concurrency limit reached",
|
|
);
|
|
}
|
|
|
|
try {
|
|
return await fn();
|
|
} finally {
|
|
activeCount--;
|
|
logger.debug(
|
|
{ activeCount, pendingCount },
|
|
"LLM request completed, concurrency slot released",
|
|
);
|
|
}
|
|
});
|
|
}
|