fix: prevent race conditions in sticky round-robin

Adds a mutex to serialize account selection and updates in the
proxy engine. This ensures that concurrent requests respect the
sticky limit and don't distribute to the same account simultaneously.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This commit is contained in:
Catalin Stanciu
2026-01-09 17:46:52 +07:00
committed by decolua
co-authored by Claude Sonnet 4.5
parent 4f292aae63
commit 3ad2f8dc58
+81 -67
View File
@@ -2,6 +2,9 @@ import { getProviderConnections, validateApiKey, updateProviderConnection, getSe
import { isAccountUnavailable, getUnavailableUntil } from "open-sse/services/accountFallback.js";
import * as log from "../utils/logger.js";
// Mutex to prevent race conditions during account selection
let selectionMutex = Promise.resolve();
/**
* Get provider credentials from localDb
* Filters out unavailable accounts and returns the selected account based on strategy
@@ -9,86 +12,97 @@ import * as log from "../utils/logger.js";
* @param {string|null} excludeConnectionId - Connection ID to exclude (for retry with next account)
*/
export async function getProviderCredentials(provider, excludeConnectionId = null) {
const connections = await getProviderConnections({ provider, isActive: true });
// Acquire mutex to prevent race conditions
const currentMutex = selectionMutex;
let resolveMutex;
selectionMutex = new Promise(resolve => { resolveMutex = resolve; });
if (connections.length === 0) {
log.warn("AUTH", `No credentials for ${provider}`);
return null;
}
try {
await currentMutex;
// Filter out unavailable accounts and excluded connection
const availableConnections = connections.filter(c => {
if (excludeConnectionId && c.id === excludeConnectionId) return false;
if (isAccountUnavailable(c.rateLimitedUntil)) return false;
return true;
});
const connections = await getProviderConnections({ provider, isActive: true });
if (availableConnections.length === 0) {
log.warn("AUTH", `All ${connections.length} accounts for ${provider} unavailable`);
return null;
}
if (connections.length === 0) {
log.warn("AUTH", `No credentials for ${provider}`);
return null;
}
const settings = await getSettings();
const strategy = settings.fallbackStrategy || "fill-first";
let connection;
if (strategy === "round-robin") {
const stickyLimit = settings.stickyRoundRobinLimit || 3;
// Sort by lastUsed (most recent first) to find current candidate
const byRecency = [...availableConnections].sort((a, b) => {
if (!a.lastUsedAt && !b.lastUsedAt) return (a.priority || 999) - (b.priority || 999);
if (!a.lastUsedAt) return 1;
if (!b.lastUsedAt) return -1;
return new Date(b.lastUsedAt) - new Date(a.lastUsedAt);
// Filter out unavailable accounts and excluded connection
const availableConnections = connections.filter(c => {
if (excludeConnectionId && c.id === excludeConnectionId) return false;
if (isAccountUnavailable(c.rateLimitedUntil)) return false;
return true;
});
const current = byRecency[0];
const currentCount = current?.consecutiveUseCount || 0;
if (availableConnections.length === 0) {
log.warn("AUTH", `All ${connections.length} accounts for ${provider} unavailable`);
return null;
}
if (current && current.lastUsedAt && currentCount < stickyLimit) {
// Stay with current account
connection = current;
// Update lastUsedAt and increment count
updateProviderConnection(connection.id, {
lastUsedAt: new Date().toISOString(),
consecutiveUseCount: (connection.consecutiveUseCount || 0) + 1
}).catch(() => {});
} else {
// Pick the least recently used (excluding current if possible)
const sortedByOldest = [...availableConnections].sort((a, b) => {
const settings = await getSettings();
const strategy = settings.fallbackStrategy || "fill-first";
let connection;
if (strategy === "round-robin") {
const stickyLimit = settings.stickyRoundRobinLimit || 3;
// Sort by lastUsed (most recent first) to find current candidate
const byRecency = [...availableConnections].sort((a, b) => {
if (!a.lastUsedAt && !b.lastUsedAt) return (a.priority || 999) - (b.priority || 999);
if (!a.lastUsedAt) return -1;
if (!b.lastUsedAt) return 1;
return new Date(a.lastUsedAt) - new Date(b.lastUsedAt);
if (!a.lastUsedAt) return 1;
if (!b.lastUsedAt) return -1;
return new Date(b.lastUsedAt) - new Date(a.lastUsedAt);
});
connection = sortedByOldest[0];
const current = byRecency[0];
const currentCount = current?.consecutiveUseCount || 0;
// Update lastUsedAt and reset count to 1
updateProviderConnection(connection.id, {
lastUsedAt: new Date().toISOString(),
consecutiveUseCount: 1
}).catch(() => {});
if (current && current.lastUsedAt && currentCount < stickyLimit) {
// Stay with current account
connection = current;
// Update lastUsedAt and increment count (await to ensure persistence)
await updateProviderConnection(connection.id, {
lastUsedAt: new Date().toISOString(),
consecutiveUseCount: (connection.consecutiveUseCount || 0) + 1
});
} else {
// Pick the least recently used (excluding current if possible)
const sortedByOldest = [...availableConnections].sort((a, b) => {
if (!a.lastUsedAt && !b.lastUsedAt) return (a.priority || 999) - (b.priority || 999);
if (!a.lastUsedAt) return -1;
if (!b.lastUsedAt) return 1;
return new Date(a.lastUsedAt) - new Date(b.lastUsedAt);
});
connection = sortedByOldest[0];
// Update lastUsedAt and reset count to 1 (await to ensure persistence)
await updateProviderConnection(connection.id, {
lastUsedAt: new Date().toISOString(),
consecutiveUseCount: 1
});
}
} else {
// Default: fill-first (already sorted by priority in getProviderConnections)
connection = availableConnections[0];
}
} else {
// Default: fill-first (already sorted by priority in getProviderConnections)
connection = availableConnections[0];
}
return {
apiKey: connection.apiKey,
accessToken: connection.accessToken,
refreshToken: connection.refreshToken,
projectId: connection.projectId,
copilotToken: connection.providerSpecificData?.copilotToken,
providerSpecificData: connection.providerSpecificData,
connectionId: connection.id,
// Include current status for optimization check
testStatus: connection.testStatus,
lastError: connection.lastError,
rateLimitedUntil: connection.rateLimitedUntil
};
return {
apiKey: connection.apiKey,
accessToken: connection.accessToken,
refreshToken: connection.refreshToken,
projectId: connection.projectId,
copilotToken: connection.providerSpecificData?.copilotToken,
providerSpecificData: connection.providerSpecificData,
connectionId: connection.id,
// Include current status for optimization check
testStatus: connection.testStatus,
lastError: connection.lastError,
rateLimitedUntil: connection.rateLimitedUntil
};
} finally {
if (resolveMutex) resolveMutex();
}
}
/**