LibreChat/packages/api/src/mcp/oauth/OAuthReconnectionTracker.ts
Danny Avila 96870e0da0
Some checks failed
Docker Dev Branch Images Build / build (Dockerfile, lc-dev, node) (push) Has been cancelled
Docker Dev Branch Images Build / build (Dockerfile.multi, lc-dev-api, api-build) (push) Has been cancelled
Docker Dev Images Build / build (Dockerfile, librechat-dev, node) (push) Has been cancelled
Docker Dev Images Build / build (Dockerfile.multi, librechat-dev-api, api-build) (push) Has been cancelled
Sync Locize Translations & Create Translation PR / Sync Translation Keys with Locize (push) Has been cancelled
Sync Locize Translations & Create Translation PR / Create Translation PR on Version Published (push) Has been cancelled
refactor: MCP OAuth Polling with Gradual Backoff and Timeout Handling (#9752)
* refactor: Implement gradual backoff polling for oauth connection status with timeout handling

* refactor: Enhance OAuth polling with gradual backoff and timeout handling; update reconnection tracking

* refactor: reconnection timeout behavior in OAuthReconnectionManager and OAuthReconnectionTracker

- Implement tests to verify reconnection timeout handling, including tracking of reconnection states and cleanup of timed-out entries.
- Enhance existing methods in OAuthReconnectionManager and OAuthReconnectionTracker to support timeout checks and cleanup logic.
- Ensure proper handling of multiple servers with different timeout periods and edge cases for active states.

* chore: remove comment

* refactor: Enforce strict 3-minute OAuth timeout with updated polling intervals and improved timeout handling

* refactor: Remove unused polling logic and prevent duplicate polling for servers in MCP server manager

* refactor: Update localization key for no memories message in MemoryViewer

* refactor: Improve MCP tool initialization by handling server failures

- Introduced a mechanism to track failed MCP servers, preventing retries for unavailable servers.
- Added logging for failed tool creation attempts to enhance debugging and monitoring.

* refactor: Update reconnection timeout to enforce a strict 3-minute limit

* ci: Update reconnection timeout tests to reflect a strict 3-minute limit

* ci: Update reconnection timeout tests to enforce a strict 3-minute limit

* chore: Remove unused MCP connection timeout message
2025-09-21 22:58:19 -04:00

89 lines
2.9 KiB
TypeScript

export class OAuthReconnectionTracker {
/** Map of userId -> Set of serverNames that have failed reconnection */
private failed: Map<string, Set<string>> = new Map();
/** Map of userId -> Set of serverNames that are actively reconnecting */
private active: Map<string, Set<string>> = new Map();
/** Map of userId:serverName -> timestamp when reconnection started */
private activeTimestamps: Map<string, number> = new Map();
/** Maximum time (ms) a server can be in reconnecting state before auto-cleanup */
private readonly RECONNECTION_TIMEOUT_MS = 3 * 60 * 1000; // 3 minutes
public isFailed(userId: string, serverName: string): boolean {
return this.failed.get(userId)?.has(serverName) ?? false;
}
/** Check if server is in the active set (original simple check) */
public isActive(userId: string, serverName: string): boolean {
return this.active.get(userId)?.has(serverName) ?? false;
}
/** Check if server is still reconnecting (considers timeout) */
public isStillReconnecting(userId: string, serverName: string): boolean {
if (!this.isActive(userId, serverName)) {
return false;
}
const key = `${userId}:${serverName}`;
const startTime = this.activeTimestamps.get(key);
// If there's a timestamp and it has timed out, it's not still reconnecting
if (startTime && Date.now() - startTime > this.RECONNECTION_TIMEOUT_MS) {
return false;
}
return true;
}
/** Clean up server if it has timed out - returns true if cleanup was performed */
public cleanupIfTimedOut(userId: string, serverName: string): boolean {
const key = `${userId}:${serverName}`;
const startTime = this.activeTimestamps.get(key);
if (startTime && Date.now() - startTime > this.RECONNECTION_TIMEOUT_MS) {
this.removeActive(userId, serverName);
return true;
}
return false;
}
public setFailed(userId: string, serverName: string): void {
if (!this.failed.has(userId)) {
this.failed.set(userId, new Set());
}
this.failed.get(userId)?.add(serverName);
}
public setActive(userId: string, serverName: string): void {
if (!this.active.has(userId)) {
this.active.set(userId, new Set());
}
this.active.get(userId)?.add(serverName);
/** Track when reconnection started */
const key = `${userId}:${serverName}`;
this.activeTimestamps.set(key, Date.now());
}
public removeFailed(userId: string, serverName: string): void {
const userServers = this.failed.get(userId);
userServers?.delete(serverName);
if (userServers?.size === 0) {
this.failed.delete(userId);
}
}
public removeActive(userId: string, serverName: string): void {
const userServers = this.active.get(userId);
userServers?.delete(serverName);
if (userServers?.size === 0) {
this.active.delete(userId);
}
/** Clear timestamp tracking */
const key = `${userId}:${serverName}`;
this.activeTimestamps.delete(key);
}
}