chore(release): v2.2.8

fix(docker): healthcheck now uses /api/monitoring/health (#296, PR #301)
fix(rate-limit): maxWait=120s on Bottleneck prevents endless queue (#297, PR #302)

CHANGELOG.md

@@ -11,6 +11,17 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ---
 
+## [2.2.8] — 2026-03-11
+
+> ### Bug Fixes
+
+### Bug Fixes
+
+- **Docker healthcheck wrong endpoint (#296)** — `scripts/healthcheck.mjs` now queries `/api/monitoring/health` instead of `/api/settings`. Aligns the healthcheck with all other health monitoring components (PR #301).
+- **429 causes endless queue / requests hang forever (#297)** — Added `maxWait=120000` (2 min) to all Bottleneck instances. When all provider quotas are exhausted, requests now fail-fast with a clean error instead of queueing indefinitely. Configurable via `RATE_LIMIT_MAX_WAIT_MS` env var (PR #302).
+
+---
+
 ## [2.2.7] — 2026-03-10
 
 > ### Bug Fixes & Dependency Updates

docs/openapi.yaml

@@ -1,7 +1,7 @@
 openapi: 3.1.0
 info:
   title: OmniRoute API
-  version: 2.2.7
+  version: 2.2.8
   description: |
     OmniRoute is a local-first AI API proxy router. It provides an OpenAI-compatible
     endpoint that routes requests to multiple AI providers with load balancing,

open-sse/services/rateLimitManager.ts

@@ -59,6 +59,11 @@ const PERSIST_DEBOUNCE_MS = 60_000; // Debounce persistence to every 60s max
 // Track initialization
 let initialized = false;
 
+// Max time (ms) a job can wait in queue before failing with a timeout error.
+// Prevents infinite queuing when all providers are exhausted after a 429.
+// Configurable via RATE_LIMIT_MAX_WAIT_MS env var (default: 2 minutes).
+const MAX_WAIT_MS = parseInt(process.env.RATE_LIMIT_MAX_WAIT_MS || "120000", 10);
+
 // Default conservative settings (before we learn from headers)
 const DEFAULT_SETTINGS = {
   maxConcurrent: 10,
@@ -66,6 +71,7 @@ const DEFAULT_SETTINGS = {
   reservoir: null, // No initial reservoir — unlimited until we learn
   reservoirRefreshAmount: null,
   reservoirRefreshInterval: null,
+  maxWait: MAX_WAIT_MS, // Fail-fast: don't queue forever on 429 exhaustion
 };
 
 /**
@@ -111,6 +117,7 @@ export async function initializeRateLimits() {
               reservoir: rpm,
               reservoirRefreshAmount: rpm,
               reservoirRefreshInterval: 60 * 1000,
+              maxWait: MAX_WAIT_MS,
               id: key,
             })
           );
@@ -135,6 +142,7 @@ export async function initializeRateLimits() {
               reservoir: DEFAULT_API_LIMITS.requestsPerMinute,
               reservoirRefreshAmount: DEFAULT_API_LIMITS.requestsPerMinute,
               reservoirRefreshInterval: 60 * 1000, // Refresh every minute
+              maxWait: MAX_WAIT_MS,
               id: key,
             })
           );

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "omniroute",
-  "version": "2.2.7",
+  "version": "2.2.8",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "omniroute",
-      "version": "2.2.7",
+      "version": "2.2.8",
       "hasInstallScript": true,
       "license": "MIT",
       "workspaces": [

package.json

@@ -1,6 +1,6 @@
 {
   "name": "omniroute",
-  "version": "2.2.7",
+  "version": "2.2.8",
   "description": "Smart AI Router with auto fallback — route to FREE & cheap models, zero downtime. Works with Cursor, Cline, Claude Desktop, Codex, and any OpenAI-compatible tool.",
   "type": "module",
   "bin": {

scripts/healthcheck.mjs

@@ -2,12 +2,12 @@
 
 /**
  * Docker healthcheck script for OmniRoute.
- * Checks the /api/settings endpoint on the dashboard port.
+ * Checks the /api/monitoring/health endpoint on the dashboard port.
  * Used by Dockerfile and docker-compose files.
  */
 const port = process.env.DASHBOARD_PORT || process.env.PORT || "20128";
 
-fetch(`http://127.0.0.1:${port}/api/settings`)
+fetch(`http://127.0.0.1:${port}/api/monitoring/health`)
   .then((r) => {
     if (!r.ok) throw new Error(`HTTP ${r.status}`);
   })