fix(distributed): worker container healthcheck always unhealthy

The Dockerfile's HEALTHCHECK probes http://localhost:8080/readyz, which
is the OpenAI API server port. When the same image runs as a worker, it
listens on the gRPC base port (50051) and an HTTP file transfer server
on port-1 (50050) — nothing on 8080 — so docker always reports the
container as unhealthy.

Add unauthenticated /readyz and /healthz endpoints to the worker's HTTP
file transfer server, and override HEALTHCHECK_ENDPOINT for worker-1 in
the distributed compose file. Disable the healthcheck for agent-worker
since it is NATS-only and exposes no HTTP server.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: claude-code:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

Author: mudler

core/services/nodes/file_transfer_server.go

@@ -109,6 +109,21 @@ func StartFileTransferServerWithListener(lis net.Listener, stagingDir, modelsDir
 		registerBackendLogHandlers(mux, token, ls)
 	}
 
+	// Liveness/readiness probes — unauthenticated so container orchestrators
+	// (Docker HEALTHCHECK, k8s probes) can hit them without the bearer token.
+	// Reaching this point means the listener is bound and the mux is serving.
+	healthHandler := func(w http.ResponseWriter, r *http.Request) {
+		if r.Method != http.MethodGet && r.Method != http.MethodHead {
+			http.Error(w, "method not allowed", http.StatusMethodNotAllowed)
+			return
+		}
+		w.Header().Set("Content-Type", "text/plain; charset=utf-8")
+		w.WriteHeader(http.StatusOK)
+		_, _ = w.Write([]byte("ok"))
+	}
+	mux.HandleFunc("/readyz", healthHandler)
+	mux.HandleFunc("/healthz", healthHandler)
+
 	addr := lis.Addr().String()
 	server := &http.Server{
 		Handler:           mux,

docker-compose.distributed.yaml

@@ -96,7 +96,12 @@ services:
         - BASE_IMAGE=ubuntu:24.04
     command:
       - worker
+    # The image's default HEALTHCHECK targets the server's /readyz on 8080.
+    # Workers don't run the OpenAI API server — their HTTP file transfer
+    # server runs on the gRPC base port - 1 (50050 here) and exposes /readyz.
+    # Override the env var so the inherited HEALTHCHECK probes the right port.
     environment:
+      HEALTHCHECK_ENDPOINT: "http://localhost:50050/readyz"
       LOCALAI_SERVE_ADDR: "0.0.0.0:50051"
       LOCALAI_ADVERTISE_ADDR: "worker-1:50051"
       LOCALAI_ADVERTISE_HTTP_ADDR: "worker-1:50050"
@@ -187,6 +192,10 @@ services:
       - |
         apt-get update -qq && apt-get install -y -qq docker.io >/dev/null 2>&1
         exec /entrypoint.sh agent-worker
+    # The agent worker is NATS-only — no HTTP server to probe. Disable the
+    # image's inherited HEALTHCHECK so the container doesn't show unhealthy.
+    healthcheck:
+      disable: true
     environment:
       LOCALAI_NATS_URL: "nats://nats:4222"
       LOCALAI_REGISTER_TO: "http://localai:8080"