From 341dbd30073270117a1f3fd1e019e519781613e3 Mon Sep 17 00:00:00 2001
From: fahadahmadansari111
 <57217561+fahadahmadansari111@users.noreply.github.com>
Date: Mon, 16 Feb 2026 09:23:11 +0530
Subject: [PATCH] Add health check endpoints (/health and /ready) for container
 orchestration liveness and readiness probes. (#104)

* added health endpoint

* formatted files

---------

Co-authored-by: lxowalle <83055338+lxowalle@users.noreply.github.com>
---
 Dockerfile           |   4 ++
 cmd/picoclaw/main.go |  11 +++
 pkg/health/server.go | 164 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 179 insertions(+)
 create mode 100644 pkg/health/server.go

diff --git a/Dockerfile b/Dockerfile
index 433d962..dd98ec0 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -22,6 +22,10 @@ FROM alpine:3.23
 
 RUN apk add --no-cache ca-certificates tzdata curl
 
+# Health check
+HEALTHCHECK --interval=30s --timeout=3s --start-period=5s --retries=3 \
+  CMD wget -q --spider http://localhost:18790/health || exit 1
+
 # Copy binary
 COPY --from=builder /src/build/picoclaw /usr/local/bin/picoclaw
 
diff --git a/cmd/picoclaw/main.go b/cmd/picoclaw/main.go
index 2129662..cd3637a 100644
--- a/cmd/picoclaw/main.go
+++ b/cmd/picoclaw/main.go
@@ -13,6 +13,7 @@ import (
 	"fmt"
 	"io"
 	"io/fs"
+	"net/http"
 	"os"
 	"os/signal"
 	"path/filepath"
@@ -28,6 +29,7 @@ import (
 	"github.com/sipeed/picoclaw/pkg/config"
 	"github.com/sipeed/picoclaw/pkg/cron"
 	"github.com/sipeed/picoclaw/pkg/devices"
+	"github.com/sipeed/picoclaw/pkg/health"
 	"github.com/sipeed/picoclaw/pkg/heartbeat"
 	"github.com/sipeed/picoclaw/pkg/logger"
 	"github.com/sipeed/picoclaw/pkg/migrate"
@@ -658,6 +660,14 @@ func gatewayCmd() {
 		fmt.Printf("Error starting channels: %v\n", err)
 	}
 
+	healthServer := health.NewServer(cfg.Gateway.Host, cfg.Gateway.Port)
+	go func() {
+		if err := healthServer.Start(); err != nil && err != http.ErrServerClosed {
+			logger.ErrorCF("health", "Health server error", map[string]interface{}{"error": err.Error()})
+		}
+	}()
+	fmt.Printf("✓ Health endpoints available at http://%s:%d/health and /ready\n", cfg.Gateway.Host, cfg.Gateway.Port)
+
 	go agentLoop.Run(ctx)
 
 	sigChan := make(chan os.Signal, 1)
@@ -666,6 +676,7 @@ func gatewayCmd() {
 
 	fmt.Println("\nShutting down...")
 	cancel()
+	healthServer.Stop(context.Background())
 	deviceService.Stop()
 	heartbeatService.Stop()
 	cronService.Stop()
diff --git a/pkg/health/server.go b/pkg/health/server.go
new file mode 100644
index 0000000..77b3603
--- /dev/null
+++ b/pkg/health/server.go
@@ -0,0 +1,164 @@
+package health
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"net/http"
+	"sync"
+	"time"
+)
+
+type Server struct {
+	server    *http.Server
+	mu        sync.RWMutex
+	ready     bool
+	checks    map[string]Check
+	startTime time.Time
+}
+
+type Check struct {
+	Name      string    `json:"name"`
+	Status    string    `json:"status"`
+	Message   string    `json:"message,omitempty"`
+	Timestamp time.Time `json:"timestamp"`
+}
+
+type StatusResponse struct {
+	Status string           `json:"status"`
+	Uptime string           `json:"uptime"`
+	Checks map[string]Check `json:"checks,omitempty"`
+}
+
+func NewServer(host string, port int) *Server {
+	mux := http.NewServeMux()
+	s := &Server{
+		ready:     false,
+		checks:    make(map[string]Check),
+		startTime: time.Now(),
+	}
+
+	mux.HandleFunc("/health", s.healthHandler)
+	mux.HandleFunc("/ready", s.readyHandler)
+
+	addr := fmt.Sprintf("%s:%d", host, port)
+	s.server = &http.Server{
+		Addr:         addr,
+		Handler:      mux,
+		ReadTimeout:  5 * time.Second,
+		WriteTimeout: 5 * time.Second,
+	}
+
+	return s
+}
+
+func (s *Server) Start() error {
+	s.mu.Lock()
+	s.ready = true
+	s.mu.Unlock()
+	return s.server.ListenAndServe()
+}
+
+func (s *Server) StartContext(ctx context.Context) error {
+	s.mu.Lock()
+	s.ready = true
+	s.mu.Unlock()
+
+	errCh := make(chan error, 1)
+	go func() {
+		errCh <- s.server.ListenAndServe()
+	}()
+
+	select {
+	case err := <-errCh:
+		return err
+	case <-ctx.Done():
+		return s.server.Shutdown(context.Background())
+	}
+}
+
+func (s *Server) Stop(ctx context.Context) error {
+	s.mu.Lock()
+	s.ready = false
+	s.mu.Unlock()
+	return s.server.Shutdown(ctx)
+}
+
+func (s *Server) SetReady(ready bool) {
+	s.mu.Lock()
+	s.ready = ready
+	s.mu.Unlock()
+}
+
+func (s *Server) RegisterCheck(name string, checkFn func() (bool, string)) {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+
+	status, msg := checkFn()
+	s.checks[name] = Check{
+		Name:      name,
+		Status:    statusString(status),
+		Message:   msg,
+		Timestamp: time.Now(),
+	}
+}
+
+func (s *Server) healthHandler(w http.ResponseWriter, r *http.Request) {
+	w.Header().Set("Content-Type", "application/json")
+	w.WriteHeader(http.StatusOK)
+
+	uptime := time.Since(s.startTime)
+	resp := StatusResponse{
+		Status: "ok",
+		Uptime: uptime.String(),
+	}
+
+	json.NewEncoder(w).Encode(resp)
+}
+
+func (s *Server) readyHandler(w http.ResponseWriter, r *http.Request) {
+	w.Header().Set("Content-Type", "application/json")
+
+	s.mu.RLock()
+	ready := s.ready
+	checks := make(map[string]Check)
+	for k, v := range s.checks {
+		checks[k] = v
+	}
+	s.mu.RUnlock()
+
+	if !ready {
+		w.WriteHeader(http.StatusServiceUnavailable)
+		json.NewEncoder(w).Encode(StatusResponse{
+			Status: "not ready",
+			Checks: checks,
+		})
+		return
+	}
+
+	for _, check := range checks {
+		if check.Status == "fail" {
+			w.WriteHeader(http.StatusServiceUnavailable)
+			json.NewEncoder(w).Encode(StatusResponse{
+				Status: "not ready",
+				Checks: checks,
+			})
+			return
+		}
+	}
+
+	w.WriteHeader(http.StatusOK)
+	uptime := time.Since(s.startTime)
+	json.NewEncoder(w).Encode(StatusResponse{
+		Status: "ready",
+		Uptime: uptime.String(),
+		Checks: checks,
+	})
+}
+
+func statusString(ok bool) string {
+	if ok {
+		return "ok"
+	}
+	return "fail"
+}