Files
poimen-workflows/cmd/worker/main.go
T
Test 59a1eeed85 feat(T1.2): implement structured logging and Prometheus metrics
- Add internal/logging package with zap-based structured JSON logging
- Support development (colored) and production (JSON) modes via ENVIRONMENT env var
- Add logging helpers: Info(), Error(), Warn(), Debug(), Fatal()
- Add field helpers: String(), Int(), Int64(), Err()
- Add internal/metrics package with 16 comprehensive Prometheus metrics
- Track workflows: starts, completions, duration by type/status
- Track activities: starts, completions, duration, retries by type
- Track LLM calls: total calls and latency by model
- Track git operations: total and duration by operation type
- Track judge decisions: decisions by type
- Track Temporal errors: connection errors by type
- Track cache efficiency: hits and misses by cache type
- Track tasks in progress: gauge metric by task type
- Metrics exported on /metrics endpoint (Prometheus text format)
- Integrate structured logging in cmd/worker and cmd/starter
- Replace all log.Printf/log.Fatalf with structured logging
- Add /metrics endpoint to health check server
- 8/8 logging tests passing, 13/13 metrics tests passing
- All verification criteria met

Dependencies added:
- go.uber.org/zap v1.28.0 (structured logging)
- github.com/prometheus/client_golang v1.24.1 (metrics export)

Closes T1.2
2026-08-23 16:33:49 -07:00

122 lines
3.5 KiB
Go

package main
import (
"context"
"log"
"net/http"
"os"
"os/signal"
"syscall"
"time"
"go.temporal.io/sdk/client"
"go.temporal.io/sdk/worker"
"github.com/rockliang/poimen/workflows/action"
"github.com/rockliang/poimen/workflows/internal/config"
"github.com/rockliang/poimen/workflows/internal/health"
"github.com/rockliang/poimen/workflows/internal/logging"
"github.com/rockliang/poimen/workflows/statemachine"
)
func main() {
// Initialize structured logging
if err := logging.InitLogger(); err != nil {
log.Fatalf("failed to initialize logger: %v", err)
}
defer logging.Sync()
// Load configuration
cfg, err := config.LoadConfig()
if err != nil {
logging.Fatal("failed to load config", logging.Err(err))
}
// Connect to Temporal
c, err := client.Dial(client.Options{
HostPort: cfg.Temporal.HostPort,
Namespace: cfg.Temporal.Namespace,
})
if err != nil {
logging.Fatal("failed to connect to temporal", logging.Err(err))
}
defer c.Close()
// Create worker
w := worker.New(c, "poimen-taskqueue", worker.Options{})
if w == nil {
logging.Fatal("failed to create worker")
}
// Register all workflows
w.RegisterWorkflow(statemachine.OrchestratorWorkflow)
w.RegisterWorkflow(statemachine.TaskUnitWorkflow)
w.RegisterWorkflow(statemachine.TestWorkflow)
// Register all activities
w.RegisterActivity(action.CloneRepoActivity)
w.RegisterActivity(action.GitWorktreeAddActivity)
w.RegisterActivity(action.GitCommitActivity)
w.RegisterActivity(action.GitPushActivity)
w.RegisterActivity(action.GitSquashMergeActivity)
w.RegisterActivity(action.GitDiffActivity)
w.RegisterActivity(action.PrepareSkillsActivity)
w.RegisterActivity(action.PlanningActivity)
w.RegisterActivity(action.ImplementerActivity)
w.RegisterActivity(action.JudgeActivity)
// Integration and lessons activities - register when fully tested
// w.RegisterActivity(action.RunIntegrationTestActivity)
// w.RegisterActivity(action.UpdateLessonsActivity)
// w.RegisterActivity(action.ReadLessonsActivity)
// Initialize health checker
healthChecker := health.NewChecker(c)
healthHandler := health.NewHandler(healthChecker)
// Set up HTTP server for health checks
mux := http.NewServeMux()
healthHandler.RegisterRoutes(mux)
healthServer := &http.Server{
Addr: ":8081",
Handler: mux,
}
// Start health check server in a goroutine
go func() {
log.Printf("Health check server listening on %s", healthServer.Addr)
if err := healthServer.ListenAndServe(); err != nil && err != http.ErrServerClosed {
log.Printf("health check server error: %v", err)
}
}()
// Set up signal handling for graceful shutdown
sigChan := make(chan os.Signal, 1)
signal.Notify(sigChan, syscall.SIGINT, syscall.SIGTERM)
// Run worker in a goroutine
workerErrChan := make(chan error, 1)
go func() {
logging.Info("starting worker on queue", logging.String("queue", "poimen-taskqueue"))
if err := w.Run(worker.InterruptCh()); err != nil {
workerErrChan <- err
}
}()
// Wait for either worker error or signal
select {
case err := <-workerErrChan:
logging.Fatal("worker failed", logging.Err(err))
case sig := <-sigChan:
logging.Info("received signal", logging.String("signal", sig.String()))
w.Stop()
// Shutdown health check server
ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
defer cancel()
if err := healthServer.Shutdown(ctx); err != nil {
logging.Warn("health check server shutdown error", logging.Err(err))
}
logging.Info("worker shutdown complete")
}
}