Files
poimen-workflows/cmd/starter/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

146 lines
4.6 KiB
Go

package main
import (
"context"
"flag"
"fmt"
"log"
"strings"
"time"
"go.temporal.io/sdk/client"
"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() {
var (
repoPath = flag.String("repo", "", "target repo path")
remoteURL = flag.String("remote", "", "remote URL")
milestone = flag.String("milestone", "T0", "milestone ID")
dryRun = flag.Bool("dry-run", false, "disable git push/merge")
plannerModel = flag.String("planner-model", "ornith", "planner model ID")
judgeModel = flag.String("judge-model", "ornith", "judge model ID")
implementerModel = flag.String("implementer-model", "claude-sonnet-5", "implementer model ID")
healthCheck = flag.Bool("health", false, "check health and exit")
)
flag.Parse()
// Initialize structured logging
if err := logging.InitLogger(); err != nil {
log.Fatalf("failed to initialize logger: %v", err)
}
defer logging.Sync()
// Load configuration first
cfg, err := config.LoadConfig()
if err != nil {
logging.Fatal("failed to load config", logging.Err(err))
}
// Connect to Temporal
logging.Info("connecting to Temporal", logging.String("hostPort", cfg.Temporal.HostPort), logging.String("namespace", cfg.Temporal.Namespace))
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()
// If health check requested, do it and exit
if *healthCheck {
logging.Info("running health check")
healthChecker := health.NewChecker(c)
report := healthChecker.Check(context.Background())
jsonReport, _ := report.ToJSON()
fmt.Println(string(jsonReport))
if report.Status != health.StatusHealthy {
logging.Fatal("health check failed")
}
return
}
// Validate required flags for workflow start
if *repoPath == "" || *remoteURL == "" {
logging.Fatal("--repo and --remote flags are required")
}
// Build OrchestratorInput
input := statemachine.OrchestratorInput{
TargetRepoPath: *repoPath,
RemoteURL: *remoteURL,
Milestone: *milestone,
DryRun: *dryRun,
MaxCyclesBeforeCAN: 100,
Config: statemachine.OrchestratorConfig{
SystemPrompt: "You are an expert software developer orchestrating multi-agent work.",
Skills: []statemachine.SkillRef{},
RolePrompts: map[string]statemachine.PromptSpec{
"planner": {
TemplateRef: "planner/default.tmpl",
Model: statemachine.ModelSpec{
ModelID: *plannerModel,
Thinking: "adaptive",
Effort: "high",
},
},
"judge": {
TemplateRef: "judge/default.tmpl",
Model: statemachine.ModelSpec{
ModelID: *judgeModel,
Thinking: "adaptive",
Effort: "high",
},
},
"implementer": {
TemplateRef: "implementer/default.tmpl",
Model: statemachine.ModelSpec{
ModelID: *implementerModel,
},
},
},
Tuning: statemachine.NewActivityTuning(),
},
}
// Start workflow
workflowID := "orch-" + strings.ReplaceAll(*repoPath, "/", "-")
logging.Info("starting orchestrator workflow", logging.String("workflowID", workflowID), logging.String("repo", *repoPath))
run, err := c.ExecuteWorkflow(context.Background(), client.StartWorkflowOptions{
ID: workflowID,
TaskQueue: "poimen-taskqueue",
}, statemachine.OrchestratorWorkflow, input)
if err != nil {
logging.Fatal("failed to start workflow", logging.Err(err))
}
fmt.Printf("\n=== Workflow Started ===\n")
fmt.Printf("Workflow ID: %s\n", workflowID)
fmt.Printf("Task Queue: poimen-taskqueue\n")
fmt.Printf("\n=== Model Configuration ===\n")
fmt.Printf("Planner Model: %s\n", *plannerModel)
fmt.Printf("Judge Model: %s\n", *judgeModel)
fmt.Printf("Implementer Model: %s\n", *implementerModel)
fmt.Printf("\n=== Monitoring ===\n")
fmt.Printf("Web UI: http://%s:8080/namespaces/%s/workflows/%s\n",
strings.Split(cfg.Temporal.HostPort, ":")[0], cfg.Temporal.Namespace, workflowID)
// Optionally wait for completion (with timeout)
ctx, cancel := context.WithTimeout(context.Background(), 1*time.Minute)
defer cancel()
var result statemachine.OrchestratorOutput
if err := run.Get(ctx, &result); err != nil {
fmt.Printf("\nWorkflow initiated (execution in progress).\n")
fmt.Printf("Check the Web UI for real-time status updates.\n")
} else {
fmt.Printf("\nWorkflow completed: %+v\n", result)
}
}