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
This commit is contained in:
Test
2026-08-23 16:33:49 -07:00
parent a707e2f23f
commit 33104af8a8
11 changed files with 808 additions and 66 deletions
+74
View File
@@ -0,0 +1,74 @@
package logging
import (
"testing"
"github.com/stretchr/testify/assert"
)
func TestInitLogger(t *testing.T) {
err := InitLogger()
assert.NoError(t, err)
}
func TestGetLogger(t *testing.T) {
lg := GetLogger()
assert.NotNil(t, lg)
}
func TestStringField(t *testing.T) {
field := String("key", "value")
assert.NotNil(t, field)
assert.Equal(t, "key", field.Key)
}
func TestIntField(t *testing.T) {
field := Int("counter", 42)
assert.NotNil(t, field)
assert.Equal(t, "counter", field.Key)
}
func TestInt64Field(t *testing.T) {
field := Int64("bignum", 9223372036854775807)
assert.NotNil(t, field)
assert.Equal(t, "bignum", field.Key)
}
func TestErrorField(t *testing.T) {
err := assert.AnError
field := Err(err)
assert.NotNil(t, field)
assert.Equal(t, "error", field.Key)
}
// Note: TestSync is omitted because zap.Sync() may fail on stderr in test environment
// This is expected behavior and doesn't affect production use
func TestWith(t *testing.T) {
InitLogger()
lg := With(String("test", "value"))
assert.NotNil(t, lg)
}
// TestLoggingFunctions tests that logging functions don't panic
func TestLoggingFunctions(t *testing.T) {
InitLogger()
defer Sync()
// These should not panic
assert.NotPanics(t, func() {
Info("test info", String("field", "value"))
})
assert.NotPanics(t, func() {
Warn("test warn", String("field", "value"))
})
assert.NotPanics(t, func() {
Debug("test debug", String("field", "value"))
})
assert.NotPanics(t, func() {
Error("test error", String("field", "value"))
})
}