dance-lessons-coach/pkg/config/config_hot_reload_test.go

package config

import (
	"context"
	"errors"
	"os"
	"path/filepath"
	"sync"
	"testing"
	"time"

	"github.com/spf13/viper"
	"github.com/stretchr/testify/assert"
	"github.com/stretchr/testify/require"
)

// loadFromFile is a helper that mimics LoadConfig() for a specific file path
// without going through the env-prefix and singleton machinery — keeps the
// test hermetic.
func loadFromFile(t *testing.T, path string) *Config {
	t.Helper()
	v := viper.New()
	v.SetConfigFile(path)
	v.SetConfigType("yaml")
	v.SetDefault("logging.level", "info")
	v.SetDefault("auth.jwt.ttl", time.Hour)
	require.NoError(t, v.ReadInConfig())

	c := &Config{viper: v}
	require.NoError(t, v.Unmarshal(c))
	return c
}

// TestWatchAndApply_LoggingLevel proves the hot-reload pipe end-to-end:
// write a new logging.level to the watched file, the OnConfigChange handler
// re-unmarshals, and the in-memory Config reflects the new value.
func TestWatchAndApply_LoggingLevel(t *testing.T) {
	dir := t.TempDir()
	path := filepath.Join(dir, "config.yaml")
	require.NoError(t, os.WriteFile(path, []byte("logging:\n  level: info\n"), 0644))

	c := loadFromFile(t, path)
	assert.Equal(t, "info", c.GetLogLevel())

	ctx, cancel := context.WithCancel(context.Background())
	defer cancel()
	c.WatchAndApply(ctx)

	// Mutate the file. fsnotify needs a real write event; rewrite atomically.
	require.NoError(t, os.WriteFile(path, []byte("logging:\n  level: debug\n"), 0644))

	// Poll for up to 2s waiting for the in-memory level to flip.
	deadline := time.Now().Add(2 * time.Second)
	for time.Now().Before(deadline) {
		c.reloadMu.RLock()
		level := c.GetLogLevel()
		c.reloadMu.RUnlock()
		if level == "debug" {
			return
		}
		time.Sleep(20 * time.Millisecond)
	}
	c.reloadMu.RLock()
	defer c.reloadMu.RUnlock()
	t.Fatalf("logging level did not hot-reload to debug: still %q", c.GetLogLevel())
}

// TestWatchAndApply_NoFileNoOp confirms the watcher is a safe no-op when no
// config file is in use (env-only / defaults) — important so production
// containers without a mounted config.yaml don't crash.
func TestWatchAndApply_NoFileNoOp(t *testing.T) {
	c := &Config{viper: viper.New()}
	ctx, cancel := context.WithCancel(context.Background())
	defer cancel()
	c.WatchAndApply(ctx) // should return without panicking
}

// TestWatchAndApply_NilViperNoOp confirms the watcher tolerates a Config
// constructed without the viper field (e.g. tests that build a Config{}
// manually — same defensive code path as production but exercised explicitly).
func TestWatchAndApply_NilViperNoOp(t *testing.T) {
	c := &Config{}
	ctx, cancel := context.WithCancel(context.Background())
	defer cancel()
	c.WatchAndApply(ctx)
}

// TestWatchAndApply_JWTTTL proves Phase 2 of ADR-0023: the JWT TTL is
// re-read on every token generation via the GetJWTTTL method value, so
// after a config-file change the new TTL takes effect without restart.
func TestWatchAndApply_JWTTTL(t *testing.T) {
	dir := t.TempDir()
	path := filepath.Join(dir, "config.yaml")
	require.NoError(t, os.WriteFile(path, []byte("auth:\n  jwt:\n    ttl: 1h\n"), 0644))

	c := loadFromFile(t, path)
	assert.Equal(t, time.Hour, c.GetJWTTTL())

	ctx, cancel := context.WithCancel(context.Background())
	defer cancel()
	c.WatchAndApply(ctx)

	require.NoError(t, os.WriteFile(path, []byte("auth:\n  jwt:\n    ttl: 30m\n"), 0644))

	deadline := time.Now().Add(2 * time.Second)
	for time.Now().Before(deadline) {
		c.reloadMu.RLock()
		ttl := c.GetJWTTTL()
		c.reloadMu.RUnlock()
		if ttl == 30*time.Minute {
			return
		}
		time.Sleep(20 * time.Millisecond)
	}
	c.reloadMu.RLock()
	defer c.reloadMu.RUnlock()
	t.Fatalf("auth.jwt.ttl did not hot-reload to 30m: still %s", c.GetJWTTTL())
}

// TestWatchAndApply_TelemetrySamplerType proves Phase 3 of ADR-0023:
// when telemetry.sampler.type changes, the callback registered via
// SetSamplerReconfigureCallback is invoked exactly once with the new value.
func TestWatchAndApply_TelemetrySamplerType(t *testing.T) {
	dir := t.TempDir()
	path := filepath.Join(dir, "config.yaml")
	initial := []byte(`telemetry:
  sampler:
    type: parentbased_always_on
    ratio: 1.0
`)
	changed := []byte(`telemetry:
  sampler:
    type: traceidratio
    ratio: 1.0
`)
	require.NoError(t, os.WriteFile(path, initial, 0644))

	c := loadFromFile(t, path)
	assert.Equal(t, "parentbased_always_on", c.GetSamplerType())

	// Setup callback tracker
	var mu sync.Mutex
	callbackCalled := false
	var recordedType string
	var recordedRatio float64
	c.SetSamplerReconfigureCallback(func(ctx context.Context, samplerType string, samplerRatio float64) error {
		mu.Lock()
		defer mu.Unlock()
		callbackCalled = true
		recordedType = samplerType
		recordedRatio = samplerRatio
		return nil
	})

	ctx, cancel := context.WithCancel(context.Background())
	defer cancel()
	c.WatchAndApply(ctx)

	// Mutate the file
	require.NoError(t, os.WriteFile(path, changed, 0644))

	// Poll for up to 2s waiting for callback
	deadline := time.Now().Add(2 * time.Second)
	for time.Now().Before(deadline) {
		mu.Lock()
		if callbackCalled {
			mu.Unlock()
			assert.Equal(t, "traceidratio", recordedType)
			assert.Equal(t, 1.0, recordedRatio)
			return
		}
		mu.Unlock()
		time.Sleep(20 * time.Millisecond)
	}
	mu.Lock()
	defer mu.Unlock()
	t.Fatalf("sampler reconfigure callback was not invoked: callbackCalled=%v", callbackCalled)
}

// TestWatchAndApply_TelemetrySamplerRatio proves Phase 3 of ADR-0023:
// when telemetry.sampler.ratio changes, the callback registered via
// SetSamplerReconfigureCallback is invoked exactly once with the new value.
func TestWatchAndApply_TelemetrySamplerRatio(t *testing.T) {
	dir := t.TempDir()
	path := filepath.Join(dir, "config.yaml")
	initial := []byte(`telemetry:
  sampler:
    type: parentbased_always_on
    ratio: 1.0
`)
	changed := []byte(`telemetry:
  sampler:
    type: parentbased_always_on
    ratio: 0.5
`)
	require.NoError(t, os.WriteFile(path, initial, 0644))

	c := loadFromFile(t, path)
	assert.Equal(t, 1.0, c.GetSamplerRatio())

	// Setup callback tracker
	var mu sync.Mutex
	callbackCalled := false
	var recordedType string
	var recordedRatio float64
	c.SetSamplerReconfigureCallback(func(ctx context.Context, samplerType string, samplerRatio float64) error {
		mu.Lock()
		defer mu.Unlock()
		callbackCalled = true
		recordedType = samplerType
		recordedRatio = samplerRatio
		return nil
	})

	ctx, cancel := context.WithCancel(context.Background())
	defer cancel()
	c.WatchAndApply(ctx)

	// Mutate the file
	require.NoError(t, os.WriteFile(path, changed, 0644))

	// Poll for up to 2s waiting for callback
	deadline := time.Now().Add(2 * time.Second)
	for time.Now().Before(deadline) {
		mu.Lock()
		if callbackCalled {
			mu.Unlock()
			assert.Equal(t, "parentbased_always_on", recordedType)
			assert.Equal(t, 0.5, recordedRatio)
			return
		}
		mu.Unlock()
		time.Sleep(20 * time.Millisecond)
	}
	mu.Lock()
	defer mu.Unlock()
	t.Fatalf("sampler reconfigure callback was not invoked: callbackCalled=%v", callbackCalled)
}

// TestWatchAndApply_SamplerCallbackNotCalledWhenNoChange proves that
// the sampler callback is NOT invoked when the config file changes but
// sampler type and ratio remain the same.
func TestWatchAndApply_SamplerCallbackNotCalledWhenNoChange(t *testing.T) {
	dir := t.TempDir()
	path := filepath.Join(dir, "config.yaml")
	initial := []byte(`telemetry:
  sampler:
    type: parentbased_always_on
    ratio: 1.0
logging:
  level: info
`)
	changed := []byte(`telemetry:
  sampler:
    type: parentbased_always_on
    ratio: 1.0
logging:
  level: debug
`)
	require.NoError(t, os.WriteFile(path, initial, 0644))

	c := loadFromFile(t, path)

	// Setup callback tracker
	var mu sync.Mutex
	callbackCalled := false
	c.SetSamplerReconfigureCallback(func(ctx context.Context, samplerType string, samplerRatio float64) error {
		mu.Lock()
		defer mu.Unlock()
		callbackCalled = true
		return nil
	})

	ctx, cancel := context.WithCancel(context.Background())
	defer cancel()
	c.WatchAndApply(ctx)

	// Mutate the file (logging level changes, but sampler stays the same)
	require.NoError(t, os.WriteFile(path, changed, 0644))

	// Poll for up to 2s - callback should NOT be called
	deadline := time.Now().Add(2 * time.Second)
	for time.Now().Before(deadline) {
		mu.Lock()
		wasCalled := callbackCalled
		mu.Unlock()
		if wasCalled {
			t.Fatalf("sampler reconfigure callback was invoked but sampler did not change")
		}
		time.Sleep(20 * time.Millisecond)
	}
}

// TestWatchAndApply_SamplerCallbackErrorHandling proves that when the
// sampler reconfigure callback returns an error, the previous sampler values
// are NOT updated, allowing retry on next config change.
func TestWatchAndApply_SamplerCallbackErrorHandling(t *testing.T) {
	dir := t.TempDir()
	path := filepath.Join(dir, "config.yaml")
	initial := []byte(`telemetry:
  sampler:
    type: parentbased_always_on
    ratio: 1.0
`)
	changed := []byte(`telemetry:
  sampler:
    type: traceidratio
    ratio: 0.5
`)
	require.NoError(t, os.WriteFile(path, initial, 0644))

	c := loadFromFile(t, path)

	// Setup callback that returns an error
	expectedErr := errors.New("reconfigure failed")
	var mu sync.Mutex
	callbackCalled := false
	c.SetSamplerReconfigureCallback(func(ctx context.Context, samplerType string, samplerRatio float64) error {
		mu.Lock()
		defer mu.Unlock()
		callbackCalled = true
		return expectedErr
	})

	ctx, cancel := context.WithCancel(context.Background())
	defer cancel()
	c.WatchAndApply(ctx)

	// Mutate the file
	require.NoError(t, os.WriteFile(path, changed, 0644))

	// Poll for up to 2s waiting for callback error
	deadline := time.Now().Add(2 * time.Second)
	for time.Now().Before(deadline) {
		mu.Lock()
		if callbackCalled {
			mu.Unlock()
			// Verify previous values were NOT updated (so retry can work)
			c.reloadMu.RLock()
			assert.Equal(t, "parentbased_always_on", c.prevSamplerType)
			assert.Equal(t, 1.0, c.prevSamplerRatio)
			c.reloadMu.RUnlock()
			return
		}
		mu.Unlock()
		time.Sleep(20 * time.Millisecond)
	}
	mu.Lock()
	defer mu.Unlock()
	t.Fatalf("sampler reconfigure callback was not invoked: callbackCalled=%v", callbackCalled)
}