fix(target-allocator): tolerate missing ServiceMonitor/PodMonitor CRDs

cmd/amazon-cloudwatch-agent-target-allocator/config/config.go

@@ -119,6 +119,13 @@ func LoadFromCLI(target *Config, flagSet *pflag.FlagSet) error {
 		return err
 	}
 
+	// OR the CLI flag into the YAML value so either source can enable the watcher.
+	prometheusCREnabled, err := getPrometheusCREnabled(flagSet)
+	if err != nil {
+		return err
+	}
+	target.PrometheusCR.Enabled = target.PrometheusCR.Enabled || prometheusCREnabled
+
 	target.HTTPS.Enabled, err = getHttpsEnabled(flagSet)
 	if err != nil {
 		return err

cmd/amazon-cloudwatch-agent-target-allocator/config/flags.go

@@ -34,6 +34,7 @@ func getFlagSet(errorHandling pflag.ErrorHandling) *pflag.FlagSet {
 	flagSet := pflag.NewFlagSet(targetAllocatorName, errorHandling)
 	flagSet.String(configFilePathFlagName, DefaultConfigFilePath, "The path to the config file.")
 	flagSet.String(kubeConfigPathFlagName, filepath.Join(homedir.HomeDir(), ".kube", "config"), "absolute path to the KubeconfigPath file")
+	flagSet.Bool(prometheusCREnabledFlagName, false, "Enable watching of Prometheus Operator custom resources (ServiceMonitor/PodMonitor) to dynamically generate scrape configs.")
 	flagSet.Bool(reloadConfigFlagName, false, "Enable automatic configuration reloading. This functionality is deprecated and will be removed in a future release.")
 	flagSet.Bool(httpsEnabledFlagName, true, "Enable HTTPS additional server")
 	flagSet.String(listenAddrHttpsFlagName, ":8443", "The address where this service serves over HTTPS.")
@@ -58,6 +59,10 @@ func getConfigReloadEnabled(flagSet *pflag.FlagSet) (bool, error) {
 	return flagSet.GetBool(reloadConfigFlagName)
 }
 
+func getPrometheusCREnabled(flagSet *pflag.FlagSet) (bool, error) {
+	return flagSet.GetBool(prometheusCREnabledFlagName)
+}
+
 func getHttpsListenAddr(flagSet *pflag.FlagSet) (string, error) {
 	return flagSet.GetString(listenAddrHttpsFlagName)
 }

cmd/amazon-cloudwatch-agent-target-allocator/config/flags_test.go

@@ -17,6 +17,7 @@ func TestGetFlagSet(t *testing.T) {
 	// Check if each flag exists
 	assert.NotNil(t, fs.Lookup(configFilePathFlagName), "Flag %s not found", configFilePathFlagName)
 	assert.NotNil(t, fs.Lookup(kubeConfigPathFlagName), "Flag %s not found", kubeConfigPathFlagName)
+	assert.NotNil(t, fs.Lookup(prometheusCREnabledFlagName), "Flag %s not found", prometheusCREnabledFlagName)
 }
 
 func TestFlagGetters(t *testing.T) {
@@ -45,6 +46,18 @@ func TestFlagGetters(t *testing.T) {
 			expectedValue: true,
 			getterFunc:    func(fs *pflag.FlagSet) (interface{}, error) { return getConfigReloadEnabled(fs) },
 		},
+		{
+			name:          "GetPrometheusCREnabled",
+			flagArgs:      []string{"--" + prometheusCREnabledFlagName},
+			expectedValue: true,
+			getterFunc:    func(fs *pflag.FlagSet) (interface{}, error) { return getPrometheusCREnabled(fs) },
+		},
+		{
+			name:          "GetPrometheusCREnabledDefault",
+			flagArgs:      []string{},
+			expectedValue: false,
+			getterFunc:    func(fs *pflag.FlagSet) (interface{}, error) { return getPrometheusCREnabled(fs) },
+		},
 		{
 			name:        "InvalidFlag",
 			flagArgs:    []string{"--invalid-flag", "value"},

cmd/amazon-cloudwatch-agent-target-allocator/config/scrape_protocols_regression_test.go

@@ -0,0 +1,36 @@
+// Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+// SPDX-License-Identifier: Apache-2.0
+
+package config
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// TestScrapeProtocolsDefaultedOnLoad guards against "scrape_protocols cannot be empty" regression.
+func TestScrapeProtocolsDefaultedOnLoad(t *testing.T) {
+	got := CreateDefaultConfig()
+	err := LoadFromFile("./testdata/scrape_protocols_omitted_test.yaml", &got)
+	require.NoError(t, err)
+
+	require.NotNil(t, got.PromConfig)
+	require.NotEmpty(t, got.PromConfig.ScrapeConfigs)
+
+	for _, sc := range got.PromConfig.ScrapeConfigs {
+		assert.NotEmpty(t, sc.ScrapeProtocols,
+			"scrape_protocols must be defaulted for job %q", sc.JobName)
+	}
+
+	// Spot-check the specific static job from the reproduction by name.
+	found := false
+	for _, sc := range got.PromConfig.ScrapeConfigs {
+		if sc.JobName == "prometheus-sample-app" {
+			found = true
+			assert.Greater(t, len(sc.ScrapeProtocols), 0)
+		}
+	}
+	require.True(t, found, "expected the 'prometheus-sample-app' job to be present")
+}

cmd/amazon-cloudwatch-agent-target-allocator/config/testdata/scrape_protocols_omitted_test.yaml

@@ -0,0 +1,14 @@
+# Regression fixture: a scrape job that omits scrape_protocols.
+# The TA config-load path must default scrape_protocols so the agent does not
+# reject the config with "scrape_protocols cannot be empty".
+config:
+  scrape_configs:
+    - job_name: prometheus-sample-app
+      kubernetes_sd_configs:
+        - role: pod
+      relabel_configs:
+        - source_labels: [__meta_kubernetes_pod_label_app]
+          regex: prometheus-sample-app
+          action: keep
+        - target_label: label1
+          replacement: value1