chore(config): Update field labels for commonly used sources and transforms

lib/vector-config-common/src/human_friendly.rs

@@ -48,7 +48,7 @@ static WELL_KNOWN_ACRONYMS: Lazy<HashSet<String>> = Lazy::new(|| {
         "api", "amqp", "aws", "ec2", "ecs", "gcp", "hec", "http", "https", "nats", "nginx", "s3",
         "sqs", "tls", "ssl", "otel", "gelf", "csv", "json", "rfc3339", "lz4", "us", "eu", "bsd",
         "vrl", "tcp", "udp", "id", "uuid", "kms", "uri", "url", "acp", "uid", "ip", "pid",
-        "ndjson", "ewma", "rtt", "cpu", "acl", "imds", "acl", "alpn",
+        "ndjson", "ewma", "rtt", "cpu", "acl", "imds", "acl", "alpn", "sasl",
     ];
 
     acronyms.iter().map(|s| s.to_lowercase()).collect()

lib/vector-core/src/tcp.rs

@@ -6,6 +6,7 @@ use vector_config::configurable_component;
 #[configurable_component]
 #[derive(Clone, Copy, Debug, PartialEq, Eq)]
 #[serde(deny_unknown_fields)]
+#[configurable(metadata(docs::human_name = "Wait Time"))]
 pub struct TcpKeepaliveConfig {
     /// The time to wait before starting to send TCP keepalive probes on an idle connection.
     #[configurable(metadata(docs::type_unit = "seconds"))]

src/sources/apache_metrics/mod.rs

@@ -42,6 +42,7 @@ pub struct ApacheMetricsConfig {
     /// The interval between scrapes.
     #[serde(default = "default_scrape_interval_secs")]
     #[serde_as(as = "serde_with::DurationSeconds<u64>")]
+    #[configurable(metadata(docs::human_name = "Scrape Interval"))]
     scrape_interval_secs: Duration,
 
     /// The namespace of the metric.

src/sources/aws_ecs_metrics/mod.rs

@@ -87,6 +87,7 @@ pub struct AwsEcsMetricsSourceConfig {
     /// The interval between scrapes, in seconds.
     #[serde(default = "default_scrape_interval_secs")]
     #[serde_as(as = "serde_with::DurationSeconds<u64>")]
+    #[configurable(metadata(docs::human_name = "Scrape Interval"))]
     scrape_interval_secs: Duration,
 
     /// The namespace of the metric.

src/sources/aws_kinesis_firehose/mod.rs

@@ -37,15 +37,15 @@ pub struct AwsKinesisFirehoseConfig {
     #[configurable(metadata(docs::examples = "localhost:443"))]
     address: SocketAddr,
 
-    /// An optional access key to authenticate requests against.
+    /// An access key to authenticate requests against.
     ///
     /// AWS Kinesis Firehose can be configured to pass along a user-configurable access key with each request. If
     /// configured, `access_key` should be set to the same value. Otherwise, all requests are allowed.
     #[configurable(deprecated = "This option has been deprecated, use `access_keys` instead.")]
     #[configurable(metadata(docs::examples = "A94A8FE5CCB19BA61C4C08"))]
     access_key: Option<SensitiveString>,
 
-    /// An optional list of access keys to authenticate requests against.
+    /// A list of access keys to authenticate requests against.
     ///
     /// AWS Kinesis Firehose can be configured to pass along a user-configurable access key with each request. If
     /// configured, `access_keys` should be set to the same value. Otherwise, all requests are allowed.

src/sources/aws_s3/sqs.rs

@@ -90,6 +90,7 @@ pub(super) struct Config {
     #[serde(default = "default_visibility_timeout_secs")]
     #[derivative(Default(value = "default_visibility_timeout_secs()"))]
     #[configurable(metadata(docs::type_unit = "seconds"))]
+    #[configurable(metadata(docs::human_name = "Visibility Timeout"))]
     pub(super) visibility_timeout_secs: u32,
 
     /// Whether to delete the message once it is processed.

src/sources/aws_sqs/config.rs

@@ -58,6 +58,7 @@ pub struct AwsSqsConfig {
     #[serde(default = "default_visibility_timeout_secs")]
     #[derivative(Default(value = "default_visibility_timeout_secs()"))]
     #[configurable(metadata(docs::type_unit = "seconds"))]
+    #[configurable(metadata(docs::human_name = "Visibility Timeout"))]
     pub(super) visibility_timeout_secs: u32,
 
     /// Whether to delete the message once it is processed.

src/sources/gcp_pubsub.rs

@@ -163,13 +163,15 @@ pub struct PubsubConfig {
     /// are all busy and so open a new stream.
     #[serde(default = "default_poll_time")]
     #[serde_as(as = "serde_with::DurationSeconds<f64>")]
+    #[configurable(metadata(docs::human_name = "Poll Time"))]
     pub poll_time_seconds: Duration,
 
     /// The acknowledgement deadline, in seconds, to use for this stream.
     ///
     /// Messages that are not acknowledged when this deadline expires may be retransmitted.
     #[serde(default = "default_ack_deadline")]
     #[serde_as(as = "serde_with::DurationSeconds<u64>")]
+    #[configurable(metadata(docs::human_name = "Acknowledgement Deadline"))]
     pub ack_deadline_secs: Duration,
 
     /// The acknowledgement deadline, in seconds, to use for this stream.
@@ -183,6 +185,7 @@ pub struct PubsubConfig {
     /// The amount of time, in seconds, to wait between retry attempts after an error.
     #[serde(default = "default_retry_delay")]
     #[serde_as(as = "serde_with::DurationSeconds<f64>")]
+    #[configurable(metadata(docs::human_name = "Retry Delay"))]
     pub retry_delay_secs: Duration,
 
     /// The amount of time, in seconds, to wait between retry attempts after an error.
@@ -196,6 +199,7 @@ pub struct PubsubConfig {
     /// `60`, you may see periodic errors sent from the server.
     #[serde(default = "default_keepalive")]
     #[serde_as(as = "serde_with::DurationSeconds<f64>")]
+    #[configurable(metadata(docs::human_name = "Keepalive"))]
     pub keepalive_secs: Duration,
 
     /// The namespace to use for logs. This overrides the global setting.

src/sources/http_client/client.rs

@@ -55,6 +55,7 @@ pub struct HttpClientConfig {
     #[serde(default = "default_interval")]
     #[serde_as(as = "serde_with::DurationSeconds<u64>")]
     #[serde(rename = "scrape_interval_secs")]
+    #[configurable(metadata(docs::human_name = "Scrape Interval"))]
     pub interval: Duration,
 
     /// Custom parameters for the HTTP request query string.

src/sources/kafka.rs

@@ -107,26 +107,30 @@ pub struct KafkaSourceConfig {
     #[configurable(metadata(docs::examples = 5000, docs::examples = 10000))]
     #[configurable(metadata(docs::advanced))]
     #[serde(default = "default_session_timeout_ms")]
+    #[configurable(metadata(docs::human_name = "Session Timeout"))]
     session_timeout_ms: Duration,
 
     /// Timeout for network requests.
     #[serde_as(as = "serde_with::DurationMilliSeconds<u64>")]
     #[configurable(metadata(docs::examples = 30000, docs::examples = 60000))]
     #[configurable(metadata(docs::advanced))]
     #[serde(default = "default_socket_timeout_ms")]
+    #[configurable(metadata(docs::human_name = "Socket Timeout"))]
     socket_timeout_ms: Duration,
 
     /// Maximum time the broker may wait to fill the response.
     #[serde_as(as = "serde_with::DurationMilliSeconds<u64>")]
     #[configurable(metadata(docs::examples = 50, docs::examples = 100))]
     #[configurable(metadata(docs::advanced))]
     #[serde(default = "default_fetch_wait_max_ms")]
+    #[configurable(metadata(docs::human_name = "Max Fetch Wait Time"))]
     fetch_wait_max_ms: Duration,
 
     /// The frequency that the consumer offsets are committed (written) to offset storage.
     #[serde_as(as = "serde_with::DurationMilliSeconds<u64>")]
     #[serde(default = "default_commit_interval_ms")]
     #[configurable(metadata(docs::examples = 5000, docs::examples = 10000))]
+    #[configurable(metadata(docs::human_name = "Commit Interval"))]
     commit_interval_ms: Duration,
 
     /// Overrides the name of the log field used to add the message key to each event.

src/sources/prometheus/scrape.rs

@@ -57,6 +57,7 @@ pub struct PrometheusScrapeConfig {
     #[serde(default = "default_interval")]
     #[serde_as(as = "serde_with::DurationSeconds<u64>")]
     #[serde(rename = "scrape_interval_secs")]
+    #[configurable(metadata(docs::human_name = "Scrape Interval"))]
     interval: Duration,
 
     /// The tag name added to each event representing the scraped instance's `host:port`.

src/sources/splunk_hec/acknowledgements.rs

@@ -27,28 +27,32 @@ pub struct HecAcknowledgementsConfig {
     /// Enables end-to-end acknowledgements.
     pub enabled: Option<bool>,
 
-    /// The maximum number of ack statuses pending query across all channels.
+    /// The maximum number of acknowledgement statuses pending query across all channels.
     ///
     /// Equivalent to the `max_number_of_acked_requests_pending_query` Splunk HEC setting.
     ///
     /// Minimum of `1`.
+    #[configurable(metadata(docs::human_name = "Max Number of Pending Acknowledgements"))]
     pub max_pending_acks: NonZeroU64,
 
     /// The maximum number of Splunk HEC channels clients can use with this source.
     ///
     /// Minimum of `1`.
+    #[configurable(metadata(docs::human_name = "Max Number of Acknowledgement Channels"))]
     pub max_number_of_ack_channels: NonZeroU64,
 
-    /// The maximum number of ack statuses pending query for a single channel.
+    /// The maximum number of acknowledgement statuses pending query for a single channel.
     ///
     /// Equivalent to the `max_number_of_acked_requests_pending_query_per_ack_channel` Splunk HEC setting.
     ///
     /// Minimum of `1`.
+    #[configurable(metadata(docs::human_name = "Max Number of Pending Acknowledgements Per Channel"))]
     pub max_pending_acks_per_channel: NonZeroU64,
 
     /// Whether or not to remove channels after idling for `max_idle_time` seconds.
     ///
-    /// A channel is idling if it is not used for sending data or querying ack statuses.
+    /// A channel is idling if it is not used for sending data or querying acknowledgement statuses.
+    #[configurable(metadata(docs::human_name = "Acknowledgement Idle Cleanup"))]
     pub ack_idle_cleanup: bool,
 
     /// The amount of time, in seconds, a channel is allowed to idle before removal.

src/sources/util/multiline_config.rs

@@ -41,6 +41,7 @@ pub struct MultilineConfig {
     #[serde_as(as = "serde_with::DurationMilliSeconds<u64>")]
     #[configurable(metadata(docs::examples = 1000))]
     #[configurable(metadata(docs::examples = 600000))]
+    #[configurable(metadata(docs::human_name = "Timeout"))]
     pub timeout_ms: Duration,
 }
 

src/transforms/aggregate.rs

@@ -26,6 +26,7 @@ pub struct AggregateConfig {
     ///
     /// During this time frame, metrics with the same series data (name, namespace, tags, and so on) are aggregated.
     #[serde(default = "default_interval_ms")]
+    #[configurable(metadata(docs::human_name = "Flush Interval"))]
     pub interval_ms: u64,
 }
 

src/transforms/reduce/mod.rs

@@ -47,12 +47,14 @@ pub struct ReduceConfig {
     #[serde(default = "default_expire_after_ms")]
     #[serde_as(as = "serde_with::DurationMilliSeconds<u64>")]
     #[derivative(Default(value = "default_expire_after_ms()"))]
+    #[configurable(metadata(docs::human_name = "Expire After"))]
     pub expire_after_ms: Duration,
 
     /// The interval to check for and flush any expired events, in milliseconds.
     #[serde(default = "default_flush_period_ms")]
     #[serde_as(as = "serde_with::DurationMilliSeconds<u64>")]
     #[derivative(Default(value = "default_flush_period_ms()"))]
+    #[configurable(metadata(docs::human_name = "Flush Period"))]
     pub flush_period_ms: Duration,
 
     /// The maximum number of events to group together.

src/transforms/remap.rs

@@ -102,6 +102,7 @@ pub struct RemapConfig {
     /// Additionally, dropped events can potentially be diverted to a specially named output for
     /// further logging and analysis by setting `reroute_dropped`.
     #[serde(default = "crate::serde::default_false")]
+    #[configurable(metadata(docs::human_name = "Drop Event on Error"))]
     pub drop_on_error: bool,
 
     /// Drops any event that is manually aborted during processing.
@@ -117,6 +118,7 @@ pub struct RemapConfig {
     ///
     /// [vrl_docs_abort]: https://vector.dev/docs/reference/vrl/expressions/#abort
     #[serde(default = "crate::serde::default_true")]
+    #[configurable(metadata(docs::human_name = "Drop Event on Abort"))]
     pub drop_on_abort: bool,
 
     /// Reroutes dropped events to a named output instead of halting processing on them.
@@ -129,6 +131,7 @@ pub struct RemapConfig {
     /// to a specially-named output, `dropped`. The original event is annotated with additional
     /// fields describing why the event was dropped.
     #[serde(default = "crate::serde::default_false")]
+    #[configurable(metadata(docs::human_name = "Reroute Dropped Events"))]
     pub reroute_dropped: bool,
 
     #[configurable(derived, metadata(docs::hidden))]

src/transforms/tag_cardinality_limit/config.rs

@@ -60,6 +60,7 @@ pub struct BloomFilterConfig {
     /// The larger the cache size, the less likely it is to have a false positive, or a case where
     /// we allow a new value for tag even after we have reached the configured limits.
     #[serde(default = "default_cache_size")]
+    #[configurable(metadata(docs::human_name = "Cache Size per Key"))]
     pub cache_size_per_key: usize,
 }
 

src/transforms/throttle.rs

@@ -31,6 +31,7 @@ pub struct ThrottleConfig {
 
     /// The time window in which the configured `threshold` is applied, in seconds.
     #[serde_as(as = "serde_with::DurationSeconds<f64>")]
+    #[configurable(metadata(docs::human_name = "Time Window"))]
     window_secs: Duration,
 
     /// The value to group events into separate buckets to be rate limited independently.