Update docs version of reference.yml and improve header section (#1416)

* Update docs version of reference.yml and improve header section

* Update docs/en/ingest-management/elastic-agent/configuration/yaml/elastic-agent-reference-yaml.asciidoc

(cherry picked from commit f5344bf)

docs/en/ingest-management/elastic-agent/configuration/yaml/elastic-agent-reference-yaml.asciidoc

@@ -4,7 +4,10 @@
 The {agent} installation includes an `elastic-agent.reference.yml` file that
 describes all the settings available in a standalone configuration.
 
-This file is included here for your convenience.
+To ensure that you're accessing the latest version, refer to the original link:https://github.com/elastic/elastic-agent/blob/main/elastic-agent.reference.yml[`elastic-agent.reference.yml` file] in the `elastic/elastic-agent` repository.
+A copy is included here for your convenience.
+
+Each section of the file and available settings are also described in <<structure-config-file,Structure of a config file>>.
 
 [source,yaml]
 ----

docs/en/ingest-management/elastic-agent/configuration/yaml/elastic-agent-reference-yaml.yml

@@ -11,30 +11,51 @@ outputs:
   default:
     type: elasticsearch
     hosts: [127.0.0.1:9200]
-    api-key: "example-key"
+    api_key: "example-key"
     # username: "elastic"
     # password: "changeme"
 
-inputs:
-    # Each input in a policy must have a unique value for the id key.
-  - id: unique-system-metrics-id
-    type: system/metrics
+    # Performance preset for elasticsearch outputs. One of "balanced", "throughput",
+    # "scale", "latency" and "custom".
+    # The default if unspecified is "custom".
+    preset: balanced
 
+inputs:
+  - type: system/metrics
+    # Each input must have a unique ID.
+    id: unique-system-metrics-input
     # Namespace name must conform to the naming conventions for Elasticsearch indices, cannot contain dashes (-), and cannot exceed 100 bytes
     # For index naming restrictions, see https://www.elastic.co/guide/en/elasticsearch/reference/current/indices-create-index.html#indices-create-api-path-params
     data_stream.namespace: default
     use_output: default
     streams:
-      - metricset: cpu
+      - metricsets:
+        - cpu
         # Dataset name must conform to the naming conventions for Elasticsearch indices, cannot contain dashes (-), and cannot exceed 100 bytes
         data_stream.dataset: system.cpu
-      - metricset: memory
+      - metricsets:
+        - memory
         data_stream.dataset: system.memory
-      - metricset: network
+      - metricsets:
+        - network
         data_stream.dataset: system.network
-      - metricset: filesystem
+      - metricsets:
+        - filesystem
         data_stream.dataset: system.filesystem
 
+#   # Collecting log files
+#   - type: filestream
+#     # Input ID allowing Elastic Agent to track the state of this input. Must be unique.
+#     id: your-input-id
+#     streams:
+#       # Stream ID for this data stream allowing Filebeat to track the state of the ingested files. Must be unique.
+#       # Each filestream data stream creates a separate instance of the Filebeat filestream input.
+#       - id: your-filestream-stream-id
+#         data_stream:
+#           dataset: generic
+#         paths:
+#           - /var/log/*.log
+
 # management:
 #   # Mode of management, the Elastic Agent support two modes of operation:
 #   #
@@ -72,12 +93,12 @@ inputs:
 #   target_directory: "${path.data}/downloads"
 #   # timeout for downloading package
 #   timeout: 120s
-#   # file path to a public key used for verifying downloaded artifacts
-#   # if not file is present agent will try to load public key from elastic.co website.
-#   pgpfile: "${path.data}/elastic.pgp"
 #   # install_path describes the location of installed packages/programs. It is also used
 #   # for reading program specifications.
 #   install_path: "${path.data}/install"
+#   # retry_sleep_init_duration is the duration to sleep for before the first retry attempt. This
+#   # duration will increase for subsequent retry attempts in a randomized exponential backoff manner.
+#   retry_sleep_init_duration: 30s
 
 # agent.process:
 #   # timeout for creating new processes. when process is not successfully created by this timeout
@@ -92,6 +113,9 @@ inputs:
 #   address: localhost
 #   # port for the GRPC server that spawned processes connect back to.
 #   port: 6789
+#   # max_message_size limits the message size in agent internal communication
+#   # default is 100MB
+#   max_message_size: 104857600
 
 # agent.retry:
 #   # Enabled determines whether retry is possible. Default is false.
@@ -108,17 +132,40 @@ inputs:
 #   # Default is false
 #   exponential: false
 
+# agent.limits:
+#   # limits the number of operating system threads that can execute user-level Go code simultaneously.
+#   # Translates into the GOMAXPROCS runtime parameter for each Go process started by the agent and the agent itself.
+#   # By default is set to `0` which means using all available CPUs.
+#   go_max_procs: 0
+
 # agent.monitoring:
 #   # enabled turns on monitoring of running processes
 #   enabled: false
 #   # enables log monitoring
 #   logs: false
 #   # enables metrics monitoring
 #   metrics: false
+#   # metrics_period defines how frequent we should sample monitoring metrics. Default is 60 seconds.
+#   metrics_period: 60s
 #   # exposes /debug/pprof/ endpoints
 #   # recommended that these endpoints are only enabled if the monitoring endpoint is set to localhost
 #   pprof.enabled: false
-#   # exposes agent metrics using http, by default sockets and named pipes are used
+#   # The name of the output to use for monitoring data.
+#   use_output: monitoring
+#   # Exposes agent metrics using http, by default sockets and named pipes are used.
+#   #
+#   # `http` Also exposes a /liveness endpoint that will return an HTTP code depending on agent status:
+#   # 200: Agent is healthy
+#   # 500: A component or unit is in a failed state
+#   # 503: The agent coordinator is unresponsive
+#   #
+#   # You can pass a `failon` parameter to the /liveness endpoint to determine what component state will result in a 500.
+#   # For example: `curl 'localhost:6792/liveness?failon=degraded'` will return 500 if a component is in a degraded state.
+#   # The possible values for `failon` are:
+#   # `degraded`: return an error if a component is in a degraded state or failed state, or if the agent coordinator is unresponsive.
+#   # `failed`: return an error if a unit is in a failed state, or if the agent coordinator is unresponsive.
+#   # `heartbeat`: return an error only if the agent coordinator is unresponsive.
+#   # If no `failon` parameter is provided, the default behavior is `failon=heartbeat`
 #   http:
 #       # enables http endpoint
 #       enabled: false
@@ -129,6 +176,22 @@ inputs:
 #       port: 6791
 #       # Metrics buffer endpoint
 #       buffer.enabled: false
+#   # Configuration for the diagnostics action handler
+#   diagnostics:
+#       # Rate limit for the action handler. Does not affect diagnostics collected through the CLI.
+#       limit:
+#           # Rate limit interval.
+#           interval: 1m
+#           # Rate limit burst.
+#           burst: 1
+#       # Configuration for the file-upload client. Client may retry failed requests with an exponential backoff.
+#       uploader:
+#           # Max retries allowed when uploading a chunk.
+#           max_retries: 10
+#           # Initial duration of the backoff.
+#           init_dur: 1s
+#           # Max duration of the backoff.
+#           max_dur: 1m
 
 # # Allow fleet to reload its configuration locally on disk.
 # # Notes: Only specific process configuration and external input configurations will be reloaded.
@@ -141,6 +204,13 @@ inputs:
 #   # period define how frequent we should look for changes in the configuration.
 #   period: 10s
 
+# Feature Flags
+
+# This section enables or disables feature flags supported by Agent and its components.
+#agent.features:
+#  fqdn:
+#    enabled: false
+
 # Logging
 
 # There are four options for the log output: file, stderr, syslog, eventlog
@@ -187,7 +257,7 @@ agent.logging.to_stderr: true
 
   # Configure log file size limit. If limit is reached, log file will be
   # automatically rotated
-  #rotateeverybytes: 10485760 # = 10MB
+  #rotateeverybytes: 20971520 # = 20MB
 
   # Number of rotated log files to keep. Oldest files will be deleted first.
   #keepfiles: 7
@@ -210,12 +280,65 @@ agent.logging.to_stderr: true
 # Set to true to log messages in JSON format.
 #agent.logging.json: false
 
+#=============================== Events Logging ===============================
+# Some outputs will log raw events on errors like indexing errors in the
+# Elasticsearch output, to prevent logging raw events (that may contain
+# sensitive information) together with other log messages, a different
+# log file, only for log entries containing raw events, is used. It will
+# use the same level, selectors and all other configurations from the
+# default logger, but it will have it's own file configuration.
+#
+# Having a different log file for raw events also prevents event data
+# from drowning out the regular log files.
+#
+# IMPORTANT: No matter the default logger output configuration, raw events
+# will **always** be logged to a file configured by `agent.logging.event_data.files`.
+
+# agent.logging.event_data:
+# Logging to rotating files. Set agent.logging.to_files to false to disable logging to
+# files.
+#agent.logging.event_data.to_files: true
+#agent.logging.event_data:
+  # Configure the path where the logs are written. The default is the logs directory
+  # under the home path (the binary location).
+  #path: /var/log/filebeat
+
+  # The name of the files where the logs are written to.
+  #name: filebeat-event-data
+
+  # Configure log file size limit. If the limit is reached, log file will be
+  # automatically rotated.
+  #rotateeverybytes: 5242880 # = 5MB
+
+  # Number of rotated log files to keep. The oldest files will be deleted first.
+  #keepfiles: 2
+
+  # The permissions mask to apply when rotating log files. The default value is 0600.
+  # Must be a valid Unix-style file permissions mask expressed in octal notation.
+  #permissions: 0600
+
+  # Enable log file rotation on time intervals in addition to the size-based rotation.
+  # Intervals must be at least 1s. Values of 1m, 1h, 24h, 7*24h, 30*24h, and 365*24h
+  # are boundary-aligned with minutes, hours, days, weeks, months, and years as
+  # reported by the local system clock. All other intervals are calculated from the
+  # Unix epoch. Defaults to disabled.
+  #interval: 0
+
+  # Rotate existing logs on startup rather than appending them to the existing
+  # file. Defaults to false.
+  # rotateonstartup: false
+
 # Providers
 
 # Providers supply the key/values pairs that are used for variable substitution
 # and conditionals. Each provider's keys are automatically prefixed with the name
 # of the provider.
 
+# All registered providers are enabled by default.
+
+# Disable all providers by default and only enable explicitly configured providers.
+# agent.providers.initial_default: false
+
 #providers:
 
 # Agent provides information about the running agent.