Skip to content

feat(health): include alert details in OTLP health report records #4500

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
yoks merged 1 commit into from
Aug 4, 2026
Merged

feat(health): include alert details in OTLP health report records #4500

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 9 additions & 0 deletions crates/health/example/config.example.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -113,6 +113,13 @@ flush_interval = "2s"
# attach them. OTLP exports parent logs normally and keeps diagnostics as
# latest-wins per endpoint while the drain is backed up.
include_diagnostics = false

# Include per-alert detail on health report records for this target. Health
# report records otherwise carry only alert and success counts. When enabled,
# each record with alerts gains a `health_report.alerts` attribute holding a
# JSON array of up to 64 alerts; a truncated record also carries
# `health_report.alerts.dropped` with the number omitted.
include_alert_details = false
#
# TLS-only target with an explicit CA bundle.
# The reload interval is optional and defaults to five minutes.
Expand All @@ -121,6 +128,7 @@ include_diagnostics = false
# batch_size = 1024
# flush_interval = "5s"
# include_diagnostics = true
# include_alert_details = true
#
# [sinks.otlp.targets.tls]
# ca_cert_path = "/var/run/secrets/central-otlp/ca.crt"
Expand All @@ -133,6 +141,7 @@ include_diagnostics = false
# batch_size = 1024
# flush_interval = "5s"
# include_diagnostics = true
# include_alert_details = true
#
# [sinks.otlp.targets.tls]
# ca_cert_path = "/var/run/secrets/central-otlp/ca.crt"
Expand Down
17 changes: 17 additions & 0 deletions crates/health/src/config.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -537,6 +537,14 @@ pub struct OtlpTargetConfig {
/// up.
#[serde(default)]
pub include_diagnostics: bool,

/// Emit per-alert detail on health report log records sent to this target.
///
/// Disabled by default because alert messages are free-form and a fully
/// degraded endpoint can produce many of them. When enabled, health report
/// records carry a `health_report.alerts` attribute holding a JSON array.
#[serde(default)]
pub include_alert_details: bool,
}

impl OtlpTargetConfig {
Expand Down Expand Up @@ -1932,6 +1940,7 @@ mod tests {
batch_size: 512,
flush_interval: Duration::from_secs(2),
include_diagnostics: false,
include_alert_details: false,
}
}

Expand Down Expand Up @@ -2636,6 +2645,7 @@ endpoint = "https://central.example:4317"
batch_size = 1024
flush_interval = "5s"
include_diagnostics = true
include_alert_details = true

[targets.tls]
ca_cert_path = "/central/ca.crt"
Expand All @@ -2657,6 +2667,8 @@ reload_interval = "30s"
assert_eq!(targets[1].batch_size, 1024);
assert_eq!(targets[1].flush_interval, Duration::from_secs(5));
assert!(targets[1].include_diagnostics);
assert!(!targets[0].include_alert_details);
assert!(targets[1].include_alert_details);

let tls = targets[1]
.tls
Expand Down Expand Up @@ -2892,6 +2904,7 @@ reload_interval = "30s"
batch_size: 512,
flush_interval: Duration::from_secs(2),
include_diagnostics: false,
include_alert_details: false,
tls: None,
}],
}),
Expand Down Expand Up @@ -2929,6 +2942,7 @@ reload_interval = "30s"
batch_size: 512,
flush_interval: Duration::from_secs(2),
include_diagnostics: true,
include_alert_details: false,
tls: None,
}],
}),
Expand All @@ -2946,13 +2960,15 @@ reload_interval = "30s"
batch_size: 512,
flush_interval: Duration::from_secs(2),
include_diagnostics: false,
include_alert_details: false,
tls: None,
},
OtlpTargetConfig {
endpoint: "http://central.example:4317".to_string(),
batch_size: 512,
flush_interval: Duration::from_secs(2),
include_diagnostics: true,
include_alert_details: false,
tls: None,
},
],
Expand Down Expand Up @@ -2998,6 +3014,7 @@ reload_interval = "30s"
batch_size: 512,
flush_interval: Duration::from_secs(2),
include_diagnostics: false,
include_alert_details: false,
tls: None,
}],
}),
Expand Down
Loading
Loading