Private
Public Access
1
0

feat: add CRL health status schema and UI (PR 3 of 6)
All checks were successful
CI Pipeline / Rust Format Check (push) Successful in 5s
CI Pipeline / Clippy Lints (push) Successful in 52s
CI Pipeline / Rust Unit Tests (push) Successful in 1m8s
CI Pipeline / Security Audit (push) Successful in 5s
CI Pipeline / Frontend Lint & Type Check (push) Successful in 15s
CI Pipeline / Build .deb & Release (push) Has been skipped

* feat: add CRL health status schema and UI (PR 3 of 6)

* fix(lint): strict equality for crl_age_seconds

---------

Co-authored-by: Draco Lunaris <331325+Draco-Lunaris@users.noreply.github.com>
This commit is contained in:
Draco-Lunaris-Echo
2026-06-05 16:17:17 -05:00
committed by GitHub
parent 5aec9e629c
commit ea8337b944
12 changed files with 345 additions and 78 deletions

10
crates/pm-agent-client/src/types.rs Executable file → Normal file
View File

@ -57,6 +57,16 @@ pub struct HealthData {
pub uptime_seconds: u64,
/// Agent software version string.
pub version: String,
/// CRL status reported by the agent: `"valid"`, `"expired"`, `"missing"`, `"invalid"`.
/// Absent for older agents that do not report CRL status.
#[serde(default)]
pub crl_status: Option<String>,
/// Seconds since the agent's CRL was last refreshed.
#[serde(default)]
pub crl_age_seconds: Option<i64>,
/// When the agent's CRL expires / next update is due (ISO-8601).
#[serde(default)]
pub crl_next_update: Option<String>,
}
// ============================================================

View File

@ -94,6 +94,15 @@ pub struct Host {
pub notes: String,
pub registered_at: DateTime<Utc>,
pub updated_at: DateTime<Utc>,
/// CRL status reported by the agent: valid, expired, missing, invalid, or NULL for older agents.
#[serde(skip_serializing_if = "Option::is_none")]
pub crl_status: Option<String>,
/// Seconds since the agent's CRL was last refreshed.
#[serde(skip_serializing_if = "Option::is_none")]
pub crl_age_seconds: Option<i64>,
/// When the agent's CRL expires / next update is due.
#[serde(skip_serializing_if = "Option::is_none")]
pub crl_next_update: Option<DateTime<Utc>>,
}
/// Payload for registering a new host.
@ -129,6 +138,9 @@ pub struct HostSummary {
pub patches_missing: i32,
pub health_check_status: Option<String>,
pub registered_at: DateTime<Utc>,
/// CRL status reported by the agent: valid, expired, missing, invalid, or NULL for older agents.
#[serde(skip_serializing_if = "Option::is_none")]
pub crl_status: Option<String>,
}
// ============================================================

5
crates/pm-web/src/routes/hosts.rs Executable file → Normal file
View File

@ -133,6 +133,7 @@ async fn list_hosts(
ELSE 'all_healthy'
END AS health_check_status,
h.registered_at
h.crl_status
FROM hosts h
LEFT JOIN host_patch_data hpd ON hpd.host_id = h.id
ORDER BY h.fqdn
@ -166,6 +167,7 @@ async fn list_hosts(
ELSE 'all_healthy'
END AS health_check_status,
h.registered_at
h.crl_status
FROM hosts h
LEFT JOIN host_patch_data hpd ON hpd.host_id = h.id
WHERE
@ -319,7 +321,8 @@ async fn get_host(
SELECT id, fqdn, host(ip_address)::text AS ip_address, display_name,
os_family, os_name, arch, agent_version, health_status,
last_health_at, last_patch_at, agent_port, notes,
registered_at, updated_at
registered_at, updated_at,
crl_status, crl_age_seconds, crl_next_update
FROM hosts WHERE id = $1
) h
"#,

43
crates/pm-web/src/routes/status.rs Executable file → Normal file
View File

@ -24,6 +24,16 @@ pub struct FleetStatus {
pub total_pending_patches: i64,
pub hosts_requiring_reboot: i64,
pub compliance_pct: f64,
/// Hosts with CRL status 'valid'.
pub crl_valid: i64,
/// Hosts with CRL status 'expired'.
pub crl_expired: i64,
/// Hosts with CRL status 'missing' (agent reports missing CRL).
pub crl_missing: i64,
/// Hosts with CRL status 'invalid' (security event — needs immediate attention).
pub crl_invalid: i64,
/// Hosts not reporting CRL status (older agents or no data yet).
pub crl_not_reporting: i64,
}
// ── GET /api/v1/status/fleet ──────────────────────────────────────────────────
@ -132,6 +142,34 @@ pub async fn fleet_status(
// Round to one decimal place.
let compliance_pct = (compliance_pct * 10.0).round() / 10.0;
// ── 5. CRL status counts ────────────────────────────────────────────────
let (crl_valid, crl_expired, crl_missing, crl_invalid, crl_not_reporting): (
i64,
i64,
i64,
i64,
i64,
) = sqlx::query_as(
r#"
SELECT
COALESCE(SUM(CASE WHEN crl_status = 'valid' THEN 1 END), 0),
COALESCE(SUM(CASE WHEN crl_status = 'expired' THEN 1 END), 0),
COALESCE(SUM(CASE WHEN crl_status = 'missing' THEN 1 END), 0),
COALESCE(SUM(CASE WHEN crl_status = 'invalid' THEN 1 END), 0),
COALESCE(SUM(CASE WHEN crl_status IS NULL THEN 1 END), 0)
FROM hosts
"#,
)
.fetch_one(&state.db)
.await
.map_err(|e| {
tracing::error!(error = %e, "fleet_status: failed to query CRL status counts");
(
StatusCode::INTERNAL_SERVER_ERROR,
Json(json!({ "error": { "code": "internal_error", "message": "Database error" } })),
)
})?;
Ok(Json(FleetStatus {
total_hosts,
healthy,
@ -141,5 +179,10 @@ pub async fn fleet_status(
total_pending_patches,
hosts_requiring_reboot,
compliance_pct,
crl_valid,
crl_expired,
crl_missing,
crl_invalid,
crl_not_reporting,
}))
}

View File

@ -15,13 +15,13 @@ pm-agent-client = { path = "../pm-agent-client" }
tokio = { workspace = true, features = ["full"] }
sqlx = { workspace = true }
serde = { workspace = true }
chrono = { workspace = true }
serde_json = { workspace = true }
thiserror = { workspace = true }
anyhow = { workspace = true }
tracing = { workspace = true }
tracing-subscriber = { workspace = true }
uuid = { workspace = true }
chrono = { workspace = true }
futures = { workspace = true }
rustls = { workspace = true }
tokio-rustls = { version = "0.26" }

View File

@ -116,8 +116,9 @@ pub async fn run_health_poller(pool: PgPool, config: Arc<AppConfig>) {
/// Poll a single host, persist the result, and return the determined status.
///
/// Also updates `agent_version` from the health response and
/// `os_family`/`os_name`/`arch` from the `/system/info` endpoint when available.
/// Also updates `agent_version` from the health response,
/// `os_family`/`os_name`/`arch` from the `/system/info` endpoint when available,
/// and CRL status fields from the health response when reported by the agent.
async fn poll_host_health(
pool: PgPool,
host: HostRow,
@ -125,79 +126,107 @@ async fn poll_host_health(
client_key: &[u8],
ca_cert: &[u8],
) -> HostHealthStatus {
// Determine status, payload, agent version, and optional system info.
let (status, payload, agent_version, sys_info) = match AgentClient::new(
&host.ip_address,
host.agent_port as u16,
client_cert,
client_key,
ca_cert,
) {
Err(e) => {
tracing::warn!(
host_id = %host.id,
error = %e,
"Health poller: failed to build AgentClient"
);
(
HostHealthStatus::Unreachable,
serde_json::Value::Object(Default::default()),
None,
None,
)
},
Ok(client) => {
let (status, payload, version) = match client.health().await {
Ok(data) => {
let payload = serde_json::to_value(&data).unwrap_or_default();
(HostHealthStatus::Healthy, payload, Some(data.version))
},
Err(AgentClientError::Timeout) => {
tracing::warn!(host_id = %host.id, "Health poller: agent timed out");
(
HostHealthStatus::Unreachable,
serde_json::Value::Object(Default::default()),
None,
)
},
Err(AgentClientError::Connect(_)) => {
tracing::warn!(host_id = %host.id, "Health poller: agent connection refused");
(
HostHealthStatus::Unreachable,
serde_json::Value::Object(Default::default()),
None,
)
},
Err(e) => {
tracing::warn!(host_id = %host.id, error = %e, "Health poller: agent error");
(
HostHealthStatus::Degraded,
serde_json::Value::Object(Default::default()),
None,
)
},
};
// Try to fetch system info for OS/arch details (best-effort).
let sys_info = if status != HostHealthStatus::Unreachable {
match client.system_info().await {
Ok(info) => Some(info),
Err(e) => {
tracing::debug!(
host_id = %host.id,
error = %e,
"Health poller: failed to get system info (non-fatal)"
);
None
// Determine status, payload, agent version, optional system info, and CRL fields.
let (status, payload, agent_version, sys_info, crl_status, crl_age_seconds, crl_next_update) =
match AgentClient::new(
&host.ip_address,
host.agent_port as u16,
client_cert,
client_key,
ca_cert,
) {
Err(e) => {
tracing::warn!(
host_id = %host.id,
error = %e,
"Health poller: failed to build AgentClient"
);
(
HostHealthStatus::Unreachable,
serde_json::Value::Object(Default::default()),
None,
None,
None,
None,
None,
)
},
Ok(client) => {
let (status, payload, version, crl_status, crl_age, crl_next) = match client
.health()
.await
{
Ok(data) => {
let payload = serde_json::to_value(&data).unwrap_or_default();
let crl_status = data.crl_status.clone();
let crl_age = data.crl_age_seconds;
let crl_next = data.crl_next_update.clone();
(
HostHealthStatus::Healthy,
payload,
Some(data.version),
crl_status,
crl_age,
crl_next,
)
},
}
} else {
None
};
Err(AgentClientError::Timeout) => {
tracing::warn!(host_id = %host.id, "Health poller: agent timed out");
(
HostHealthStatus::Unreachable,
serde_json::Value::Object(Default::default()),
None,
None,
None,
None,
)
},
Err(AgentClientError::Connect(_)) => {
tracing::warn!(host_id = %host.id, "Health poller: agent connection refused");
(
HostHealthStatus::Unreachable,
serde_json::Value::Object(Default::default()),
None,
None,
None,
None,
)
},
Err(e) => {
tracing::warn!(host_id = %host.id, error = %e, "Health poller: agent error");
(
HostHealthStatus::Degraded,
serde_json::Value::Object(Default::default()),
None,
None,
None,
None,
)
},
};
(status, payload, version, sys_info)
},
};
// Try to fetch system info for OS/arch details (best-effort).
let sys_info = if status != HostHealthStatus::Unreachable {
match client.system_info().await {
Ok(info) => Some(info),
Err(e) => {
tracing::debug!(
host_id = %host.id,
error = %e,
"Health poller: failed to get system info (non-fatal)"
);
None
},
}
} else {
None
};
(
status, payload, version, sys_info, crl_status, crl_age, crl_next,
)
},
};
// Insert into host_health_data.
if let Err(e) = sqlx::query(
@ -220,7 +249,13 @@ async fn poll_host_health(
.as_ref()
.map(|i| format!("{} {}", i.os, i.os_version));
// Update hosts table with health status, agent version, and OS details.
// Parse CRL next_update from ISO-8601 string to DateTime if present.
let crl_next_update_dt: Option<chrono::DateTime<chrono::Utc>> = crl_next_update
.as_ref()
.and_then(|s| chrono::DateTime::parse_from_rfc3339(s).ok())
.map(|dt| dt.to_utc());
// Update hosts table with health status, agent version, OS details, and CRL fields.
// COALESCE preserves existing values when new data is unavailable.
if let Err(e) = sqlx::query(
r#"
@ -229,7 +264,10 @@ async fn poll_host_health(
agent_version = COALESCE($3, agent_version),
os_family = COALESCE($4, os_family),
os_name = COALESCE($5, os_name),
arch = COALESCE($6, arch)
arch = COALESCE($6, arch),
crl_status = COALESCE($7, crl_status),
crl_age_seconds = COALESCE($8, crl_age_seconds),
crl_next_update = COALESCE($9, crl_next_update)
WHERE id = $1
"#,
)
@ -239,6 +277,9 @@ async fn poll_host_health(
.bind(sys_info.as_ref().map(|i| i.os.as_str()))
.bind(os_name_from_sysinfo)
.bind(sys_info.as_ref().map(|i| i.architecture.as_str()))
.bind(&crl_status)
.bind(crl_age_seconds)
.bind(crl_next_update_dt)
.execute(&pool)
.await
{