feat(tui-go): health-checks pane

Surface the health subsystem (llama/event-store/disk probes) in the TUI,
mirroring the session-stats pane: ClientMessage.GetHealthChecks ->
ServerMessage.HealthChecks (health.checks, reuses HealthReport) ->
StreamQueries.healthChecks via HealthInspectionService; Go OverlayHealth on
key H + palette 'health checks', pull-based fetch, per-subject status with
degraded loud. Empty/disabled -> visible fallback (no blank/lie). Go+Kotlin
golden tests pin the wire contract field-for-field. Observability spec §4/§3.
This commit is contained in:
2026-06-14 18:57:51 +04:00
parent 09f05549a0
commit fd67a6c68d
13 changed files with 285 additions and 3 deletions
@@ -48,6 +48,10 @@ sealed class ClientMessage {
@Serializable
data class GetSessionStats(val sessionId: SessionId) : ClientMessage()
/** Operator request for the system health checks (replied to with a HealthChecks). */
@Serializable
data object GetHealthChecks : ClientMessage()
/** Operator request for the cross-session idea board (replied to with an IdeaList). */
@Serializable
data object ListIdeas : ClientMessage()
@@ -1,5 +1,6 @@
package com.correx.apps.server.protocol
import com.correx.apps.server.health.HealthReport
import com.correx.apps.server.metrics.MetricsReport
import com.correx.core.approvals.Tier
import com.correx.core.events.events.ClarificationQuestion
@@ -490,6 +491,21 @@ sealed interface ServerMessage {
override val sessionSequence: Long? = null,
) : ServerMessage, NonEventMessage
/**
* The system health-check report, returned in response to a GetHealthChecks request. Not
* event-derived (a projection-replay snapshot read), so cursors are null. [health] is the same
* [HealthReport] the REST `GET /health/checks` endpoint serves — one definition, two wires.
* When health monitoring is disabled ([health] holds an empty/disabled report) the message is
* still sent; the client renders a "health monitoring disabled" fallback instead of going blank.
*/
@Serializable
@SerialName("health.checks")
data class HealthChecks(
val health: HealthReport,
override val sequence: Long? = null,
override val sessionSequence: Long? = null,
) : ServerMessage, NonEventMessage
/**
* The current editable config (reply to GetConfig / UpdateConfig). [restartRequired] lists the
* keys in a just-applied patch that need a server restart to take effect; [error] is set (and
@@ -234,6 +234,7 @@ class GlobalStreamHandler(private val module: ServerModule) {
is ClientMessage.ListIdeas -> sendFrame(queries.listIdeas())
is ClientMessage.DiscardIdea -> handleDiscardIdea(msg, sendFrame)
is ClientMessage.GetSessionStats -> sendFrame(queries.sessionStats(msg.sessionId))
is ClientMessage.GetHealthChecks -> sendFrame(queries.healthChecks())
is ClientMessage.GetConfig -> sendFrame(queries.configSnapshot(error = null, restartRequired = emptyList()))
is ClientMessage.UpdateConfig -> sendFrame(queries.updateConfig(msg.patch))
is ClientMessage.ResumeSession -> session.send(encodeError("ResumeSession not supported"))
@@ -2,6 +2,7 @@ package com.correx.apps.server.ws
import com.correx.apps.server.ServerModule
import com.correx.apps.server.config.ConfigUpdateResult
import com.correx.apps.server.health.HealthInspectionService
import com.correx.apps.server.metrics.MetricsInspectionService
import com.correx.apps.server.protocol.ArtifactSummaryDto
import com.correx.apps.server.protocol.ConfigFieldDto
@@ -37,6 +38,7 @@ private val lenientJson = Json { ignoreUnknownKeys = true; isLenient = true }
class StreamQueries(private val module: ServerModule) {
private val metricsService = MetricsInspectionService(module.eventStore)
private val healthService = HealthInspectionService(module.eventStore)
/**
* A session's derived metrics as a snapshot frame. Replays the event log through
@@ -48,6 +50,18 @@ class StreamQueries(private val module: ServerModule) {
return ServerMessage.SessionStats(sessionId = sessionId, stats = report)
}
/**
* The system health-check report as a snapshot frame. Replays the system session through
* [HealthInspectionService] (the same projection the REST /health/checks endpoint uses) — pure
* read, no events appended, so it is replay-neutral (invariant #1/#8). When health monitoring is
* disabled or no probes have fired yet, the report has empty subjects and overall=HEALTHY; the
* client renders a visible "no health probes recorded" fallback rather than going blank.
*/
suspend fun healthChecks(): ServerMessage.HealthChecks {
val report = withContext(Dispatchers.IO) { healthService.inspect() }
return ServerMessage.HealthChecks(health = report)
}
/**
* Reads a session's events to assemble its artifact listing (creation order preserved),
* resolving each artifact's stored bytes via the CAS artifact store. Pure snapshot read —
@@ -1,5 +1,7 @@
package com.correx.apps.server.protocol
import com.correx.apps.server.health.HealthReport
import com.correx.apps.server.health.HealthSubjectReport
import com.correx.apps.server.metrics.FailureMetrics
import com.correx.apps.server.metrics.MetricsReport
import com.correx.apps.server.metrics.ProviderStatsDto
@@ -193,6 +195,53 @@ class ServerMessageSerializationTest {
assertEquals(50.0, decoded.stats.approvalWaitPct)
}
@Test
fun `HealthChecks encodes type and nested health report`() {
val msg = ServerMessage.HealthChecks(
health = HealthReport(
overall = "DEGRADED",
subjects = listOf(
HealthSubjectReport(
subject = "DISK",
status = "DEGRADED",
metric = "free_bytes",
observedValue = 512_000_000L,
detail = "disk free below 1 GB threshold",
since = "2026-06-14T10:00:00Z",
),
HealthSubjectReport(
subject = "EVENT_STORE",
status = "HEALTHY",
metric = "write_latency_ms",
observedValue = 4L,
detail = "ok",
since = "2026-06-14T09:00:00Z",
),
),
checkedAt = "2026-06-14T10:05:00Z",
),
)
val jsonStr = ProtocolSerializer.encodeServerMessage(msg)
assert(jsonStr.contains("\"type\":\"health.checks\"")) { "expected type=health.checks" }
assert(jsonStr.contains("\"overall\":\"DEGRADED\"")) { "expected overall=DEGRADED" }
assert(jsonStr.contains("\"subject\":\"DISK\"")) { "expected DISK subject" }
assert(jsonStr.contains("\"status\":\"DEGRADED\"")) { "expected DEGRADED status" }
assert(jsonStr.contains("\"checkedAt\":\"2026-06-14T10:05:00Z\"")) { "expected checkedAt" }
// Pin every subject field name so a rename breaks the Go↔Kotlin wire contract here too.
assert(jsonStr.contains("\"metric\":\"free_bytes\"")) { "expected metric field name" }
assert(jsonStr.contains("\"observedValue\":512000000")) { "expected observedValue field name" }
assert(jsonStr.contains("\"detail\":\"disk free below 1 GB threshold\"")) { "expected detail field name" }
assert(jsonStr.contains("\"since\":\"2026-06-14T10:00:00Z\"")) { "expected since field name" }
val decoded = json.decodeFromString<ServerMessage.HealthChecks>(jsonStr)
assertEquals("DEGRADED", decoded.health.overall)
assertEquals(2, decoded.health.subjects.size)
assertEquals("DISK", decoded.health.subjects[0].subject)
assertEquals(512_000_000L, decoded.health.subjects[0].observedValue)
assertEquals("EVENT_STORE", decoded.health.subjects[1].subject)
assertEquals("HEALTHY", decoded.health.subjects[1].status)
}
@Test
fun `ClarificationRequired encodes type, stageId and structured questions`() {
val msg = ServerMessage.ClarificationRequired(