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.
2026-06-14 18:57:51 +04:00
parent 09f05549a0
commit fd67a6c68d
13 changed files with 285 additions and 3 deletions
@@ -164,6 +164,39 @@ func TestDecodeGoldenServerFrames(t *testing.T) {
 				}
 			},
 		},
+		{
+			name: "health.checks carries nested health report",
+			json: `{"type":"health.checks","health":{"overall":"DEGRADED","subjects":[` +
+				`{"subject":"DISK","status":"DEGRADED","metric":"free_bytes","observedValue":512000000,` +
+				`"detail":"disk free below 1 GB threshold","since":"2026-06-14T10:00:00Z"},` +
+				`{"subject":"EVENT_STORE","status":"HEALTHY","metric":"write_latency_ms","observedValue":4,` +
+				`"detail":"ok","since":"2026-06-14T09:00:00Z"}],` +
+				`"checkedAt":"2026-06-14T10:05:00Z"}}`,
+			wantType:  TypeHealthChecks,
+			eventBear: false,
+			check: func(t *testing.T, m ServerMessage) {
+				if m.Health == nil {
+					t.Fatalf("health.checks: Health is nil")
+				}
+				if m.Health.Overall != "DEGRADED" {
+					t.Fatalf("health.checks overall = %q, want DEGRADED", m.Health.Overall)
+				}
+				if len(m.Health.Subjects) != 2 {
+					t.Fatalf("health.checks subjects len = %d, want 2", len(m.Health.Subjects))
+				}
+				disk := m.Health.Subjects[0]
+				if disk.Subject != "DISK" || disk.Status != "DEGRADED" || disk.ObservedValue != 512000000 {
+					t.Fatalf("health.checks DISK subject: %+v", disk)
+				}
+				es := m.Health.Subjects[1]
+				if es.Subject != "EVENT_STORE" || es.Status != "HEALTHY" {
+					t.Fatalf("health.checks EVENT_STORE subject: %+v", es)
+				}
+				if m.Health.CheckedAt != "2026-06-14T10:05:00Z" {
+					t.Fatalf("health.checks checkedAt = %q", m.Health.CheckedAt)
+				}
+			},
+		},
 		{
 			name: "workflow.proposed carries candidate workflows",
 			json: `{"type":"workflow.proposed","sessionId":"s1","proposalId":"prop-1","prompt":"Run one?",` +
@@ -248,6 +281,11 @@ func TestEncodeGoldenClientFrames(t *testing.T) {
 				}
 			},
 		},
+		{
+			name:     "GetHealthChecks encodes correctly",
+			frame:    GetHealthChecks(),
+			wantType: clientPrefix + "GetHealthChecks",
+		},
 		{
 			name:     "DiscardIdea carries the ideaId",
 			frame:    DiscardIdea("i1"),
@@ -55,6 +55,7 @@ const (
 	TypeConfigSnapshot   = "config.snapshot"
 	TypeSessionStats     = "session.stats"
 	TypeIdeaList         = "idea.list"
+	TypeHealthChecks     = "health.checks"
 )

 // ServerMessage is a flat decode of every server->client variant. Field names
@@ -139,6 +140,9 @@ type ServerMessage struct {
 	// session.stats — derived metrics for a session (reply to GetSessionStats)
 	Stats *StatsDto `json:"stats"`

+	// health.checks — system health report (reply to GetHealthChecks)
+	Health *HealthDto `json:"health"`
+
 	// clarification.required — open questions a stage raised for the operator
 	Questions []ClarificationQuestionDto `json:"questions"`

@@ -242,6 +246,26 @@ type FailureMetricsDto struct {
 	WorkflowFailures  int64 `json:"workflowFailures"`
 }

+// HealthSubjectDto is one monitored subject's health status. Mirrors Kotlin HealthSubjectReport.
+// status is "HEALTHY" or "DEGRADED"; since is an ISO-8601 string for the last edge event.
+type HealthSubjectDto struct {
+	Subject       string `json:"subject"`
+	Status        string `json:"status"`
+	Metric        string `json:"metric"`
+	ObservedValue int64  `json:"observedValue"`
+	Detail        string `json:"detail"`
+	Since         string `json:"since"`
+}
+
+// HealthDto is the system health snapshot. Mirrors Kotlin HealthReport.
+// overall is "HEALTHY" or "DEGRADED". subjects is empty when health monitoring is disabled
+// or no probes have fired yet — the TUI renders a visible fallback in that case.
+type HealthDto struct {
+	Overall   string             `json:"overall"`
+	Subjects  []HealthSubjectDto `json:"subjects"`
+	CheckedAt string             `json:"checkedAt"`
+}
+
 type ConfigFieldDto struct {
 	Key             string   `json:"key"`
 	Type            string   `json:"type"`
@@ -465,3 +489,8 @@ func CreateGrant(sessionID, scope string, permittedTiers []string, reason, toolN
 func Hello(workingDir string) []byte {
 	return encode("Hello", map[string]any{"workingDir": workingDir})
 }
+
+// GetHealthChecks requests the system health-check report (replied to with health.checks).
+func GetHealthChecks() []byte {
+	return encode("GetHealthChecks", map[string]any{})
+}