feat(kiali): add aggregated health summary to mesh graph tool (containers#506)

* Added summary health for kiali_get_mesh_graph tool.

Signed-off-by: Hayk Hovsepyan <[email protected]>

* Comments approached

Signed-off-by: Hayk Hovsepyan <[email protected]>

* Approached comments

Signed-off-by: Hayk Hovsepyan <[email protected]>

* Added DefaultRateInterval value

Signed-off-by: Hayk Hovsepyan <[email protected]>

* Update pkg/kiali/get_mesh_graph.go

Co-authored-by: Alberto Gutierrez <[email protected]>
Signed-off-by: Hayk Hovsepyan <[email protected]>

---------

Signed-off-by: Hayk Hovsepyan <[email protected]>
Co-authored-by: Alberto Gutierrez <[email protected]>

Author: hhovsepy

README.md

@@ -352,7 +352,7 @@ In case multi-cluster support is enabled (default) and you have access to multip
   - `graphType` (`string`) - Type of graph to return: 'versionedApp', 'app', 'service', 'workload', 'mesh'. Default: 'versionedApp'
   - `namespace` (`string`) - Optional single namespace to include in the graph (alternative to namespaces)
   - `namespaces` (`string`) - Optional comma-separated list of namespaces to include in the graph
-  - `rateInterval` (`string`) - Rate interval for fetching (e.g., '10m', '5m', '1h'). Default: '60s'
+  - `rateInterval` (`string`) - Rate interval for fetching (e.g., '10m', '5m', '1h'). Default: '10m'
 
 - **kiali_manage_istio_config** - Manages Istio configuration objects (Gateways, VirtualServices, etc.). Can list (objects and validations), get, create, patch, or delete objects
   - `action` (`string`) **(required)** - Action to perform: list, get, create, patch, or delete
@@ -374,7 +374,7 @@ In case multi-cluster support is enabled (default) and you have access to multip
   - `duration` (`string`) - Time range to get metrics for (optional string - if provided, gets metrics; if empty, get default 1800s).
   - `namespace` (`string`) **(required)** - Namespace to get resources from
   - `quantiles` (`string`) - Comma-separated list of quantiles for histogram metrics (e.g., '0.5,0.95,0.99'). Optional
-  - `rateInterval` (`string`) - Rate interval for metrics (e.g., '1m', '5m'). Optional, defaults to '1m'
+  - `rateInterval` (`string`) - Rate interval for metrics (e.g., '1m', '5m'). Optional, defaults to '10m'
   - `reporter` (`string`) - Metrics reporter: 'source', 'destination', or 'both'. Optional, defaults to 'source'
   - `requestProtocol` (`string`) - Filter by request protocol (e.g., 'http', 'grpc', 'tcp'). Optional
   - `resource_name` (`string`) **(required)** - Name of the resource to get details for (optional string - if provided, gets details; if empty, lists all).

pkg/kiali/defaults.go

@@ -0,0 +1,8 @@
+package kiali
+
+// Default values for Kiali API parameters shared across this package.
+const (
+	// DefaultRateInterval is the default rate interval for fetching error rates and metrics.
+	// This value is used when rateInterval is not explicitly provided in API calls.
+	DefaultRateInterval = "10m"
+)

pkg/kiali/get_mesh_graph.go

@@ -7,20 +7,24 @@ import (
 	"sync"
 )
 
+// GetMeshGraphResponse contains the combined response from multiple Kiali API endpoints.
+// Note: Health data is fetched from Kiali's health API and used internally to compute
+// MeshHealthSummary, but the raw health data is not included in the response to reduce payload size.
+// MeshHealthSummary contains all the key aggregated metrics needed for mesh health overview.
 type GetMeshGraphResponse struct {
-	Graph      json.RawMessage   `json:"graph,omitempty"`
-	Health     json.RawMessage   `json:"health,omitempty"`
-	MeshStatus json.RawMessage   `json:"mesh_status,omitempty"`
-	Namespaces json.RawMessage   `json:"namespaces,omitempty"`
-	Errors     map[string]string `json:"errors,omitempty"`
+	Graph             json.RawMessage    `json:"graph,omitempty"`
+	MeshStatus        json.RawMessage    `json:"mesh_status,omitempty"`
+	Namespaces        json.RawMessage    `json:"namespaces,omitempty"`
+	MeshHealthSummary *MeshHealthSummary `json:"mesh_health_summary,omitempty"` // Aggregated summary computed from health data
+	Errors            map[string]string  `json:"errors,omitempty"`
 }
 
 // GetMeshGraph fetches multiple Kiali endpoints in parallel and returns a combined response.
 // Each field in the response corresponds to one API call result.
 // - graph:       /api/namespaces/graph (optionally filtered by namespaces)
-// - health:      /api/clusters/health  (optionally filtered by namespaces and queryParams)
-// - status(mesh):/api/mesh/graph
+// - mesh_status: /api/mesh/graph
 // - namespaces:  /api/namespaces
+// - mesh_health_summary: computed from /api/clusters/health (health data is fetched but not included in response)
 func (k *Kiali) GetMeshGraph(ctx context.Context, namespaces []string, queryParams map[string]string) (string, error) {
 	cleaned := make([]string, 0, len(namespaces))
 	for _, ns := range namespaces {
@@ -51,7 +55,7 @@ func (k *Kiali) GetMeshGraph(ctx context.Context, namespaces []string, queryPara
 		resp.Graph = data
 	}()
 
-	// Health
+	// Health - compute MeshHealthSummary inside the goroutine
 	go func() {
 		defer wg.Done()
 		data, err := k.getHealth(ctx, cleaned, queryParams)
@@ -61,7 +65,13 @@ func (k *Kiali) GetMeshGraph(ctx context.Context, namespaces []string, queryPara
 			errorsMu.Unlock()
 			return
 		}
-		resp.Health = data
+		// Compute mesh health summary from health data
+		if len(data) > 0 {
+			summary := computeMeshHealthSummary(data, cleaned, queryParams)
+			if summary != nil {
+				resp.MeshHealthSummary = summary
+			}
+		}
 	}()
 
 	// Mesh status

pkg/kiali/graph.go

@@ -18,7 +18,7 @@ func (k *Kiali) Graph(ctx context.Context, namespaces []string, queryParams map[
 	q := u.Query()
 	// Static graph parameters per requirements
 	// Defaults with optional overrides via queryParams
-	duration := "60s"
+	duration := DefaultRateInterval
 	graphType := "versionedApp"
 	if v, ok := queryParams["rateInterval"]; ok && strings.TrimSpace(v) != "" {
 		duration = strings.TrimSpace(v)

pkg/kiali/health.go

@@ -12,7 +12,7 @@ import (
 //   - namespaces: comma-separated list of namespaces (optional, if empty returns health for all accessible namespaces)
 //   - queryParams: optional query parameters map for filtering health data (e.g., "type", "rateInterval", "queryTime")
 //   - type: health type - "app", "service", or "workload" (default: "app")
-//   - rateInterval: rate interval for fetching error rate (default: "1m")
+//   - rateInterval: rate interval for fetching error rate (default: DefaultRateInterval, which is "10m")
 //   - queryTime: Unix timestamp for the prometheus query (optional)
 func (k *Kiali) Health(ctx context.Context, namespaces string, queryParams map[string]string) (string, error) {
 	// Build query parameters
@@ -34,14 +34,18 @@ func (k *Kiali) Health(ctx context.Context, namespaces string, queryParams map[s
 		}
 	}
 
-	// Ensure health "type" aligns with graphType (versionedApp -> app)
+	// Ensure health "type" aligns with graphType (versionedApp -> app, mesh -> app)
+	// The Kiali health API only accepts "app", "service", or "workload" as valid types
 	healthType := "app"
 	if gt, ok := queryParams["graphType"]; ok && strings.TrimSpace(gt) != "" {
 		v := strings.TrimSpace(gt)
 		if strings.EqualFold(v, "versionedApp") {
 			healthType = "app"
-		} else {
+		} else if v == "workload" || v == "service" {
 			healthType = v
+		} else {
+			// For "mesh" or any other graphType, default to "app"
+			healthType = "app"
 		}
 	}
 	q.Set("type", healthType)