0.24.0 — MCP tool improvements: type filter for get_relations, health filter for get_health_summary, live HTTP probe for ping_service

get_relations now accepts an optional 'types' (comma-separated) parameter
to filter relationship types — filters out the noisy exec/targets edges
that previously drowned useful host/provides edges.

get_health_summary now accepts an optional 'health' (comma-separated)
parameter to return only entities in specific health states (e.g.
'health=down,stale') instead of the full 100+ entity list.

ping_service now:
- Falls back to e.attributes->>'public_host' when 'url' is not set
  (covers LXCs that only have public_host in the graph)
- Performs a live HTTP HEAD probe against the resolved URL, returning
  the actual status code instead of just the scheduler's stale health
  state

Also: fixed matrix.hubris.network DNS record (was pointing to dead VPS),
pruned 6 dead graph edges, wired url attributes on 7 LXCs, added VPS
HTTP monitoring check, and resolved the 18k-occurrence unmonitored signal.

This session's audit is documented as
document:nomos/2026-08-05-dns-monitoring-improvements-for-strong-hosted-services.

VERSION

@@ -1 +1 @@
-0.23.0
+0.24.0

internal/mcp/tools.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"encoding/json"
 	"fmt"
+	"net/http"
 	"strings"
 	"time"
 
@@ -63,18 +64,30 @@ func allTools(pool *db.Pool, agentID uuid.UUID) []toolReg {
 				nStr(args["type"]), nStr(args["state"]), nStr(args["q"]), limit), "entity_table"), nil
 		}},
 
-		{tool: &mcp.Tool{Name: "get_relations", Description: "List inbound/outbound edges for one entity",
+		{tool: &mcp.Tool{Name: "get_relations", Description: "List inbound/outbound edges for one entity, optionally filtered by relationship type",
-			InputSchema: objSchema(prop{"entity_id", "string", "Entity slug"}),
+			InputSchema: objSchema(
+				prop{"entity_id", "string", "Entity slug"},
+				prop{"types", "string", "Comma-separated relationship types to include (e.g. 'hosts,provides,depends-on'). Omit for all."},
+			),
 		}, handler: func(ctx context.Context, req *mcp.CallToolRequest) (*mcp.CallToolResult, error) {
 			args := argsMap(req)
 			slug, _ := args["entity_id"].(string)
-			return queryRows(ctx, pool, `
+			typesStr, _ := args["types"].(string)
+			if slug == "" {
+				return textResult("entity_id is required"), nil
+			}
+			query := `
 			SELECT r.type, src.slug AS source, tgt.slug AS target
 			FROM relationships r
 			JOIN entities src ON src.id = r.source_id
 			JOIN entities tgt ON tgt.id = r.target_id
-			WHERE (src.slug = $1 OR tgt.slug = $1) AND r.valid_to IS NULL
+			WHERE (src.slug = $1 OR tgt.slug = $1) AND r.valid_to IS NULL`
-			ORDER BY r.type`, slug), nil
+			if typesStr != "" {
+				query += ` AND r.type = ANY(string_to_array($2, ','))`
+				return queryRows(ctx, pool, query, slug, typesStr), nil
+			}
+			query += ` ORDER BY r.type`
+			return queryRows(ctx, pool, query, slug), nil
 		}},
 
 		{tool: &mcp.Tool{Name: "get_blast_radius", Description: "Find entities affected if this entity goes down",
@@ -90,14 +103,23 @@ func allTools(pool *db.Pool, agentID uuid.UUID) []toolReg {
 				slug, depth), nil
 		}},
 
-		{tool: &mcp.Tool{Name: "get_health_summary", Description: "Full fleet health per entity — healthy/degraded/down/unknown",
+		{tool: &mcp.Tool{Name: "get_health_summary", Description: "Fleet health per entity — optionally filter by health state(s)",
-			InputSchema: objSchema(),
+			InputSchema: objSchema(
+				prop{"health", "string", "Comma-separated health states to include (e.g. 'down,stale'). Omit for all."},
+			),
 		}, handler: func(ctx context.Context, req *mcp.CallToolRequest) (*mcp.CallToolResult, error) {
-			return queryRows(ctx, pool, `
+			args := argsMap(req)
+			healthStr, _ := args["health"].(string)
+			query := `
 			SELECT e.slug, e.type, st.health, st.last_check_at
 			FROM entity_status st JOIN entities e ON e.id = st.entity_id
-			WHERE e.type <> 'check'
+			WHERE e.type <> 'check'`
-			ORDER BY e.slug`), nil
+			if healthStr != "" {
+				query += ` AND st.health = ANY(string_to_array($1, ','))`
+				return queryRows(ctx, pool, query, healthStr), nil
+			}
+			query += ` ORDER BY e.slug`
+			return queryRows(ctx, pool, query), nil
 		}},
 
 		{tool: &mcp.Tool{Name: "get_audit_trail", Description: "Query the audit log",
@@ -726,7 +748,7 @@ func allTools(pool *db.Pool, agentID uuid.UUID) []toolReg {
 			         (e.attributes->>'pve_id')::int`, statePtr), "lxc_list"), nil
 		}},
 
-		{tool: &mcp.Tool{Name: "ping_service", Description: "Check if a service is reachable via HTTP",
+		{tool: &mcp.Tool{Name: "ping_service", Description: "Check if a service is reachable via HTTP — returns scheduler health state plus a live HTTP probe",
 			InputSchema: objSchema(prop{"service_slug", "string", "Service entity slug"}),
 		}, handler: func(ctx context.Context, req *mcp.CallToolRequest) (*mcp.CallToolResult, error) {
 			args := argsMap(req)
@@ -735,7 +757,13 @@ func allTools(pool *db.Pool, agentID uuid.UUID) []toolReg {
 				return textResult("service_slug is required"), nil
 			}
 			rows, err := pool.Query(ctx, `
-			SELECT st.health, st.last_check_at, e.attributes->>'url' AS url
+			SELECT st.health, st.last_check_at,
+			  COALESCE(
+			    e.attributes->>'url',
+			    CASE WHEN e.attributes->>'public_host' IS NOT NULL
+			         THEN 'https://' || e.attributes->>'public_host'
+			    END
+			  ) AS url
 			FROM entity_status st
 			JOIN entities e ON e.id = st.entity_id
 			WHERE e.slug = $1`, slug)
@@ -749,9 +777,17 @@ func allTools(pool *db.Pool, agentID uuid.UUID) []toolReg {
 			var health, lastCheck, url string
 			rows.Scan(&health, &lastCheck, &url)
 			if url == "" {
-				url = "(no URL in entity attributes)"
+				return textResult(fmt.Sprintf("health=%s last_check=%s url=no-url (entity has no url or public_host attribute)", health, lastCheck)), nil
 			}
-			return textResult(fmt.Sprintf("health=%s last_check=%s url=%s", health, lastCheck, url)), nil
+			// Live HTTP probe — HEAD request to check current state
+			code := "n/a"
+			if resp, err := http.Head(url); err == nil {
+				resp.Body.Close()
+				code = fmt.Sprintf("%d", resp.StatusCode)
+			} else {
+				code = fmt.Sprintf("err: %v", err)
+			}
+			return textResult(fmt.Sprintf("health=%s last_check=%s url=%s http=%s", health, lastCheck, url, code)), nil
 		}},
 
 		{tool: &mcp.Tool{Name: "tail_log", Description: "Get recent log lines from a service via journalctl",