feat(audit): read-only knowledge-graph drift report + skill

Adds audit_knowledge_graph (MCP tool) and GET /api/v1/audit/drift (endpoint) backed by a shared internal/audit package. One pass surfaces the structural gaps an operator otherwise finds by accident: orphan check entities, checks targeting deprecated/destroyed entities, probes stuck down/unknown, unmonitored declared types, and live edges pointing at destroyed targets. Each finding carries a suggested remediation runbook. Read-only and safe to run unattended. Ships the knowledge-graph-audit skill (SKILL.md + seeded runbook) that interprets the report and routes findings to the lifecycle runbooks.
2026-07-29 13:37:16 +02:00
parent c7729b2ef6
commit 1540f74342
8 changed files with 395 additions and 0 deletions
--- a/internal/audit/audit.go
+++ b/internal/audit/audit.go
@@ -0,0 +1,125 @@
+// Package audit produces read-only drift reports over the knowledge graph and
+// monitoring state. It is the shared engine behind the
+// /api/v1/audit/drift endpoint and the audit_knowledge_graph MCP tool.
+//
+// It surfaces the structural gaps an operator otherwise discovers only by
+// accident: orphan check entities, checks targeting retired entities, probes
+// stuck down/unknown, unmonitored declared types, and live edges pointing at
+// destroyed/deprecated targets. Live-infra discovery (pct/docker/certs) is a
+// follow-up that needs host-hop execution; these categories are pure DB
+// queries, so the report is cheap, safe to run unattended, and testable.
+package audit
+
+import (
+	"context"
+
+	"github.com/dtoro/oikos/internal/db"
+)
+
+// Finding is one drift item the operator should look at.
+type Finding struct {
+	Category         string   `json:"category"`
+	Severity         string   `json:"severity"` // info | warning | critical
+	Count            int      `json:"count"`
+	Entities         []string `json:"entities"`
+	Evidence         string   `json:"evidence"`
+	SuggestedRunbook string   `json:"suggested_runbook"`
+}
+
+// Summary tallies findings by category.
+type Summary struct {
+	TotalFindings int            `json:"total_findings"`
+	ByCategory    map[string]int `json:"by_category"`
+}
+
+// Report runs every drift check and returns the findings plus a summary.
+func Report(ctx context.Context, pool *db.Pool) ([]Finding, Summary) {
+	specs := []struct {
+		finding Finding
+		query   string
+	}{
+		{
+			Finding{Category: "orphan_checks", Severity: "warning",
+				Evidence:         "check entities with truncated/random slugs (legacy shortSlug bug), no live target",
+				SuggestedRunbook: "scripts/cleanup-orphan-checks.sh"},
+			`SELECT e.slug FROM entities e
+			 WHERE e.type = 'check'
+			   AND e.slug ~ '^check:(ping|ssh-script|disk):[0-9a-f]{8}$'`,
+		},
+		{
+			Finding{Category: "dead_checks", Severity: "warning",
+				Evidence:         "enabled check_defs whose target entity is deprecated/destroyed",
+				SuggestedRunbook: "lifecycle-deprecate-node / lifecycle-destroy-node"},
+			`SELECT e.slug FROM check_defs cd
+			 JOIN entities e ON e.id = cd.entity_id
+			 JOIN entities tgt ON tgt.id = cd.target_id
+			 WHERE cd.enabled AND tgt.state IN ('deprecated','destroyed')`,
+		},
+		{
+			Finding{Category: "down_checks", Severity: "critical",
+				Evidence:         "enabled checks reporting health=down",
+				SuggestedRunbook: "service-health-check"},
+			`SELECT e.slug FROM check_defs cd JOIN entities e ON e.id = cd.entity_id
+			 WHERE cd.enabled AND cd.last_health = 'down'`,
+		},
+		{
+			Finding{Category: "unknown_checks", Severity: "warning",
+				Evidence:         "enabled checks that ran but reported health=unknown (likely misconfigured probe)",
+				SuggestedRunbook: "knowledge-graph-audit"},
+			`SELECT e.slug FROM check_defs cd JOIN entities e ON e.id = cd.entity_id
+			 WHERE cd.enabled AND cd.last_health = 'unknown'`,
+		},
+		{
+			Finding{Category: "unmonitored", Severity: "warning",
+				Evidence:         "active entities whose type declares monitoring but have no enabled check_def",
+				SuggestedRunbook: "knowledge-graph-audit"},
+			`SELECT DISTINCT e.slug FROM signals sg
+			 JOIN entities e ON e.id = sg.target_entity_id
+			 WHERE sg.kind = 'unmonitored' AND sg.state IN ('raised','acknowledged','acting')`,
+		},
+		{
+			Finding{Category: "dangling_edges", Severity: "warning",
+				Evidence:         "live relationships (hosts/provides/mounts) pointing at destroyed/deprecated targets",
+				SuggestedRunbook: "lifecycle-destroy-node"},
+			`SELECT src.slug || ' -' || r.type || '-> ' || tgt.slug FROM relationships r
+			 JOIN entities src ON src.id = r.source_id
+			 JOIN entities tgt ON tgt.id = r.target_id
+			 WHERE r.valid_to IS NULL
+			   AND src.state NOT IN ('destroyed','deprecated')
+			   AND tgt.state IN ('destroyed','deprecated')`,
+		},
+	}
+
+	findings := make([]Finding, 0, len(specs))
+	summary := Summary{ByCategory: map[string]int{}}
+	for _, sp := range specs {
+		f := runFinding(ctx, pool, sp.finding, sp.query)
+		findings = append(findings, f)
+		summary.TotalFindings += f.Count
+		summary.ByCategory[f.Category] = f.Count
+	}
+	return findings, summary
+}
+
+const entityCap = 50
+
+// runFinding runs a single-column slug query and folds the rows into a Finding.
+func runFinding(ctx context.Context, pool *db.Pool, f Finding, query string) Finding {
+	rows, err := pool.Query(ctx, query)
+	if err != nil {
+		f.Evidence = f.Evidence + " (query error: " + err.Error() + ")"
+		return f
+	}
+	defer rows.Close()
+	for rows.Next() {
+		var slug string
+		if err := rows.Scan(&slug); err != nil {
+			continue
+		}
+		f.Count++
+		if len(f.Entities) < entityCap {
+			f.Entities = append(f.Entities, slug)
+		}
+	}
+	return f
+}