feat(mcp): discover_infra_drift — live Proxmox vs DB guest reconciliation

The DB-only audit_knowledge_graph can't see guests running in Proxmox that
have no entity, or entities whose pve_id is no longer live — the drift that
the stray test LXCs were a symptom of. discover_infra_drift enumerates running
guests via pct/qm list on every proxmox host (over the same SSH/pct path the
checks use) and diffs against the DB: returns missing (live, no entity) and
ghost (DB, not live). Read-only.

Companion to audit_knowledge_graph; the skill now runs both and treats the
remaining checks (misplaced parent, undeployed scripts, seed drift) as manual.

internal/mcp/discover.go

@@ -0,0 +1,119 @@
+package mcp
+
+import (
+	"bufio"
+	"context"
+	"strings"
+
+	"github.com/dtoro/oikos/internal/db"
+	"github.com/dtoro/oikos/internal/execlog"
+	"github.com/dtoro/oikos/internal/remote"
+)
+
+// discoverInfraDrift compares the live Proxmox guests (pct/qm list on every
+// proxmox host) against the DB graph, surfacing drift the DB-only audit
+// cannot see: guests running with no entity (missing), and entities whose
+// pve_id is no longer live (ghost). This is the auto-discover/validate half
+// of the knowledge-graph audit skill — read-only, reaches hosts over the same
+// SSH/pct path the checks use.
+func discoverInfraDrift(ctx context.Context, pool *db.Pool) any {
+	// 1. proxmox hosts to query.
+	hostRows, err := pool.Query(ctx,
+		`SELECT slug FROM entities WHERE type='proxmox-host' AND COALESCE(state,'active')='active'`)
+	if err != nil {
+		return map[string]any{"error": "query hosts: " + err.Error()}
+	}
+	var hosts []string
+	for hostRows.Next() {
+		var s string
+		if hostRows.Scan(&s) == nil {
+			hosts = append(hosts, s)
+		}
+	}
+	hostRows.Close()
+
+	// 2. DB guests keyed by pve_id.
+	type dbGuest struct {
+		Slug   string `json:"slug"`
+		Type   string `json:"type"`
+		PveID  string `json:"pve_id"`
+		Host   string `json:"host"`
+	}
+	dbGuests := map[string]dbGuest{}
+	gr, err := pool.Query(ctx,
+		`SELECT slug, type, COALESCE(attributes->>'pve_id',''), COALESCE(attributes->>'host','')
+		 FROM entities WHERE type IN ('lxc','vm')`)
+	if err != nil {
+		return map[string]any{"error": "query guests: " + err.Error()}
+	}
+	for gr.Next() {
+		var g dbGuest
+		if gr.Scan(&g.Slug, &g.Type, &g.PveID, &g.Host) == nil && g.PveID != "" {
+			dbGuests[g.PveID] = g
+		}
+	}
+	gr.Close()
+
+	// 3. enumerate live guests from every host.
+	live := map[string]string{} // pve_id -> "host:name"
+	hostErrors := map[string]string{}
+	for _, hs := range hosts {
+		et, rerr := remote.ResolveExecTarget(ctx, pool, hs, sshUser)
+		if rerr != nil {
+			hostErrors[hs] = "resolve: " + rerr.Error()
+			continue
+		}
+		for _, cmd := range []string{"pct list", "qm list"} {
+			out, eerr := sshExecStream(ctx, et.Host, et.User, et.Wrap(cmd),
+				execlog.Sink(func(string, []byte) {}))
+			if eerr != nil {
+				hostErrors[hs+" "+cmd] = eerr.Error()
+				continue
+			}
+			scanIDs(out, hs, live)
+		}
+	}
+
+	// 4. diff.
+	var missing, ghost []string
+	for id, hn := range live {
+		if _, ok := dbGuests[id]; !ok {
+			missing = append(missing, id+" on "+hn)
+		}
+	}
+	for id, g := range dbGuests {
+		if _, ok := live[id]; !ok {
+			ghost = append(ghost, g.Slug+" (pve_id="+id+")")
+		}
+	}
+
+	return map[string]any{
+		"hosts_queried":   len(hosts),
+		"live_guests":     len(live),
+		"db_guests":       len(dbGuests),
+		"missing_entities": missing, // in Proxmox, no DB entity
+		"ghost_entities":  ghost,    // in DB, not live in Proxmox
+		"host_errors":     hostErrors,
+	}
+}
+
+// scanIDs parses `pct list` / `qm list` output (VMID ... Name) into the live map.
+func scanIDs(output, hostSlug string, live map[string]string) {
+	sc := bufio.NewScanner(strings.NewReader(output))
+	for sc.Scan() {
+		line := strings.TrimSpace(sc.Text())
+		if line == "" || strings.HasPrefix(strings.ToLower(line), "vmid") {
+			continue
+		}
+		fields := strings.Fields(line)
+		if len(fields) < 2 {
+			continue
+		}
+		id := fields[0]
+		name := ""
+		if len(fields) >= 4 {
+			name = fields[len(fields)-1] // pct: last col is name; qm: name near end
+		}
+		live[id] = hostSlug + ":" + name
+	}
+}

internal/mcp/tools.go

@@ -791,6 +791,13 @@ func allTools(pool *db.Pool, agentID uuid.UUID) []toolReg {
 			return textResult(string(b)), nil
 		}},
 
+		{tool: &mcp.Tool{Name: "discover_infra_drift", Description: "Read-only live discovery: compares running Proxmox guests (pct/qm list on every proxmox host) against the DB graph. Returns guests running with no entity (missing) and entities whose pve_id is no longer live (ghost) — drift the DB-only audit_knowledge_graph cannot see. Reaches hosts over the same SSH/pct path the checks use. Does NOT mutate anything.",
+			InputSchema: objSchema(),
+		}, handler: func(ctx context.Context, req *mcp.CallToolRequest) (*mcp.CallToolResult, error) {
+			b, _ := json.Marshal(discoverInfraDrift(ctx, pool))
+			return textResult(string(b)), nil
+		}},
+
 		{tool: &mcp.Tool{Name: "list_my_secrets", Description: "List secrets accessible to this client by public key",
 			InputSchema: objSchema(prop{"caller_pubkey", "string", "Age public key of the caller (optional)"}),
 		}, handler: func(ctx context.Context, req *mcp.CallToolRequest) (*mcp.CallToolResult, error) {