Monitoring coverage was 3 of 89 active entities. Three bugs, each hidden by discarded errors in checkdefaults: - writeCheck generated a fresh uuid, inserted the check entity ON CONFLICT (slug) DO NOTHING, then wrote a check_defs row referencing it. On any re-seed the slug already existed, the entity insert no-oped, and the FK violated — aborting the ingest transaction and surfacing as an unrelated failure several entities later. Re-seeding has been broken since; prod's coverage was frozen at its first successful seed. This is what TestSeedIngestIdempotentAndNoDuplicateEdges had been reporting. - shortSlug truncated to the last 8 chars, so all 21 ingress routes collapsed to ".network" and overwrote each other; service:jellyfin collided with lxc:jellyfin. - The ssh-script checker never read the `args` config checkdefaults wrote, so process_check.sh always ran without its unit name and returned "unknown". Coverage is now 75/89. Monitoring is declared per entity type in seeds/ontology.yaml and resolved through the is-a hierarchy, so a type can say it warrants nothing (site, lan, mesh, cluster) and never be reported as a gap. coverageSweep raises an `unmonitored` signal only where a type declares monitoring it lacks — 8 real gaps, no false positives. Also: - entity_types.attribute_schema was never ingested: the seed loader read "attribute_schema" but the YAML says "attributes", so all 60 types stored JSON null. - ListExecutions ignored its declared target/action/correlation_id filters and paginated on a non-unique target slug, dropping and repeating rows. - started_at was captured but only written at terminal state, so a running execution reported NULL for its whole life. The three MCP auto-run copies wrote no timing at all; they are now one autoRun helper. - SSH output was buffered to completion and discarded entirely on timeout. Both sshExec copies now stream through a shared execlog sink into execution_logs, and keep partial output when a command is cancelled. - executions.correlation_id was a random per-execution uuid that correlated nothing; it is now the chat session id, which is what lets the chat tail live output. - reversible_low had no auto-run branch despite policy declaring it unattended. Since computeCommandRisk never returns it, the class only arises when an agent declares it over a read_only command — so gating it penalised candor without adding safety. - backup-target gains a backup-freshness checker (portable find -mmin, since the first target is on macOS), resolving its host by walking backs-up-to backwards. The pre-deploy pg_dump is now a tracked backup target. UI: an Executions section on entity detail with live output tailing, and streamed output under a running `run` call in the chat timeline. Migrations 022-024. Ops.svelte and context.ts exclude execution.output from their refetch triggers, which would otherwise fire once a second per command. Co-Authored-By: Claude <noreply@anthropic.com>
122 lines
4.3 KiB
Go
122 lines
4.3 KiB
Go
package ontology
|
|
|
|
import (
|
|
"testing"
|
|
)
|
|
|
|
func kinds(v ...string) *[]string {
|
|
s := append([]string{}, v...)
|
|
return &s
|
|
}
|
|
|
|
// monitoringTree mirrors the real shape of seeds/ontology.yaml: a declaration
|
|
// on an abstract type that concrete subtypes inherit, an explicit none on a
|
|
// topological type, a probeable type outside the infrastructure layer, and an
|
|
// undeclared infrastructure type (the ontology gap this is meant to catch).
|
|
func monitoringTree() *TypeTree {
|
|
return &TypeTree{
|
|
Types: map[string]TypeInfo{
|
|
"entity": {IsAbstract: true, Layer: "meta"},
|
|
"compute-entity": {Parent: "entity", IsAbstract: true, Layer: "infrastructure"},
|
|
"machine": {Parent: "compute-entity", IsAbstract: true, Layer: "infrastructure",
|
|
Monitoring: kinds("ping", "resource")},
|
|
"proxmox-host": {Parent: "machine", Layer: "infrastructure"},
|
|
"workstation": {Parent: "machine", Layer: "infrastructure"},
|
|
"service": {Parent: "entity", Layer: "infrastructure", Monitoring: kinds("http", "process")},
|
|
"site": {Parent: "entity", Layer: "infrastructure", Monitoring: kinds()},
|
|
"vlan": {Parent: "entity", Layer: "infrastructure"}, // undeclared: a gap
|
|
"agent": {Parent: "entity", Layer: "governance", Monitoring: kinds("http")},
|
|
"signal": {Parent: "entity", Layer: "cognition"},
|
|
"document": {Parent: "entity", Layer: "governance"},
|
|
},
|
|
}
|
|
}
|
|
|
|
func TestMonitoringResolvesThroughHierarchy(t *testing.T) {
|
|
tree := monitoringTree()
|
|
|
|
cases := []struct {
|
|
typ string
|
|
wantKinds []string
|
|
wantDecl bool
|
|
wantSource string
|
|
desc string
|
|
}{
|
|
{"machine", []string{"ping", "resource"}, true, "machine", "declared on itself"},
|
|
{"proxmox-host", []string{"ping", "resource"}, true, "machine", "inherited from abstract parent"},
|
|
{"workstation", []string{"ping", "resource"}, true, "machine", "inherited by a sibling too"},
|
|
{"service", []string{"http", "process"}, true, "service", "declared on itself"},
|
|
{"site", nil, true, "site", "explicitly none — not a gap"},
|
|
{"agent", []string{"http"}, true, "agent", "explicit declaration beats the layer default"},
|
|
{"signal", nil, true, "", "cognition layer is implicitly none"},
|
|
{"document", nil, true, "", "governance layer is implicitly none"},
|
|
{"vlan", nil, false, "", "undeclared infrastructure type is a genuine gap"},
|
|
{"nonexistent", nil, false, "", "unknown type resolves to undeclared"},
|
|
}
|
|
|
|
for _, c := range cases {
|
|
got := tree.Monitoring(c.typ)
|
|
if got.Declared != c.wantDecl {
|
|
t.Errorf("%s (%s): Declared = %v, want %v", c.typ, c.desc, got.Declared, c.wantDecl)
|
|
}
|
|
if got.Source != c.wantSource {
|
|
t.Errorf("%s (%s): Source = %q, want %q", c.typ, c.desc, got.Source, c.wantSource)
|
|
}
|
|
if len(got.Kinds) != len(c.wantKinds) {
|
|
t.Errorf("%s (%s): Kinds = %v, want %v", c.typ, c.desc, got.Kinds, c.wantKinds)
|
|
continue
|
|
}
|
|
for i, k := range c.wantKinds {
|
|
if got.Kinds[i] != k {
|
|
t.Errorf("%s (%s): Kinds[%d] = %q, want %q", c.typ, c.desc, i, got.Kinds[i], k)
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
// The distinction between these two is what keeps coverageSweep from raising
|
|
// permanent, unresolvable signals against entities that are working as intended.
|
|
func TestMonitoringNoneIsNotTheSameAsUndeclared(t *testing.T) {
|
|
tree := monitoringTree()
|
|
|
|
site := tree.Monitoring("site")
|
|
if !site.None() {
|
|
t.Error("site declared `monitoring: none`, expected None() to report true")
|
|
}
|
|
|
|
vlan := tree.Monitoring("vlan")
|
|
if vlan.None() {
|
|
t.Error("vlan declared nothing at all — None() must not claim it opted out")
|
|
}
|
|
if vlan.Declared {
|
|
t.Error("vlan is an undeclared infrastructure type; it should read as a gap")
|
|
}
|
|
}
|
|
|
|
func TestMonitoringWants(t *testing.T) {
|
|
tree := monitoringTree()
|
|
|
|
svc := tree.Monitoring("service")
|
|
if !svc.Wants("http") {
|
|
t.Error("service should want an http check")
|
|
}
|
|
if svc.Wants("resource") {
|
|
t.Error("service should not want a resource check")
|
|
}
|
|
if tree.Monitoring("site").Wants("http") {
|
|
t.Error("an explicitly unmonitorable type wants nothing")
|
|
}
|
|
}
|
|
|
|
func TestMonitoringSurvivesParentCycle(t *testing.T) {
|
|
// The ingest rejects cycles; this guards the walker regardless.
|
|
tree := &TypeTree{Types: map[string]TypeInfo{
|
|
"a": {Parent: "b", Layer: "infrastructure"},
|
|
"b": {Parent: "a", Layer: "infrastructure"},
|
|
}}
|
|
got := tree.Monitoring("a")
|
|
if got.Declared {
|
|
t.Errorf("cyclic chain declared nothing, got %+v", got)
|
|
}
|
|
}
|