while-stopped names the container as the machine knows it (hq ADR 0189) #259

Merged
mesh-admin merged 1 commits from fix/while-stopped-names-the-composed-id into main 2026-10-04 02:18:45 +00:00
2 changed files with 65 additions and 0 deletions
+9
View File
@@ -907,6 +907,15 @@ func (r Resolution) compose(with Rendering, owner map[string]string,
if renamed := reflectsRenamed(m.Module, resource["reload-on"]); renamed != nil {
copied["reload-on"] = renamed
}
// And which of its module's containers a scheduled step holds still (novox/hq ADR 0189).
// **The loudest of the three when it is missed.** An unprefixed `restart-on` matches
// nothing and a service quietly never restarts; an unprefixed `while-stopped` names a
// container the declaration does not contain, and the host refuses the whole
// declaration — so the machine takes nothing at all, for every push, until this is
// right. That is what it did on the control node (2026-10-04).
if renamed := reflectsRenamed(m.Module, resource[WhileStopped]); renamed != nil {
copied[WhileStopped] = renamed
}
// And what a process replaces (novox/hq issue 213): a resource of this module's that it
// no longer declares, named as the host recorded it, or the host hands nothing over and
// removes it first.
+56
View File
@@ -2,6 +2,7 @@ package catalogue
import (
"encoding/json"
"fmt"
"strings"
"testing"
)
@@ -87,3 +88,58 @@ func TestAMaintenanceWindowIsRefusedWhereTheDefinitionShowsItCannotMean(t *testi
}
}
}
// A composed declaration names the step's held containers the way the machine knows them.
//
// **The gap that let a bug through to the control node.** The manifest says `while-stopped:
// ["store"]`, because a module names its own resources locally; the declaration a machine
// receives calls that container `distribution.store`, because every resource is composed under
// its module. `restart-on` and `reload-on` are rewritten for exactly this reason, and
// `while-stopped` was not — so the host found no container by that id and refused the whole
// declaration, every push, until it was fixed.
//
// It passed every test on both sides: the controller's tests read manifests, the host's read
// hand-written declarations with bare ids. Only composing one and judging the result catches it.
func TestAComposedWindowNamesTheContainerAsTheMachineKnowsIt(t *testing.T) {
store := Manifest{
Module: "distribution", Version: "1",
Provides: FromAnywhere("artifact-store"),
Listens: []Listening{{Port: 5000, Protocol: "tcp", From: FromMesh}},
Serves: map[string]map[string]any{"artifact-store": {"port": 5000}},
Resources: []map[string]any{
{"id": "store", "type": "container", "name": "mesh-registry",
"image": "registry@sha256:" + strings.Repeat("a", 64), "ports": []any{"5000"}},
{"id": "collect", "type": "container", "name": "mesh-registry-collect",
"image": "registry@sha256:" + strings.Repeat("a", 64),
"schedule": "30 3 * * *", WhileStopped: []any{"store"}},
},
}
r, err := Resolve(shelf(store), []string{"distribution"}, reachable(), World{})
if err != nil {
t.Fatal(err)
}
out, err := r.Declaration(Rendering{})
if err != nil {
t.Fatal(err)
}
collect := fileNamed(out, "distribution.collect")
if collect == nil {
for _, res := range out {
if res["id"] == "distribution.collect" {
collect = res
}
}
}
if collect == nil {
t.Fatalf("the step was not composed at all: %v", out)
}
held, _ := collect[WhileStopped].([]any)
if len(held) != 1 {
t.Fatalf("the composed step holds %v still; want one container", collect[WhileStopped])
}
if got := fmt.Sprint(held[0]); got != "distribution.store" {
t.Fatalf("the composed step says it holds %q still, and the machine's container is "+
"called %q — the host refuses a declaration naming a container it does not have, "+
"whole, so the machine would take nothing at all", got, "distribution.store")
}
}