Files
mesh-host/internal/agent/agent_test.go
T
jschoubben 1cdb4d1a29 Say a module found running on its own have again at the agent's start, so its health is this engine's and not an older engine's unknown
xorg's have on g14 and shanks kept the unknown an engine before 958ccbd wrote: the
baseline believed the have and never handed the module to the session, so no look
rewrote its health, and the assigner held every module requiring x11-display back.
2026-10-25 15:27:23 +01:00

887 lines
32 KiB
Go

package agent
import (
"context"
"crypto/ed25519"
"encoding/json"
"strings"
"sync"
"testing"
"time"
"git.novox.be/novox/mesh-sdk/go/delivery"
)
const node = "n1"
// The keys of the tests: the controller's and the operator's are trusted, a stranger's is not.
var controllerPub, controllerKey = newKey()
var operatorPub, operatorKey = newKey()
var _, strangerKey = newKey()
func newKey() (ed25519.PublicKey, ed25519.PrivateKey) {
pub, key, err := ed25519.GenerateKey(nil)
if err != nil {
panic(err)
}
return pub, key
}
func fpOf(c string) string { return delivery.SourcePrefix2 + strings.Repeat(c, 64) }
// A watcher the test writes to; it says Caught once the keys written before the watch began are out.
type feed struct {
mu sync.Mutex
ch chan Update
rev uint64
first []Update
}
func newFeed() *feed { return &feed{ch: make(chan Update, 256)} }
func (f *feed) Watch(_ context.Context, _ string) (<-chan Update, error) {
f.mu.Lock()
defer f.mu.Unlock()
for _, u := range f.first {
f.ch <- u
}
f.ch <- Update{Caught: true}
return f.ch, nil
}
// before writes a key as if it was there when the watch began.
func (f *feed) before(key string, value []byte) {
f.mu.Lock()
defer f.mu.Unlock()
f.rev++
f.first = append(f.first, Update{Key: key, Value: value, Revision: f.rev})
}
func (f *feed) put(key string, value []byte) {
f.mu.Lock()
f.rev++
r := f.rev
f.mu.Unlock()
f.ch <- Update{Key: key, Value: value, Revision: r}
}
type haves struct {
mu sync.Mutex
stored map[string]Have
log []Have
removed []string
}
func (h *haves) Read(_ context.Context, module string) (Have, bool) {
h.mu.Lock()
defer h.mu.Unlock()
x, ok := h.stored[module]
return x, ok
}
func (h *haves) Write(_ context.Context, x Have) {
h.mu.Lock()
defer h.mu.Unlock()
if h.stored == nil {
h.stored = map[string]Have{}
}
h.stored[x.Module] = x
h.log = append(h.log, x)
}
func (h *haves) Removed(_ context.Context, m string) {
h.mu.Lock()
defer h.mu.Unlock()
h.removed = append(h.removed, m)
}
func (h *haves) last(module string) Have {
h.mu.Lock()
defer h.mu.Unlock()
return h.stored[module]
}
type bed struct {
t *testing.T
wants *feed
comps *feed
haves *haves
mu sync.Mutex
applied []string
removed []string
backups []string
failWith string
backup func(module string) Backup
kept map[string][]json.RawMessage
others [][]delivery.Composed
said []string
env Env
}
func newBed(t *testing.T) *bed {
b := &bed{t: t, wants: newFeed(), comps: newFeed(), haves: &haves{}}
b.env = Env{Node: node, Wants: b.wants, Composed: b.comps, Haves: b.haves,
Apply: func(_ context.Context, c delivery.Composed, others []delivery.Composed) Result {
b.mu.Lock()
defer b.mu.Unlock()
b.others = append(b.others, others)
name := c.Module
if name == "" {
name = NodeModule
}
b.applied = append(b.applied, name)
if b.failWith != "" {
return Result{Failed: true, Detail: b.failWith}
}
return Result{}
},
Remove: func(_ context.Context, m string, _ []delivery.Composed) Result {
b.mu.Lock()
defer b.mu.Unlock()
b.removed = append(b.removed, m)
return Result{}
},
Backup: func(_ context.Context, m string) Backup {
b.mu.Lock()
defer b.mu.Unlock()
b.backups = append(b.backups, m)
if b.backup != nil {
return b.backup(m)
}
return Backup{Done: true}
},
Kept: func() map[string][]json.RawMessage { return b.kept },
Trusted: func() []ed25519.PublicKey { return []ed25519.PublicKey{controllerPub, operatorPub} },
Say: func(s string) {
t.Log(s)
b.mu.Lock()
b.said = append(b.said, s)
b.mu.Unlock()
},
}
return b
}
func (b *bed) run() (stop func()) {
ctx, cancel := context.WithCancel(context.Background())
done := make(chan struct{})
go func() { defer close(done); _ = New(b.env).Run(ctx) }()
return func() { cancel(); <-done }
}
func file(module, id, content string) json.RawMessage {
raw, _ := json.Marshal(map[string]any{"id": module + "." + id, "type": "file", "path": "/tmp/r6/" + module + "/" + id,
"content": content, "module": module})
return raw
}
// composition is a module's composition at a fingerprint: its key, its bytes and its digest, from the writer's code.
func composition(t *testing.T, module, fp string, data bool, rs ...json.RawMessage) (key string, raw []byte, digest string) {
t.Helper()
c := delivery.Composed{Node: node, Module: module, FP: fp, Data: data, Resources: rs}
var err error
if module == NodeModule {
c.Module, c.FP = "", ""
key, err = delivery.ComposedNodeKey(node)
} else {
key, err = delivery.ComposedKey(node, module, fp)
}
if err != nil {
t.Fatal(err)
}
return signedBy(t, c, key, controllerKey)
}
// signedBy is c signed with signer, as the writer's code signs it: its key, its bytes and its digest.
func signedBy(t *testing.T, c delivery.Composed, key string, signer ed25519.PrivateKey) (string, []byte, string) {
t.Helper()
signed, err := delivery.SignComposed(c, signer)
if err != nil {
t.Fatal(err)
}
raw, err := delivery.EncodeComposed(signed)
if err != nil {
t.Fatal(err)
}
digest, err := delivery.ComposedDigestOf(signed)
if err != nil {
t.Fatal(err)
}
return key, raw, digest
}
func wantFor(t *testing.T, module, fp, digest, backup string) (string, []byte) {
t.Helper()
key, err := delivery.WantKey(node, module)
if err != nil {
t.Fatal(err)
}
raw, err := delivery.EncodeWant(delivery.Want{FP: fp, Composed: digest, Backup: backup})
if err != nil {
t.Fatal(err)
}
return key, raw
}
func eventually(t *testing.T, what string, ok func() bool) {
t.Helper()
deadline := time.Now().Add(3 * time.Second)
for !ok() {
if time.Now().After(deadline) {
t.Fatal(what)
}
time.Sleep(5 * time.Millisecond)
}
}
func (b *bed) appliedList() []string {
b.mu.Lock()
defer b.mu.Unlock()
return append([]string(nil), b.applied...)
}
// R6-A AC1 (the agent, with a bus that is a fake): given a want naming a digest and that composition, the module is
// applied and its have names the fingerprint and the digest; a composition whose digest no want names is not applied.
func TestAWantAndItsCompositionApplyTheModuleAndTheHaveNamesBoth(t *testing.T) {
b := newBed(t)
stop := b.run()
defer stop()
fp := fpOf("a")
ck, craw, dig := composition(t, "web", fp, false, file("web", "x", "1"))
// A composition no want names yet is not applied.
b.comps.put(ck, craw)
time.Sleep(100 * time.Millisecond)
if got := b.appliedList(); len(got) != 0 {
t.Fatalf("a composition no want names was applied: %v", got)
}
wk, wraw := wantFor(t, "web", fp, dig, "")
b.wants.put(wk, wraw)
eventually(t, "the module was not applied", func() bool { return len(b.appliedList()) == 1 })
eventually(t, "the have does not name both", func() bool {
h := b.haves.last("web")
return h.FP == fp && h.Composed == dig && h.Phase == string(delivery.PhaseRunning)
})
// A want naming a digest the composition at that fingerprint does not have: nothing is applied.
fp2 := fpOf("b")
ck2, craw2, _ := composition(t, "web", fp2, false, file("web", "x", "2"))
b.comps.put(ck2, craw2)
wk2, wraw2 := wantFor(t, "web", fp2, "sha256:"+strings.Repeat("0", 64), "")
b.wants.put(wk2, wraw2)
time.Sleep(100 * time.Millisecond)
if got := b.appliedList(); len(got) != 1 {
t.Fatalf("a want naming another digest applied the composition: %v", got)
}
}
// R6-A AC2: given a kept declaration and wants and compositions equal to it, when the agent starts, nothing is applied
// and every have names its fingerprint and digest.
func TestStartingOnWhatTheKeptDeclarationHoldsAppliesNothing(t *testing.T) {
b := newBed(t)
fp := fpOf("a")
rs := []json.RawMessage{file("web", "x", "1"), file("web", "y", "2")}
ck, craw, dig := composition(t, "web", fp, false, rs...)
wk, wraw := wantFor(t, "web", fp, dig, "")
b.comps.before(ck, craw)
b.wants.before(wk, wraw)
// The kept declaration holds the same resources, in another order and spacing.
b.kept = map[string][]json.RawMessage{"web": {json.RawMessage(strings.ReplaceAll(string(rs[1]), ",", " , ")), rs[0]}}
stop := b.run()
defer stop()
eventually(t, "the have was not written", func() bool { return b.haves.last("web").Composed == dig })
if h := b.haves.last("web"); h.FP != fp || h.Phase != string(delivery.PhaseRunning) {
t.Fatalf("the have: %+v", h)
}
time.Sleep(50 * time.Millisecond)
if got := b.appliedList(); len(got) != 0 {
t.Fatalf("a module that already runs what the want names was applied: %v", got)
}
}
// What the node-engine itself last applied is what runs after a restart, not the kept declaration.
func TestStartingOnItsOwnHaveAppliesNothing(t *testing.T) {
b := newBed(t)
fp := fpOf("a")
ck, craw, dig := composition(t, "web", fp, false, file("web", "x", "1"))
wk, wraw := wantFor(t, "web", fp, dig, "")
b.haves.stored = map[string]Have{"web": {Module: "web", FP: fp, Composed: dig, Phase: "running"}}
b.comps.before(ck, craw)
b.wants.before(wk, wraw)
stop := b.run()
defer stop()
time.Sleep(150 * time.Millisecond)
if got := b.appliedList(); len(got) != 0 {
t.Fatalf("a module that runs what the want names was applied after a restart: %v", got)
}
}
// A module found running on its own have after a restart is said again, once, through the haves: the session then holds
// it and writes the health this engine judges. Not said, its key kept the health an older engine wrote: xorg's have on
// g14 and shanks said unknown from before the engine said a module with nothing to judge ok, and the assigner held every
// module requiring x11-display back for it (2026-10-25).
func TestStartingOnItsOwnHaveSaysTheHaveAgainSoItsHealthIsThisEngines(t *testing.T) {
b := newBed(t)
fp := fpOf("a")
ck, craw, dig := composition(t, "xorg", fp, false, file("xorg", "x", "1"))
wk, wraw := wantFor(t, "xorg", fp, dig, "")
b.haves.stored = map[string]Have{"xorg": {Module: "xorg", FP: fp, Composed: dig, Phase: "running", Detail: "kept"}}
b.comps.before(ck, craw)
b.wants.before(wk, wraw)
stop := b.run()
defer stop()
eventually(t, "the have found running was not said again", func() bool {
b.haves.mu.Lock()
defer b.haves.mu.Unlock()
return len(b.haves.log) > 0
})
time.Sleep(50 * time.Millisecond)
b.haves.mu.Lock()
log := append([]Have(nil), b.haves.log...)
b.haves.mu.Unlock()
if len(log) != 1 {
t.Fatalf("the have was said %d times, want once: %+v", len(log), log)
}
if h := log[0]; h.Module != "xorg" || h.FP != fp || h.Composed != dig || h.Phase != string(delivery.PhaseRunning) || h.Detail != "kept" {
t.Fatalf("the have said again: %+v", h)
}
if got := b.appliedList(); len(got) != 0 {
t.Fatalf("a module that runs what the want names was applied: %v", got)
}
}
// A module whose kept resources differ from the composition is applied, and a failed apply is retried only by a change
// of either key.
func TestAFailedApplyIsRetriedOnlyByAChangeOfEitherKey(t *testing.T) {
b := newBed(t)
b.failWith = "web.x: no space"
stop := b.run()
defer stop()
fp := fpOf("a")
ck, craw, dig := composition(t, "web", fp, false, file("web", "x", "1"))
wk, wraw := wantFor(t, "web", fp, dig, "")
b.comps.put(ck, craw)
b.wants.put(wk, wraw)
eventually(t, "not applied", func() bool { return len(b.appliedList()) == 1 })
eventually(t, "the have does not say failed", func() bool {
h := b.haves.last("web")
return h.Phase == string(delivery.PhaseFailed) && strings.Contains(h.Detail, "no space") && h.FP == fp
})
// An unrelated key changes: not a retry.
ck9, craw9, _ := composition(t, "web", fpOf("9"), false, file("web", "x", "9"))
b.comps.put(ck9, craw9)
time.Sleep(150 * time.Millisecond)
if n := len(b.appliedList()); n != 1 {
t.Fatalf("a failed apply was retried by an unrelated key (%d applies)", n)
}
// The want is written again: the retry.
b.mu.Lock()
b.failWith = ""
b.mu.Unlock()
b.wants.put(wk, wraw)
eventually(t, "the change of the want did not retry", func() bool { return len(b.appliedList()) == 2 })
eventually(t, "not running", func() bool { return b.haves.last("web").Phase == string(delivery.PhaseRunning) })
}
// R6-A AC5: a data module that ran before asks its backup before any resource changes; a refusal holds it, nothing is
// applied and the have says held; when the want then says skip, the module is applied.
func TestADataModuleIsBackedUpFirstAndHeldWhenItFails(t *testing.T) {
b := newBed(t)
fp1, fp2 := fpOf("a"), fpOf("b")
ck1, craw1, dig1 := composition(t, "db", fp1, true, file("db", "x", "1"))
wk1, wraw1 := wantFor(t, "db", fp1, dig1, "")
b.comps.before(ck1, craw1)
b.wants.before(wk1, wraw1)
b.kept = map[string][]json.RawMessage{"db": {file("db", "x", "1")}}
refuse := true
b.backup = func(string) Backup {
if refuse {
return Backup{Words: "restic: the repository is locked"}
}
return Backup{Done: true}
}
stop := b.run()
defer stop()
eventually(t, "baseline", func() bool { return b.haves.last("db").Composed == dig1 })
ck2, craw2, dig2 := composition(t, "db", fp2, true, file("db", "x", "2"))
b.comps.put(ck2, craw2)
wk2, wraw2 := wantFor(t, "db", fp2, dig2, "")
b.wants.put(wk2, wraw2)
eventually(t, "the backup was not asked", func() bool {
b.mu.Lock()
defer b.mu.Unlock()
return len(b.backups) == 1
})
eventually(t, "the have does not say held", func() bool {
h := b.haves.last("db")
return h.Phase == string(delivery.PhaseHeld) && strings.Contains(h.Detail, "repository is locked") && h.FP == fp1
})
if got := b.appliedList(); len(got) != 0 {
t.Fatalf("something was applied behind a failed backup: %v", got)
}
// The answer arrives in the module's own want: back up again (it fails again), then skip.
wk, again := wantFor(t, "db", fp2, dig2, delivery.BackupAgain)
b.wants.put(wk, again)
eventually(t, "back up again did not ask the backup", func() bool {
b.mu.Lock()
defer b.mu.Unlock()
return len(b.backups) == 2
})
if got := b.appliedList(); len(got) != 0 {
t.Fatalf("applied behind a second failed backup: %v", got)
}
_, skip := wantFor(t, "db", fp2, dig2, delivery.BackupSkip)
b.wants.put(wk, skip)
eventually(t, "skip did not apply the module", func() bool { return len(b.appliedList()) == 1 })
b.mu.Lock()
n := len(b.backups)
b.mu.Unlock()
if n != 2 {
t.Fatalf("a backup was asked after the answer was to skip: %d asks", n)
}
eventually(t, "not running at the new fingerprint", func() bool {
h := b.haves.last("db")
return h.Phase == string(delivery.PhaseRunning) && h.FP == fp2 && h.Composed == dig2
})
}
// A data module with a good backup is applied after it; one that never ran has nothing to back up.
func TestABackupDoneIsFollowedByTheApplyAndANewModuleIsNotBackedUp(t *testing.T) {
b := newBed(t)
stop := b.run()
defer stop()
fp := fpOf("c")
ck, craw, dig := composition(t, "db", fp, true, file("db", "x", "1"))
wk, wraw := wantFor(t, "db", fp, dig, "")
b.comps.put(ck, craw)
b.wants.put(wk, wraw)
eventually(t, "not applied", func() bool { return len(b.appliedList()) == 1 })
b.mu.Lock()
n := len(b.backups)
b.mu.Unlock()
if n != 0 {
t.Fatalf("a module that never ran was backed up (%d)", n)
}
fp2 := fpOf("d")
ck2, craw2, dig2 := composition(t, "db", fp2, true, file("db", "x", "2"))
wk2, wraw2 := wantFor(t, "db", fp2, dig2, "")
b.comps.put(ck2, craw2)
b.wants.put(wk2, wraw2)
eventually(t, "second not applied", func() bool { return len(b.appliedList()) == 2 })
b.mu.Lock()
n = len(b.backups)
b.mu.Unlock()
if n != 1 {
t.Fatalf("a module that ran before was backed up %d times, want once", n)
}
}
// R6-A AC4 at the agent: a removed want removes that module only, and its have is written removed.
func TestARemovedWantRemovesThatModuleOnly(t *testing.T) {
b := newBed(t)
stop := b.run()
defer stop()
fp := fpOf("a")
ck, craw, dig := composition(t, "web", fp, false, file("web", "x", "1"))
b.comps.put(ck, craw)
wk, wraw := wantFor(t, "web", fp, dig, "")
b.wants.put(wk, wraw)
eventually(t, "not applied", func() bool { return len(b.appliedList()) == 1 })
gone, _ := delivery.EncodeWant(delivery.Want{Removed: true})
b.wants.put(wk, gone)
eventually(t, "not removed", func() bool {
b.mu.Lock()
defer b.mu.Unlock()
return len(b.removed) == 1 && b.removed[0] == "web"
})
eventually(t, "the have was not written removed", func() bool {
b.haves.mu.Lock()
defer b.haves.mu.Unlock()
return len(b.haves.removed) == 1
})
}
// The node's own composition is applied before any module's, whichever key came first.
func TestTheNodesOwnCompositionComesBeforeAnyModules(t *testing.T) {
b := newBed(t)
fp := fpOf("a")
ck, craw, dig := composition(t, "web", fp, false, file("web", "x", "1"))
wk, wraw := wantFor(t, "web", fp, dig, "")
nk, nraw, ndig := composition(t, NodeModule, "", false)
nwk, err := delivery.WantNodeKey(node)
if err != nil {
t.Fatal(err)
}
nwraw, err := delivery.EncodeNodeWant(delivery.NodeWant{Composed: ndig})
if err != nil {
t.Fatal(err)
}
b.comps.before(ck, craw)
b.comps.before(nk, nraw)
b.wants.before(wk, wraw)
b.wants.before(nwk, nwraw)
stop := b.run()
defer stop()
eventually(t, "both not applied", func() bool { return len(b.appliedList()) == 2 })
if got := b.appliedList(); got[0] != NodeModule || got[1] != "web" {
t.Fatalf("the order was %v, the node's own first", got)
}
}
// R6-A AC9: a composition signed by either trusted key is applied; one signed by another key, one changed after it was
// signed and one unsigned are refused and nothing of them is applied (ADR 0539 §3).
func TestOnlyACompositionSignedByATrustedKeyIsApplied(t *testing.T) {
b := newBed(t)
stop := b.run()
defer stop()
plain := func(module, fp, content string) delivery.Composed {
return delivery.Composed{Node: node, Module: module, FP: fp, Resources: []json.RawMessage{file(module, "x", content)}}
}
put := func(c delivery.Composed, signer ed25519.PrivateKey, tamper func([]byte) []byte) {
key, _ := delivery.ComposedKey(node, c.Module, c.FP)
var raw []byte
var dig string
if signer == nil {
raw, _ = delivery.EncodeComposed(c)
dig, _ = delivery.ComposedDigestOf(c)
} else {
_, raw, dig = signedBy(t, c, key, signer)
}
if tamper != nil {
raw = tamper(raw)
}
b.comps.put(key, raw)
wk, wraw := wantFor(t, c.Module, c.FP, dig, "")
b.wants.put(wk, wraw)
}
// Refused: signed by a stranger, changed after signing, unsigned.
put(plain("stranger", fpOf("1"), "x"), strangerKey, nil)
put(plain("changed", fpOf("2"), "before"), controllerKey, func(raw []byte) []byte {
return []byte(strings.Replace(string(raw), "before", "after!", 1))
})
put(plain("unsigned", fpOf("3"), "x"), nil, nil)
time.Sleep(200 * time.Millisecond)
if got := b.appliedList(); len(got) != 0 {
t.Fatalf("a composition that is not signed by a trusted key was applied: %v", got)
}
// Applied: signed by the controller, signed by the operator.
put(plain("bycontroller", fpOf("4"), "x"), controllerKey, nil)
put(plain("byoperator", fpOf("5"), "x"), operatorKey, nil)
eventually(t, "the trusted signers' compositions were not applied", func() bool { return len(b.appliedList()) == 2 })
got := b.appliedList()
if !(got[0] == "bycontroller" && got[1] == "byoperator") && !(got[0] == "byoperator" && got[1] == "bycontroller") {
t.Fatalf("applied %v", got)
}
if h := b.haves.last("byoperator"); h.Phase != string(delivery.PhaseRunning) || h.FP != fpOf("5") {
t.Fatalf("the operator's module has no running have: %+v", h)
}
}
// With no key trusted, nothing is applied: a node that does not know its signers fails closed.
func TestWithNoTrustedKeyNothingIsApplied(t *testing.T) {
b := newBed(t)
b.env.Trusted = nil
stop := b.run()
defer stop()
fp := fpOf("a")
ck, craw, dig := composition(t, "web", fp, false, file("web", "x", "1"))
b.comps.put(ck, craw)
wk, wraw := wantFor(t, "web", fp, dig, "")
b.wants.put(wk, wraw)
time.Sleep(200 * time.Millisecond)
if got := b.appliedList(); len(got) != 0 {
t.Fatalf("applied with no trusted key: %v", got)
}
}
// What a module's apply must not take is every other module that runs, those the agent holds and those still running from
// the kept declaration (ADR 0429 §4): the resources of the kept declaration reach Apply as the others.
func TestApplyingOneModuleHoldsOutTheModulesStillRunningFromTheKeptDeclaration(t *testing.T) {
b := newBed(t)
b.kept = map[string][]json.RawMessage{"db": {file("db", "x", "1")}, NodeModule: {file("node", "n", "n")}}
stop := b.run()
defer stop()
fp := fpOf("a")
ck, craw, dig := composition(t, "web", fp, false, file("web", "x", "1"))
b.comps.put(ck, craw)
wk, wraw := wantFor(t, "web", fp, dig, "")
b.wants.put(wk, wraw)
eventually(t, "not applied", func() bool { return len(b.appliedList()) == 1 })
b.mu.Lock()
defer b.mu.Unlock()
var names []string
for _, c := range b.others[0] {
names = append(names, c.Module)
}
if len(names) != 2 || !strings.Contains(strings.Join(names, ","), "db") {
t.Fatalf("the others of web were %v: db and the node's own run from the kept declaration", names)
}
}
// Everything is what runs: the agent's compositions and the kept resources of each module it does not hold.
func TestEverythingIsWhatTheAgentRunsAndWhatIsKeptForTheRest(t *testing.T) {
b := newBed(t)
b.kept = map[string][]json.RawMessage{"db": {file("db", "x", "1")}, "web": {file("web", "x", "old")}}
a := New(b.env)
if got := a.Everything(); len(got) != 2 {
t.Fatalf("before the agent holds anything: %d compositions, want the 2 kept", len(got))
}
a.running["web"] = delivery.Have{FP: fpOf("a"), Composed: "sha256:" + strings.Repeat("1", 64), Phase: delivery.PhaseRunning}
ck, craw, dig := composition(t, "web", fpOf("a"), false, file("web", "x", "new"))
a.running["web"] = delivery.Have{FP: fpOf("a"), Composed: dig, Phase: delivery.PhaseRunning}
a.takeComposition(Update{Key: ck, Value: craw, Revision: 1})
got := a.Everything()
if len(got) != 2 {
t.Fatalf("%d compositions", len(got))
}
for _, c := range got {
if c.Module == "web" && !strings.Contains(string(c.Resources[0]), "new") {
t.Fatal("web is the kept declaration's, not the composition the agent runs")
}
}
if a.HoldsNode() {
t.Fatal("the agent holds no node composition")
}
}
// A failed apply is applied again after a restart even when the kept declaration holds the composition: once this
// node-engine wrote its haves, they are what it knows (the kept declaration is only for the first start after the switch).
func TestAFailedApplyIsAppliedAgainAfterARestartWhateverIsKept(t *testing.T) {
b := newBed(t)
fp := fpOf("a")
ck, craw, dig := composition(t, "web", fp, false, file("web", "x", "1"))
wk, wraw := wantFor(t, "web", fp, dig, "")
b.comps.before(ck, craw)
b.wants.before(wk, wraw)
b.kept = map[string][]json.RawMessage{"web": {file("web", "x", "1")}}
b.haves.stored = map[string]Have{"web": {Module: "web", FP: fp, Composed: dig, Phase: string(delivery.PhaseFailed)}}
stop := b.run()
defer stop()
eventually(t, "a failed apply was marked running from the kept declaration", func() bool { return len(b.appliedList()) == 1 })
}
// A have written before the switch carries no composition: then the kept declaration says what runs.
func TestAHaveWithNoCompositionDefersToTheKeptDeclaration(t *testing.T) {
b := newBed(t)
fp := fpOf("a")
ck, craw, dig := composition(t, "web", fp, false, file("web", "x", "1"))
wk, wraw := wantFor(t, "web", fp, dig, "")
b.comps.before(ck, craw)
b.wants.before(wk, wraw)
b.kept = map[string][]json.RawMessage{"web": {file("web", "x", "1")}}
b.haves.stored = map[string]Have{"web": {Module: "web", Phase: "running"}}
stop := b.run()
defer stop()
eventually(t, "the have was not written", func() bool { return b.haves.last("web").Composed == dig })
time.Sleep(50 * time.Millisecond)
if got := b.appliedList(); len(got) != 0 {
t.Fatalf("applied %v", got)
}
}
// A module that leaves the node's own composition for a composition of its own keeps its resources until that one is
// applied: the node's own apply holds out every module whose composition the node's bucket holds and the agent does not
// run yet (issue 1945, live on 2026-10-25 at 02:32: shanks' node-engine applied a node's own composition that no longer
// carried systemd-resolved, whose own composition waited for its credential, and removed its guard, so the machine lost
// its resolver).
func TestTheNodesOwnApplyHoldsOutAModuleThatMovedToItsOwnComposition(t *testing.T) {
b := newBed(t)
fp := fpOf("b")
// systemd-resolved's own composition is written; no want names it yet.
rk, rraw, _ := composition(t, "systemd-resolved", fp, false, file("systemd-resolved", "guard", "g"))
b.comps.before(rk, rraw)
nk, nraw, ndig := composition(t, NodeModule, "", false)
nwk, err := delivery.WantNodeKey(node)
if err != nil {
t.Fatal(err)
}
nwraw, err := delivery.EncodeNodeWant(delivery.NodeWant{Composed: ndig})
if err != nil {
t.Fatal(err)
}
b.comps.before(nk, nraw)
b.wants.before(nwk, nwraw)
stop := b.run()
defer stop()
eventually(t, "the node's own not applied", func() bool { return len(b.appliedList()) == 1 })
b.mu.Lock()
defer b.mu.Unlock()
var names []string
for _, c := range b.others[0] {
names = append(names, c.Module)
}
if !strings.Contains(strings.Join(names, ","), "systemd-resolved") {
t.Fatalf("the others of the node's own apply were %v: systemd-resolved's resources would be removed", names)
}
}
// A module the assigner removed holds nothing back, its compositions still in the bucket or not: its resources are its
// removal's to take (issue 1945).
func TestARemovedModulesCompositionHoldsNothingBack(t *testing.T) {
b := newBed(t)
fp := fpOf("b")
rk, rraw, _ := composition(t, "gone", fp, false, file("gone", "x", "1"))
b.comps.before(rk, rraw)
gk, err := delivery.WantKey(node, "gone")
if err != nil {
t.Fatal(err)
}
graw, err := delivery.EncodeWant(delivery.Want{Removed: true})
if err != nil {
t.Fatal(err)
}
b.wants.before(gk, graw)
nk, nraw, ndig := composition(t, NodeModule, "", false)
nwk, _ := delivery.WantNodeKey(node)
nwraw, _ := delivery.EncodeNodeWant(delivery.NodeWant{Composed: ndig})
b.comps.before(nk, nraw)
b.wants.before(nwk, nwraw)
stop := b.run()
defer stop()
eventually(t, "the node's own not applied", func() bool {
for _, m := range b.appliedList() {
if m == NodeModule {
return true
}
}
return false
})
b.mu.Lock()
defer b.mu.Unlock()
for _, others := range b.others {
for _, c := range others {
if c.Module == "gone" {
t.Fatal("a removed module's composition was held out")
}
}
}
}
// The node's own composition is not applied while a module's composition in the node's bucket cannot be read or is not
// signed by a trusted key: what that one carries may be what left the node's own, and the node's own apply would remove
// it (issue 1945, the review's gap 2). It is said, naming the composition, and applied once that one reads.
func TestTheNodesOwnWaitsWhileAModulesCompositionCannotBeRead(t *testing.T) {
b := newBed(t)
bad, err := delivery.ComposedKey(node, "broken", fpOf("c"))
if err != nil {
t.Fatal(err)
}
b.comps.before(bad, []byte(`{"v":1,"not":"a composition"}`))
nk, nraw, ndig := composition(t, NodeModule, "", false)
nwk, _ := delivery.WantNodeKey(node)
nwraw, _ := delivery.EncodeNodeWant(delivery.NodeWant{Composed: ndig})
b.comps.before(nk, nraw)
b.wants.before(nwk, nwraw)
stop := b.run()
defer stop()
eventually(t, "the wait not said", func() bool {
b.mu.Lock()
defer b.mu.Unlock()
for _, s := range b.said {
if strings.Contains(s, bad) {
return true
}
}
return false
})
if got := b.appliedList(); len(got) != 0 {
t.Fatalf("applied %v while a composition could not be read", got)
}
// Read again, the node's own is applied.
gk, graw, _ := composition(t, "broken", fpOf("c"), false, file("broken", "x", "1"))
b.comps.put(gk, graw)
eventually(t, "the node's own not applied", func() bool { return len(b.appliedList()) == 1 })
}
// A stale refused composition beside a newer readable one of the same module does not hold the node's own apply back:
// only the composition the module's want names, else its newest, counts (the review of issue 1945: the bucket keeps
// compositions written before the filled paths, which the SDK now refuses, and nobody applies them).
func TestAStaleRefusedCompositionDoesNotHoldTheNodesOwnBack(t *testing.T) {
b := newBed(t)
stale, err := delivery.ComposedKey(node, "power", fpOf("a"))
if err != nil {
t.Fatal(err)
}
b.comps.before(stale, []byte(`{"v":1,"not":"a composition"}`))
gk, graw, _ := composition(t, "power", fpOf("b"), false, file("power", "x", "1"))
b.comps.before(gk, graw)
nk, nraw, ndig := composition(t, NodeModule, "", false)
nwk, _ := delivery.WantNodeKey(node)
nwraw, _ := delivery.EncodeNodeWant(delivery.NodeWant{Composed: ndig})
b.comps.before(nk, nraw)
b.wants.before(nwk, nwraw)
stop := b.run()
defer stop()
eventually(t, "the node's own not applied", func() bool { return len(b.appliedList()) == 1 })
}
// A composition the kept declaration or the node's own have says runs is applied all the same when the engine holds no
// record of its resources: they were removed since (issue 1945, live on 2026-10-25: ace's and g14's node-engines removed
// ca-trust's, power's and matrix's resources in a node's own apply, and the wants that named those modules' own
// compositions were judged already running from the kept declaration, so nothing made them again).
func TestACompositionWhoseResourcesWereRemovedIsAppliedAgain(t *testing.T) {
for _, from := range []string{"kept", "have"} {
t.Run(from, func(t *testing.T) {
b := newBed(t)
fp := fpOf("a")
rs := []json.RawMessage{file("ca-trust", "trust", "1")}
ck, craw, dig := composition(t, "ca-trust", fp, false, rs...)
wk, wraw := wantFor(t, "ca-trust", fp, dig, "")
b.comps.before(ck, craw)
b.wants.before(wk, wraw)
if from == "kept" {
b.kept = map[string][]json.RawMessage{"ca-trust": rs}
} else {
b.haves.stored = map[string]Have{"ca-trust": {Module: "ca-trust", FP: fp, Composed: dig, Phase: "running"}}
}
b.env.Recorded = func(context.Context, delivery.Composed) bool { return false }
stop := b.run()
defer stop()
eventually(t, "not applied", func() bool { return len(b.appliedList()) == 1 })
})
}
}
// The composition a want names is applied from the key's history when a newer one has replaced it under the same key:
// a want held at a fingerprint keeps naming the digest it was written with, and the controller writes every new
// composition at that fingerprint over the same key (ADR 0539 clause 1, the sweep's kept revisions; issue 1945, live on
// 2026-10-25: shanks' node-tools composition had digest 575a5c96, its held want named a36e63c8, and nothing was applied).
func TestTheRevisionAWantNamesIsAppliedFromHistory(t *testing.T) {
b := newBed(t)
fp := fpOf("a")
ck, oldRaw, oldDig := composition(t, "node-tools", fp, false, file("node-tools", "x", "old"))
_, newRaw, _ := composition(t, "node-tools", fp, false, file("node-tools", "x", "new"))
b.comps.before(ck, newRaw) // the key's latest value
wk, wraw := wantFor(t, "node-tools", fp, oldDig, "")
b.wants.before(wk, wraw)
b.env.Revisions = func(_ context.Context, key string) ([]Update, error) {
if key != ck {
return nil, nil
}
return []Update{{Key: ck, Value: oldRaw, Revision: 3}, {Key: ck, Value: newRaw, Revision: 7}}, nil
}
stop := b.run()
defer stop()
eventually(t, "the revision the want names was not applied", func() bool { return len(b.appliedList()) == 1 })
if h := b.haves.last("node-tools"); h.Composed != oldDig {
t.Fatalf("the have names %s, want %s", h.Composed, oldDig)
}
}
// 1945/AC18 (unit): a module that still runs from the kept declaration carries the kept declaration's filled paths of
// its files, so the filling writes them ("not named as filled" for claude-code and screen-lock, 2026-10-25).
func TestAModuleRunningFromTheKeptDeclarationKeepsItsFilledPaths(t *testing.T) {
b := newBed(t)
b.kept = map[string][]json.RawMessage{"claude-code": {file("claude-code", "settings", "")}}
b.env.KeptFilled = func() map[string][]string {
return map[string][]string{"claude-code": {"/tmp/r6/claude-code/settings"}}
}
a := New(b.env)
got := a.Everything()
if len(got) != 1 || got[0].Module != "claude-code" || strings.Join(got[0].Filled, ",") != "/tmp/r6/claude-code/settings" {
t.Fatalf("what runs from the kept declaration: %+v", got)
}
}