Compare commits

..
Author SHA1 Message Date
jochen 3647928668 Judge an upstream pin's host like any name, and harden the upstream unpack (review 35, hq issue 345)
mesh/delivery-group group fix/345-reminder-test rejected: a member's own check failed
mesh/merge-gate pass: builds build-agent, mesh-controller → ace, g14, novox, shanks; no bus step; every machine composes with the change as it did without …
mesh/repo-check fail: its merge-check.sh failed: --- FAIL: TestTheInstallersFirstUserListIsWhatTheControllerWouldCompose (0.64s)
mesh/delivery stopped: the pull request closed unmerged
The url was skipped by the installation check, so an installation's host or
an address passed; it is judged whole now, the vendor's host declared in the
artifact's names-on-purpose, and an address or a reserved name as the host
is refused. Only the version's dotted-quad reading is skipped. The unpack
caps its entries, drains xz before waiting for it, reads a pax global
header and a nested within's parents, and a redirect off https is not
followed.
2026-10-12 13:25:18 +02:00
jochen 9d108feab8 Let an archive be an upstream release pinned by URL and sha256, mirrored by the build seat (hq issue 345, ADR 0316)
mesh/merge-gate pass: builds build-agent, mesh-controller → ace, g14, novox, shanks; no bus step; every machine composes with the change as it did without …
mesh/repo-check pass: its merge-check.sh passed
mesh/delivery-group group fix/345-reminder-test rejected: a member's own check failed
mesh/delivery superseded: a newer head of the same pull request
A mail client's release is about 80 MB per version, too large to keep in a
repository at every upgrade, and an add-on whose licence forbids copying it
to third parties may not be in a repository at all. An archive artifact may
now name url, sha256 and version (and file or within) instead of from: the
build seat fetches it once, refuses it when its digest is not the pin's and
names both, keeps it in its workspace under the digest (a vendor that serves
only its newest version cannot break a later build of the same pin), and
packs it like any archive, so a node gets the mesh's own archive by digest
and never asks the vendor. The build seat's image carries xz, which Go's
standard library does not read. The installation check takes the vendor's
address and version of such a pin for the world's, as a registry is an
image's.
2026-10-12 12:57:30 +02:00
65 changed files with 239 additions and 4198 deletions
+15 -67
View File
@@ -4,7 +4,6 @@ import (
"context"
"fmt"
"github.com/novox/mesh-controller/internal/broker"
"io"
"slices"
"sort"
"strings"
@@ -55,9 +54,6 @@ func assignWith(ctx context.Context, open *stores, node string, opts assignOptio
if err := refusedMovingTheController(modules); err != nil {
return "", err
}
// Every line of the answer comes from the one resolution after the write (novox/hq issue 237):
// what the reads before it would say about a machine left out is not the answer's.
ctx = leftOutSaidBy(ctx, io.Discard)
// Held while it is recorded, so it cannot land between a converge's preview and its flip and
// be taken without ever having been previewed (novox/hq ADR 0100).
ctx, release, err := holdNodes(ctx, open, []string{node})
@@ -129,28 +125,22 @@ func assignWith(ctx context.Context, open *stores, node string, opts assignOptio
for _, line := range settled {
answer += "\n " + line
}
// What this act changed about this node's unmet seat dependencies, and nothing else (novox/hq
// ADR 0207): a dependency of a module just assigned, or one this assignment met. The rest of the
// node's list, and every other node's, is `status`'s.
for _, line := range unheldChange(shelf, node, before, append(append([]string(nil), before...), added...)) {
answer += "\n " + line
}
// Its bus credential, in the same act (novox/hq issue 203): an assignment pushed before its
// credential exists delivers a process that cannot authenticate and crash-loops until somebody
// runs a second verb and a second push. Issued here when the module speaks on the bus and has
// no credential yet; kept when it has one, so re-assigning rotates nothing.
var issued []string
for _, module := range added {
if line := issueOnAssign(ctx, open, node, module); line != "" {
issued = append(issued, line)
answer += "\n " + line
}
}
// **The one resolution the rest of the answer is said from** (novox/hq issue 237), taken after
// the write: what this act changed about this node's unmet seat dependencies, and nothing else
// (novox/hq ADR 0207) — a dependency of a module just assigned, or one this assignment met; the
// rest of the node's list, and every other node's, is `status`'s — and whether the node resolves.
after := resolvedAfter(ctx, open, shelf, node)
for _, line := range unheldChangeTo(shelf, node, before, after.modules, after.unheld) {
answer += "\n " + line
}
for _, line := range issued {
answer += "\n " + line
}
plan, err := after.plan, after.err
plan, _, err := planFor(ctx, open, node)
if err != nil {
// Kept, and still refused. Both halves are the answer, and the rest of the mesh is still
// worth reporting: this machine's refusal is rarely the only consequence.
@@ -228,8 +218,6 @@ func unassign(ctx context.Context, open *stores, node string, modules ...string)
if len(modules) == 0 {
return "", fmt.Errorf("unassign %s names no module", node)
}
// One resolution after the write, as assign's answer (novox/hq issue 237).
ctx = leftOutSaidBy(ctx, io.Discard)
ctx, release, err := holdNodes(ctx, open, []string{node})
if err != nil {
return "", err
@@ -274,21 +262,14 @@ func unassign(ctx context.Context, open *stores, node string, modules ...string)
}
answer := fmt.Sprintf("%s no longer runs %s — run `push %s` to make it so",
node, strings.Join(modules, ", "), node)
after := resolvedAfter(ctx, open, shelf, node)
for _, line := range unheldChangeTo(shelf, node, assigned, after.modules, after.unheld) {
answer += "\n " + line
var left []string
for _, a := range assigned {
if !slices.Contains(modules, a) {
left = append(left, a)
}
}
// Whether the node itself still resolves, from the same resolution: before, only the rest of the
// mesh's reads said it, on standard error and once per other machine.
if after.err != nil {
if unresolvable(after.err) {
answer += fmt.Sprintf("\n but %s does not resolve now, so nothing will be sent to it:", node)
} else {
answer += fmt.Sprintf("\n but whether %s still resolves could not be read:", node)
}
for _, line := range strings.Split(strings.TrimRight(after.err.Error(), "\n"), "\n") {
answer += "\n " + strings.TrimSpace(line)
}
for _, line := range unheldChange(shelf, node, assigned, left) {
answer += "\n " + line
}
// What it leaves behind that is irreplaceable is kept and retired, never removed (novox/hq ADR 0233).
for _, line := range keptOnUnassign(ctx, open.inventory, node, modules) {
@@ -297,39 +278,6 @@ func unassign(ctx context.Context, open *stores, node string, modules ...string)
return answer + blockedElsewhere(ctx, open, node), nil
}
// afterAct is the one resolution of a node an act's answer is said from, taken after its write
// (novox/hq issue 237): the plan or why there is none, the modules it has on the node, and its unmet
// seat dependencies.
type afterAct struct {
plan catalogue.Resolution
err error
modules []string
unheld []catalogue.Unheld
}
// resolvedAfter resolves the node as `plan` does, once, after the act's write. When the node resolves,
// its modules and unmet seat dependencies are the resolution's — the closure, so a holder pulled in by
// a requirement counts as `plan` counts it. When it does not, they are judged over the assignments read
// after the write, which can only find more unmet than the closure would: a seat said held there is
// held in the closure too.
func resolvedAfter(ctx context.Context, open *stores, shelf map[string]catalogue.Manifest, node string) afterAct {
plan, _, err := planFor(ctx, open, node)
if err == nil {
out := afterAct{plan: plan, unheld: plan.Unheld}
for _, m := range plan.Modules {
out.modules = append(out.modules, m.Module)
}
return out
}
out := afterAct{err: err}
assigned, readErr := open.inventory.Assigned(ctx, node)
if readErr != nil {
return out
}
out.modules, out.unheld = assigned, unheldOver(shelf, node, assigned)
return out
}
// splitModules is a surface's one `module` field as the modules it names: several, comma-separated,
// are one act (novox/hq ADR 0207), so the holders that depend on each other go on together from the
// command API and the controller seat's verbs as they do from the command line.
-9
View File
@@ -213,8 +213,6 @@ type asker struct {
saidNoRouter bool
saidNoGrant bool
// saidGrantCaveat is whether a grant held with a caveat was said, so it is said once.
saidGrantCaveat bool
mu sync.Mutex
nudged chan struct{}
@@ -319,13 +317,6 @@ func (a *asker) reconcile(ctx context.Context) error {
}
return a.sayUnasked(ctx, unasked, "the bus does not hold the controller's grant to ask yet: "+why)
}
if why != "" && !a.saidGrantCaveat {
// Held, with a caveat worth one line (an older bus module cannot confirm the reload).
a.logf("the controller asks: %s", why)
a.saidGrantCaveat = true
} else if why == "" {
a.saidGrantCaveat = false
}
a.saidNoGrant = false
}
channels := ""
-205
View File
@@ -12,7 +12,6 @@ import (
"git.novox.be/novox/mesh-sdk/go/asks"
"github.com/novox/mesh-controller/internal/broker"
"github.com/novox/mesh-controller/internal/conditions"
"github.com/novox/mesh-controller/internal/link"
)
@@ -809,207 +808,3 @@ func TestARefusalIsAskedAgainAndTheUndeliveredConditionClearsOnceTaken(t *testin
t.Errorf("the explanation says its verdict twice: %q", e)
}
}
// hq issue 353, the review: the bus holds the controller's grant to ask only when both facts hold — the mesh
// composes the controller's own grant, and the bus's module says it is in force on the running server — and
// each fact not known is not held, said with why.
func TestTheGrantIsHeldOnlyWhenComposedAndInForceOnTheBus(t *testing.T) {
yes := func(context.Context) (bool, string, error) { return true, "", nil }
no := func(why string) grantJudge {
return func(context.Context) (bool, string, error) { return false, why, nil }
}
broken := func(context.Context) (bool, string, error) { return false, "", errors.New("the store is away") }
for _, c := range []struct {
name string
composed, inForce grantJudge
held bool
says string
}{
{"composed and in force", yes, yes, true, ""},
{"not composed", no("no router is assigned"), yes, false, "no router is assigned"},
{"composed, written, not reloaded", yes, no("the server has not reloaded"), false, "has not reloaded"},
{"the composition unknown", broken, yes, false, "could not be worked out: the store is away"},
{"the bus unknown", yes, broken, false, "could not be worked out: the store is away"},
{"nothing judges the bus", yes, nil, false, "not judged"},
} {
held, why, err := grantHeldBy(c.composed, c.inForce, time.Now)(context.Background())
if err != nil || held != c.held || !strings.Contains(why, c.says) {
t.Errorf("%s: held %v (%q, %v)", c.name, held, why, err)
}
}
// Remembered for grantLookEvery, then judged again.
now := time.Date(2026, 10, 9, 18, 0, 0, 0, time.UTC)
inForce := false
judge := grantHeldBy(yes, func(context.Context) (bool, string, error) { return inForce, "not yet", nil },
func() time.Time { return now })
if held, _, _ := judge(context.Background()); held {
t.Fatal("held before the bus enforces it")
}
inForce = true
if held, _, _ := judge(context.Background()); held {
t.Error("judged again inside grantLookEvery")
}
now = now.Add(grantLookEvery)
if held, _, _ := judge(context.Background()); !held {
t.Error("not judged again after grantLookEvery")
}
}
// The controller's own grant, as composed: present while a router that takes asks is assigned, absent
// otherwise — whatever else in the user list changes.
func TestTheControllersOwnGrantToAskIsReadFromTheComposition(t *testing.T) {
router := broker.Declared{Module: "messenger", Holds: []broker.Seat{{Name: broker.AsksSeat, Scope: "mesh",
Accepts: []string{"ask", "cancel"}, Emits: []string{"decided"}, ByCaller: []string{"ask", "cancel", "decided"}}}}
other := broker.Declared{Module: "dunst"}
with := broker.Records{Nodes: []string{"anchor"}, Assigned: map[string][]broker.Declared{"anchor": {router, other}}}
without := broker.Records{Nodes: []string{"anchor"}, Assigned: map[string][]broker.Declared{"anchor": {other}}}
if may, err := controllerMayAsk(with); err != nil || !may {
t.Errorf("with a router assigned: %v %v", may, err)
}
if may, err := controllerMayAsk(without); err != nil || may {
t.Errorf("with no router assigned: %v %v", may, err)
}
}
// The bus module's answer, with the record's word on the list sent as the check only where the answer does
// not settle it (reviews 22 and 31 of PR 188); each way it is not held names its own remedy.
func TestTheBusModulesAnswerNamesTheRemedyForEachCase(t *testing.T) {
const (
reloaded = `{"allowed":true,"in_force":true,"file_written":"2026-10-09T15:55:56Z","server_loaded":"2026-10-09T15:56:05Z"}`
notLoaded = `{"allowed":true,"in_force":false,"why":"the user list on the machine allows it, and the server has not reloaded since it was written","file_written":"2026-10-09T15:55:56Z","server_loaded":"2026-10-09T15:50:00Z"}`
noVarz = `{"allowed":true,"in_force":false,"why":"the server's last configuration load could not be read: refused"}`
noStat = `{"allowed":true,"in_force":false,"why":"when the bus's user list was written could not be read inside mesh-broker-nats: exit 1"}`
notAllowed = `{"allowed":false,"in_force":false,"why":"the user list on the machine does not allow it"}`
)
current := busListState{Machine: "anchor"}
behind := busListState{Machine: "anchor", Behind: true}
stepped := busListState{Machine: "anchor", Behind: true, BusStep: "sending anchor would replace the bus; `bus upgrade --why …`"}
uncomposed := busListState{Machine: "anchor", Behind: true, Uncomposed: errors.New("module foo requires a provision nobody provides")}
for _, c := range []struct {
name, answer string
askErr error
list busListState
listErr error
held bool
says, not string
}{
{"in force", reloaded, nil, behind, nil, true, "", "push"},
{"written, not reloaded", notLoaded, nil, current, nil, false, "within about 5 s", "push"},
{"in force not known: varz", noVarz, nil, current, nil, false, "is not known: the server's last configuration load", "wait"},
{"in force not known: stat", noStat, nil, current, nil, false, "is not known: when the bus's user list was written", "wait"},
{"not allowed, list behind", notAllowed, nil, behind, nil, false, "`push anchor` carries it", "5 s"},
{"not allowed, bus step pending", notAllowed, nil, stepped, nil, false, "`bus upgrade", "`push anchor`"},
{"not allowed, list uncomposed", notAllowed, nil, uncomposed, nil, false, "`plan anchor`", "`push anchor`"},
{"older module, allowed, list current", `{"allowed":true}`, nil, current, nil, true, "not confirmed", "push"},
{"older module, allowed, list behind", `{"allowed":true}`, nil, behind, nil, true, "not confirmed", "push"},
{"older module, allowed, list unknown", `{"allowed":true}`, nil, current, errors.New("the store is away"), true, "`bus upgrade`", "push"},
{"older module, not allowed, list behind", `{"allowed":false}`, nil, behind, nil, false, "`push anchor` carries it", "5 s"},
{"module cannot answer, list current", "", errors.New("no responders"), current, nil, true, "could not answer", "push"},
{"module cannot answer, list behind", "", errors.New("no responders"), behind, nil, false, "`push anchor` carries it", ""},
{"module cannot answer, list unknown", "", errors.New("no responders"), current, errors.New("the store is away"), false, "could not be worked out", ""},
{"answer unreadable, list behind", `not json`, nil, behind, nil, false, "could not be read", ""},
} {
judge := busGrantBy(
func(context.Context) (string, json.RawMessage, error) {
return "anchor", json.RawMessage(c.answer), c.askErr
},
func(context.Context) (busListState, error) { return c.list, c.listErr })
held, why, _ := judgeGrantOnce(judge)
if held != c.held || !strings.Contains(why, c.says) || (c.not != "" && strings.Contains(why, c.not)) {
t.Errorf("%s: held %v (%q)", c.name, held, why)
}
}
none := busGrantBy(func(context.Context) (string, json.RawMessage, error) { return "", nil, nil }, nil)
if held, why, _ := judgeGrantOnce(none); held || !strings.Contains(why, "no module holds the bus") {
t.Errorf("no bus: held %v (%q)", held, why)
}
}
// judgeGrantOnce is the whole judgement with the composed grant held, as the asker makes it.
func judgeGrantOnce(bus grantJudge) (bool, string, error) {
yes := func(context.Context) (bool, string, error) { return true, "", nil }
return grantHeldBy(yes, bus, time.Now)(context.Background())
}
// The orders reviews 22 and 31 of PR 188 found: this controller live before the bus module that answers
// in_force, with the bus's machine behind on its list — and, after mesh-catalog #166 merged, unpushable until a
// person's bus upgrade. An older module that allows the ask asks (once, with the caveat said); a new module that
// has not reloaded names the wait, not a push; one that cannot say whether it reloaded names what is not known.
func TestAnOlderBusModuleNeitherSilencesTheAsksNorNamesTheWrongRemedy(t *testing.T) {
for _, c := range []struct {
name, answer string
list busListState
asks bool
says, not string
}{
{"older module, list current", `{"allowed":true}`, busListState{Machine: "anchor"}, true, "not confirmed", ""},
{"older module, list behind, bus step pending", `{"allowed":true}`,
busListState{Machine: "anchor", Behind: true, BusStep: "a planned step"}, true, "not confirmed", ""},
{"new module, not reloaded",
`{"allowed":true,"in_force":false,"why":"not reloaded","file_written":"2026-10-09T15:55:56Z","server_loaded":"2026-10-09T15:50:00Z"}`,
busListState{Machine: "anchor"}, false, "within about 5 s", "push"},
{"new module, reload not known", `{"allowed":true,"in_force":false,"why":"the server's last configuration load could not be read: refused"}`,
busListState{Machine: "anchor"}, false, "is not known", "wait"},
} {
t.Run(c.name, func(t *testing.T) {
r := newAskerRig(t)
var said []string
r.a.logf = func(f string, a ...any) { said = append(said, fmt.Sprintf(f, a...)) }
var raised [][]conditions.Observation
r.a.raise = func(_ context.Context, obs []conditions.Observation) error {
raised = append(raised, obs)
return nil
}
yes := func(context.Context) (bool, string, error) { return true, "", nil }
r.a.grantHeld = grantHeldBy(yes, busGrantBy(
func(context.Context) (string, json.RawMessage, error) {
return "anchor", json.RawMessage(c.answer), nil
},
func(context.Context) (busListState, error) { return c.list, nil }),
func() time.Time { return r.now })
r.open = []conditions.Condition{heldCondition()}
_ = r.a.reconcile(context.Background())
_ = r.a.reconcile(context.Background())
sent := r.asksSent(t)
if c.asks {
if len(sent) != 1 || sent[0].About != heldCondition().Key {
t.Fatalf("not asked: %+v", sent)
}
n := 0
for _, s := range said {
if strings.Contains(s, c.says) {
n++
}
}
if n != 1 {
t.Errorf("the caveat said %d times: %q", n, said)
}
return
}
if len(sent) != 0 {
t.Fatalf("asked while the bus does not hold the grant: %+v", sent)
}
if len(raised) == 0 || len(raised[len(raised)-1]) != 1 ||
raised[len(raised)-1][0].Kind != "asks-undelivered" {
t.Fatalf("not said as undelivered: %+v", raised)
}
summary := raised[len(raised)-1][0].Summary
if !strings.Contains(summary, c.says) || (c.not != "" && strings.Contains(summary, c.not)) {
t.Errorf("the condition names the wrong remedy: %q", summary)
}
})
}
}
// The serving asker is wired to the real judgement: with records and a bus it cannot read, the grant is not
// held, and so nothing is asked (a stub saying yes, or no judgement at all, would ask).
func TestTheServingAskerJudgesTheGrantForReal(t *testing.T) {
a := servingAsker(&stores{}, nil, nil, nil)
if a.grantHeld == nil {
t.Fatal("the serving asker does not judge the bus's grant")
}
held, why, err := a.grantHeld(context.Background())
if err != nil || held || !strings.Contains(why, "could not be worked out") {
t.Errorf("held %v (%q, %v) with nothing to read", held, why, err)
}
}
+21 -271
View File
@@ -235,27 +235,12 @@ func routerHereIn(inv *inventory.Inventory) func(ctx context.Context) (bool, err
}
}
// grantHeldIn says whether the bus holds the controller's grant to ask (novox/hq issue 353), judged on the two
// facts that make it so, and failing closed on each:
//
// 1. **composed**: the user list the mesh composes now grants the controller itself to publish its ask
// (controllerMayAsk) — the controller's own grant, not whether any user of the list changed;
// 2. **in force**: the bus's own module, on the machine holding the bus, says the user list there allows it
// and the server reloaded after that list was written (the nats module's `nats_user_can`, `in_force`) — a
// list sent is not a list the bus enforces until it reloads.
//
// Anything that cannot be worked out is not held, with why, so the conditions that need the operator are said
// as undelivered rather than asked into a refusal.
func grantHeldIn(open *stores, conn *nats.Conn) func(ctx context.Context) (bool, string, error) {
return grantHeldBy(composedGrantIn(open), busGrantIn(open, conn), time.Now)
}
// grantJudge is one of the two facts: whether it holds, and why not.
type grantJudge func(ctx context.Context) (bool, string, error)
// grantHeldBy is the judgement over the two facts, remembered for grantLookEvery: composing the list resolves
// the bus's machine whole, and asking the bus's module is a call.
func grantHeldBy(composed, inForce grantJudge, now func() time.Time) func(ctx context.Context) (bool, string, error) {
// grantHeldIn says whether the bus holds the controller's grant to ask (novox/hq issue 353): the user list the
// machine holding the bus was last sent is the one the mesh composes now (brokerBehind, the same judgement a
// push makes to send that machine first). While it is behind, the controller's ask is refused by the bus,
// whatever the record says of the router, so nothing is asked and the operator is told to push that machine.
// Judged at most every grantLookEvery: composing the list resolves the bus's machine whole.
func grantHeldIn(open *stores) func(ctx context.Context) (bool, string, error) {
var mu sync.Mutex
var at time.Time
var held bool
@@ -263,251 +248,22 @@ func grantHeldBy(composed, inForce grantJudge, now func() time.Time) func(ctx co
return func(ctx context.Context) (bool, string, error) {
mu.Lock()
defer mu.Unlock()
if !at.IsZero() && now().Sub(at) < grantLookEvery {
if !at.IsZero() && time.Since(at) < grantLookEvery {
return held, why, nil
}
held, why = judgeGrant(ctx, composed, inForce)
at = now()
return held, why, nil
}
}
// judgeGrant is held only when both facts hold; an error is a fact not known, never a yes. A fact that holds
// with a caveat (a reload not confirmed) gives that caveat as the why of a yes.
func judgeGrant(ctx context.Context, composed, inForce grantJudge) (bool, string) {
var caveat []string
for _, fact := range []struct {
judge grantJudge
what string
}{{composed, "whether the mesh composes the controller a grant to ask"}, {inForce, "whether the bus enforces it"}} {
if fact.judge == nil {
return false, fact.what + " is not judged here"
}
ok, why, err := fact.judge(ctx)
if err != nil {
return false, fact.what + " could not be worked out: " + err.Error()
}
if !ok {
return false, why
}
if why != "" {
caveat = append(caveat, why)
}
}
return true, strings.Join(caveat, "; ")
}
// controllerMayAsk says whether the controller's own grant, as composed from these records, lets it publish its
// ask (ADR 0259 §3: composed while a router that takes asks under its asker's name is assigned).
func controllerMayAsk(records broker.Records) (bool, error) {
users, err := broker.Users(records)
if err != nil {
return false, err
}
for _, u := range users {
if u.Kind != broker.KindController {
continue
}
perms, err := broker.PermissionsFor(u)
if err != nil {
return false, err
}
return broker.MayPublish(perms, asks.AskSubject(askerName)), nil
}
return false, errors.New("the composition holds no controller")
}
// composedGrantIn is the first fact, from the mesh's records.
func composedGrantIn(open *stores) grantJudge {
return func(ctx context.Context) (bool, string, error) {
if open == nil || open.inventory == nil {
return false, "", errors.New("the mesh's records are not open")
}
records, err := open.inventory.BusRecords(ctx)
machine, behind, err := brokerBehind(ctx, open, nil)
if err != nil {
return false, "", err
}
may, err := controllerMayAsk(records)
if err != nil || may {
return may, "", err
at, held, why = time.Now(), !behind, ""
if behind {
why = fmt.Sprintf("the bus's user list on %s is behind what the mesh composes, so the bus has not been "+
"given the controller's grant to ask; `push %s` carries it", machine, machine)
}
return false, "the mesh composes the controller no grant to ask: no router that takes asks under its " +
"asker's name is assigned", nil
return held, why, nil
}
}
// busGrantIn is the second fact, asked of the bus's own module on the machine holding the bus, with the check
// main made before it (novox/hq issue 353, PR 186: is the user list sent to the bus's machine the one composed
// now) kept for the cases the module's word does not settle.
func busGrantIn(open *stores, conn *nats.Conn) grantJudge {
ask := func(ctx context.Context) (string, json.RawMessage, error) {
if open == nil || open.inventory == nil || conn == nil {
return "", nil, errors.New("the mesh's records or the bus are not open")
}
holders, err := seatHolders(ctx, open.inventory)
if err != nil {
return "", nil, err
}
h, held := holders[theBrokerSeat]
if !held || h.Node == "" || h.Module == "" {
return "", nil, nil
}
a, err := link.AskModuleToolOn(ctx, conn, h.Module, busUserCanTool, h.Node, map[string]any{
"user": broker.ControllerName, "action": "publish", "subject": asks.AskSubject(askerName)}, 15*time.Second)
if err != nil {
return h.Node, nil, err
}
if a.Error != "" {
return h.Node, nil, errors.New(a.Error)
}
return h.Node, a.Result, nil
}
list := func(ctx context.Context) (busListState, error) {
if open == nil || open.inventory == nil {
return busListState{}, errors.New("the mesh's records are not open")
}
s, err := brokerListState(ctx, open, nil)
if err != nil || s.Machine == "" || !s.Behind {
return s, err
}
step, err := busHeld(ctx, open.inventory, []string{s.Machine})
if err != nil {
return busListState{}, err
}
s.BusStep = step[s.Machine]
return s, nil
}
return busGrantBy(ask, list)
}
// busListState is the user list on the bus's machine as the controller's record knows it: whether the list
// sent there is behind the one composed now, why it could not be composed, and the bus step a send there waits
// on (that machine cannot be pushed until a person's `bus upgrade`).
type busListState struct {
Machine string
Behind bool
Uncomposed error
BusStep string
}
// remedy is the one thing that sends the bus's machine the list composed now: the plan's own reason when it
// cannot be composed, the bus upgrade while sends there wait on it, and otherwise a push of that machine.
func (s busListState) remedy(node string) string {
if s.Machine != "" {
node = s.Machine
}
switch {
case s.Uncomposed != nil:
return fmt.Sprintf("the user list for %s cannot be composed (%v); `plan %s` says what to fix first",
node, s.Uncomposed, node)
case s.BusStep != "":
return fmt.Sprintf("sends to %s wait on the bus's planned step, so a push will not carry it: %s", node, s.BusStep)
}
return fmt.Sprintf("`push %s` carries it", node)
}
// busGrantBy judges the bus's word, and names for each way it is not held the one thing that makes it held:
//
// - **in force**: held;
// - **allowed, from a module older than `in_force`**: held, with the caveat that the reload is not confirmed.
// The file allows the publish, and the bus reloads within about 5 s of a change to it, so the worst case is
// one ask refused in those seconds, which is asked again (issue 369). The list check is not consulted:
// while a bus step is pending the bus's machine cannot be pushed, so any change to the composed list would
// read as behind for good and silence every ask until a person's bus upgrade (the review of PR 188);
// - **allowed, written, not reloaded** (the module gives both times): wait about 5 s;
// - **allowed, in force not known** (the module could not read a time): what is not known, said;
// - **not allowed, or the module cannot answer**: the list check decides — the remedy that sends the list
// when it is behind (busListState.remedy), and, for a module that cannot answer, held while the list sent
// is current, as main judged it.
//
// ask answers the machine holding the bus and its module's answer ("" when nothing holds the bus); list is the
// record's word on the list sent to that machine.
func busGrantBy(ask func(ctx context.Context) (string, json.RawMessage, error),
list func(ctx context.Context) (busListState, error)) grantJudge {
return func(ctx context.Context) (bool, string, error) {
node, raw, askErr := ask(ctx)
if askErr == nil && node == "" {
return false, "no module holds the bus, so nothing says what it enforces", nil
}
var answer busAnswer
if askErr == nil {
if answer, askErr = readBusAnswer(raw); askErr != nil {
askErr = fmt.Errorf("its answer could not be read: %w", askErr)
}
}
if askErr != nil {
if node == "" {
node = "the bus's machine"
}
s, err := list(ctx)
if err != nil {
return false, "", fmt.Errorf("the bus module on %s could not answer (%v), and whether the list sent "+
"there is the one composed now could not be worked out: %w", node, askErr, err)
}
if s.Behind {
return false, fmt.Sprintf("the bus module on %s could not answer (%v), and the user list sent there is "+
"behind what the mesh composes; %s", node, askErr, s.remedy(node)), nil
}
return true, fmt.Sprintf("the bus module on %s could not answer (%v); judged by the user list sent there, "+
"which is the one composed now", node, askErr), nil
}
notAllowed := func(older string) (bool, string, error) {
s, err := list(ctx)
if err != nil {
return false, "", fmt.Errorf("the user list on %s does not allow the controller to ask%s, and whether "+
"the list sent there is the one composed now could not be worked out: %w", node, older, err)
}
if s.Behind {
return false, fmt.Sprintf("the user list on %s does not allow the controller to ask%s: it is behind "+
"what the mesh composes; %s", node, older, s.remedy(node)), nil
}
return false, fmt.Sprintf("the user list on %s does not allow the controller to ask%s, though the list "+
"sent there is the one composed now; %s again", node, older, s.remedy(node)), nil
}
switch {
case answer.InForce == nil && answer.Allowed:
return true, fmt.Sprintf("the user list on %s allows the controller to ask, but its reload is not "+
"confirmed: the bus module there is older than the answer whether a grant is in force, and the bus "+
"upgrade (`bus upgrade`) carries one that confirms it", node), nil
case answer.InForce == nil:
return notAllowed(" (the bus module there is older than the answer whether a grant is in force)")
case !answer.Allowed:
return notAllowed("")
case *answer.InForce:
return true, "", nil
case answer.FileWritten != "" && answer.ServerLoaded != "":
return false, fmt.Sprintf("the bus on %s has the controller's grant to ask written (%s) but has not "+
"reloaded since (last load %s); it reloads in place within about 5 s, so nothing is to be done but wait",
node, answer.FileWritten, answer.ServerLoaded), nil
}
why := answer.Why
if why == "" {
why = "it gives no reason"
}
return false, fmt.Sprintf("the user list on %s allows the controller to ask, but whether the bus enforces it "+
"is not known: %s", node, why), nil
}
}
// busUserCanTool is the bus module's answer to whether a user may do something, and whether it is in force.
const busUserCanTool = "nats_user_can"
// busAnswer is the bus module's answer to busUserCanTool; InForce is nil from a module older than that field,
// and FileWritten and ServerLoaded are given only when it could read both times (mesh-catalog's nats InForce).
type busAnswer struct {
Allowed bool `json:"allowed"`
InForce *bool `json:"in_force"`
Why string `json:"why"`
FileWritten string `json:"file_written"`
ServerLoaded string `json:"server_loaded"`
}
func readBusAnswer(raw json.RawMessage) (busAnswer, error) {
var answer busAnswer
err := json.Unmarshal(raw, &answer)
return answer, err
}
// grantLookEvery is how often the bus's user list is judged against the one its machine was last sent.
const grantLookEvery = 30 * time.Second
@@ -546,19 +302,7 @@ func startAsking(ctx context.Context, open *stores, server *link.Server, conn *n
fmt.Printf("the operator cannot be asked: %v\n", err)
return
}
a := servingAsker(open, conn, js, keeper)
if err := server.Decides(a); err != nil {
fmt.Printf("the operator's answers cannot be heard, so nothing is asked: %v\n", err)
return
}
askerFrom = a
go a.keep(ctx)
}
// servingAsker is the serving controller's asker, wired to the mesh: what it reads, publishes, performs and
// records, and the judgements it asks by — the bus's grant to ask among them (novox/hq issue 353).
func servingAsker(open *stores, conn *nats.Conn, js jetstream.JetStream, keeper *conditions.Keeper) *asker {
return &asker{
a := &asker{
open: keeper.Open,
silence: func(ctx context.Context, key string, d time.Duration, by, why string) error {
_, err := keeper.Silence(ctx, key, d, by, why)
@@ -578,7 +322,7 @@ func servingAsker(open *stores, conn *nats.Conn, js jetstream.JetStream, keeper
},
routerRecord: routerRecordOf(conn, open.inventory),
routerHere: routerHereIn(open.inventory),
grantHeld: grantHeldIn(open, conn),
grantHeld: grantHeldIn(open),
channels: channelsIn(open.inventory),
raise: func(ctx context.Context, obs []conditions.Observation) error {
return keeper.Reconcile(ctx, sourceAsker, obs)
@@ -586,4 +330,10 @@ func servingAsker(open *stores, conn *nats.Conn, js jetstream.JetStream, keeper
now: time.Now,
logf: func(format string, args ...any) { fmt.Printf(format+"\n", args...) },
}
if err := server.Decides(a); err != nil {
fmt.Printf("the operator's answers cannot be heard, so nothing is asked: %v\n", err)
return
}
askerFrom = a
go a.keep(ctx)
}
+18 -243
View File
@@ -37,11 +37,6 @@ import (
// own commit, the newest first, one walk each, until one is delivered; the older ones are then answered
// by that one.
//
// **A merge waits only for a batch it shares something with** (novox/hq ADR 0304 decision 1, ADR 0306 decisions
// 2 and 3, issue 525): it joins a batch it is related to, and one that is related to none and whose delivery
// group has no member still to merge is a batch whose window is closed at once (batchToJoin). Walks stay one at
// a time: such a batch is cut when no walk is open, and queued behind the one that is otherwise.
//
// A merge on the controller's own path (a module whose walk waits for nobody's word) never shares a batch with
// one that waits for mesh-delivery's: each kind has a batch of its own, an own-path batch is cut first and folds
// no waiting catalogue walk, and a catalogue walk let go while another walk runs starts once it ended — so no
@@ -178,12 +173,6 @@ func (f following) hearMerge(ctx context.Context, m link.SourceMoved, now time.T
fmt.Printf("%s merged into %s (%.8s); nothing the mesh holds reads it\n", repository, m.Base, m.Commit)
return nil
}
// **Its delivery group's word, before the plans are held** (ADR 0306 decision 2): a slow answer holds up no walk.
own := ownPath(touches)
waits, err := groupWait(ctx, inv, m, deliverySeatHeld(entries), own)
if err != nil {
return notNow(err)
}
release, err := inv.HoldPlans(ctx, true)
if err != nil {
return notNow(err)
@@ -209,6 +198,7 @@ func (f following) hearMerge(ctx context.Context, m link.SourceMoved, now time.T
// **A merge on the controller's own path never shares a batch with one that waits for the delivery's
// word** (decided during the build, 2026-10-10): batched together, the catalogue's deliveries would start
// with the controller's and skip their turn. Each kind has a batch of its own.
own := ownPath(touches)
if p, ok, err := answeredByALaterMerge(ctx, inv, heard, touches, own, deliverySeatHeld(entries)); err != nil {
return notNow(err)
} else if ok {
@@ -228,7 +218,7 @@ func (f following) hearMerge(ctx context.Context, m link.SourceMoved, now time.T
return cutBatchesHeld(ctx, f.open, now)
}
batch, why, err := batchToJoin(ctx, inv, heard, entries, read, now, own, waits)
batch, err := theOpenBatch(ctx, inv, heard, now, own)
if err != nil {
return notNow(err)
}
@@ -239,7 +229,7 @@ func (f following) hearMerge(ctx context.Context, m link.SourceMoved, now time.T
if err := keepBatch(ctx, inv, &batch, now, ""); err != nil {
return notNow(err)
}
fmt.Printf("%s merged into %s (%.8s); %s, it joins %s — %s\n", repository, m.Base, m.Commit, why, batch.ID,
fmt.Printf("%s merged into %s (%.8s); it joins %s — %s\n", repository, m.Base, m.Commit, batch.ID,
batchWords(batch, now))
return cutBatchesHeld(ctx, f.open, now)
}
@@ -330,211 +320,22 @@ func ownPath(touches []inventory.Entry) bool {
return false
}
// **A merge waits only for a batch it shares something with** (novox/hq ADR 0304 decision 1, as ADR 0306
// decisions 2 and 3 read it). batchToJoin is the batch a merge heard now joins, and why in words:
//
// - an assembling or queued batch of its kind it is related to (related.go): it joins it and waits for the
// window, which its coming restarts. Related to two or more, the newer are folded into the oldest, which
// answers all their merges: a merge never waits in two windows, and what it shares with each walks in one.
// - none, and its delivery group has a member still to merge, or mesh-delivery could not say (groupWait, waits
// names why): a new batch, which waits for the window, beside the ones it shares nothing with; its words say
// why.
// - none, and no member of its group is still to merge: a new batch whose window is closed at once. Cut at
// once means only that: walks stay one at a time (ADR 0276 decision 4), so with a walk open the batch is
// queued behind it as any closed batch is.
func batchToJoin(ctx context.Context, inv *inventory.Inventory, heard inventory.BatchedMerge, entries []inventory.Entry,
read map[string][]inventory.ReadRepository, now time.Time, own bool, waits string) (inventory.Plan, string, error) {
edges, err := inv.Dependencies(ctx)
if err != nil {
return inventory.Plan{}, "", err
}
joins, whys, _, err := relatedBatches(ctx, inv, []inventory.BatchedMerge{heard}, own, "", entries, read, edges)
if err != nil {
return inventory.Plan{}, "", err
}
if len(joins) > 0 {
into := joins[0]
why := "related to " + into.ID + " (" + whys[0] + ")"
if len(joins) > 1 {
plans, moves, err := foldInto(ctx, inv, &into, joins[1:])
if err != nil {
return inventory.Plan{}, "", err
}
if err := inv.SavePlansMoving(ctx, plans, moves); err != nil {
return inventory.Plan{}, "", err
}
var folded []string
for i, b := range joins[1:] {
folded = append(folded, b.ID+" ("+whys[i+1]+")")
}
why += ", and to " + strings.Join(folded, ", ") + ", folded into it"
}
into.Delivery.Batch.CutAtOnce = false
return into, why, nil
}
if waits != "" {
// Its own window, beside the batches it shares nothing with: waiting is for its group's members, which
// are related to it by their head and join it (ADR 0306 decision 2).
b, err := newBatch(ctx, inv, heard, now, own, false, waits)
return b, waits + ", it waits for the window in a batch of its own", err
}
b, err := newBatch(ctx, inv, heard, now, own, true, "")
return b, "it shares nothing with a batch assembling and no member of a group is still to merge: it is cut at once", err
}
// relatedBatches are the batches not yet cut of a kind, oldest first, parted into those related to merges (with
// the first reason of each) and the others. Each batch is judged by what its cut would move (ADR 0306 decision
// 3): its merges' moves as they were kept and as they read now — the catalogue may have moved since a merge was
// heard — widened to their dependents, and, for a catalogue batch, every walk waiting for its word, which the
// cut folds in (cutBatch's carry). A merge kept with no moves leaves its batch unknown, related to everything.
// except is a walk not to count as folded: the one being stopped.
func relatedBatches(ctx context.Context, inv *inventory.Inventory, merges []inventory.BatchedMerge, own bool,
except string, entries []inventory.Entry, read map[string][]inventory.ReadRepository,
edges []inventory.Edge) (joins []inventory.Plan, whys []string, others []inventory.Plan, err error) {
// theOpenBatch is the batch a merge heard now joins: the one of its kind not yet cut, or a new one.
func theOpenBatch(ctx context.Context, inv *inventory.Inventory, first inventory.BatchedMerge, now time.Time, own bool) (inventory.Plan, error) {
batches, err := inv.Batches(ctx)
if err != nil {
return nil, nil, nil, err
return inventory.Plan{}, err
}
var kind []inventory.Plan
for _, b := range batches {
if b.OwnPath() == own {
kind = append(kind, b)
return b, nil
}
}
if len(kind) == 0 {
return nil, nil, nil, nil
}
carry := newFootprint()
if !own {
// An own-path batch folds no waiting walk (cutBatchesHeld); a catalogue batch may fold every one.
plans, err := inv.OpenPlans(ctx)
if err != nil {
return nil, nil, nil, err
}
for _, p := range plans {
if p.Release != nil || !p.Waiting() || p.ID == except {
continue
}
kept, err := inv.MergesOf(ctx, p.ID)
if err != nil {
return nil, nil, nil, err
}
carry = unionFootprint(carry, footprintOfWalk(p, kept))
}
}
mine := footprintAsCut(merges, entries, read, edges)
for _, b := range kind {
held, err := inv.MergesOf(ctx, b.ID)
if err != nil {
return nil, nil, nil, err
}
if b.Delivery == nil {
b.Delivery = &inventory.PlanDelivery{}
}
if b.Delivery.Batch == nil {
b.Delivery.Batch = &inventory.PlanBatch{Own: own}
}
if ok, why := related(mine, unionFootprint(footprintAsCut(held, entries, read, edges), carry), edges); ok {
joins, whys = append(joins, b), append(whys, why)
} else {
others = append(others, b)
}
}
return joins, whys, others, nil
}
// footprintAsCut is a batch's footprint as a cut now would read it: footprintOfBatch, widened by the modules each
// merge moves as the catalogue reads now (planBatch judges each merge again at the cut, so what it moves may
// have changed since it was heard). Both are kept: when in doubt, related.
func footprintAsCut(merges []inventory.BatchedMerge, entries []inventory.Entry,
read map[string][]inventory.ReadRepository, edges []inventory.Edge) footprint {
f := footprintOfBatch(merges, edges)
var moved []string
for _, m := range merges {
s := announcedOf(m).SourceMoved
if s.Owner == "" {
continue
}
s.MergedAt = "" // news, whatever a cut marked seen since (as planBatch reads it)
for _, e := range wouldMove(s, entries, read) {
moved = append(moved, e.Manifest.Module)
}
}
for _, name := range reachableFrom(moved, edges) {
f.modules[name] = true
}
return f
}
// unionFootprint is what two changes reach together.
func unionFootprint(a, b footprint) footprint {
f := newFootprint()
for _, from := range []footprint{a, b} {
for k := range from.repos {
f.repos[k] = true
}
for k := range from.modules {
f.modules[k] = true
}
for k := range from.heads {
f.heads[k] = true
}
}
f.unknown = a.unknown
if f.unknown == "" {
f.unknown = b.unknown
}
return f
}
// foldInto folds batches into the oldest one related to a merge: the plans to write (into first, so no merge
// names a plan the store does not hold) and the merges to move, for one SavePlansMoving. The folded batches name
// the batch that took them over; a stop's closed window and its withheld modules (ADR 0299) go with their merges.
func foldInto(ctx context.Context, inv *inventory.Inventory, into *inventory.Plan, from []inventory.Plan) ([]*inventory.Plan,
[]inventory.MergeMove, error) {
if into.Delivery == nil {
into.Delivery = &inventory.PlanDelivery{}
}
if into.Delivery.Batch == nil {
into.Delivery.Batch = &inventory.PlanBatch{Own: into.OwnPath()}
}
plans := []*inventory.Plan{into}
var moves []inventory.MergeMove
for i := range from {
f := from[i]
merges, err := inv.MergesOf(ctx, f.ID)
if err != nil {
return nil, nil, err
}
for _, m := range merges {
moves = append(moves, inventory.MergeMove{Repository: m.Repository, Commit: m.Commit, Plan: into.ID, Alone: m.Alone})
}
if f.Delivery == nil {
f.Delivery = &inventory.PlanDelivery{}
}
if w := f.Delivery.Batch; w != nil {
into.Delivery.Batch.Closed = into.Delivery.Batch.Closed || w.Closed
into.Delivery.Batch.Withheld = union(into.Delivery.Batch.Withheld, w.Withheld)
sort.Strings(into.Delivery.Batch.Withheld)
}
f.State = inventory.PlanSuperseded
f.Delivery.Batch = nil
f.Delivery.TakenOverBy = into.ID
f.Note = fmt.Sprintf("folded into %s before it was cut: a merge related to both joined it, and %s answers "+
"its merges", into.ID, into.ID)
plans = append(plans, &f)
}
return plans, moves, nil
}
// newBatch is a new batch of a kind, kept before its first merge names it: a merge never names a plan the store
// does not hold. cutAtOnce closes its window at once; waits says why it waits for its group, when it does.
func newBatch(ctx context.Context, inv *inventory.Inventory, first inventory.BatchedMerge, now time.Time, own,
cutAtOnce bool, waits string) (inventory.Plan, error) {
b := inventory.Plan{ID: fmt.Sprintf("plan-%d", now.UnixNano()), Repository: first.Repository, Branch: first.Branch,
Commit: first.Commit, Merged: first.Merged, Created: now, State: inventory.PlanAssembling,
Tiers: [][]string{}, Modules: map[string]*inventory.PlanModule{},
Delivery: &inventory.PlanDelivery{Batch: &inventory.PlanBatch{Own: own, CutAtOnce: cutAtOnce, Waits: waits}}}
Delivery: &inventory.PlanDelivery{Batch: &inventory.PlanBatch{Own: own}}}
// Kept before its first merge names it: a merge never names a plan the store does not hold.
if err := inv.SavePlan(ctx, &b); err != nil {
return inventory.Plan{}, err
}
@@ -566,16 +367,13 @@ func keepBatch(ctx context.Context, inv *inventory.Inventory, b *inventory.Plan,
}
closes, latest := windowOf(merges, b.Created, window, atMost)
b.Delivery.Merges = named
var closed, cutAtOnce bool
var closed bool
var withheld []string
var waits string
if was := b.Delivery.Batch; was != nil {
closed, withheld = was.Closed, was.Withheld // a stop's, which no look takes back (novox/hq ADR 0299)
cutAtOnce = was.CutAtOnce // the merge's, until another joins it (ADR 0304 decision 1)
waits = was.Waits // its group's, as said when it was made (ADR 0306 decision 2)
}
b.Delivery.Batch = &inventory.PlanBatch{ClosesAt: closes, AtMost: latest, Behind: behind, Own: b.OwnPath(),
Closed: closed, Withheld: withheld, CutAtOnce: cutAtOnce, Waits: waits}
Closed: closed, Withheld: withheld}
b.State = inventory.PlanAssembling
if behind != "" && windowClosed(*b, now) {
b.State = inventory.PlanQueued
@@ -604,14 +402,13 @@ func windowOf(merges []inventory.BatchedMerge, created time.Time, window, atMost
return last.Add(window), created.Add(atMost)
}
// windowClosed says a batch's window is closed: closed by a stop, closed at once for a merge that shares
// nothing (ADR 0304 decision 1), no merge for the window's length, or its maximum reached.
// windowClosed says a batch's window is closed: no merge for the window's length, or its maximum reached.
func windowClosed(b inventory.Plan, now time.Time) bool {
if b.Delivery == nil || b.Delivery.Batch == nil {
return true
}
w := b.Delivery.Batch
return w.Closed || w.CutAtOnce || !now.Before(w.ClosesAt) || !now.Before(w.AtMost)
return w.Closed || !now.Before(w.ClosesAt) || !now.Before(w.AtMost)
}
// carriedOf is a set of merges as a walk carries them: the latest merge of each repository's branch, and
@@ -820,9 +617,8 @@ func cutBatchesHeld(ctx context.Context, open *stores, now time.Time) error {
return err
}
// The oldest batch whose window closed is cut, an own-path one before a catalogue one (it goes first, and
// the catalogue batch queues behind it rather than being cut and overtaken). Several of a kind may be open
// since a merge that shares nothing is cut at once (ADR 0304 decision 1): walks stay one at a time, so one
// is cut per look, and once its walk started the others are queued behind it.
// the catalogue batch queues behind it rather than being cut and overtaken); one of each kind at most is
// open (theOpenBatch).
sort.SliceStable(batches, func(i, j int) bool { return batches[i].OwnPath() && !batches[j].OwnPath() })
for i := range batches {
b := &batches[i]
@@ -1090,9 +886,6 @@ func walkTimesAtCut(batch, walk inventory.Plan, entries []inventory.Entry, now t
if !w.AtMost.IsZero() && w.AtMost.Before(closed) {
closed = w.AtMost
}
if w.CutAtOnce && !batch.Created.IsZero() {
closed = batch.Created // closed when it was made (ADR 0304 decision 1)
}
if !closed.IsZero() {
if closed.After(now) {
closed = now
@@ -1109,16 +902,6 @@ const resolverSeat = "mesh-dns-resolver"
// classOf is a walk's class (novox/hq ADR 0282 decision 1): core when it walks a module on the controller's own
// path or one holding the mesh's resolver, leaf otherwise.
func classOf(walk inventory.Plan, entries []inventory.Entry) string {
modules := make([]string, 0, len(walk.Modules))
for m := range walk.Modules {
modules = append(modules, m)
}
return classOfModules(modules, entries)
}
// classOfModules is the class of modules moved together: core when one is on the controller's own path or holds
// the mesh's resolver, leaf otherwise (ADR 0282 decision 1).
func classOfModules(modules []string, entries []inventory.Entry) string {
resolvers := map[string]bool{}
for _, e := range entries {
for _, c := range e.Manifest.Claims {
@@ -1127,7 +910,7 @@ func classOfModules(modules []string, entries []inventory.Entry) string {
}
}
}
for _, m := range modules {
for m := range walk.Modules {
if _, own := onTheControllersPath[m]; own || resolvers[m] {
return inventory.ClassCore
}
@@ -1359,10 +1142,6 @@ func batchWords(b inventory.Plan, now time.Time) string {
if b.State == inventory.PlanQueued {
return fmt.Sprintf("queued behind %s; grouped: %s; plan not yet calculated", w.Behind, grouped)
}
if w.CutAtOnce {
return fmt.Sprintf("cut at once, sharing nothing with a batch assembling; grouped: %s; plan not yet calculated",
grouped)
}
left := w.ClosesAt.Sub(now)
if w.AtMost.Before(w.ClosesAt) {
left = w.AtMost.Sub(now)
@@ -1370,12 +1149,8 @@ func batchWords(b inventory.Plan, now time.Time) string {
if left < 0 {
left = 0
}
waits := ""
if w.Waits != "" {
waits = " — " + w.Waits
}
return fmt.Sprintf("assembling: %s left (at the latest %s)%s; grouped: %s; plan not yet calculated",
secondsWords(left), w.AtMost.Local().Format("15:04:05"), waits, grouped)
return fmt.Sprintf("assembling: %s left (at the latest %s); grouped: %s; plan not yet calculated",
secondsWords(left), w.AtMost.Local().Format("15:04:05"), grouped)
}
// groupedWords is a batch's commits, each with the earlier merges it answers.
+13 -77
View File
@@ -34,7 +34,6 @@ func windowed(t *testing.T) *stores {
t.Fatal(err)
}
t.Setenv(mergeWindowFileVar, settings)
noGroups(t)
if err := inv.RegisterModule(ctx, catalogue.Manifest{Module: "mesh-controller", Version: "1"},
inventory.Source{Repository: "novox/mesh-controller", Seat: "git", Ref: "main", BuiltFrom: "c0",
Head: "c0"}); err != nil {
@@ -59,70 +58,19 @@ func windowed(t *testing.T) *stores {
// t0 is the moment a test's clock starts: merges are dated by it, and heard after it.
var t0 = time.Now().UTC().Truncate(time.Second)
// catalogueMerge is a merge of the catalogue changing one module's directory, made at a moment, from a pull
// request's head branch of its own, as the forge announces every merge. Whether its head names a delivery group
// with a member still to merge is mesh-delivery's word, which windowed stubs as no group at all (noGroups); a test
// whose merges wait for the window as a group's says so (groupsWaiting).
// catalogueMerge is a merge of the catalogue changing one module's directory, made at a moment.
func catalogueMerge(commit, module string, made time.Time) link.SourceMoved {
return link.SourceMoved{Owner: "novox", Repo: "mesh-catalog", Base: "main", Head: "pr/" + commit, Commit: commit,
return link.SourceMoved{Owner: "novox", Repo: "mesh-catalog", Base: "main", Commit: commit,
MergedAt: made.Format(time.RFC3339Nano), Paths: []string{"modules/" + module + "/module.json"},
ModuleDirs: []string{"modules/" + module}, ModuleDirsSaid: true}
}
// repoMerge is a merge of a repository of one module's own, from a head branch of its own (catalogueMerge).
// repoMerge is a merge of a repository of one module's own.
func repoMerge(repo, commit string, made time.Time) link.SourceMoved {
return link.SourceMoved{Owner: "novox", Repo: repo, Base: "main", Head: "pr/" + commit, Commit: commit,
return link.SourceMoved{Owner: "novox", Repo: repo, Base: "main", Commit: commit,
MergedAt: made.Format(time.RFC3339Nano), Paths: []string{"main.go"}}
}
// noGroups stubs mesh-delivery's word on groups for a test: no head names a group.
func noGroups(t *testing.T) {
t.Helper()
was := deliveryGroupOf
deliveryGroupOf = func(context.Context, bool, string) ([]groupMember, bool, error) { return nil, false, nil }
t.Cleanup(func() { deliveryGroupOf = was })
}
// groupsWaiting stubs mesh-delivery's word on groups for a test: each head named is a group with a member of another
// repository whose pull request is open (novox/elsewhere, ready), so a merge from it waits for the window (ADR 0306
// decision 2); every other head names no group.
func groupsWaiting(t *testing.T, heads ...string) {
t.Helper()
was := deliveryGroupOf
deliveryGroupOf = func(_ context.Context, _ bool, head string) ([]groupMember, bool, error) {
if slices.Contains(heads, head) {
return []groupMember{{Repository: "novox/elsewhere", State: "ready"}}, true, nil
}
return nil, false, nil
}
t.Cleanup(func() { deliveryGroupOf = was })
}
// everyHeadWaits stubs mesh-delivery's word on groups for a test whose merges each wait for the window as they did
// before novox/hq ADR 0304: every head is a group with a member of another repository still to merge.
func everyHeadWaits(t *testing.T) {
t.Helper()
was := deliveryGroupOf
deliveryGroupOf = func(context.Context, bool, string) ([]groupMember, bool, error) {
return []groupMember{{Repository: "novox/elsewhere", State: "ready"}}, true, nil
}
t.Cleanup(func() { deliveryGroupOf = was })
}
// fromHead is a merge from a head branch a test names: merges from one head are members of one delivery group,
// related by it (novox/hq ADR 0304 decision 1), so they share a batch whatever else they share.
func fromHead(m link.SourceMoved, head string) link.SourceMoved {
m.Head = head
return m
}
// lone is a merge that names no head: known to be no delivery group's, it waits for no window unless it is
// related to a batch assembling (ADR 0304 decision 1).
func lone(m link.SourceMoved) link.SourceMoved {
m.Head = ""
return m
}
// hear is a merge heard at a moment.
func hear(t *testing.T, open *stores, m link.SourceMoved, now time.Time) {
t.Helper()
@@ -160,7 +108,6 @@ func walks(t *testing.T, open *stores) (walks, batches []inventory.Plan) {
// later commit, which names both merges — the earlier carried by the later.
func TestTwoMergesSecondsApartAreOneWalkAtTheLaterCommit(t *testing.T) {
open := windowed(t)
everyHeadWaits(t)
asked := asksWithPaths(t)
claude := catalogueMerge("553b7191claude", "app", t0)
dunst := catalogueMerge("48bda475dunst", "notes", t0.Add(17*time.Second))
@@ -205,10 +152,9 @@ func TestTwoMergesSecondsApartAreOneWalkAtTheLaterCommit(t *testing.T) {
// Merges of three repositories in one window are one walk, one commit for each.
func TestThreeRepositoriesInOneWindowAreOneWalk(t *testing.T) {
open := windowed(t)
groupsWaiting(t, "feat/three")
asksRecorded(t)
for i, r := range []string{"one", "two", "three"} {
hear(t, open, fromHead(repoMerge(r, "c-"+r, t0.Add(time.Duration(i)*20*time.Second)), "feat/three"),
hear(t, open, repoMerge(r, "c-"+r, t0.Add(time.Duration(i)*20*time.Second)),
t0.Add(time.Duration(i)*20*time.Second+time.Second))
}
cutAt(t, open, t0.Add(41*time.Second+90*time.Second))
@@ -241,10 +187,9 @@ func TestThreeRepositoriesInOneWindowAreOneWalk(t *testing.T) {
// closes at most ten minutes after its first merge however busy.
func TestAMergeRestartsTheWindowAndTheMaximumClosesIt(t *testing.T) {
open := windowed(t)
groupsWaiting(t, "feat/both", "feat/busy")
asksWithPaths(t)
hear(t, open, fromHead(repoMerge("one", "c1", t0), "feat/both"), t0)
hear(t, open, fromHead(repoMerge("two", "c2", t0.Add(80*time.Second)), "feat/both"), t0.Add(80*time.Second))
hear(t, open, repoMerge("one", "c1", t0), t0)
hear(t, open, repoMerge("two", "c2", t0.Add(80*time.Second)), t0.Add(80*time.Second))
cutAt(t, open, t0.Add(100*time.Second))
if ws, _ := walks(t, open); len(ws) != 0 {
t.Fatal("the window closed 90 seconds after its first merge, not after its last")
@@ -255,13 +200,12 @@ func TestAMergeRestartsTheWindowAndTheMaximumClosesIt(t *testing.T) {
}
busy := windowed(t)
groupsWaiting(t, "feat/both", "feat/busy")
asksWithPaths(t)
var last time.Time
for i := 0; i < 12; i++ {
last = t0.Add(time.Duration(i) * time.Minute)
repo := []string{"one", "two", "three"}[i%3]
hear(t, busy, fromHead(repoMerge(repo, "c"+string(rune('a'+i)), last), "feat/busy"), last)
hear(t, busy, repoMerge(repo, "c"+string(rune('a'+i)), last), last)
if ws, _ := walks(t, busy); len(ws) > 0 {
if i != 10 {
t.Fatalf("a busy window closed at merge %d (minute %d), not at its maximum", i, i)
@@ -279,11 +223,10 @@ func TestAMergeRestartsTheWindowAndTheMaximumClosesIt(t *testing.T) {
// what is grouped, and that the plan is not yet calculated. It says so on the bus as plan-moved, too.
func TestTheAssemblingBatchIsShown(t *testing.T) {
open := windowed(t)
groupsWaiting(t, "pr/553b7191claude")
asksWithPaths(t)
var said []inventory.Plan
was := inventory.PlanSaved
inventory.PlanSaved = func(_ *inventory.Inventory, p inventory.Plan) { said = append(said, p) }
inventory.PlanSaved = func(p inventory.Plan) { said = append(said, p) }
t.Cleanup(func() { inventory.PlanSaved = was })
now := time.Now().UTC()
claude := catalogueMerge("553b7191claude", "app", now.Add(-20*time.Second))
@@ -292,7 +235,7 @@ func TestTheAssemblingBatchIsShown(t *testing.T) {
dunst.Number, dunst.Title = 175, "dunst: the font the operator chose"
hear(t, open, claude, now.Add(-19*time.Second))
hear(t, open, dunst, now.Add(-time.Second))
hear(t, open, fromHead(repoMerge("one", "a6bc0931one", now), dunst.Head), now)
hear(t, open, repoMerge("one", "a6bc0931one", now), now)
out := captured(t, func() error { return plansCommand(t.Context(), nil) })
lines := strings.Split(out, "\n")
first := lines[0]
@@ -417,7 +360,6 @@ func TestAWaitingWalkIsFoldedIntoTheNextBatch(t *testing.T) {
// moves — named at once on a walk done — and joins the next batch when it does not.
func TestALateMergeIsAnsweredByTheWalkOfTheLaterOne(t *testing.T) {
open := windowed(t)
everyHeadWaits(t)
asksWithPaths(t)
ctx := t.Context()
later := catalogueMerge("48bda475dunst", "notes", t0.Add(17*time.Second))
@@ -449,7 +391,6 @@ func TestALateMergeIsAnsweredByTheWalkOfTheLaterOne(t *testing.T) {
// first; the first delivered answers the older ones, and the search stops.
func TestAFailedWalkWalksItsEarlierMergesAlone(t *testing.T) {
open := windowed(t)
everyHeadWaits(t)
asked := asksWithPaths(t)
ctx := t.Context()
// Made before the cut marks their modules seen, as merges are: walked again, they are news all the same.
@@ -518,7 +459,6 @@ func TestAFailedWalkWalksItsEarlierMergesAlone(t *testing.T) {
func TestAGroupsOrderBecomesTiersInsideTheWalk(t *testing.T) {
for _, grouped := range []bool{true, false} {
open := windowed(t)
everyHeadWaits(t)
asksWithPaths(t)
ctx := t.Context()
for _, m := range []string{"mesh-host"} {
@@ -556,10 +496,9 @@ func TestAGroupsOrderBecomesTiersInsideTheWalk(t *testing.T) {
// store, a merge handed over again is not doubled, and the batch is cut when its window closes.
func TestABatchSurvivesARestart(t *testing.T) {
open := windowed(t)
groupsWaiting(t, "feat/both")
asksWithPaths(t)
hear(t, open, fromHead(repoMerge("one", "c1", t0), "feat/both"), t0)
hear(t, open, fromHead(repoMerge("two", "c2", t0.Add(30*time.Second)), "feat/both"), t0.Add(30*time.Second))
hear(t, open, repoMerge("one", "c1", t0), t0)
hear(t, open, repoMerge("two", "c2", t0.Add(30*time.Second)), t0.Add(30*time.Second))
// A new controller: nothing of the first one's but the store.
again, err := openStores(t.Context())
@@ -567,7 +506,7 @@ func TestABatchSurvivesARestart(t *testing.T) {
t.Fatal(err)
}
t.Cleanup(again.Close)
hear(t, again, fromHead(repoMerge("one", "c1", t0), "feat/both"), t0.Add(60*time.Second)) // the bus hands it over again
hear(t, again, repoMerge("one", "c1", t0), t0.Add(60*time.Second)) // the bus hands it over again
cutAt(t, again, t0.Add(119*time.Second))
if ws, bs := walks(t, again); len(ws) != 0 || len(bs) != 1 || len(bs[0].Delivery.Merges) != 2 {
t.Fatalf("the restarted controller's batch: %d walk(s), %+v", len(ws), bs)
@@ -624,7 +563,6 @@ func TestAWaitingWalkNamesTheMergesItAnswers(t *testing.T) {
// nothing, and the merge joins the next batch.
func TestALateMergeOfAOneModuleRepositoryIsNamed(t *testing.T) {
open := windowed(t)
everyHeadWaits(t)
asksWithPaths(t)
ctx := t.Context()
c2 := repoMerge("one", "c2", t0.Add(-50*time.Second))
@@ -778,7 +716,6 @@ func TestTheCatchUpKeepsWhatACutMadeHistory(t *testing.T) {
// still waits for the word, so no catalogue delivery skips its turn.
func TestAMergeOnTheControllersPathNeverSharesABatch(t *testing.T) {
open := windowed(t)
everyHeadWaits(t)
asked := asksWithPaths(t)
ctx := t.Context()
if err := open.inventory.RegisterModule(ctx, catalogue.Manifest{Module: "mesh-delivery", Version: "1",
@@ -923,7 +860,6 @@ func sameMerge(a, b inventory.PlanMerge) bool {
// its delivery would skip its turn. It joins the next catalogue batch.
func TestALateCatalogueMergeIsNotAnsweredByAnOwnPathWalk(t *testing.T) {
open := windowed(t)
everyHeadWaits(t)
asksWithPaths(t)
ctx := t.Context()
for _, m := range []struct {
-4
View File
@@ -48,10 +48,6 @@ func gatherBatches(ctx context.Context, inv *inventory.Inventory, now time.Time)
if f.atMost.Before(f.closed) {
f.closed = f.atMost
}
if w.Batch.CutAtOnce && !b.Created.IsZero() {
// Its window closed when it was made, which is its latest too (ADR 0304 decision 1).
f.atMost, f.closed = b.Created, b.Created
}
}
if f.behind != "" {
if walk, err := inv.PlanByID(ctx, f.behind); err == nil {
-24
View File
@@ -2,7 +2,6 @@ package main
import (
"fmt"
"path"
"slices"
"sort"
"strings"
@@ -106,32 +105,9 @@ func changePlanOf(repository, base, head string, r mergeReach, entries []invento
p.Machines = append(p.Machines, *machines[name])
}
p.Summary = summaryOf(p)
p.Class = changeClassOf(p, entries)
return p
}
// classNone is the class of a change that moves no module: nothing for a walk to move (novox/hq ADR 0313 §2).
const classNone = "none"
// changeClassOf is a change plan's class (novox/hq ADR 0313 §2): that of the slowest-budgeted module it moves,
// itself or as a dependent — core when one is on the controller's own path or holds the mesh's resolver, leaf
// otherwise — and none when it moves nothing. A module it adds a directory for counts by its own class: the
// catalogue names a module's directory by the module, so the directory's last element is its name. The graph holds
// no manifest of it yet, so a new module is core by its name alone (on the controller's own path), never by a
// resolver claim its manifest makes.
func changeClassOf(p link.ChangePlan, entries []inventory.Entry) string {
if len(p.Moved) == 0 && len(p.Dependents) == 0 && len(p.New) == 0 {
return classNone
}
modules := append(append([]string{}, p.Moved...), p.Dependents...)
for _, dir := range p.New {
if name := path.Base(strings.Trim(dir, "/")); name != "." && name != "/" && name != "" {
modules = append(modules, name)
}
}
return classOfModules(modules, entries)
}
// grantsStepWord names the grants step (novox/hq issue 490): the bus's user list sent alone to the machine
// holding the bus ahead of a walk's gate. Not the bus step, which replaces the bus itself.
const grantsStepWord = "grants step"
+29 -105
View File
@@ -10,7 +10,6 @@ import (
"slices"
"sort"
"strings"
"sync"
"time"
"github.com/nats-io/nats.go"
@@ -241,7 +240,7 @@ func stopWalkWithout(ctx context.Context, inv *inventory.Inventory, id, by, why
}
return p, said, inv.SavePlan(ctx, &p)
}
target, folded, foldMoves, err := batchToWalkAgain(ctx, inv, p.ID, again, now)
target, err := batchToWalkAgain(ctx, inv, again, now)
if err != nil {
return p, said, fmt.Errorf("%s is not stopped: %w", p.ID, err)
}
@@ -262,10 +261,8 @@ func stopWalkWithout(ctx context.Context, inv *inventory.Inventory, id, by, why
if len(said.Kept) > 0 {
p.Note += "; " + keptWords(said.Kept)
}
// The batch first, so no merge names a plan the store does not hold; all of it, or nothing (decision 7) — the
// batches folded into it too.
if err := inv.SavePlansMoving(ctx, append([]*inventory.Plan{&target, &p}, folded...),
append(moves, foldMoves...)); err != nil {
// The batch first, so no merge names a plan the store does not hold; all of it, or nothing (decision 7).
if err := inv.SavePlansMoving(ctx, []*inventory.Plan{&target, &p}, moves); err != nil {
return p, said, fmt.Errorf("%s is not stopped, and none of its merges moved: %w", p.ID, err)
}
// What the batch holds and names now: written again by the cutter's next look should this fail.
@@ -320,42 +317,36 @@ func stopInBatch(ctx context.Context, inv *inventory.Inventory, b *inventory.Pla
return nil
}
// batchToWalkAgain is the batch a stopped walk's merges join (novox/hq ADR 0299): a batch of their kind not yet cut
// that they are related to (ADR 0304 decision 1, ADR 0306 decision 3), or a new one, not yet written. Related to
// two or more, the newer are folded into the oldest: the plans and merge moves that fold them, to be written in
// the stop's one act. The kind is read from what the merges moved; the stopped walk itself is no walk a cut folds.
func batchToWalkAgain(ctx context.Context, inv *inventory.Inventory, stopping string, again []inventory.BatchedMerge,
now time.Time) (inventory.Plan, []*inventory.Plan, []inventory.MergeMove, error) {
// batchToWalkAgain is the batch a stopped walk's merges join: the open batch of their kind, or a new one, not yet
// written. The kind is read from what the merges moved.
func batchToWalkAgain(ctx context.Context, inv *inventory.Inventory, again []inventory.BatchedMerge,
now time.Time) (inventory.Plan, error) {
own := false
for _, n := range movesOf(again) {
if _, on := onTheControllersPath[n]; on {
own = true
}
}
entries, read, edges, err := theGraph(ctx, inv)
batches, err := inv.Batches(ctx)
if err != nil {
return inventory.Plan{}, nil, nil, err
return inventory.Plan{}, err
}
joins, _, _, err := relatedBatches(ctx, inv, again, own, stopping, entries, read, edges)
if err != nil {
return inventory.Plan{}, nil, nil, err
}
if len(joins) > 0 {
into := joins[0]
if len(joins) == 1 {
return into, nil, nil, nil
for _, b := range batches {
if b.OwnPath() == own {
if b.Delivery == nil {
b.Delivery = &inventory.PlanDelivery{}
}
if b.Delivery.Batch == nil {
b.Delivery.Batch = &inventory.PlanBatch{Own: own}
}
return b, nil
}
plans, moves, err := foldInto(ctx, inv, &into, joins[1:])
if err != nil {
return inventory.Plan{}, nil, nil, err
}
return into, plans[1:], moves, nil
}
first := again[0]
return inventory.Plan{ID: fmt.Sprintf("plan-%d", now.UnixNano()), Repository: first.Repository, Branch: first.Branch,
Commit: first.Commit, Merged: first.Merged, Created: now, State: inventory.PlanAssembling,
Tiers: [][]string{}, Modules: map[string]*inventory.PlanModule{},
Delivery: &inventory.PlanDelivery{Batch: &inventory.PlanBatch{Own: own}}}, nil, nil, nil
Delivery: &inventory.PlanDelivery{Batch: &inventory.PlanBatch{Own: own}}}, nil
}
// leaveOut splits a walk's merges by the merges named to leave out, each `<repository>@<commit>` (a commit's
@@ -949,7 +940,7 @@ func deliveryCommand(ctx context.Context, args []string) error {
if *group == "" && len(members) == 1 {
// One head, checked again as the forge's announcement would have it (a recheck): the controller's
// own path for a pull request, run because the delivery's owner asked.
if err := sayingOnTheBus(ctx, inv, func() error { return (following{open}).PullUpdated(ctx, members[0].pull()) }); err != nil {
if err := sayingOnTheBus(ctx, func() error { return (following{open}).PullUpdated(ctx, members[0].pull()) }); err != nil {
return err
}
return answer(map[string]any{"rechecked": members[0].ID})
@@ -967,7 +958,7 @@ func deliveryCommand(ctx context.Context, args []string) error {
return errors.New("delivery go <plan> [--by <who>] [--why <text>]")
}
var p inventory.Plan
if err := sayingOnTheBus(ctx, inv, func() (err error) {
if err := sayingOnTheBus(ctx, func() (err error) {
p, err = letGo(ctx, inv, positionals[0], *by, strings.TrimSpace(*why))
return err
}); err != nil {
@@ -982,7 +973,7 @@ func deliveryCommand(ctx context.Context, args []string) error {
}
var p inventory.Plan
var said stopAnswer
if err := sayingOnTheBus(ctx, inv, func() (err error) {
if err := sayingOnTheBus(ctx, func() (err error) {
p, said, err = stopWalkWithout(ctx, inv, positionals[0], *by, strings.TrimSpace(*why), splitList(*without),
time.Now().UTC())
return err
@@ -1224,19 +1215,15 @@ func shelfOf(entries []inventory.Entry) map[string]catalogue.Manifest {
// delivery it walks reads its steps from. Never in the way of the walk: said beside it, and a save that could
// not be said is logged — the delivery's owner, which also asks for the walks it follows, finds it by
// comparison. Records arriving out of order are told apart by the plan's revision.
//
// On the save that starts the walk and the one that ends it, the walk also says what it touches, its bound and,
// at the end, its outcome (novox/hq ADR 0308 decision 1, walk_said.go), read from facts; nil facts say only what
// the walk recorded.
func sayPlanMoved(ctx context.Context, bus link.Bus, facts walkFacts, p inventory.Plan) {
go publishPlanMoved(ctx, bus, facts, p)
func sayPlanMoved(ctx context.Context, bus link.Bus, p inventory.Plan) {
go publishPlanMoved(ctx, bus, p)
}
func publishPlanMoved(ctx context.Context, bus link.Bus, facts walkFacts, p inventory.Plan) {
func publishPlanMoved(ctx context.Context, bus link.Bus, p inventory.Plan) {
// Its phases so far (novox/hq ADR 0282 decision 6): the rest's reports come after the walk ends, and are
// read by whoever asks for the walk (`delivery walks`).
p.Phases = p.WalkPhases(time.Now(), nil)
body, err := json.Marshal(planMovedBody{Plan: p, walkSaid: sayWalk(ctx, facts, p)})
body, err := json.Marshal(p)
if err != nil {
return
}
@@ -1251,7 +1238,7 @@ func publishPlanMoved(ctx context.Context, bus link.Bus, facts walkFacts, p inve
// controller's, or a connection of the command's own — a verb runs as a command of its own, and what it kept
// would otherwise be said by nobody until the delivery's owner read the walks back. Without a bus the command
// still runs; what it did is found by comparison.
func sayingOnTheBus(ctx context.Context, facts walkFacts, f func() error) error {
func sayingOnTheBus(ctx context.Context, f func() error) error {
if checkEvents != nil {
return f()
}
@@ -1262,10 +1249,9 @@ func sayingOnTheBus(ctx context.Context, facts walkFacts, f func() error) error
return err
}
bus := link.OverNATS{Conn: conn, JS: js}
was := inventory.PlanSaved
checkEvents = bus
inventory.PlanSaved = func(_ *inventory.Inventory, p inventory.Plan) { publishPlanMoved(ctx, bus, facts, p) }
defer func() { checkEvents, inventory.PlanSaved = nil, was }()
inventory.PlanSaved = func(p inventory.Plan) { publishPlanMoved(ctx, bus, p) }
defer func() { checkEvents, inventory.PlanSaved = nil, nil }()
ran = true
return f()
})
@@ -1275,65 +1261,3 @@ func sayingOnTheBus(ctx context.Context, facts walkFacts, f func() error) error
}
return err
}
// sayingWhatAVerbKept is PlanSaved for a process that is not the serving controller: each walk the verb keeps is
// said as `plan-moved` before the save returns, with the facts of the inventory that kept it, on the bus the verb
// reaches. It reaches the bus on the first save and never for a verb that keeps no walk. When the bus cannot be
// reached, a save that started or ended a walk says so on the verb's error output: its mark is kept and no later
// save says it, so the router holds what the walk touched until its bound, or not at all for a start. done lets
// the bus go and takes the hook back.
func sayingWhatAVerbKept(ctx context.Context) (said func(*inventory.Inventory, inventory.Plan), done func()) {
var (
mu sync.Mutex
reached bool
bus link.Bus
closing func()
failed error
)
said = func(inv *inventory.Inventory, p inventory.Plan) {
mu.Lock()
defer mu.Unlock()
if !reached {
reached = true
if handActConn != nil {
bus, failed = overNATS(handActConn)
} else if js, err := aBus(); err != nil {
failed = err
} else if bus, failed = overNATS(js.Conn()); failed == nil {
closing = js.Close
} else {
js.Close()
}
}
if bus == nil {
switch p.WalkSaid {
case inventory.WalkStarted:
fmt.Fprintf(os.Stderr, "%s: its start is kept and could NOT be said as plan-moved (%v): the router "+
"does not hold what it touches\n", p.ID, failed)
case inventory.WalkEnded:
fmt.Fprintf(os.Stderr, "%s: its end is kept and could NOT be said as plan-moved (%v): the router holds "+
"what it touched until its bound\n", p.ID, failed)
}
return
}
publishPlanMoved(ctx, bus, inv, p)
}
done = func() {
mu.Lock()
defer mu.Unlock()
inventory.PlanSaved = nil
if closing != nil {
closing()
}
}
return said, done
}
// overNATS is the bus a connection carries, with its JetStream.
func overNATS(conn *nats.Conn) (link.Bus, error) {
js, err := conn.JetStream()
if err != nil {
return nil, err
}
return link.OverNATS{Conn: conn, JS: js}, nil
}
+4 -8
View File
@@ -47,14 +47,10 @@ type stalledLine struct {
// issue 443): a time inside a finished sentence cannot be said again in another zone. A mesh-delivery from before
// says none, and Waiting is said as it reads.
Checks []waitingCheck `json:"checks,omitempty"`
// Held is the state of the delivery of a line of the state `unanswered`, ready or rejected, when one is held
// (novox/hq issues 441, 451): its check answered once, so a recheck is the step. Empty for a head with no
// delivery, and from a mesh-delivery that does not say it yet; the words are never read for it.
Held string `json:"held,omitempty"`
For string `json:"for"`
Bound string `json:"bound"`
H2 string `json:"h2"`
Says string `json:"says"`
For string `json:"for"`
Bound string `json:"bound"`
H2 string `json:"h2"`
Says string `json:"says"`
}
// waitingCheck is one merge check a stalled line waits on, as mesh-delivery gives it: its context, its state —
@@ -119,13 +119,6 @@ func TestTheBusMachineIsBehindByItsUserListAlone(t *testing.T) {
if userListBehind("", "") {
t.Fatal("a machine sent no list reads as behind")
}
// A list that could not be composed is behind: not known is never "not behind" (the review of hq issue 353).
if !listBehind("", errors.New("the plan cannot be worked out"), digestOf([]byte(list))) {
t.Fatal("a list nobody could compose reads as current")
}
if listBehind(list, nil, digestOf([]byte(list))) || !listBehind(list, nil, "") {
t.Fatal("listBehind does not read the digest as userListBehind does")
}
}
// The machine holding the bus goes first: its declaration carries the user list the new grants are
-54
View File
@@ -1,54 +0,0 @@
package main
import (
"testing"
"github.com/novox/mesh-controller/internal/catalogue"
"github.com/novox/mesh-controller/internal/inventory"
"github.com/novox/mesh-controller/internal/link"
)
// **A change plan says its class** (novox/hq ADR 0313 §2): the issue tracker holds a fix to the budget of the
// slowest-budgeted module the fix moves, and a fix that moves no module has no fix budget. The plan says core,
// leaf or none, so mesh-delivery can pass it on with the fix's delivery.
func TestAChangePlanSaysTheClassOfWhatItMoves(t *testing.T) {
const repo = "http://forge.internal:20000/novox/mesh-catalog.git"
entry := func(name, path string) inventory.Entry {
e := fromRepo(name, repo, path)
e.Source.BuiltFrom = "old"
e.On = []string{"anchor"}
return e
}
gitea := entry("gitea", "modules/gitea")
resolver := entry("dnsmasq", "modules/dnsmasq")
resolver.Manifest.Claims = []catalogue.Claim{{Name: resolverSeat}}
delivery := entry(catalogue.DeliverySeat, "modules/mesh-delivery")
webApp := entry("photos", "modules/photos")
entries := []inventory.Entry{gitea, resolver, delivery, webApp}
// photos stands on gitea: a change to gitea moves photos as its dependent.
edges := []inventory.Edge{{From: "photos", To: "gitea", Kind: inventory.EdgeStandsOn}}
policy := func(string) (inventory.Upgrade, bool) { return inventory.Upgrade{RollOut: true}, true }
plan := func(paths ...string) link.ChangePlan {
m := link.SourceMoved{Owner: "novox", Repo: "mesh-catalog", Base: "main", Commit: "head", Paths: paths}
return changePlanOf("novox/mesh-catalog", "main", "head", reachOfMerge(m, entries, nil, edges), entries, policy)
}
for _, c := range []struct {
why string
paths []string
want string
}{
{"a leaf module and its dependent", []string{"modules/gitea/index.ts"}, inventory.ClassLeaf},
{"the delivery's owner, on the controller's own path", []string{"modules/mesh-delivery/cmd/x.go"}, inventory.ClassCore},
{"the mesh's resolver", []string{"modules/dnsmasq/module.json"}, inventory.ClassCore},
{"a leaf and a core module together: the slowest-budgeted", []string{"modules/gitea/index.ts", "modules/dnsmasq/module.json"}, inventory.ClassCore},
{"nothing any module's build reads", []string{"README.md"}, "none"},
{"a new leaf module alone", []string{"modules/weather/module.json"}, inventory.ClassLeaf},
{"a new module on the controller's own path, by its own class", []string{"next/mesh-delivery/module.json"}, inventory.ClassCore},
{"a new leaf module beside a core one moved", []string{"modules/weather/module.json", "modules/dnsmasq/module.json"}, inventory.ClassCore},
} {
if got := plan(c.paths...).Class; got != c.want {
t.Errorf("%s: class %q, want %q", c.why, got, c.want)
}
}
}
-158
View File
@@ -1,158 +0,0 @@
package main
import (
"context"
"encoding/json"
"errors"
"fmt"
"strings"
"time"
"github.com/novox/mesh-controller/internal/catalogue"
"github.com/novox/mesh-controller/internal/inventory"
"github.com/novox/mesh-controller/internal/link"
)
// **A delivery group still assembles** (novox/hq ADR 0306 decision 2): a merge whose delivery group has a member
// not yet merged waits for the merge window, whether or not a batch is assembling, so the group's members walk in
// one batch, in their order (ADR 0276 decision 5). Which groups exist and where each member stands is
// mesh-delivery's record (ADR 0239): a group is the pull requests of two repositories or more sharing a head
// branch name, which is its id. The controller asks it, through its `groups` verb, when a merge from a head is
// heard; a member whose pull request is open (proposed, checked, ready or rejected) is still to merge. When
// mesh-delivery does not answer within groupAskWithin, or answers something unreadable, the merge waits: the safe
// error is to wait, and its batch says why.
// groupAskWithin is how long mesh-delivery is given to say a merge's group, while the merge is being heard.
var groupAskWithin = 3 * time.Second
// openPullStates are the states of a delivery whose pull request is open and not merged (mesh-delivery's table):
// a member in one of them is still to merge. Closed unmerged is stopped, final, and waits for nothing.
var openPullStates = map[string]bool{"proposed": true, "checked": true, "ready": true, "rejected": true}
// groupMember is one member of a delivery group as mesh-delivery's `groups` says it: `<owner/repo>@<commit> (state)`.
type groupMember struct {
Repository, State string
}
// deliveryGroupOf is what mesh-delivery says of the group a head names: its members, and whether the head names a
// group at all; an error when it cannot be asked or did not answer. A seam a test replaces.
var deliveryGroupOf = func(ctx context.Context, held bool, head string) ([]groupMember, bool, error) {
if !held {
return nil, false, fmt.Errorf("no holder of %s is on record to say it", catalogue.DeliverySeat)
}
serving := servingBus.Load()
if serving == nil {
return nil, false, errors.New("this controller is not on the bus")
}
asking, cancel := context.WithTimeout(ctx, groupAskWithin)
defer cancel()
raw, err := askDeliveryOwner(asking, serving.Conn(), "groups", map[string]any{})
if err != nil {
if errors.Is(err, link.ErrNothingServes) {
return nil, false, fmt.Errorf("nothing serves %s.groups", catalogue.DeliverySeat)
}
return nil, false, err
}
var lines []struct {
ID string `json:"id"`
Members []string `json:"members"`
}
if err := json.Unmarshal(raw, &lines); err != nil {
return nil, false, fmt.Errorf("%s.groups answered something unreadable: %w", catalogue.DeliverySeat, err)
}
for _, l := range lines {
if l.ID != head {
continue
}
var members []groupMember
for _, s := range l.Members {
members = append(members, memberOf(s))
}
return members, true, nil
}
return nil, false, nil
}
// memberOf reads one member as `groups` says it: `novox/mesh-sdk@d41d255f28ad (held)`.
func memberOf(s string) groupMember {
id, state := strings.TrimSpace(s), ""
if i := strings.LastIndex(id, " ("); i >= 0 && strings.HasSuffix(id, ")") {
id, state = id[:i], id[i+2:len(id)-1]
}
repository, _, _ := strings.Cut(id, "@")
return groupMember{Repository: repository, State: state}
}
// groupWait says whether a merge heard now waits for the window for its delivery group, and why in words; nothing
// when it names no head, its head names no group, or every other member is merged or closed. own is the merge's
// kind (ownPath).
//
// A member of another repository whose merge this controller already keeps in a batch not yet cut of the same
// kind is merged, whatever mesh-delivery says yet (it marks a member merged once its walk opened): the merge joins
// that batch by their head. One kept in a batch of the other kind keeps the merge waiting, whatever mesh-delivery
// says (review of #250): kinds never share a batch, so the merge's batch is a new one, and cut at once it would
// walk before that member's batch is cut and break the group's order (ADR 0276 decision 5). Waiting, the two
// batches are cut in the order their windows close, an own-path one first at one look, as cutBatchesHeld cuts
// every pair of kinds.
//
// Asked before the plans are held: a slow answer holds up no walk.
func groupWait(ctx context.Context, inv *inventory.Inventory, m link.SourceMoved, held, own bool) (string, error) {
if m.Head == "" {
return "", nil
}
same, other, err := keptFromHead(ctx, inv, m.Head, own)
if err != nil {
return "", err
}
if len(other) > 0 {
return "group " + m.Head + " has a member waiting in a batch of the other kind: " + strings.Join(other, ", "), nil
}
members, isGroup, err := deliveryGroupOf(ctx, held, m.Head)
if err != nil {
return fmt.Sprintf("%s did not say whether group %s has a member still to merge (%v): it waits for the "+
"window, the safe side", catalogue.DeliverySeat, m.Head, err), nil
}
if !isGroup {
return "", nil
}
var open []string
for _, g := range members {
if strings.EqualFold(g.Repository, m.Owner+"/"+m.Repo) || same[strings.ToLower(g.Repository)] ||
!openPullStates[g.State] {
continue
}
open = append(open, g.Repository+" ("+g.State+")")
}
if len(open) == 0 {
return "", nil
}
return "group " + m.Head + " has a member still to merge: " + strings.Join(open, ", "), nil
}
// keptFromHead are the merges from a head that batches not yet cut hold: the repositories (lower case) of those in
// a batch of the kind own says, and, in words, each of the other kind with its batch.
func keptFromHead(ctx context.Context, inv *inventory.Inventory, head string, own bool) (map[string]bool, []string, error) {
batches, err := inv.Batches(ctx)
if err != nil {
return nil, nil, err
}
same := map[string]bool{}
var other []string
for _, b := range batches {
merges, err := inv.MergesOf(ctx, b.ID)
if err != nil {
return nil, nil, err
}
for _, k := range merges {
if announcedOf(k).Head != head {
continue
}
if b.OwnPath() == own {
same[strings.ToLower(k.Repository)] = true
} else {
other = append(other, fmt.Sprintf("%s@%s in %s", k.Repository, short(k.Commit), b.ID))
}
}
}
return same, other, nil
}
-51
View File
@@ -167,54 +167,3 @@ func TestASetuidSearchAsksOnlyAKnownNodeAndFailsOnARefusal(t *testing.T) {
t.Fatalf("a start: %v, printed %q", err, out.String())
}
}
// The directory judgement's line asks only a known node, one name and nothing else, fails on a refusal, and says it
// changed nothing (novox/hq issue 358).
func TestADirectoryJudgementAsksOnlyAKnownNodeAndSaysItIsReadOnly(t *testing.T) {
t.Setenv(link.CallerVar, "jo through mesh-cli on anchor")
asked := 0
ask := func(answer link.HandOverAnswer) func(node, by string) (link.HandOverAnswer, error) {
return func(node, by string) (link.HandOverAnswer, error) {
asked++
if node != "novox" || by != "jo through mesh-cli on anchor" {
t.Fatalf("asked %q %q", node, by)
}
return answer, nil
}
}
known := func(string) error { return nil }
var out bytes.Buffer
for _, args := range [][]string{nil, {"novox", "extra"}, {"-x"}} {
if err := judgeDirectoriesAsked(args, known, ask(link.HandOverAnswer{Said: "x"}), &out); err == nil || asked != 0 {
t.Fatalf("%v was asked: %v", args, err)
}
}
if err := judgeDirectoriesAsked([]string{"novox"}, func(string) error { return errors.New("no node called novox") },
ask(link.HandOverAnswer{Said: "x"}), &out); err == nil || asked != 0 {
t.Fatalf("an unknown node: %v", err)
}
if err := judgeDirectoriesAsked([]string{"novox"}, known, ask(link.HandOverAnswer{Refused: "no; nothing was judged"}),
&out); err == nil || !strings.Contains(err.Error(), "novox refused") || out.Len() != 0 {
t.Fatalf("a refusal: %v, printed %q", err, out.String())
}
said := "2 directories declared: 1 placed, 1 would be refused\n/var/lib/a: placed\n/var/lib/b: would be refused: …"
if err := judgeDirectoriesAsked([]string{"novox"}, known, ask(link.HandOverAnswer{Said: said}), &out); err != nil ||
out.String() != "novox (read-only: nothing on novox was changed)\n"+said+"\n" {
t.Fatalf("a judgement: %v, printed %q", err, out.String())
}
}
// The judgement is a seat verb an agent may call — it reads, and changes nothing on the node — and runs exactly
// `node judge-directories <node>` (novox/hq issue 358).
func TestTheDirectoryJudgementIsAVerbThatOnlyReads(t *testing.T) {
argv, err := argvFor("judge-directories", map[string]any{"node": "novox"})
if err != nil || strings.Join(argv, " ") != "node judge-directories novox" {
t.Fatalf("the verb runs %v, %v", argv, err)
}
if _, err := argvFor("judge-directories", map[string]any{}); err == nil {
t.Fatal("the verb ran with no node")
}
if !readingVerbs["judge-directories"] {
t.Fatal("the judgement is not counted a reading verb")
}
}
+5 -11
View File
@@ -123,12 +123,11 @@ func TestDeliveryStopTakesTheMergesToLeaveOut(t *testing.T) {
// that builds the other repository's module alone.
func TestAStopWithoutAMergeWalksTheOthersAgain(t *testing.T) {
open := windowed(t)
groupsWaiting(t, "pr/cat1aaaaaaaa")
endsItsLine(t)
asksRecorded(t)
ctx := t.Context()
cat := catalogueMerge("cat1aaaaaaaa", "app", t0)
one := fromHead(repoMerge("one", "one1bbbbbbbb", t0.Add(5*time.Second)), cat.Head)
one := repoMerge("one", "one1bbbbbbbb", t0.Add(5*time.Second))
hear(t, open, cat, t0.Add(time.Second))
hear(t, open, one, t0.Add(6*time.Second))
cutAt(t, open, t0.Add(2*time.Minute))
@@ -182,13 +181,12 @@ func TestAStopWithoutAMergeWalksTheOthersAgain(t *testing.T) {
// ended. A merge the walk does not answer is refused, and nothing ends.
func TestAStopWithoutAMergeEndsTheMergesThatContainIt(t *testing.T) {
open := windowed(t)
groupsWaiting(t, "pr/cat1aaaaaaaa")
endsItsLine(t)
asksRecorded(t)
ctx := t.Context()
first := catalogueMerge("cat1aaaaaaaa", "app", t0)
later := catalogueMerge("cat2cccccccc", "notes", t0.Add(10*time.Second))
one := fromHead(repoMerge("one", "one1bbbbbbbb", t0.Add(5*time.Second)), first.Head)
one := repoMerge("one", "one1bbbbbbbb", t0.Add(5*time.Second))
hear(t, open, first, t0.Add(time.Second))
hear(t, open, one, t0.Add(6*time.Second))
hear(t, open, later, t0.Add(11*time.Second))
@@ -240,12 +238,11 @@ func TestAStopWithoutAMergeEndsTheMergesThatContainIt(t *testing.T) {
// (review of #232): its window closes, and its walk is at the newer commit, answering both.
func TestAStopWalksTheOthersAgainInTheOpenBatch(t *testing.T) {
open := windowed(t)
groupsWaiting(t, "pr/cat1aaaaaaaa")
endsItsLine(t)
asksRecorded(t)
ctx := t.Context()
cat := catalogueMerge("cat1aaaaaaaa", "app", t0)
one1 := fromHead(repoMerge("one", "one1bbbbbbbb", t0.Add(5*time.Second)), cat.Head)
one1 := repoMerge("one", "one1bbbbbbbb", t0.Add(5*time.Second))
hear(t, open, cat, t0.Add(time.Second))
hear(t, open, one1, t0.Add(6*time.Second))
cutAt(t, open, t0.Add(2*time.Minute))
@@ -293,12 +290,11 @@ func TestAStopWalksTheOthersAgainInTheOpenBatch(t *testing.T) {
// that walked its merges again is refused a retry, saying why.
func TestAStopNamesWhatStaysOnTheMachinesAndWhatStillCarriesIt(t *testing.T) {
open := windowed(t)
groupsWaiting(t, "pr/cat1aaaaaaaa")
endsItsLine(t)
asksRecorded(t)
ctx := t.Context()
cat := catalogueMerge("cat1aaaaaaaa", "app", t0)
one1 := fromHead(repoMerge("one", "one1bbbbbbbb", t0.Add(5*time.Second)), cat.Head)
one1 := repoMerge("one", "one1bbbbbbbb", t0.Add(5*time.Second))
hear(t, open, cat, t0.Add(time.Second))
hear(t, open, one1, t0.Add(6*time.Second))
cutAt(t, open, t0.Add(2*time.Minute))
@@ -339,12 +335,11 @@ func TestAStopNamesWhatStaysOnTheMachinesAndWhatStillCarriesIt(t *testing.T) {
// with the others and withholds the stopped merge's modules; with every merge left out, the batch is stopped.
func TestAStopWithoutAMergeLeavesItOutOfABatch(t *testing.T) {
open := windowed(t)
everyHeadWaits(t)
endsItsLine(t)
asksRecorded(t)
ctx := t.Context()
cat := catalogueMerge("cat1aaaaaaaa", "app", t0)
one := fromHead(repoMerge("one", "one1bbbbbbbb", t0.Add(5*time.Second)), cat.Head)
one := repoMerge("one", "one1bbbbbbbb", t0.Add(5*time.Second))
hear(t, open, cat, t0.Add(time.Second))
hear(t, open, one, t0.Add(6*time.Second))
_, bs := walks(t, open)
@@ -387,7 +382,6 @@ func TestAStopWithoutAMergeLeavesItOutOfABatch(t *testing.T) {
// else since it was read refuses all of it, and no merge moves, no plan is written.
func TestSavingPlansAndMovingMergesIsOneAct(t *testing.T) {
open := windowed(t)
everyHeadWaits(t)
endsItsLine(t)
ctx := t.Context()
hear(t, open, catalogueMerge("cat1aaaaaaaa", "app", t0), t0.Add(time.Second))
-398
View File
@@ -1,398 +0,0 @@
package main
import (
"context"
"errors"
"strings"
"testing"
"time"
"github.com/novox/mesh-controller/internal/catalogue"
"github.com/novox/mesh-controller/internal/inventory"
)
// The tests of novox/hq issue 525's window skip: a merge waits for the merge window only when a batch assembling
// holds a merge related to it, or its delivery group may have a member still to merge (ADR 0304 decision 1, ADR
// 0306 decisions 2 and 3). Walks stay one at a time.
// A merge from no head that shares nothing, with no walk open, is cut into its walk when it is heard: no window.
func TestALoneMergeSharingNothingIsCutAtOnce(t *testing.T) {
open := windowed(t)
asksWithPaths(t)
hear(t, open, lone(repoMerge("one", "c1", t0)), t0)
ws, bs := walks(t, open)
if len(ws) != 1 || len(bs) != 0 || !ws[0].Open() || ws[0].Commit != "c1" {
t.Fatalf("a lone merge sharing nothing: %d walk(s) %+v, %d batch(es)", len(ws), ws, len(bs))
}
if ws[0].Times == nil || ws[0].Times.WindowClosed == nil || !ws[0].Times.WindowClosed.Equal(t0) {
t.Fatalf("its window closed at %+v; want when it was heard, %s", ws[0].Times, t0)
}
}
// A merge related to the batch assembling joins it and waits for the window, which its coming restarts: by its
// repository, by a module in common (a dependent of what the batch moves), by an edge of the module graph between
// their modules (one that widens nothing), or by its delivery group's head.
func TestARelatedMergeJoinsTheBatchAndWaitsForTheWindow(t *testing.T) {
ctx := t.Context()
for _, c := range []string{"same repository", "a module in common", "an edge of the graph", "the same group head"} {
t.Run(c, func(t *testing.T) {
open := windowed(t)
groupsWaiting(t, "pr/c1")
asksWithPaths(t)
inv := open.inventory
first := repoMerge("one", "c1", t0)
second := lone(repoMerge("two", "c2", t0.Add(10*time.Second)))
why := map[string]string{"same repository": "both change novox/one", "a module in common": "both move two",
"an edge of the graph": "two depends on builder (built-by)",
"the same group head": "both are members of group " + first.Head}[c]
switch c {
case "same repository":
second = lone(repoMerge("one", "c2", t0.Add(10*time.Second)))
case "a module in common":
// two is built on one: a merge of one moves two too.
if err := inv.RegisterModule(ctx, catalogue.Manifest{Module: "two", Version: "1",
Build: &catalogue.Build{On: []catalogue.BuildsOn{{Arg: "BASE", Module: "one"}}}},
inventory.Source{Repository: "novox/two", Seat: "git", Ref: "main", BuiltFrom: "c0", Head: "c0"}); err != nil {
t.Fatal(err)
}
case "an edge of the graph":
// two is built by the build machine: an edge that orders and widens nothing.
if err := inv.RegisterModule(ctx, catalogue.Manifest{Module: "builder", Version: "1",
Claims: []catalogue.Claim{{Name: "mesh-build-machine", Scope: catalogue.ScopeMesh}}},
inventory.Source{Repository: "novox/builder", Seat: "git", Ref: "main", BuiltFrom: "c0", Head: "c0"}); err != nil {
t.Fatal(err)
}
first = repoMerge("builder", "c1", t0)
case "the same group head":
second = fromHead(repoMerge("two", "c2", t0.Add(10*time.Second)), first.Head)
}
hear(t, open, first, t0)
said := captured(t, func() error {
return (following{open: open}).hearMerge(ctx, second, t0.Add(10*time.Second))
})
if !strings.Contains(said, "("+why+")") {
t.Fatalf("the merge was not said related by %q: %s", why, said)
}
ws, bs := walks(t, open)
if len(ws) != 0 || len(bs) != 1 || len(bs[0].Delivery.Merges) != 2 {
t.Fatalf("the related merge: %d walk(s), batches %+v", len(ws), bs)
}
if bs[0].Delivery.Batch.CutAtOnce {
t.Fatal("a batch a related merge joined is cut at once")
}
cutAt(t, open, t0.Add(99*time.Second))
if ws, _ := walks(t, open); len(ws) != 0 {
t.Fatalf("cut before the window the related merge restarted closed: %+v", ws)
}
cutAt(t, open, t0.Add(100*time.Second))
ws, bs = walks(t, open)
if len(ws) != 1 || len(bs) != 0 || len(ws[0].Delivery.Merges) != 2 {
t.Fatalf("after the window: %d walk(s), %d batch(es)", len(ws), len(bs))
}
})
}
}
// A merge from a head whose delivery group has a member still to merge waits for the window, even with no batch
// assembling, and says why; its sibling joins the same batch by their head (ADR 0306 decision 2). A merge from a
// head that names no group shares nothing and is cut at once, as one from no head is.
func TestAMergeOfAGroupWaitsEvenAlone(t *testing.T) {
open := windowed(t)
asksWithPaths(t)
groupsWaiting(t, "feat/x")
hear(t, open, fromHead(repoMerge("one", "c1", t0), "feat/x"), t0)
ws, bs := walks(t, open)
if len(ws) != 0 || len(bs) != 1 || bs[0].Delivery.Batch.CutAtOnce || windowClosed(bs[0], t0) {
t.Fatalf("a group's merge alone: %d walk(s), batches %+v", len(ws), bs)
}
if words := batchWords(bs[0], t0); !strings.HasPrefix(words, "assembling: 90 s left") ||
!strings.Contains(words, "group feat/x has a member still to merge: novox/elsewhere (ready)") {
t.Fatalf("it reads %q", words)
}
hear(t, open, fromHead(repoMerge("two", "c2", t0.Add(5*time.Second)), "feat/x"), t0.Add(5*time.Second))
if _, bs := walks(t, open); len(bs) != 1 || len(bs[0].Delivery.Merges) != 2 {
t.Fatalf("the group's second member did not join the first: %+v", bs)
}
cutAt(t, open, t0.Add(94*time.Second))
if ws, _ := walks(t, open); len(ws) != 0 {
t.Fatalf("cut before its window closed: %+v", ws)
}
cutAt(t, open, t0.Add(95*time.Second))
ws, bs = walks(t, open)
if len(ws) != 1 || len(bs) != 0 || ws[0].CommitOf("novox/one") != "c1" || ws[0].CommitOf("novox/two") != "c2" {
t.Fatalf("at its window: %d walk(s) %+v, %d batch(es)", len(ws), ws, len(bs))
}
}
// A merge from a head that names no group, sharing nothing, with no walk open, is cut at once.
func TestAHeadedMergeInNoGroupIsCutAtOnce(t *testing.T) {
open := windowed(t)
asksWithPaths(t)
hear(t, open, fromHead(repoMerge("one", "c1", t0), "fix/alone"), t0)
if ws, bs := walks(t, open); len(ws) != 1 || len(bs) != 0 || !ws[0].Open() {
t.Fatalf("a headed merge in no group: %d walk(s), %d batch(es)", len(ws), len(bs))
}
}
// When mesh-delivery cannot say a head's group, the merge waits for the window, the safe side, and its batch says
// why.
func TestAGroupNobodyCanSayWaits(t *testing.T) {
open := windowed(t)
asksWithPaths(t)
was := deliveryGroupOf
deliveryGroupOf = func(context.Context, bool, string) ([]groupMember, bool, error) {
return nil, false, errors.New("nothing serves mesh-delivery.groups")
}
t.Cleanup(func() { deliveryGroupOf = was })
hear(t, open, fromHead(repoMerge("one", "c1", t0), "feat/x"), t0)
ws, bs := walks(t, open)
if len(ws) != 0 || len(bs) != 1 || bs[0].Delivery.Batch.CutAtOnce {
t.Fatalf("a merge whose group nobody could say: %d walk(s), batches %+v", len(ws), bs)
}
if words := batchWords(bs[0], t0); !strings.Contains(words, "mesh-delivery did not say whether group feat/x has a "+
"member still to merge (nothing serves mesh-delivery.groups): it waits for the window, the safe side") {
t.Fatalf("it reads %q", words)
}
}
// A member counts as still to merge only while its pull request is open, and not once this controller keeps its
// merge: a group whose other members are merged or closed makes nobody wait.
func TestAGroupsMergedOrClosedMembersMakeNobodyWait(t *testing.T) {
open := windowed(t)
asksWithPaths(t)
ctx := t.Context()
members := []groupMember{{Repository: "novox/one", State: "ready"}, {Repository: "novox/two", State: "published"},
{Repository: "novox/three", State: "stopped"}}
was := deliveryGroupOf
deliveryGroupOf = func(context.Context, bool, string) ([]groupMember, bool, error) { return members, true, nil }
t.Cleanup(func() { deliveryGroupOf = was })
m := fromHead(repoMerge("one", "c1", t0), "feat/x")
if why, err := groupWait(ctx, open.inventory, m, true, false); err != nil || why != "" {
t.Fatalf("the group's other members are merged or closed, yet: %q %v", why, err)
}
members = append(members, groupMember{Repository: "novox/four", State: "checked"})
if why, _ := groupWait(ctx, open.inventory, m, true, false); !strings.Contains(why, "novox/four (checked)") {
t.Fatalf("an open member: %q", why)
}
// novox/four's merge is kept in a batch already: merged, whatever mesh-delivery says yet.
hear(t, open, fromHead(repoMerge("two", "c4", t0), "feat/x"), t0)
members[3].Repository = "novox/two"
if why, _ := groupWait(ctx, open.inventory, m, true, false); why != "" {
t.Fatalf("a member this controller keeps the merge of still waits: %q", why)
}
if got := memberOf("novox/mesh-sdk@d41d255f28ad (held)"); got != (groupMember{Repository: "novox/mesh-sdk", State: "held"}) {
t.Fatalf("a member reads %+v", got)
}
}
// A merge related to two batches assembling folds the newer into the older, which answers every merge of both
// and names nothing twice; the folded one names the batch that took it over.
func TestAMergeRelatedToTwoBatchesFoldsThem(t *testing.T) {
open := windowed(t)
groupsWaiting(t, "feat/a", "feat/b")
asksWithPaths(t)
ctx := t.Context()
hear(t, open, fromHead(repoMerge("one", "c1", t0), "feat/a"), t0)
hear(t, open, fromHead(repoMerge("two", "c2", t0.Add(5*time.Second)), "feat/b"), t0.Add(5*time.Second))
_, bs := walks(t, open)
if len(bs) != 2 {
t.Fatalf("two merges sharing nothing: %d batch(es)", len(bs))
}
older, newer := bs[1], bs[0] // newest first
// Of one's repository and from two's head: related to both.
hear(t, open, fromHead(repoMerge("one", "c3", t0.Add(10*time.Second)), "feat/b"), t0.Add(10*time.Second))
_, bs = walks(t, open)
if len(bs) != 1 || bs[0].ID != older.ID || len(bs[0].Delivery.Merges) != 3 {
t.Fatalf("after a merge related to both: batches %+v; want %s answering three merges", bs, older.ID)
}
folded, err := open.inventory.PlanByID(ctx, newer.ID)
if err != nil || folded.State != inventory.PlanSuperseded || folded.Delivery == nil ||
folded.Delivery.TakenOverBy != older.ID {
t.Fatalf("the newer batch reads %s %+v (%v)", folded.State, folded.Delivery, err)
}
if left, _ := open.inventory.MergesOf(ctx, newer.ID); len(left) != 0 {
t.Fatalf("the folded batch still answers %+v", left)
}
cutAt(t, open, t0.Add(100*time.Second))
ws, bs := walks(t, open)
var cut []inventory.Plan
for _, w := range ws {
if w.State != inventory.PlanSuperseded {
cut = append(cut, w)
}
}
if len(cut) != 1 || len(bs) != 0 || cut[0].ID != older.ID || cut[0].CommitOf("novox/one") != "c3" ||
cut[0].CommitOf("novox/two") != "c2" {
t.Fatalf("the folded batch's walk: %+v, %d batch(es)", cut, len(bs))
}
}
// With a walk open, a batch cut at once still waits for it, said queued behind it (walks stay one at a time, ADR
// 0276 decision 4); it is cut once that walk ended, with no window to wait for.
func TestACutAtOnceBatchQueuesBehindAnOpenWalk(t *testing.T) {
open := windowed(t)
groupsWaiting(t, "pr/c1")
asksWithPaths(t)
hear(t, open, repoMerge("one", "c1", t0), t0)
cutAt(t, open, t0.Add(90*time.Second))
ws, _ := walks(t, open)
if len(ws) != 1 || !ws[0].Open() {
t.Fatalf("no walk open: %+v", ws)
}
first := ws[0]
heard := t0.Add(100 * time.Second)
hear(t, open, lone(repoMerge("two", "c2", heard)), heard)
ws, bs := walks(t, open)
if len(ws) != 1 || len(bs) != 1 || bs[0].State != inventory.PlanQueued || bs[0].Delivery.Batch.Behind != first.ID ||
!bs[0].Delivery.Batch.CutAtOnce {
t.Fatalf("a lone merge during a walk: %d walk(s), batches %+v", len(ws), bs)
}
if !strings.HasPrefix(batchWords(bs[0], heard), "queued behind "+first.ID) {
t.Fatalf("it reads %q", batchWords(bs[0], heard))
}
first.State = inventory.PlanDone
if err := open.inventory.SavePlan(t.Context(), &first); err != nil {
t.Fatal(err)
}
cutAt(t, open, heard.Add(time.Second))
ws, bs = walks(t, open)
if len(ws) != 2 || len(bs) != 0 || ws[0].Commit != "c2" {
t.Fatalf("the queued batch was not cut once the walk ended: %+v %+v", ws, bs)
}
if ws[0].Times == nil || ws[0].Times.WindowClosed == nil || !ws[0].Times.WindowClosed.Equal(heard) {
t.Fatalf("its window closed at %+v; want when its merge was heard, %s", ws[0].Times, heard)
}
}
// A stopped walk's other merges are walked again in a batch they are related to, and a batch of their own when
// they share nothing with the one assembling (ADR 0299, ADR 0304 decision 1): never in a batch of another
// change, whose window the stop would close.
func TestAStopWalksTheOthersAgainInABatchOfTheirOwnWhenTheyShareNothing(t *testing.T) {
open := windowed(t)
groupsWaiting(t, "pr/cat1aaaaaaaa")
endsItsLine(t)
asksRecorded(t)
ctx := t.Context()
cat := catalogueMerge("cat1aaaaaaaa", "app", t0)
one := fromHead(repoMerge("one", "one1bbbbbbbb", t0.Add(5*time.Second)), cat.Head)
hear(t, open, cat, t0.Add(time.Second))
hear(t, open, one, t0.Add(6*time.Second))
cutAt(t, open, t0.Add(2*time.Minute))
ws, _ := walks(t, open)
walk := ws[0]
hear(t, open, repoMerge("two", "two1cccccccc", t0.Add(3*time.Minute)), t0.Add(3*time.Minute))
_, bs := walks(t, open)
if len(bs) != 1 {
t.Fatalf("the merge heard while the walk ran is in %d batches", len(bs))
}
other := bs[0]
_, said, err := stopWalkWithout(ctx, open.inventory, walk.ID, "mesh-delivery for jochen", "its group stopped",
[]string{"novox/mesh-catalog@" + cat.Commit}, t0.Add(3*time.Minute+10*time.Second))
if err != nil {
t.Fatal(err)
}
if said.WalkedAgainBy == "" || said.WalkedAgainBy == other.ID {
t.Fatalf("walked again by %q; want a batch of its own, not %s", said.WalkedAgainBy, other.ID)
}
b, _ := open.inventory.PlanByID(ctx, other.ID)
if b.Delivery.Batch == nil || b.Delivery.Batch.Closed || len(b.Delivery.Merges) != 1 {
t.Fatalf("the other change's batch reads %+v; want it untouched by the stop", b.Delivery)
}
}
// A catalogue batch's cut folds in every walk waiting for its delivery's word (cutBatch's carry), so what that
// walk moves is the batch's too: a lone merge related to the waiting walk joins the batch assembling and waits for
// its window, rather than being cut at once as sharing nothing with what the batch's own merges move.
func TestALoneMergeRelatedToAWalkTheCutFoldsJoinsTheBatch(t *testing.T) {
open := windowed(t)
groupsWaiting(t, "pr/c3")
asksWithPaths(t)
ctx := t.Context()
if err := open.inventory.RegisterModule(ctx, catalogue.Manifest{Module: "mesh-delivery", Version: "1",
Claims: []catalogue.Claim{{Name: catalogue.DeliverySeat, Scope: catalogue.ScopeMesh}}},
inventory.Source{Repository: "novox/mesh-catalog", Seat: "git", Path: "modules/mesh-delivery", Ref: "main",
BuiltFrom: "c0", Head: "c0"}); err != nil {
t.Fatal(err)
}
if _, err := open.inventory.Assign(ctx, "anchor", "mesh-delivery"); err != nil {
t.Fatal(err)
}
hear(t, open, repoMerge("one", "c1", t0), t0)
cutAt(t, open, t0.Add(90*time.Second))
if ws, _ := walks(t, open); len(ws) != 1 || !ws[0].Waiting() {
t.Fatalf("the walk does not wait for its word: %+v", ws)
}
hear(t, open, repoMerge("three", "c3", t0.Add(2*time.Minute)), t0.Add(2*time.Minute))
hear(t, open, lone(repoMerge("one", "c2", t0.Add(2*time.Minute+5*time.Second))), t0.Add(2*time.Minute+5*time.Second))
_, bs := walks(t, open)
if len(bs) != 1 || len(bs[0].Delivery.Merges) != 2 || bs[0].Delivery.Batch.CutAtOnce {
t.Fatalf("a lone merge related to the waiting walk: batches %+v", bs)
}
}
// A delivery group with a member of each kind (review of #250): a merge on the controller's own path and a
// catalogue merge never share a batch, so the later member cannot join the earlier one's. Kept in a batch of the
// other kind, the earlier member keeps the later one waiting, whatever mesh-delivery says yet — never cut at once
// to walk before it. The two batches are then cut in the order their windows close (cutBatchesHeld: the oldest
// closed batch first, an own-path one first at one look, and the other queued behind a walk that started): the
// earlier member's window closes first, so it walks first, in both orders.
func TestAGroupAcrossBothKindsKeepsItsOrder(t *testing.T) {
for _, ownFirst := range []bool{true, false} {
name := "catalogue member first"
if ownFirst {
name = "controller member first"
}
t.Run(name, func(t *testing.T) {
open := windowed(t)
asksWithPaths(t)
ctx := t.Context()
was := deliveryGroupOf
// mesh-delivery still says both members ready: it marks one merged only once its walk opened.
deliveryGroupOf = func(context.Context, bool, string) ([]groupMember, bool, error) {
return []groupMember{{Repository: "novox/mesh-controller", State: "ready"},
{Repository: "novox/mesh-catalog", State: "ready"}}, true, nil
}
t.Cleanup(func() { deliveryGroupOf = was })
own := fromHead(repoMerge("mesh-controller", "k1", t0), "feat/both-kinds")
cat := fromHead(catalogueMerge("cat1aaaaaaaa", "app", t0), "feat/both-kinds")
first, second := cat, own
if ownFirst {
first, second = own, cat
}
second.MergedAt = t0.Add(10 * time.Second).Format(time.RFC3339Nano)
hear(t, open, first, t0)
hear(t, open, second, t0.Add(10*time.Second))
ws, bs := walks(t, open)
if len(ws) != 0 || len(bs) != 2 {
t.Fatalf("both members heard: %d walk(s), %d batch(es); want two batches, nothing cut", len(ws), len(bs))
}
later := bs[0] // newest first
if later.Delivery.Batch.CutAtOnce || !strings.Contains(later.Delivery.Batch.Waits,
"has a member waiting in a batch of the other kind: novox/"+first.Repo+"@") {
t.Fatalf("the later member's batch reads %+v; want it waiting for the earlier member", later.Delivery.Batch)
}
// The earlier member's window closes first: its batch alone is cut.
cutAt(t, open, t0.Add(90*time.Second))
ws, bs = walks(t, open)
if len(ws) != 1 || !ws[0].Open() || ws[0].CommitOf("novox/"+first.Repo) != first.Commit || len(bs) != 1 ||
bs[0].ID != later.ID {
t.Fatalf("at the earlier window: walks %+v, batches %+v; want the earlier member alone cut", ws, bs)
}
earlier := ws[0]
// The later member's window closes while the earlier walk runs: it queues behind it.
cutAt(t, open, t0.Add(100*time.Second))
if _, bs := walks(t, open); len(bs) != 1 || bs[0].State != inventory.PlanQueued || bs[0].Delivery.Batch.Behind != earlier.ID {
t.Fatalf("the later member's batch does not queue behind the earlier walk: %+v", bs)
}
earlier.State = inventory.PlanDone
if err := open.inventory.SavePlan(ctx, &earlier); err != nil {
t.Fatal(err)
}
cutAt(t, open, t0.Add(101*time.Second))
got, err := open.inventory.PlanByID(ctx, later.ID)
if err != nil || got.Batch() || got.CommitOf("novox/"+second.Repo) != second.Commit {
t.Fatalf("the later member was not walked after the earlier: %s %v", got.State, err)
}
})
}
}
-9
View File
@@ -63,15 +63,6 @@ func run() error {
// 45 §6), so the next controller takes it at once rather than after its age.
defer theLease.release()
// Every walk a verb keeps is said on the bus, whichever verb kept it (novox/hq ADR 0308 decision 1): the save
// that starts or ends a walk keeps its mark, and no later save says it again. The serving controller says its
// own saves.
if args[0] != "serve" {
said, done := sayingWhatAVerbKept(ctx)
inventory.PlanSaved = said
defer done()
}
switch args[0] {
case "build":
return buildCommand(ctx, args[1:])
+2 -61
View File
@@ -127,14 +127,9 @@ func nodeCommand(ctx context.Context, args []string) error {
// and whoever may call a verb includes agents.
return nodeSetuidSearch(ctx, open, args[1:])
case "judge-directories":
// Which of a node's declared directories the walk that follows no link another account could make would
// refuse (novox/hq issue 358). Read-only on the node and here, so a verb may run it too.
return nodeJudgeDirectories(ctx, open, args[1:])
default:
return fmt.Errorf("node has no %q; it has add, list, show, public-domain, account, agent-account, hand-over, "+
"setuid-search and judge-directories", args[0])
return fmt.Errorf("node has no %q; it has add, list, show, public-domain, account, agent-account, hand-over "+
"and setuid-search", args[0])
}
}
@@ -942,57 +937,3 @@ func printJSONTo(w io.Writer, v any) error {
fmt.Fprintln(w, string(body))
return nil
}
const judgeDirectoriesUsage = "node judge-directories <node> — read-only: which of the directories <node> is " +
"declared the node-engine's walk that follows no link another account could make would refuse, one line each " +
"(novox/hq issue 358). Nothing is made, chmodded or chowned"
// nodeJudgeDirectories asks the node's engine to judge its declared directories, signed with the mesh's key as a
// hand-over is. Read-only: the engine changes nothing and keeps nothing.
func nodeJudgeDirectories(ctx context.Context, open *stores, args []string) error {
known := func(node string) error {
_, err := open.inventory.NodeByName(ctx, node)
return err
}
ask := func(node, by string) (link.HandOverAnswer, error) {
ident, err := open.Identity(ctx)
if err != nil {
return link.HandOverAnswer{}, fmt.Errorf("the mesh's signing key cannot be read, so nothing was asked of %s: %w",
node, err)
}
address, err := broker.BusAddress()
if err != nil {
return link.HandOverAnswer{}, err
}
js, err := broker.Dial(address)
if err != nil {
return link.HandOverAnswer{}, fmt.Errorf("cannot reach the bus, so nothing was asked of %s: %w", node, err)
}
defer js.Close()
return link.AskJudgeDirectories(ctx, js.Conn(), ident, node, by, link.HandOverWithin)
}
return judgeDirectoriesAsked(args, known, ask, os.Stdout)
}
// judgeDirectoriesAsked is the line with its two acts given: whether the mesh knows the node, and the ask. The
// engine's refusal is this command's failure.
func judgeDirectoriesAsked(args []string, known func(node string) error,
ask func(node, by string) (link.HandOverAnswer, error), out io.Writer) error {
if len(args) != 1 || args[0] == "" || strings.HasPrefix(args[0], "-") {
return errors.New(judgeDirectoriesUsage)
}
node := args[0]
if err := known(node); err != nil {
return fmt.Errorf("nothing was asked: %w", err)
}
answer, err := ask(node, handOverBy())
if err != nil {
return err
}
if answer.Refused != "" {
return fmt.Errorf("%s refused: %s", node, answer.Refused)
}
fmt.Fprintf(out, "%s (read-only: nothing on %s was changed)\n", node, node)
fmt.Fprintln(out, answer.Said)
return nil
}
-112
View File
@@ -1,112 +0,0 @@
package main
import (
"bytes"
"context"
"errors"
"strings"
"testing"
"github.com/novox/mesh-controller/internal/catalogue"
)
// novox/hq issue 237: every line of an act's answer comes from one resolution of the node taken after
// its write, so the answer agrees with `plan` for the node right after.
func aProviderAndItsConsumer(t *testing.T, open *stores) {
t.Helper()
register(t, open, catalogue.Manifest{Module: "db", Version: "1",
Provides: []catalogue.Offer{{Name: "rows", Scope: catalogue.ScopeNode}}})
register(t, open, catalogue.Manifest{Module: "app", Version: "1", Requires: []string{"rows"}})
}
// twoRivalsAndANote is a node that does not resolve — two modules claim one node seat there — and a
// module beside them that changes nothing about it.
func twoRivalsAndANote(t *testing.T, open *stores) {
t.Helper()
one, two := rivals()
register(t, open, one)
register(t, open, two)
register(t, open, catalogue.Manifest{Module: "notes", Version: "1"})
}
func TestAnUnassignThatLeavesItsNodeUnresolvedSaysSoOnceInItsAnswer(t *testing.T) {
open := aMesh(t)
ctx := t.Context()
twoRivalsAndANote(t, open)
// Straight into the store, as a node that came to this before the act.
for _, m := range []string{"rival-one", "rival-two", "notes"} {
if _, err := open.inventory.Assign(ctx, "laptop", m); err != nil {
t.Fatal(err)
}
}
said := answered(t, func() error { return assignCommand(ctx, "unassign", []string{"laptop", "notes"}) })
if _, _, err := planFor(ctx, open, "laptop"); err == nil || !unresolvable(err) {
t.Fatalf("laptop resolves with two claimants of one seat: %v", err)
}
if n := strings.Count(said, "laptop does not resolve now"); n != 1 {
t.Errorf("the answer says laptop does not resolve %d times, want once:\n%s", n, said)
}
if strings.Contains(said, "is left out of the rest of the mesh") {
t.Errorf("the answer carries a line from a read that is not its resolution:\n%s", said)
}
}
func TestAnUnassignThatLeavesItsNodeResolvedSaysNothingOfIt(t *testing.T) {
open := aMesh(t)
ctx := t.Context()
aProviderAndItsConsumer(t, open)
if _, err := assign(ctx, open, "laptop", "db", "app"); err != nil {
t.Fatal(err)
}
said, err := unassign(ctx, open, "laptop", "app")
if err != nil {
t.Fatal(err)
}
if _, _, err := planFor(ctx, open, "laptop"); err != nil {
t.Fatal(err)
}
if strings.Contains(said, "does not resolve") || strings.Contains(said, "could not be read") {
t.Errorf("a node that resolves is said not to:\n%s", said)
}
}
func TestAnAssignThatLeavesItsNodeUnresolvedSaysOnlyThePlansRefusal(t *testing.T) {
open := aMesh(t)
ctx := t.Context()
twoRivalsAndANote(t, open)
if _, err := assign(ctx, open, "laptop", "rival-one"); err != nil {
t.Fatal(err)
}
// Kept and not resolvable: a second claimant of the seat, which assignment keeps.
said, err := assign(ctx, open, "laptop", "rival-two")
if err == nil {
t.Fatalf("two claimants of one node seat resolved:\n%s", said)
}
_, _, planErr := planFor(ctx, open, "laptop")
if planErr == nil || planErr.Error() != err.Error() {
t.Errorf("the act's refusal is not the plan's right after:\nact: %v\nplan: %v", err, planErr)
}
if strings.Contains(said, "now has") {
t.Errorf("the answer says a seat is now held on a node that does not resolve:\n%s", said)
}
}
// The other readers of the whole mesh still say a machine they leave out, on standard error (novox/hq
// issue 188); an act sends it elsewhere.
func TestAMachineLeftOutIsSaidWhereTheContextSays(t *testing.T) {
var buf bytes.Buffer
sayLeftOut(leftOutSaidBy(context.Background(), &buf), "laptop", errors.New("why"))
if buf.String() != "laptop is left out of the rest of the mesh: it does not resolve: why\n" {
t.Errorf("said %q", buf.String())
}
got := answered(t, func() error {
sayLeftOut(context.Background(), "laptop", errors.New("why"))
return nil
})
if !strings.Contains(got, "laptop is left out") {
t.Errorf("without an act's writer the line did not reach standard error: %q", got)
}
}
+5 -20
View File
@@ -885,11 +885,6 @@ func stalledWords(l stalledLine, o conditions.Observation) (headline, explanatio
// within its bound (novox/hq issue 438): mesh-delivery holds no delivery of it, so there is nothing to stop, release
// or close, and no action is offered. The operator's acts are a new commit, which asks the check again, or a look
// at the build queue, where a check that never ran may still wait.
//
// A head whose delivery is held in ready or rejected is said the same way (novox/hq issue 441), and mesh-delivery
// names that state as data (Held). Its check answered once, so the build queue is the wrong place to look: the step
// is a recheck of the delivery, named by its id, which asks the check again (novox/hq issue 451). It is advised, not
// offered as an action, since the controller is not granted the recheck.
func unansweredWords(l stalledLine, o conditions.Observation) (headline, explanation, resolved, needs string,
actions []conditions.Action) {
repository, _, _ := strings.Cut(l.ID, "@")
@@ -904,23 +899,13 @@ func unansweredWords(l stalledLine, o conditions.Observation) (headline, explana
if d, err := time.ParseDuration(l.Bound); err == nil {
limit = ", past its limit of " + humanDuration(d)
}
check := "merge check"
which := "Its merge check"
if said := uncheckedWaitWords(l); len(said) > 0 {
check = "merge check (" + strings.Join(said, ", ") + ")"
which = "Its merge check (" + strings.Join(said, ", ") + ")"
}
which := "Its " + check
switch l.Held {
case "ready", "rejected":
which = "Its delivery is " + l.Held + ", but on the forge its " + check
if o.Resolver == conditions.ResolverOperator {
needs = "recheck its delivery, which asks its check again — mesh-delivery.recheck with id " + l.ID +
" and why — or push a new commit to its branch, " + FromMeshMCPServer
}
default:
if o.Resolver == conditions.ResolverOperator {
needs = "push a new commit to its branch, which asks the check again, or see whether its check still " +
"waits in the build queue: mesh-controller.queue."
}
if o.Resolver == conditions.ResolverOperator {
needs = "push a new commit to its branch, which asks the check again, or see whether its check still waits " +
"in the build queue: mesh-controller.queue."
}
return fmt.Sprintf("%s's merge check has not answered %s", pull, long),
fmt.Sprintf("%s is open on a branch that requires the merge check. %s was asked and has not answered %s%s. "+
-46
View File
@@ -452,49 +452,3 @@ func TestAnUnansweredMergeChecksTimeIsSaidInLocalTime(t *testing.T) {
t.Fatalf("a pending check without its time reads %q", o.Explanation)
}
}
// **An unanswered merge check on a ready or rejected delivery is told to recheck it** (novox/hq issue 451):
// mesh-delivery says such a line too (issue 441) and names the delivery's state as data, `held`. That check already
// answered once, so the build queue is the wrong place to look; a recheck of the delivery, named by its id, asks the
// check again. A line with no delivery held keeps the advice of issue 438, and so does a line from a mesh-delivery
// that does not say `held` yet: the controller never guesses the state from the words.
func TestAnUnansweredMergeCheckOnAReadyOrRejectedDeliveryOffersARecheck(t *testing.T) {
line := func(held string) stalledLine {
var l stalledLine
raw := `{"id":"novox/mesh-controller@c11222026a3b","number":212,"state":"unanswered",` +
`"waiting":["mesh/merge-gate pending since 2026-10-11T00:11:39Z"],"for":"1h1m0s","bound":"1h0m0s",` +
`"h2":"none: its delivery is ` + held + `, a state the operator moves — the operator's",` +
`"says":"novox/mesh-controller#212 is open on main, which requires the merge check, and its delivery is ` +
held + ` here, but on the forge its check has not answered: mesh/merge-gate pending since ` +
`2026-10-11T00:11:39Z. The pull request waits on that status and nothing asks it again. A recheck of the ` +
`delivery asks its check again, as does a new commit on its branch"`
if held != "" {
raw += `,"held":"` + held + `"`
}
if err := json.Unmarshal([]byte(raw+`}`), &l); err != nil {
t.Fatal(err)
}
return l
}
for _, held := range []string{"ready", "rejected"} {
o := stalledObservations([]stalledLine{line(held)})[0]
t.Logf("%s: %s\nneeds: %s", held, o.Explanation, o.Needs)
if !strings.Contains(o.Needs, "mesh-delivery.recheck") || !strings.Contains(o.Needs, "novox/mesh-controller@c11222026a3b") {
t.Fatalf("a %s delivery's unanswered check is not offered its recheck: %q", held, o.Needs)
}
if strings.Contains(o.Needs, "build queue") || strings.Contains(o.Needs, "mesh-controller.queue") {
t.Fatalf("a %s delivery's unanswered check, which answered once, is sent to the build queue: %q", held, o.Needs)
}
if !strings.Contains(o.Explanation, "Its delivery is "+held) {
t.Fatalf("a %s delivery's explanation does not say its state: %q", held, o.Explanation)
}
if len(o.Actions) != 0 {
t.Fatalf("it offers an action the controller is not granted: %+v", o.Actions)
}
}
// No delivery held, or a mesh-delivery that does not say: the advice of issue 438, and no recheck.
o := stalledObservations([]stalledLine{line("")})[0]
if !strings.Contains(o.Needs, "in the build queue: mesh-controller.queue") || strings.Contains(o.Needs, "recheck") {
t.Fatalf("a line with no delivery held says to %q", o.Needs)
}
}
+17 -61
View File
@@ -292,7 +292,7 @@ func theRestOfTheMesh(ctx context.Context, inv *inventory.Inventory,
if err != nil {
// Said, not skipped: a machine dropped here offers nothing and holds nothing as far
// as every other machine's plan can tell (novox/hq issue 188).
sayLeftOut(ctx, o.node.Name, err)
fmt.Fprintf(os.Stderr, "%s is left out of the rest of the mesh: it does not resolve: %v\n", o.node.Name, err)
continue
}
firstHeld = append(firstHeld, got.Claims...)
@@ -337,7 +337,7 @@ func theRestOfTheMesh(ctx context.Context, inv *inventory.Inventory,
// resolved without its offers, and one that consumes them cannot resolve here by
// design — that is not the machine being dropped, it is the view being partial.
if exclude == "" {
sayLeftOut(ctx, o.node.Name, err)
fmt.Fprintf(os.Stderr, "%s is left out of the rest of the mesh: it does not resolve: %v\n", o.node.Name, err)
}
continue
}
@@ -347,35 +347,6 @@ func theRestOfTheMesh(ctx context.Context, inv *inventory.Inventory,
return world, nil
}
// leftOutKey carries where theRestOfTheMesh says a machine it leaves out, for an act that answers with
// its own resolution instead (novox/hq issue 237).
type leftOutKey struct{}
// leftOutSaidBy is ctx with theRestOfTheMesh's "left out" lines written to w rather than to standard
// error.
//
// **An act's answer is one resolution taken after its write** (novox/hq issue 237, decided 2026-10-11).
// `assign` read the whole mesh once before its write — to record the seats held by derivation — and that
// read said, on standard error, that the node did not resolve for lack of the seat the act was about to
// give it. The controller seat's verb answers with both streams, so the stale line came last, after the
// act's own "now has it held", and named as its remedy the assignment just made. An act gives io.Discard
// here: what the node resolves to after the write is said by its own planFor, and every other machine
// that does not resolve by blockedElsewhere, both read after the write.
func leftOutSaidBy(ctx context.Context, w io.Writer) context.Context {
return context.WithValue(ctx, leftOutKey{}, w)
}
// sayLeftOut says that a machine is left out of the rest of the mesh, where ctx says to: standard
// error unless an act said otherwise. Said, not skipped: a machine dropped there offers nothing and
// holds nothing as far as every other machine's plan can tell (novox/hq issue 188).
func sayLeftOut(ctx context.Context, node string, err error) {
w, ok := ctx.Value(leftOutKey{}).(io.Writer)
if !ok {
w = os.Stderr
}
fmt.Fprintf(w, "%s is left out of the rest of the mesh: it does not resolve: %v\n", node, err)
}
// declarationFor is everything a node would be sent.
//
// One place, because there were three and one of them was written before credentials existed and
@@ -1780,43 +1751,28 @@ func (l *unheldLogger) log(node string, unheld []catalogue.Unheld) {
// which includes every one of a module just assigned — and each now met that was not. Nothing about
// any other node, and nothing that was already true before the act.
func unheldChange(shelf map[string]catalogue.Manifest, node string, before, after []string) []string {
return unheldChangeTo(shelf, node, before, after, unheldOver(shelf, node, after))
}
// unheldOver is the node's unmet seat dependencies judged over a set of module names alone.
func unheldOver(shelf map[string]catalogue.Manifest, node string, names []string) []catalogue.Unheld {
var set []catalogue.Manifest
for _, n := range names {
if m, known := shelf[n]; known {
set = append(set, m)
judge := func(names []string) map[string]catalogue.Unheld {
var set []catalogue.Manifest
for _, n := range names {
if m, known := shelf[n]; known {
set = append(set, m)
}
}
out := map[string]catalogue.Unheld{}
for _, u := range catalogue.UnheldDependencies(shelf, node, set, nil) {
out[u.Module+" "+u.Seat] = u
}
return out
}
return catalogue.UnheldDependencies(shelf, node, set, nil)
}
// unheldChangeTo is unheldChange with the node's dependencies as they now stand given: `now` is what
// the act's one resolution after its write says is unmet, and `after` the modules that resolution has
// on the node (novox/hq issue 237). A line about how things stand after the act is never judged from
// anything else, so it cannot disagree with `plan` for the node.
func unheldChangeTo(shelf map[string]catalogue.Manifest, node string, before, after []string,
now []catalogue.Unheld) []string {
key := func(u catalogue.Unheld) string { return u.Module + " " + u.Seat }
was := map[string]catalogue.Unheld{}
for _, u := range unheldOver(shelf, node, before) {
was[key(u)] = u
}
is := map[string]catalogue.Unheld{}
for _, u := range now {
is[key(u)] = u
}
was, now := judge(before), judge(after)
var lines []string
for _, k := range sortedNames(is) {
for _, k := range sortedNames(now) {
if _, already := was[k]; !already {
lines = append(lines, "but "+is[k].String())
lines = append(lines, "but "+now[k].String())
}
}
for _, k := range sortedNames(was) {
if _, still := is[k]; still {
if _, still := now[k]; still {
continue
}
u := was[k]
-12
View File
@@ -251,16 +251,6 @@ func resumed(p *inventory.Plan, why string) {
if p.State == inventory.PlanFailed && len(failedIn(*p)) == 0 {
p.State = inventory.PlanBuilding
p.Note = why
goesOnAgain(p)
}
}
// goesOnAgain clears a stop from a walk that walks again: a stop said why the walk ended, and a walk resumed has
// not ended. Kept, it would end a retried walk that fails again as stopped, not failed (novox/hq ADR 0308
// decision 1), and keep the search for the merge that brought the failure from running (searchAfterFailures).
func goesOnAgain(p *inventory.Plan) {
if p.Delivery != nil {
p.Delivery.Stopped, p.Delivery.StoppedWhy = "", ""
}
}
@@ -470,7 +460,6 @@ func retryRollouts(ctx context.Context, open *stores, p *inventory.Plan) (string
said = append(said, m+" to "+strings.Join(again, ", "))
}
p.State = inventory.PlanRolling
goesOnAgain(p)
p.Note = fmt.Sprintf("tier %d retried by hand; sent %s first again", p.Tier, strings.Join(said, "; "))
if err := open.inventory.SavePlan(ctx, p); err != nil {
return "", err
@@ -536,7 +525,6 @@ func retryTierWhole(ctx context.Context, open *stores, p *inventory.Plan, again
}
if p.State == inventory.PlanFailed && len(failedIn(*p)) == 0 {
p.State = inventory.PlanBuilding
goesOnAgain(p)
p.Note = fmt.Sprintf("tier %d retried by hand: %s asked again; %s sent again with the tier", p.Tier,
strings.Join(again, ", "), orNone(strings.Join(resent, ", ")))
}
+1 -1
View File
@@ -591,7 +591,7 @@ func proposeCommand(ctx context.Context, module, node, valuesArg string, clear,
return err
},
routerHere: routerHereIn(open.inventory),
grantHeld: grantHeldIn(open, conn),
grantHeld: grantHeldIn(open),
routerRecord: func(ctx context.Context, id string) (string, error) {
bucket, err := asksRecords(ctx, open.inventory)
if err != nil || bucket == "" {
+14 -30
View File
@@ -249,7 +249,7 @@ func serve(ctx context.Context) (err error) {
// (novox/hq to-be 45 §9).
checkEvents = bus
// And every walk this controller keeps in a new state, for the delivery it walks (novox/hq ADR 0239).
inventory.PlanSaved = func(_ *inventory.Inventory, p inventory.Plan) { sayPlanMoved(ctx, bus, open.inventory, p) }
inventory.PlanSaved = func(p inventory.Plan) { sayPlanMoved(ctx, bus, p) }
if err := server.Checks(following{open}); err != nil {
return err
}
@@ -1084,58 +1084,42 @@ func brokerFirst(names []string, holder string, behind bool) []string {
// send anywhere, and a module running there always put it in its first wave. A digest of the list
// last sent is kept for this (ADR 0043: the list is composed on each push, never kept itself).
func brokerBehind(ctx context.Context, open *stores, names []string) (string, bool, error) {
s, err := brokerListState(ctx, open, names)
return s.Machine, s.Behind, err
}
// brokerListState is brokerBehind with why the list could not be composed, when it could not: the plan's own
// reason, which a remedy names rather than a push that would fail on it (the review of hq issue 353).
func brokerListState(ctx context.Context, open *stores, names []string) (busListState, error) {
inv := open.inventory
holders, err := seatHolders(ctx, inv)
if err != nil {
return busListState{}, err
return "", false, err
}
h, held := holders[theBrokerSeat]
if !held || h.Node == "" {
return busListState{}, nil
return "", false, nil
}
shelf, err := inv.Catalogue(ctx)
if err != nil {
return busListState{}, err
return "", false, err
}
if m, known := shelf[h.Module]; !known || m.BusUsers == "" {
// A holder that is sent no user list carries no grant: nothing to send first.
return busListState{}, nil
return "", false, nil
}
for _, n := range names {
if n == h.Node {
return busListState{Machine: h.Node}, nil
return h.Node, false, nil
}
}
// **What cannot be worked out is behind** (the review of hq issue 353). The list it would be sent cannot be
// composed, so whether it carries the grants a send relies on is not known; it is taken as behind, so a push
// sends that machine first and says why it cannot (`plan` says it too), and a rollout that needs the list
// refuses rather than sending code whose grants the bus may not hold. It said "not behind" until then: a
// send went ahead as if the bus held a list nobody could compose.
list, composeErr := "", error(nil)
plan, _, err := planFor(ctx, open, h.Node)
if err != nil {
composeErr = err
} else if list, _, err = busUserList(ctx, inv, plan.Modules); err != nil {
composeErr = err
// It cannot be worked out: sending it would refuse the whole send, and `plan` says why.
return h.Node, false, nil
}
list, _, err := busUserList(ctx, inv, plan.Modules)
if err != nil {
return h.Node, false, nil
}
sent, err := inv.SentBusUsers(ctx, h.Node)
if err != nil {
return busListState{}, err
return "", false, err
}
return busListState{Machine: h.Node, Behind: listBehind(list, composeErr, sent), Uncomposed: composeErr}, nil
}
// listBehind is whether the bus's machine is behind: the list composed now is not the one last sent, or it
// could not be composed at all — not known is behind, never "not behind".
func listBehind(list string, composeErr error, sentDigest string) bool {
return composeErr != nil || userListBehind(list, sentDigest)
return h.Node, userListBehind(list, sent), nil
}
// userListBehind is whether the user list composed now is not the one last sent, by its digest. An
+3 -81
View File
@@ -8,7 +8,6 @@ import (
"fmt"
"io"
"os"
"regexp"
"sort"
"strings"
"time"
@@ -68,95 +67,18 @@ func listQueue(ctx context.Context, args []string, w io.Writer) error {
if err != nil {
return err
}
now := time.Now()
if *asJSON {
body, err := json.MarshalIndent(queueAnswerOf(q, now), "", " ")
body, err := json.MarshalIndent(q, "", " ")
if err != nil {
return err
}
fmt.Fprintln(w, string(body))
return nil
}
fmt.Fprint(w, queueText(q, now))
fmt.Fprint(w, queueText(q, time.Now()))
return nil
}
// queueAnswer is the queue as data (novox/hq issue 455): what a caller reads to say how far back an ask
// waits — "waiting in the build queue behind 2" — which the table alone could not tell it. Text is the
// table, written from the same read: the verb answers it as its output and the rest as its answer, so the
// two never disagree.
type queueAnswer struct {
Seat string `json:"seat"`
Waiting int `json:"waiting"`
InFlight int `json:"in-flight"`
Dead int `json:"dead"`
MaxDeliver int `json:"max-deliver"`
Asks []queuedAnswer `json:"asks"`
Text string `json:"text"`
}
// queuedAnswer is one ask as data. Never what the request carries beyond its source — not `held`, every
// artifact the mesh has built, nor a check's checkouts beside it.
type queuedAnswer struct {
ID string `json:"id"`
State string `json:"state"`
// Kind is "check" for a pull request's merge check, "build" for anything else.
Kind string `json:"kind"`
Repository string `json:"repository"`
Path string `json:"path,omitempty"`
Ref string `json:"ref,omitempty"`
// Commit is the ref when it names a commit; empty when the ask follows a branch or the default.
Commit string `json:"commit,omitempty"`
// Machine is the one building an ask in flight; WasOn the one that started it and handed it back.
Machine string `json:"machine,omitempty"`
WasOn string `json:"was-on,omitempty"`
AskedAt time.Time `json:"asked-at,omitzero"`
// Since is when the ask came to its state: its start on the machine for one in flight that a
// machine said it started, otherwise when it was asked.
Since time.Time `json:"since,omitzero"`
// Position is its place among the waiting, 1 being handed out next; 0 for an ask not waiting.
Position int `json:"position,omitempty"`
Seq uint64 `json:"seq"`
}
// aCommitRef is a ref that names a commit by its full hash (SHA-1 or SHA-256).
var aCommitRef = regexp.MustCompile(`^(?:[0-9a-f]{40}|[0-9a-f]{64})$`)
// queueAnswerOf is the queue as data, in the table's order: in flight, the waiting from the next one to
// be handed out, then the dead. A pure function of one read (novox/hq issue 455).
func queueAnswerOf(q link.Queue, now time.Time) queueAnswer {
waiting, running, dead := q.Of(link.AskWaiting), q.Of(link.AskInFlight), q.Of(link.AskDead)
out := queueAnswer{Seat: q.Seat, Waiting: len(waiting), InFlight: len(running), Dead: len(dead),
MaxDeliver: q.MaxDeliver, Asks: []queuedAnswer{}, Text: queueText(q, now)}
one := func(a link.QueuedAsk, position int) queuedAnswer {
kind := "build"
if a.Request.Check != nil {
kind = "check"
}
since := a.AskedAt
if a.State == link.AskInFlight && a.On != "" && !a.Started.IsZero() {
since = a.Started
}
commit := ""
if aCommitRef.MatchString(a.Ref) {
commit = a.Ref
}
return queuedAnswer{ID: a.ID, State: a.State, Kind: kind, Repository: link.WithoutPassword(a.Repository), Path: a.Path,
Ref: a.Ref, Commit: commit, Machine: a.On, WasOn: a.Was, AskedAt: a.AskedAt, Since: since,
Position: position, Seq: a.Seq}
}
for _, a := range running {
out.Asks = append(out.Asks, one(a, 0))
}
for i, a := range waiting {
out.Asks = append(out.Asks, one(a, i+1))
}
for _, a := range dead {
out.Asks = append(out.Asks, one(a, 0))
}
return out
}
// queueText is the queue as a person reads it: a summary line, then each kind in queue order.
// Never what an ask carries as `held` — that is every artifact the mesh has built.
func queueText(q link.Queue, now time.Time) string {
@@ -170,7 +92,7 @@ func queueText(q link.Queue, now time.Time) string {
return "asked " + now.Sub(t).Round(time.Second).String() + " ago"
}
what := func(a link.QueuedAsk) string {
s := link.WithoutPassword(a.Repository)
s := a.Repository
if a.Path != "" {
s += " at " + a.Path
}
-137
View File
@@ -1,137 +0,0 @@
package main
import (
"encoding/json"
"reflect"
"strings"
"testing"
"time"
"github.com/novox/mesh-controller/internal/link"
)
// The queue answers as data as well as text (novox/hq issue 455): each ask's repository, commit, kind,
// machine, since and position among the waiting, read from the same queue the table is written from.
const aCommit = "0123456789abcdef0123456789abcdef01234567"
func aQueueOfEachKind(now time.Time) link.Queue {
asked := now.Add(-5 * time.Minute)
started := now.Add(-2 * time.Minute)
return link.Queue{Seat: link.TheBuildMachine, Delivered: 2, AckPending: 1, MaxDeliver: 5, Asks: []link.QueuedAsk{
{Seq: 1, ID: "build-dead", Repository: "ssh://forge/novox/x", AskedAt: asked, State: link.AskDead},
{Seq: 2, ID: "build-running", Repository: "ssh://forge/novox/mesh-host", Ref: aCommit, AskedAt: asked,
State: link.AskInFlight, On: "ace", Started: started,
Request: link.BuildRequest{ID: "build-running", Check: &link.CheckRequest{Owner: "novox", Repo: "mesh-host"}}},
{Seq: 3, ID: "build-first", Repository: "ssh://forge/novox/mesh-catalog", Ref: "main", AskedAt: asked,
State: link.AskWaiting},
{Seq: 4, ID: "build-second", Repository: "ssh://forge/novox/mesh-catalog", Path: "modules/gitea", Ref: aCommit,
AskedAt: now.Add(-time.Minute), State: link.AskWaiting,
Request: link.BuildRequest{ID: "build-second", Check: &link.CheckRequest{Owner: "novox", Repo: "mesh-catalog"}}},
}}
}
func TestTheQueueVerbAnswersEachAskAsData(t *testing.T) {
now := time.Date(2026, 10, 12, 12, 0, 0, 0, time.UTC)
q := aQueueOfEachKind(now)
got := queueAnswerOf(q, now)
if got.Waiting != 2 || got.InFlight != 1 || got.Dead != 1 || got.Seat != link.TheBuildMachine {
t.Fatalf("counts: %+v", got)
}
if got.Text != queueText(q, now) {
t.Fatalf("the data's text is not the table read from the same queue:\n%s", got.Text)
}
byID := map[string]queuedAnswer{}
for _, a := range got.Asks {
byID[a.ID] = a
}
running := byID["build-running"]
if running.Kind != "check" || running.Machine != "ace" || running.Commit != aCommit || running.Position != 0 ||
!running.Since.Equal(now.Add(-2*time.Minute)) || running.State != link.AskInFlight {
t.Errorf("in flight: %+v", running)
}
first, second := byID["build-first"], byID["build-second"]
if first.Position != 1 || first.Kind != "build" || first.Commit != "" || first.Ref != "main" || first.Machine != "" ||
!first.Since.Equal(now.Add(-5*time.Minute)) {
t.Errorf("first waiting: %+v", first)
}
if second.Position != 2 || second.Kind != "check" || second.Commit != aCommit || second.Path != "modules/gitea" ||
second.Repository != "ssh://forge/novox/mesh-catalog" {
t.Errorf("second waiting: %+v", second)
}
if dead := byID["build-dead"]; dead.Position != 0 || dead.State != link.AskDead {
t.Errorf("dead: %+v", dead)
}
// In the table's order: in flight, then the waiting by position, then the dead.
var order []string
for _, a := range got.Asks {
order = append(order, a.ID)
}
if want := []string{"build-running", "build-first", "build-second", "build-dead"}; !reflect.DeepEqual(order, want) {
t.Errorf("order %v, want %v", order, want)
}
}
// The verb asks its command for JSON, and its answer carries the data while its output stays the table a
// person reads, so a text caller reads what it always did.
func TestTheQueueVerbKeepsTheTableAndCarriesTheData(t *testing.T) {
argv, err := argvFor("queue", nil)
if err != nil || !reflect.DeepEqual(argv, []string{"queue", "--json"}) {
t.Fatalf("queue's command line: %v %v", argv, err)
}
now := time.Now()
q := aQueueOfEachKind(now)
body, err := json.Marshal(queueAnswerOf(q, now))
if err != nil {
t.Fatal(err)
}
answer := answerOf(argv, body, "", true)
if answer.Output != queueText(q, now) {
t.Fatalf("the output is not the table:\n%s", answer.Output)
}
data, ok := answer.Answer.(map[string]any)
if !ok {
t.Fatalf("no data: %#v", answer.Answer)
}
if _, doubled := data["text"]; doubled {
t.Error("the table is said twice: once as the output and again inside the data")
}
asks, _ := data["asks"].([]any)
if len(asks) != 4 || data["waiting"] != float64(2) {
t.Fatalf("data: %v", data)
}
second := asks[2].(map[string]any)
if second["position"] != float64(2) || second["kind"] != "check" || second["commit"] != aCommit {
t.Errorf("second waiting: %v", second)
}
for _, a := range asks {
if _, held := a.(map[string]any)["held"]; held {
t.Error("an ask carries what the mesh holds")
}
}
// A failure is said as text, as before.
failed := answerOf(argv, nil, "mesh-controller: the bus cannot be reached\n", false)
if failed.Answer != nil || !strings.Contains(failed.Output, "cannot be reached") {
t.Errorf("a failure: %+v", failed)
}
}
// A repository named with a password never shows it, in the table or the data.
func TestTheQueueNeverShowsARepositorysPassword(t *testing.T) {
if got := link.WithoutPassword("https://agent:s3cret@forge.example/novox/x.git"); strings.Contains(got, "s3cret") ||
!strings.Contains(got, "agent@forge.example/novox/x.git") {
t.Errorf("redacted: %s", got)
}
now := time.Now()
q := link.Queue{Seat: link.TheBuildMachine, Asks: []link.QueuedAsk{{Seq: 1, ID: "build-1",
Repository: "https://agent:s3cret@forge.example/novox/x.git", State: link.AskWaiting}}}
body, _ := json.Marshal(queueAnswerOf(q, now))
if strings.Contains(string(body), "s3cret") {
t.Errorf("the queue said a password: %s", body)
}
for _, kept := range []string{"ssh://git@forge:222/novox/x.git", "novox/x", "git@forge:novox/x.git", ""} {
if got := link.WithoutPassword(kept); got != kept {
t.Errorf("%q became %q", kept, got)
}
}
}
+1 -1
View File
@@ -326,7 +326,7 @@ func TestTheQueueVerbsRunTheirCommands(t *testing.T) {
args map[string]any
want []string
}{
{"queue", nil, []string{"queue", "--json"}},
{"queue", nil, []string{"queue"}},
{"cancel", map[string]any{"id": "build-1"}, []string{"cancel", "build-1"}},
{"clear", nil, []string{"clear"}},
{"clear", map[string]any{"dead": "true"}, []string{"clear", "--dead"}},
+1 -1
View File
@@ -80,7 +80,7 @@ func TestAVerbsOwnProcessNamesItsConnection(t *testing.T) {
// A silence acts, so it is still its own process; it dials, and finds no such condition.
_, _ = handlers["conditions"](context.Background(),
json.RawMessage(`{"silence":"bus.nothing.here","for":"1h","why":"a test"}`))
names := closedNames(t, bus, "mesh-controller verb conditions")
names := closedNames(t, bus)
found := false
for _, n := range names {
found = found || n == "mesh-controller verb conditions"
+7 -12
View File
@@ -812,19 +812,14 @@ func backlogCommand(ctx context.Context, sub string, args []string) error {
}
defer open.Close()
if sub == "release-backlog" {
// Said on the bus (novox/hq ADR 0308 decision 1): the release plan starts walking here, and its start is
// said by the verb that opens it.
var p *inventory.Plan
if err := sayingOnTheBus(ctx, open.inventory, func() error {
release, err := open.inventory.HoldPlans(ctx, true)
if err != nil {
return err
}
defer release()
why.record(ctx, "upgrade release-backlog", nil)
p, err = releaseBacklog(ctx, open, link.Caller())
release, err := open.inventory.HoldPlans(ctx, true)
if err != nil {
return err
}); err != nil {
}
defer release()
why.record(ctx, "upgrade release-backlog", nil)
p, err := releaseBacklog(ctx, open, link.Caller())
if err != nil {
return err
}
if p == nil {
+23 -43
View File
@@ -1559,7 +1559,7 @@ func plansCommand(ctx context.Context, args []string) error {
if len(positionals) == 2 && positionals[0] == "go" {
why.record(ctx, "plans go", positionals[1:])
var p inventory.Plan
if err := sayingOnTheBus(ctx, inv, func() (err error) {
if err := sayingOnTheBus(ctx, func() (err error) {
p, err = letGo(ctx, inv, positionals[1], "a person ("+whoAsked()+")", strings.TrimSpace(*why.why))
return err
}); err != nil {
@@ -1571,13 +1571,8 @@ func plansCommand(ctx context.Context, args []string) error {
}
// `retry` (novox/hq ADR 0219): a failed plan's failed builds asked again, and the plan goes on.
if len(positionals) == 2 && positionals[0] == "retry" {
// Said on the bus (novox/hq ADR 0308 decision 1): a retried walk starts again, and its start is said
// by the verb that starts it.
var said string
if err := sayingOnTheBus(ctx, inv, func() (err error) {
said, err = retryPlan(ctx, open, positionals[1])
return err
}); err != nil {
said, err := retryPlan(ctx, open, positionals[1])
if err != nil {
return err
}
fmt.Println(said)
@@ -1591,29 +1586,26 @@ func plansCommand(ctx context.Context, args []string) error {
if positionals[0] == "close" {
how = "closed"
}
// Said on the bus (novox/hq ADR 0308 decision 1): the walk's end, outcome stopped, is said by the verb
// that ends it, so what it touched is not held until its bound.
var p inventory.Plan
if err := sayingOnTheBus(ctx, inv, func() error {
release, err := inv.HoldPlans(ctx, true)
if err != nil {
return err
}
defer release()
if p, err = inv.PlanByID(ctx, positionals[1]); err != nil {
return err
}
if !p.Open() {
return fmt.Errorf("%s is already %s", p.ID, p.State)
}
why.record(ctx, "plans "+positionals[0], positionals[1:])
stopByHand(&p, how, "a person ("+whoAsked()+")", strings.TrimSpace(*why.why))
sayUnsent(&p, func(m string) bool {
u, err := inv.UpgradeOf(ctx, m)
return err == nil && u.RollOut
})
return inv.SavePlan(ctx, &p)
}); err != nil {
release, err := inv.HoldPlans(ctx, true)
if err != nil {
return err
}
defer release()
p, err := inv.PlanByID(ctx, positionals[1])
if err != nil {
return err
}
if !p.Open() {
return fmt.Errorf("%s is already %s", p.ID, p.State)
}
why.record(ctx, "plans "+positionals[0], positionals[1:])
p.State = inventory.PlanFailed
p.Note = how + " by hand at tier " + fmt.Sprint(p.Tier) + ": " + strings.TrimSpace(*why.why)
sayUnsent(&p, func(m string) bool {
u, err := inv.UpgradeOf(ctx, m)
return err == nil && u.RollOut
})
if err := inv.SavePlan(ctx, &p); err != nil {
return err
}
fmt.Printf("%s %s at tier %d of %d; what was asked still builds and registers, nothing further is asked\n",
@@ -1932,15 +1924,3 @@ func forgetDeleted(ctx context.Context, inv *inventory.Inventory, module string,
"`module forget %s`: %v\n", p.ID, module, module, firstLine(err.Error()))
}
}
// stopByHand ends a walk a person stopped or closed (`plans stop|close`): failed, with who stopped it and why
// kept as the delivery's owner keeps its own stop, so the walk ends with outcome stopped, not failed (novox/hq
// ADR 0308 decision 1).
func stopByHand(p *inventory.Plan, how, by, why string) {
p.State = inventory.PlanFailed
p.Note = how + " by hand at tier " + fmt.Sprint(p.Tier) + ": " + why
if p.Delivery == nil {
p.Delivery = &inventory.PlanDelivery{}
}
p.Delivery.Stopped, p.Delivery.StoppedWhy = by, why
}
-85
View File
@@ -1,85 +0,0 @@
package main
import (
"bytes"
"io"
"os"
"strings"
"testing"
"github.com/novox/mesh-controller/internal/catalogue"
)
// TestReplay237 replays novox/hq issue 237 (2026-10-04): a workstation already ran a module that
// depends on a node seat nothing there held, and the module holding that seat was assigned to it. The
// answer said the seat was now held, and then that the workstation was left out of the rest of the mesh
// for lack of it, naming as the remedy the assignment just made. `plan` for the node, right after,
// resolved. The outcome asserted: every line of the answer, as the controller seat's verb gives it
// (standard output, then standard error), agrees with `plan` for the node right after the act. Written
// with only what the controller had before its fix — register, assign's command, planFor — so it is laid
// over the commit before.
func TestReplay237(t *testing.T) {
open := aMesh(t)
ctx := t.Context()
register(t, open, aContainer("web"))
register(t, open, catalogue.Manifest{Module: "docker", Version: "1",
Claims: []catalogue.Claim{{Name: catalogue.ContainerRuntimeSeat, Scope: catalogue.ScopeNode}}})
// Already on the node, from before the rule refused it: the node does not resolve until the
// holder comes.
if _, err := open.inventory.Assign(ctx, "laptop", "web"); err != nil {
t.Fatal(err)
}
said := answered(t, func() error { return assignCommand(ctx, "assign", []string{"laptop", "docker"}) })
if _, _, err := planFor(ctx, open, "laptop"); err != nil {
t.Fatalf("laptop does not resolve right after the act: %v\nthe answer was:\n%s", err, said)
}
if !strings.Contains(said, "web on laptop now has "+catalogue.ContainerRuntimeSeat+" held") {
t.Errorf("the answer does not say the seat is now held:\n%s", said)
}
for _, not := range []string{"laptop is left out", "does not resolve", "which nothing on laptop holds"} {
if strings.Contains(said, not) {
t.Errorf("the answer says %q, which `plan` right after contradicts:\n%s", not, said)
}
}
}
// answered is what a command says as the controller seat's verb answers it: standard output, then
// standard error (answerOf).
func answered(t *testing.T, f func() error) string {
t.Helper()
read := func(w **os.File) (func() string, error) {
old := *w
r, pw, err := os.Pipe()
if err != nil {
return nil, err
}
*w = pw
got := make(chan string)
go func() {
var buf bytes.Buffer
_, _ = io.Copy(&buf, r)
got <- buf.String()
}()
return func() string {
_ = pw.Close()
*w = old
return <-got
}, nil
}
stdout, err := read(&os.Stdout)
if err != nil {
t.Fatal(err)
}
stderr, err := read(&os.Stderr)
if err != nil {
t.Fatal(err)
}
runErr := f()
said := stdout() + stderr()
if runErr != nil {
t.Fatalf("%v\n%s", runErr, said)
}
return said
}
+3 -11
View File
@@ -84,12 +84,8 @@ func asAProcess(t *testing.T, url string) {
t.Setenv(broker.CertificateVar, "")
}
// closedNames are the names of the connections the bus saw closed, waited for by want's own name: the
// bus can register another connection's close first (the test's own setup connection, say), so returning
// on the first non-empty list names whichever closed first, not necessarily the one being waited for
// (novox/hq issue 543). closedNames instead waits until want itself appears among the closed connections,
// or the deadline passes, and returns whatever names it last saw either way.
func closedNames(t *testing.T, bus *server.Server, want string) []string {
// closedNames are the names of the connections the bus saw closed.
func closedNames(t *testing.T, bus *server.Server) []string {
t.Helper()
deadline := time.Now().Add(5 * time.Second)
var names []string
@@ -99,14 +95,10 @@ func closedNames(t *testing.T, bus *server.Server, want string) []string {
t.Fatal(err)
}
names = names[:0]
found := false
for _, c := range connz.Conns {
names = append(names, c.Name)
if c.Name == want {
found = true
}
}
if found {
if len(names) > 0 {
return names
}
time.Sleep(50 * time.Millisecond)
@@ -15,8 +15,7 @@ import (
func serviceManagerHolder() catalogue.Manifest {
return catalogue.Manifest{Module: "systemd", Version: "1",
Claims: []catalogue.Claim{{Name: catalogue.ServiceManagerSeat, Scope: catalogue.ScopeNode,
Serves: []string{"units", "status", "start", "stop", "restart", "enable", "disable", "journal",
"reset-failed", "wanted-by", "unlink-dangling"}}},
Serves: []string{"units", "status", "start", "stop", "restart", "enable", "disable", "journal"}}},
Resources: []map[string]any{{"id": "systemd", "type": "package", "package": "systemd"}}}
}
+3 -24
View File
@@ -314,11 +314,6 @@ func (a *verbArguments) commandLine() ([]string, error) {
return nil, err
}
return []string{"node", "show", str("node")}, nil
case "judge-directories":
if err := need("node"); err != nil {
return nil, err
}
return []string{"node", "judge-directories", str("node")}, nil
case "modules":
return []string{"module", "list", "--json"}, nil
case "seats":
@@ -431,8 +426,7 @@ func (a *verbArguments) commandLine() ([]string, error) {
return argv, nil
// The build queue (novox/hq ADR 0219).
case "queue":
// As data, the table its output (novox/hq issue 455).
return []string{"queue", "--json"}, nil
return []string{"queue"}, nil
case "cancel", "kill":
if err := need("id"); err != nil {
return nil, err
@@ -983,14 +977,7 @@ var jsonVerbs = map[string]bool{"status": true, "seats": true, "plan": true, "co
// What the records say the registries may keep (novox/hq ADR 0251).
"artifacts": true, "collect": true, "images": true, "mirrors": true,
// The delivery's owner's verbs answer JSON where they read (plan, order, check, walks) — novox/hq ADR 0239.
"delivery": true,
// The build queue, each ask with its position among the waiting (novox/hq issue 455).
"queue": true}
// tableBesideVerbs are the JSON verbs whose document carries the table a person reads as its `text`: the
// verb answers that table as its output, as it did before it answered data, and the rest as `answer` —
// both from the one read, so they never disagree (novox/hq issue 455).
var tableBesideVerbs = map[string]bool{"queue": true}
"delivery": true}
// overviewVerbs are the JSON verbs whose answer is said once, as data, and not again as the text the
// command printed: the overviews, which grow with the mesh (novox/hq issue 314). Every reader of theirs
@@ -1110,12 +1097,6 @@ func answerOf(argv []string, stdout []byte, stderr string, ok bool) verbAnswer {
var parsed any
if json.Unmarshal(bytes.TrimSpace(stdout), &parsed) == nil {
answer.Answer = parsed
if doc, isDoc := parsed.(map[string]any); isDoc && tableBesideVerbs[argv[0]] {
if table, said := doc["text"].(string); said {
answer.Output = table + stderr
delete(doc, "text")
}
}
if overviewVerbs[argv[0]] {
// Once, as data: the same document again as text doubled an answer that already
// outgrew one message of the bus (novox/hq issue 314).
@@ -1498,9 +1479,7 @@ func seatAnnouncement(handlers map[string]link.ToolHandler) micro.Info {
}
// nodeReads are the `node` subcommands a verb may run: the ones that only read.
var nodeReads = map[string]bool{"list": true, "show": true,
// Read-only on the node too: the engine judges its directories and changes nothing (novox/hq issue 358).
"judge-directories": true}
var nodeReads = map[string]bool{"list": true, "show": true}
// flagsOnly says a command line's rest names no subcommand: empty, or beginning with a flag. For a command
// with no subcommands every word is a flag, its value or a name it reads.
+1 -1
View File
@@ -256,7 +256,7 @@ func stringLit(e ast.Expr) (string, bool) {
var accountedFlags = map[string]map[string]string{
"status": {"json": "set by the verb: the answer is data"},
"seats": {"json": "set by the verb: the answer is data"},
"queue": {"json": "set by the verb: the answer is data, its output the table (novox/hq issue 455)"},
"queue": {"json": "not set: the verb answers the table a person reads"},
"plan": {"json": "set by the verb unless files is asked"},
"push": {
"wait": "set by the verb to 0: a tool call cannot hold a connection for a whole apply",
+1 -1
View File
@@ -172,7 +172,7 @@ func composeStatus(open *stores) func(context.Context) ([]byte, error) {
var readingVerbs = map[string]bool{
"tools": true, "calls": true, "status": true, "nodes": true, "node": true, "modules": true,
"seats": true, "builds": true, "plan": true, "queue": true, "durations": true, "hand-acts": true,
"doctor": true, "conditions": true, "healers": true, "judge-directories": true,
"doctor": true, "conditions": true, "healers": true,
}
// nudgingListener is the enrolment, nudging the summary when a machine said something new.
-334
View File
@@ -1,334 +0,0 @@
package main
import (
"context"
"fmt"
"os"
"slices"
"sort"
"time"
"github.com/novox/mesh-controller/internal/broker"
"github.com/novox/mesh-controller/internal/catalogue"
"github.com/novox/mesh-controller/internal/inventory"
)
// What a walk touches, its bound and its outcome (novox/hq ADR 0308 decision 1, decision 5): said in
// `plan-moved` on the save that starts the walk and the save that ends it, beside the walk whole, for the holder
// of the operator's channel to hold what the walk touches while it runs and tell its result once.
//
// **What a walk touches** is every module it moves on every machine it sends it to, and every module a moved
// tool runner (node-tools) or node-engine (mesh-host) carries on that machine: what restarts there. At the start
// that is what the walk will send — each module of its tiers whose policy rolls it out, on every machine running
// it; at the end it is what it reached — the machines each module was sent to, first and rest, and what a gated
// send carried with it.
//
// **Its bound** is twice the largest delivery budget among the walk's deliveries (deliveryBudgets: a core
// module's ten minutes, a leaf module's budget in force), and fifteen minutes, not doubled, for a walk none of
// whose deliveries has a budget: a release plan (builds waiting for a person's gate), a walk whose every module's
// policy records rather than rolls out (held for a person, ADR 0282 decision 1), or a walk kept without a class.
// walkNoBudgetBound is the bound of a walk with no budget (ADR 0308 decision 5): not doubled.
const walkNoBudgetBound = 15 * time.Minute
// budgetNone is the budget class of a walk none of whose deliveries has a budget.
const budgetNone = "none"
// walkSaid is what `plan-moved` adds on a walk's start and end, beside the walk whole.
type walkSaid struct {
Walk string `json:"walk"`
Phase string `json:"phase"`
// Touches is, per machine, the modules the walk moves or reaches there and what a moved tool runner or
// node-engine carries there; never null.
Touches []walkTouch `json:"touches"`
// Outcome is on the end only: delivered, failed or stopped.
Outcome string `json:"outcome,omitempty"`
// BoundSeconds and BudgetClass are said on both, read from the walk's class at the start.
BoundSeconds int `json:"bound_seconds"`
BudgetClass string `json:"budget_class"`
// StartedAt is when the walk was said started, on both; EndedAt when it was said ended, on the end: the
// bound runs from StartedAt, whenever the event is heard.
StartedAt *time.Time `json:"started_at,omitempty"`
EndedAt *time.Time `json:"ended_at,omitempty"`
}
// walkTouch is what a walk touches on one machine.
type walkTouch struct {
Machine string `json:"machine"`
Modules []string `json:"modules"`
// Carried names those of Modules that are there only because a moved tool runner or node-engine carries
// them: what restarts with it, not what the walk builds.
Carried []string `json:"carried,omitempty"`
}
// planMovedBody is `plan-moved`'s body: the walk whole, as before, and on its start and end what it touches.
type planMovedBody struct {
inventory.Plan
*walkSaid
}
// walkFacts is what the touches are read from: the controller's inventory.
type walkFacts interface {
Running(ctx context.Context, module string) ([]string, error)
UpgradeOf(ctx context.Context, module string) (inventory.Upgrade, error)
Assigned(ctx context.Context, node string) ([]string, error)
SentBuilds(ctx context.Context, node string) (map[string]string, bool, error)
Catalogue(ctx context.Context) (map[string]catalogue.Manifest, error)
}
// sayWalk is what `plan-moved` adds to the save that started or ended the walk; nil on every other save. A fact
// that cannot be read is said on the controller's log and left out, never in the way of the event: a walk said
// with fewer touches is held less, never longer.
func sayWalk(ctx context.Context, facts walkFacts, p inventory.Plan) *walkSaid {
if p.WalkSaid == "" {
return nil
}
w := &walkSaid{Walk: p.ID, Phase: p.WalkSaid}
if p.Times != nil {
w.StartedAt = p.Times.Started
if p.WalkSaid == inventory.WalkEnded {
w.EndedAt, w.Outcome = p.Times.Ended, p.Outcome()
}
}
read := readWalkFacts(ctx, facts, p)
w.BudgetClass = walkBudgetClass(p, read.rollsOut)
w.BoundSeconds = int(walkBound(w.BudgetClass) / time.Second)
var moved map[string][]string
if p.WalkSaid == inventory.WalkStarted {
moved = walkSends(p, read.running, read.rollsOut)
} else {
moved = walkReached(p, read.running)
}
var shelf map[string]catalogue.Manifest
if len(moved[broker.RuntimeModule]) > 0 {
// Which modules the tool runner serves is the catalogue's: read only when the walk moves it.
shelf = read.shelf()
}
w.Touches = touchesOf(moved, read.onMachine(moved), shelf)
return w
}
// walkBudgetClass is the largest budget class among the walk's deliveries: its class read at the cut when one of
// its modules rolls out, and none when it has no budget.
func walkBudgetClass(p inventory.Plan, rollsOut func(string) bool) string {
if p.Release != nil || p.Times == nil {
return budgetNone
}
if _, budgeted := deliveryBudgets[p.Times.Class]; !budgeted {
return budgetNone
}
for _, tier := range p.Tiers {
for _, m := range tier {
if rollsOut(m) {
return p.Times.Class
}
}
}
return budgetNone
}
// walkBound is a walk's bound by its budget class: twice its budget, or fifteen minutes with none.
func walkBound(class string) time.Duration {
if b, ok := deliveryBudgets[class]; ok {
return 2 * b
}
return walkNoBudgetBound
}
// walkSends is what a walk will send at its start, per module the machines it goes to: each module of its tiers
// whose policy rolls it out, on every machine running it (for a release plan, those of its order).
func walkSends(p inventory.Plan, running func(string) []string, rollsOut func(string) bool) map[string][]string {
out := map[string][]string{}
for _, tier := range p.Tiers {
for _, m := range tier {
if s := p.Modules[m]; s != nil && s.State == planDeleted {
continue
}
if p.Release == nil && !rollsOut(m) {
continue
}
for _, n := range running(m) {
if p.Release != nil && !slices.Contains(p.Release.Order, n) {
continue
}
out[m] = appendNew(out[m], n)
}
}
}
return out
}
// walkReached is what a walk sent by its end, per module the machines it reached: its first machines, its rest,
// and every module a gated send carried with it. A release plan reached the machines it walked: those done and
// the one being judged.
func walkReached(p inventory.Plan, running func(string) []string) map[string][]string {
out := map[string][]string{}
carried := func(g *inventory.PlanGate) {
if g == nil {
return
}
for _, c := range g.Carried {
out[c.Module] = appendNew(out[c.Module], c.Node)
}
}
if r := p.Release; r != nil {
reached := append([]string{}, r.Done...)
if r.Gate != nil {
reached = appendNew(reached, r.Gate.Machines...)
carried(r.Gate)
}
for _, tier := range p.Tiers {
for _, m := range tier {
for _, n := range running(m) {
if slices.Contains(reached, n) {
out[m] = appendNew(out[m], n)
}
}
}
}
return out
}
for m, s := range p.Modules {
if s == nil {
continue
}
out[m] = appendNew(out[m], s.First...)
for n := range s.Rest {
out[m] = appendNew(out[m], n)
}
carried(s.Gate)
if len(out[m]) == 0 {
delete(out, m)
}
}
return out
}
// touchesOf turns what a walk moves, per module, into what it touches, per machine: the modules it moves there,
// and, where it moves the tool runner, every module there whose tools it serves, and where it moves the
// node-engine, every module there. Sorted by machine and module.
func touchesOf(moved map[string][]string, on map[string][]string, shelf map[string]catalogue.Manifest) []walkTouch {
byMachine := map[string][]string{}
for m, machines := range moved {
for _, n := range machines {
byMachine[n] = appendNew(byMachine[n], m)
}
}
out := make([]walkTouch, 0, len(byMachine))
for n, modules := range byMachine {
t := walkTouch{Machine: n, Modules: modules}
engine, runner := slices.Contains(modules, hostModule), slices.Contains(modules, broker.RuntimeModule)
if engine || runner {
for _, m := range on[n] {
if slices.Contains(t.Modules, m) || (!engine && !servesTools(shelf[m])) {
continue
}
t.Modules = append(t.Modules, m)
t.Carried = append(t.Carried, m)
}
}
sort.Strings(t.Modules)
sort.Strings(t.Carried)
out = append(out, t)
}
sort.Slice(out, func(i, j int) bool { return out[i].Machine < out[j].Machine })
return out
}
// servesTools says the tool runner serves something of this module: a bundle it loads entrypoints from, or the
// module's own tools.
func servesTools(m catalogue.Manifest) bool {
if len(m.Tools) > 0 {
return true
}
for _, b := range m.Bundles {
if len(b.Loads) > 0 {
return true
}
}
return false
}
// walkRead is the facts a walk's touches are worked out from, read once per event.
type walkRead struct {
running func(string) []string
rollsOut func(string) bool
onMachine func(moved map[string][]string) map[string][]string
shelf func() map[string]catalogue.Manifest
}
// readWalkFacts reads what the walk's touches need. Without facts (a test, a command with no store), nothing runs
// anywhere and every module rolls out: the touches are then what the walk itself recorded.
func readWalkFacts(ctx context.Context, facts walkFacts, p inventory.Plan) walkRead {
cantRead := func(what string, err error) {
fmt.Fprintf(os.Stderr, "%s: %s cannot be read for what the walk touches: %v\n", p.ID, what, err)
}
r := walkRead{
running: func(string) []string { return nil },
rollsOut: func(string) bool { return true },
onMachine: func(map[string][]string) map[string][]string { return nil },
shelf: func() map[string]catalogue.Manifest { return nil },
}
if facts == nil {
return r
}
running := map[string][]string{}
r.running = func(m string) []string {
if on, read := running[m]; read {
return on
}
on, err := facts.Running(ctx, m)
if err != nil {
cantRead("where "+m+" runs", err)
}
running[m] = on
return on
}
rolls := map[string]bool{}
r.rollsOut = func(m string) bool {
if yes, read := rolls[m]; read {
return yes
}
u, err := facts.UpgradeOf(ctx, m)
if err != nil {
cantRead(m+"'s policy", err)
}
// A policy that cannot be read is taken to roll out: the walk is then held more, never less.
rolls[m] = err != nil || u.RollOut
return rolls[m]
}
r.onMachine = func(moved map[string][]string) map[string][]string {
out := map[string][]string{}
for _, core := range []string{hostModule, broker.RuntimeModule} {
for _, n := range moved[core] {
if _, read := out[n]; read {
continue
}
var there []string
if sent, known, err := facts.SentBuilds(ctx, n); err != nil {
cantRead("what "+n+" was sent", err)
} else if known {
for m := range sent {
there = append(there, m)
}
}
if assigned, err := facts.Assigned(ctx, n); err != nil {
cantRead("what "+n+" is assigned", err)
} else {
there = appendNew(there, assigned...)
}
sort.Strings(there)
out[n] = there
}
}
return out
}
r.shelf = func() map[string]catalogue.Manifest {
shelf, err := facts.Catalogue(ctx)
if err != nil {
cantRead("the catalogue", err)
}
return shelf
}
return r
}
-514
View File
@@ -1,514 +0,0 @@
package main
import (
"context"
"encoding/json"
"os"
"reflect"
"testing"
"time"
"github.com/nats-io/nats.go"
"github.com/novox/mesh-controller/internal/broker"
"github.com/novox/mesh-controller/internal/catalogue"
"github.com/novox/mesh-controller/internal/inventory"
"github.com/novox/mesh-controller/internal/link"
"github.com/novox/mesh-controller/internal/testbus"
)
// fakeWalkFacts is the inventory as far as a walk's touches read it.
type fakeWalkFacts struct {
running map[string][]string
records map[string]bool // modules whose policy records rather than rolls out
sent map[string]map[string]string
assigned map[string][]string
shelf map[string]catalogue.Manifest
}
func (f fakeWalkFacts) Running(_ context.Context, m string) ([]string, error) {
return f.running[m], nil
}
func (f fakeWalkFacts) UpgradeOf(_ context.Context, m string) (inventory.Upgrade, error) {
return inventory.Upgrade{RollOut: !f.records[m]}, nil
}
func (f fakeWalkFacts) Assigned(_ context.Context, n string) ([]string, error) {
return f.assigned[n], nil
}
func (f fakeWalkFacts) SentBuilds(_ context.Context, n string) (map[string]string, bool, error) {
s, ok := f.sent[n]
return s, ok, nil
}
func (f fakeWalkFacts) Catalogue(context.Context) (map[string]catalogue.Manifest, error) {
return f.shelf, nil
}
// theMesh is four machines: the tool runner on each, messenger and mesh-issues on novox, gitea on ace.
func theMesh() fakeWalkFacts {
return fakeWalkFacts{
running: map[string][]string{
broker.RuntimeModule: {"ace", "g14", "novox", "shanks"},
"messenger": {"novox"},
"gitea": {"ace"},
"plex": {"ace"},
},
sent: map[string]map[string]string{
"novox": {broker.RuntimeModule: "c0", "messenger": "c1", "mesh-issues": "c2", "postgres": "c3"},
"ace": {broker.RuntimeModule: "c0", "gitea": "c4"},
},
assigned: map[string][]string{"g14": {broker.RuntimeModule, "desktop"}, "shanks": {broker.RuntimeModule}},
shelf: map[string]catalogue.Manifest{
"messenger": {Module: "messenger", Tools: []string{"notify"}},
"mesh-issues": {Module: "mesh-issues", Bundles: []catalogue.Bundle{{Name: "tools", Loads: []string{"main"}}}},
"postgres": {Module: "postgres"},
"gitea": {Module: "gitea", Tools: []string{"gitea_api"}},
"desktop": {Module: "desktop", Tools: []string{"notify_send"}},
},
}
}
func walkOfTiers(class string, tiers ...[]string) inventory.Plan {
cut := time.Date(2026, 10, 12, 11, 0, 0, 0, time.UTC)
started := cut.Add(time.Second)
p := inventory.Plan{ID: "plan-308", State: inventory.PlanBuilding, Tiers: tiers,
Modules: map[string]*inventory.PlanModule{}, Times: &inventory.PlanTimes{Cut: &cut, Class: class, Started: &started}}
for _, tier := range tiers {
for _, m := range tier {
p.Modules[m] = &inventory.PlanModule{}
}
}
p.WalkSaid = inventory.WalkStarted
return p
}
// novox/hq ADR 0308 How it is checked §1: the start names the modules the walk moves and the machines it sends
// them to, and every module a moved tool runner carries there.
func TestAWalksStartNamesWhatItTouchesWithWhatTheToolRunnerCarries(t *testing.T) {
p := walkOfTiers(inventory.ClassCore, []string{broker.RuntimeModule}, []string{"messenger"})
w := sayWalk(t.Context(), theMesh(), p)
if w == nil || w.Walk != "plan-308" || w.Phase != inventory.WalkStarted || w.Outcome != "" {
t.Fatalf("the start is said: %+v", w)
}
want := []walkTouch{
{Machine: "ace", Modules: []string{"gitea", broker.RuntimeModule}, Carried: []string{"gitea"}},
{Machine: "g14", Modules: []string{"desktop", broker.RuntimeModule}, Carried: []string{"desktop"}},
// postgres serves no tools: the tool runner does not carry it.
{Machine: "novox", Modules: []string{"mesh-issues", "messenger", broker.RuntimeModule}, Carried: []string{"mesh-issues"}},
{Machine: "shanks", Modules: []string{broker.RuntimeModule}},
}
if !reflect.DeepEqual(w.Touches, want) {
t.Fatalf("touches:\n got %+v\nwant %+v", w.Touches, want)
}
if w.BudgetClass != inventory.ClassCore || w.BoundSeconds != 1200 || w.StartedAt == nil {
t.Fatalf("a core walk is bound at 20 minutes: %+v", w)
}
}
// A moved node-engine carries every module on its machine; a module whose policy records is not sent, and not
// touched.
func TestAMovedNodeEngineCarriesEverythingOnItsMachine(t *testing.T) {
f := theMesh()
f.running[hostModule] = []string{"novox"}
f.records = map[string]bool{"plex": true}
p := walkOfTiers(inventory.ClassCore, []string{hostModule, "plex"})
w := sayWalk(t.Context(), f, p)
want := []walkTouch{{Machine: "novox",
Modules: []string{"mesh-host", "mesh-issues", "messenger", "node-tools", "postgres"},
Carried: []string{"mesh-issues", "messenger", "node-tools", "postgres"}}}
if !reflect.DeepEqual(w.Touches, want) {
t.Fatalf("touches:\n got %+v\nwant %+v", w.Touches, want)
}
}
// The end names what the walk reached — its first machines, its rest, what a gated send carried — and its
// outcome; the modules a reached tool runner carries are touched there too.
func TestAWalksEndNamesWhatItReachedAndItsOutcome(t *testing.T) {
p := walkOfTiers(inventory.ClassCore, []string{broker.RuntimeModule}, []string{"messenger"})
ended := p.Times.Started.Add(4 * time.Minute)
p.Times.Ended = &ended
p.State, p.WalkSaid = inventory.PlanDone, inventory.WalkEnded
p.Modules[broker.RuntimeModule] = &inventory.PlanModule{First: []string{"shanks"},
Rest: map[string]inventory.SentDeclaration{"novox": {}},
Gate: &inventory.PlanGate{Carried: []inventory.CarriedMove{{Module: "gitea", Node: "shanks"}}}}
// messenger was built and found unchanged: no move, not reached.
p.Modules["messenger"] = &inventory.PlanModule{Why: "no move"}
w := sayWalk(t.Context(), theMesh(), p)
if w.Phase != inventory.WalkEnded || w.Outcome != inventory.WalkDelivered || w.EndedAt == nil {
t.Fatalf("the end is said with its outcome: %+v", w)
}
want := []walkTouch{
{Machine: "novox", Modules: []string{"mesh-issues", "messenger", broker.RuntimeModule},
Carried: []string{"mesh-issues", "messenger"}},
{Machine: "shanks", Modules: []string{"gitea", broker.RuntimeModule}},
}
if !reflect.DeepEqual(w.Touches, want) {
t.Fatalf("touches:\n got %+v\nwant %+v", w.Touches, want)
}
for outcome, end := range map[string]func(*inventory.Plan){
inventory.WalkFailed: func(p *inventory.Plan) { p.State = inventory.PlanFailed },
inventory.WalkStopped: func(p *inventory.Plan) {
p.State, p.Delivery = inventory.PlanFailed, &inventory.PlanDelivery{Stopped: "a person"}
},
} {
q := p
end(&q)
if got := sayWalk(t.Context(), theMesh(), q).Outcome; got != outcome {
t.Errorf("outcome %q, want %q", got, outcome)
}
}
}
// novox/hq ADR 0308 How it is checked §1 and decision 5: the bound is twice the largest budget in force among
// the walk's deliveries — 20 minutes for a core walk, twice the leaf budget for a leaf walk — and 15 minutes, not
// doubled, for a walk none of whose deliveries has a budget.
func TestAWalksBoundIsTwiceItsBudgetOrFifteenMinutesWithNone(t *testing.T) {
f := theMesh()
f.records = map[string]bool{"plex": true}
release := walkOfTiers("", []string{"gitea"})
release.Times, release.Release = &inventory.PlanTimes{}, &inventory.PlanRelease{Order: []string{"ace"}}
for name, c := range map[string]struct {
p inventory.Plan
class string
bound int
}{
"core": {walkOfTiers(inventory.ClassCore, []string{"messenger"}), inventory.ClassCore, 1200},
"leaf": {walkOfTiers(inventory.ClassLeaf, []string{"messenger"}), inventory.ClassLeaf, int(2 * deliveryBudgets[inventory.ClassLeaf] / time.Second)},
"held for a person": {walkOfTiers(inventory.ClassLeaf, []string{"plex"}), budgetNone, 900},
"a release": {release, budgetNone, 900},
"kept without a class": {walkOfTiers("", []string{"messenger"}), budgetNone, 900},
} {
w := sayWalk(t.Context(), f, c.p)
if w.BudgetClass != c.class || w.BoundSeconds != c.bound {
t.Errorf("%s: %s bound %ds, want %s %ds", name, w.BudgetClass, w.BoundSeconds, c.class, c.bound)
}
}
// The leaf budget in force is three minutes (ADR 0304 decision 4): a leaf walk is bound at six.
if deliveryBudgets[inventory.ClassLeaf] == 3*time.Minute {
if w := sayWalk(t.Context(), f, walkOfTiers(inventory.ClassLeaf, []string{"messenger"})); w.BoundSeconds != 360 {
t.Errorf("a leaf walk at a three-minute budget is bound at 360 s: %d", w.BoundSeconds)
}
}
}
// plan-moved's body: the walk whole as before, and on its start the walk's fields beside it; on any other save
// none of them.
func TestPlanMovedCarriesTheWalkWholeAndOnItsStartWhatItTouches(t *testing.T) {
p := walkOfTiers(inventory.ClassLeaf, []string{"messenger"})
body, err := json.Marshal(planMovedBody{Plan: p, walkSaid: sayWalk(t.Context(), theMesh(), p)})
if err != nil {
t.Fatal(err)
}
var said map[string]any
if err := json.Unmarshal(body, &said); err != nil {
t.Fatal(err)
}
for _, k := range []string{"id", "state", "tiers", "modules", "times", "walk", "phase", "touches", "bound_seconds", "budget_class", "started_at"} {
if _, ok := said[k]; !ok {
t.Errorf("plan-moved lacks %q: %s", k, body)
}
}
if _, ok := said["outcome"]; ok {
t.Errorf("a start says no outcome: %s", body)
}
if said["walk"] != "plan-308" || said["phase"] != "started" || said["budget_class"] != "leaf" {
t.Errorf("the walk's fields: %s", body)
}
p.WalkSaid = ""
body, _ = json.Marshal(planMovedBody{Plan: p, walkSaid: sayWalk(t.Context(), theMesh(), p)})
said = map[string]any{}
_ = json.Unmarshal(body, &said)
for _, k := range []string{"walk", "phase", "touches", "bound_seconds"} {
if _, ok := said[k]; ok {
t.Errorf("a save neither starting nor ending the walk says %q: %s", k, body)
}
}
// A walk that touches nothing says an empty list, never null.
q := walkOfTiers(inventory.ClassLeaf, []string{"nobody-runs-this"})
body, _ = json.Marshal(planMovedBody{Plan: q, walkSaid: sayWalk(t.Context(), theMesh(), q)})
said = map[string]any{}
_ = json.Unmarshal(body, &said)
if touches, ok := said["touches"].([]any); !ok || len(touches) != 0 {
t.Errorf("touches nothing: %s", body)
}
}
// Live, with the store and a bus: a walk let go by the delivery's verb is said started with what it touches and
// its bound, and stopped by the verb is said ended, stopped (novox/hq ADR 0308 How it is checked §1).
func TestAWalkLetGoAndStoppedByVerbsIsSaidStartedAndEnded(t *testing.T) {
open := aMesh(t)
ctx := t.Context()
next := planMovedHeard(t)
register(t, open, catalogue.Manifest{Module: "app", Version: "1"})
if _, err := assign(ctx, open, "anchor", "app"); err != nil {
t.Fatal(err)
}
cut := time.Now().UTC()
waiting := inventory.Plan{ID: "plan-308-live", Repository: "novox/mesh-catalog", Branch: "main", Commit: "c8c8c8c8",
Created: cut, State: inventory.PlanBuilding, Tiers: [][]string{{"app"}},
Modules: map[string]*inventory.PlanModule{"app": {}},
Delivery: &inventory.PlanDelivery{Awaits: catalogue.DeliverySeat},
Times: &inventory.PlanTimes{Cut: &cut, Class: inventory.ClassLeaf}}
if err := open.inventory.SavePlan(ctx, &waiting); err != nil {
t.Fatal(err)
}
if err := deliveryCommand(ctx, []string{"go", waiting.ID, "--why", "its turn"}); err != nil {
t.Fatal(err)
}
started := next(inventory.WalkStarted)
touches, _ := json.Marshal(started["touches"])
if started["walk"] != waiting.ID || string(touches) != `[{"machine":"anchor","modules":["app"]}]` ||
started["budget_class"] != inventory.ClassLeaf ||
started["bound_seconds"] != float64(2*deliveryBudgets[inventory.ClassLeaf]/time.Second) {
t.Fatalf("the start: %v", started)
}
if err := deliveryCommand(ctx, []string{"stop", waiting.ID, "--why", "a test", "--by", "a person"}); err != nil {
t.Fatal(err)
}
ended := next(inventory.WalkEnded)
touches, _ = json.Marshal(ended["touches"])
if ended["walk"] != waiting.ID || ended["outcome"] != inventory.WalkStopped || string(touches) != `[]` {
t.Fatalf("the end, which sent nothing: %v", ended)
}
}
// planMovedHeard raises a bus of the test's own, points the verbs' hand-act connection at it, and returns what
// waits for the next plan-moved said with the given phase, failing the test when none comes within 5 s.
func planMovedHeard(t *testing.T) func(phase string) map[string]any {
t.Helper()
js, err := broker.Dial(testbus.URL(t))
if err != nil {
t.Fatal(err)
}
t.Cleanup(js.Close)
if err := broker.AssertMeshStreams(js); err != nil {
t.Fatal(err)
}
before := handActConn
handActConn = js.Conn()
t.Cleanup(func() { handActConn = before })
heard := make(chan *nats.Msg, 64)
sub, err := js.Conn().ChanSubscribe(link.SeatEventSubject(link.MeshControllerSeat, link.KeyPlanMoved), heard)
if err != nil {
t.Fatal(err)
}
t.Cleanup(func() { _ = sub.Unsubscribe() })
return func(phase string) map[string]any {
t.Helper()
deadline := time.After(5 * time.Second)
for {
select {
case m := <-heard:
var said map[string]any
if err := json.Unmarshal(m.Data, &said); err != nil {
t.Fatal(err)
}
if said["phase"] == phase {
return said
}
case <-deadline:
t.Fatalf("no walk was said %s", phase)
}
}
}
}
// Live, with the store and a bus: a walk a person stops with `plans stop` is said ended, outcome stopped, by the
// verb itself, and is kept stopped by that person; `plans close` ends one the same way (novox/hq ADR 0308
// decision 1, review 15 on mesh-controller#247).
func TestAWalkStoppedOrClosedByAPersonIsSaidEndedStopped(t *testing.T) {
open := aMesh(t)
ctx := t.Context()
next := planMovedHeard(t)
register(t, open, catalogue.Manifest{Module: "app", Version: "1"})
if _, err := assign(ctx, open, "anchor", "app"); err != nil {
t.Fatal(err)
}
for _, verb := range []string{"stop", "close"} {
cut := time.Now().UTC()
walk := inventory.Plan{ID: "plan-308-" + verb, Repository: "novox/mesh-catalog", Branch: "main",
Commit: "c8c8c8c8", Created: cut, State: inventory.PlanBuilding, Tiers: [][]string{{"app"}},
Modules: map[string]*inventory.PlanModule{"app": {}},
Times: &inventory.PlanTimes{Cut: &cut, Started: &cut, Class: inventory.ClassLeaf}}
if err := open.inventory.SavePlan(ctx, &walk); err != nil {
t.Fatal(err)
}
if err := plansCommand(ctx, []string{verb, walk.ID, "--why", "a test"}); err != nil {
t.Fatal(err)
}
ended := next(inventory.WalkEnded)
if ended["walk"] != walk.ID || ended["outcome"] != inventory.WalkStopped {
t.Fatalf("plans %s: the end is %v", verb, ended)
}
p, err := open.inventory.PlanByID(ctx, walk.ID)
if err != nil {
t.Fatal(err)
}
if p.Outcome() != inventory.WalkStopped || p.Delivery == nil || p.Delivery.StoppedWhy != "a test" {
t.Fatalf("plans %s kept the walk %s, %+v", verb, p.Outcome(), p.Delivery)
}
}
}
// Live, with the store and a bus: a failed walk retried with `plans retry` starts again, and the verb says its
// start (novox/hq ADR 0308 decision 1, review 15 on mesh-controller#247).
func TestAWalkRetriedByAPersonIsSaidStartedAgain(t *testing.T) {
open := aMesh(t)
ctx := t.Context()
asksRecorded(t)
next := planMovedHeard(t)
twoTiers(t, open)
before := time.Now().UTC().Add(-time.Hour)
ended := before.Add(time.Minute)
failed := inventory.Plan{ID: "plan-308-retry", Repository: "novox/a", Branch: "main", Commit: "c0ffee",
Created: before, State: inventory.PlanFailed, Tier: 0, Tiers: [][]string{{"a"}, {"b"}},
Note: "a failed to build in tier 0",
Modules: map[string]*inventory.PlanModule{"a": {State: "failed", AskedAt: &before, Build: "build-1",
Why: link.KilledByHand}},
Times: &inventory.PlanTimes{Cut: &before, Started: &before, Ended: &ended, Class: inventory.ClassLeaf}}
if err := open.inventory.SavePlan(ctx, &failed); err != nil {
t.Fatal(err)
}
if err := plansCommand(ctx, []string{"retry", failed.ID}); err != nil {
t.Fatal(err)
}
started := next(inventory.WalkStarted)
if started["walk"] != failed.ID || started["budget_class"] != inventory.ClassLeaf {
t.Fatalf("the retried start: %v", started)
}
}
// Live, with the store and a bus: the release plan `upgrade release-backlog` opens is said started by the verb
// (novox/hq ADR 0308 decision 1, review 15 on mesh-controller#247).
func TestABacklogReleasedByAPersonIsSaidStarted(t *testing.T) {
b := aBacklog(t)
next := planMovedHeard(t)
if err := backlogCommand(t.Context(), "release-backlog", []string{"--why", "a test"}); err != nil {
t.Fatal(err)
}
started := next(inventory.WalkStarted)
if p := b.release(t); started["walk"] != p.ID {
t.Fatalf("the release's start: %v", started)
}
}
// asTyped runs a verb as the controller's command line runs it, through run, as a person's terminal would.
func asTyped(t *testing.T, args ...string) error {
t.Helper()
was := os.Args
os.Args = append([]string{"mesh-controller"}, args...)
t.Cleanup(func() { os.Args = was })
err := run()
// run gives back the lease as the process would end; the test's process goes on, and takes it again.
theLease.mu.Lock()
theLease.held, theLease.kv, theLease.noBus = nil, nil, false
theLease.mu.Unlock()
return err
}
// aStartedWalkAsking keeps a live walk, said started, whose first tier asked a as build.
func aStartedWalkAsking(t *testing.T, open *stores, id, build string, asked time.Time) inventory.Plan {
t.Helper()
walk := inventory.Plan{ID: id, Repository: "novox/a", Branch: "main", Commit: "c0ffee", Created: asked,
State: inventory.PlanBuilding, Tiers: [][]string{{"a"}, {"b"}},
Modules: map[string]*inventory.PlanModule{"a": {State: "asked", AskedAt: &asked, Build: build}},
Times: &inventory.PlanTimes{Cut: &asked, Started: &asked, Class: inventory.ClassLeaf}}
if err := open.inventory.SavePlan(t.Context(), &walk); err != nil {
t.Fatal(err)
}
return walk
}
// Live, with the store and a bus: `cancel <build>` and `clear` fail the walk that asked the build, and the verb
// says its end, failed (novox/hq ADR 0308 decision 1, review 21 on mesh-controller#247).
func TestAWalkEndedByCancelOrClearIsSaidEnded(t *testing.T) {
_, ask := aBuildQueue(t)
open := aMesh(t)
next := planMovedHeard(t)
twoTiers(t, open)
for _, verb := range [][]string{{"cancel"}, {"clear"}} {
id := link.NewBuildID(time.Now())
ask(id, "https://forge.example/novox/a.git")
asked, _ := link.BuildAskedAt(id)
walk := aStartedWalkAsking(t, open, "plan-308-"+verb[0], id, asked)
args := verb
if verb[0] == "cancel" {
args = append(args, id)
}
if err := asTyped(t, args...); err != nil {
t.Fatal(err)
}
ended := next(inventory.WalkEnded)
if ended["walk"] != walk.ID || ended["outcome"] != inventory.WalkFailed {
t.Fatalf("%s: the end is %v", verb[0], ended)
}
// Ended, and so the next walk may be cut on the same repository.
p, _ := open.inventory.PlanByID(t.Context(), walk.ID)
if p.State != inventory.PlanFailed {
t.Fatalf("%s left the walk %s", verb[0], p.State)
}
}
}
// Live, with the store and a bus: `rebuild <module>` joining a failed walk sets it building again, and the verb
// says its start (novox/hq ADR 0308 decision 1, review 21 on mesh-controller#247).
func TestAWalkRestartedByARebuildIsSaidStarted(t *testing.T) {
open := aMesh(t)
asksRecorded(t)
next := planMovedHeard(t)
twoTiers(t, open)
before := time.Now().UTC().Add(-time.Hour)
ended := before.Add(time.Minute)
failed := inventory.Plan{ID: "plan-308-rebuild", Repository: "novox/a", Branch: "main", Commit: "c0ffee",
Created: before, State: inventory.PlanFailed, Tiers: [][]string{{"a"}, {"b"}},
Modules: map[string]*inventory.PlanModule{"a": {State: "failed", AskedAt: &before, Build: "build-1",
Why: link.CancelledByHand}},
Times: &inventory.PlanTimes{Cut: &before, Started: &before, Ended: &ended, Class: inventory.ClassLeaf}}
if err := open.inventory.SavePlan(t.Context(), &failed); err != nil {
t.Fatal(err)
}
if err := asTyped(t, "rebuild", "a"); err != nil {
t.Fatal(err)
}
if started := next(inventory.WalkStarted); started["walk"] != failed.ID {
t.Fatalf("the rebuilt walk's start: %v", started)
}
}
// Live, with the store: a walk a person stopped and then retried, by `plans retry` or by `rebuild`, walks again
// without the stop, so when it fails again it ends failed, not stopped, and the search for the merge that
// brought the failure is not kept from it (novox/hq ADR 0308 decision 1, review 21 on mesh-controller#247).
func TestAWalkStoppedByHandAndRetriedEndsFailedWhenItFailsAgain(t *testing.T) {
open := aMesh(t)
ctx := t.Context()
asksRecorded(t)
twoTiers(t, open)
for _, again := range [][]string{{"plans", "retry"}, {"rebuild", "a"}} {
before := time.Now().UTC().Add(-time.Hour)
walk := aStartedWalkAsking(t, open, "plan-308-again-"+again[0], "build-1", before)
if err := asTyped(t, "plans", "stop", walk.ID, "--why", "a test"); err != nil {
t.Fatal(err)
}
// The build asked before the stop fails after it.
p, _ := open.inventory.PlanByID(ctx, walk.ID)
p.Modules["a"].State, p.Modules["a"].Why = "failed", "it broke"
if err := open.inventory.SavePlan(ctx, &p); err != nil {
t.Fatal(err)
}
args := again
if again[0] == "plans" {
args = append(append([]string(nil), again...), walk.ID)
}
if err := asTyped(t, args...); err != nil {
t.Fatal(err)
}
p, _ = open.inventory.PlanByID(ctx, walk.ID)
if p.State != inventory.PlanBuilding || (p.Delivery != nil && p.Delivery.Stopped != "") {
t.Fatalf("%s: the walk is %s and keeps its stop: %+v", again[0], p.State, p.Delivery)
}
asking, _ := link.BuildAskedAt(p.Modules["a"].Build)
planBuilt(ctx, open, "a", "c0ffee", "it broke again", asking, p.Modules["a"].Build)
if p, _ = open.inventory.PlanByID(ctx, walk.ID); p.State != inventory.PlanFailed || p.Outcome() != inventory.WalkFailed {
t.Fatalf("%s: failing again, the walk is %s and ends %s", again[0], p.State, p.Outcome())
}
}
}
+2 -14
View File
@@ -262,12 +262,9 @@ func MaySubscribe(perms Permissions, subject string) bool {
// delivery held past its bound, and calls them on the operator's warrant, with its why.
//
// And, since novox/hq ADR 0282, `times`: the self-check reads the delivery times to say a delivery over its budget.
//
// And, since novox/hq ADR 0306, `groups`: a merge heard from a head waits for the window while its delivery group
// has a member still to merge.
var VerbsTheControllerAsksTheDeliveryOwner = []SeatVerb{{Seat: "mesh-delivery", Verb: "stalled"},
{Seat: "mesh-delivery", Verb: "close"}, {Seat: "mesh-delivery", Verb: "release"}, {Seat: "mesh-delivery", Verb: "stop"},
{Seat: "mesh-delivery", Verb: "times"}, {Seat: "mesh-delivery", Verb: "groups"}}
{Seat: "mesh-delivery", Verb: "times"}}
// VerbsTheControllerActsOnAWarrant are the other seat verbs the controller calls when the operator's warrant
// chooses them (novox/hq ADR 0259): a machine's service restarted, and a walk started or stopped through the
@@ -336,13 +333,6 @@ func AskHandOverSubject(node string) string { return "mesh.node." + node + ".ask
// a hand-over is (link.SetuidSearchContext), for the same reason.
func AskSetuidSearchSubject(node string) string { return "mesh.node." + node + ".ask.setuid-search" }
// AskJudgeDirectoriesSubject is where the controller asks one machine's node-engine to judge, read-only, which of
// its declared directories the walk that follows no link another account could make would refuse (novox/hq issue
// 358): a request answered once, signed as a hand-over is (link.JudgeDirectoriesContext), for the same reason.
func AskJudgeDirectoriesSubject(node string) string {
return "mesh.node." + node + ".ask.judge-directories"
}
// inbox is a principal's own reply space. No user is ever granted a bare `_INBOX.>` (design 25
// §4): with one account, inbox privacy is the permission list or it is nothing, so each user's
// inbox is derived from its own identity and its permissions name that prefix and no other.
@@ -621,9 +611,7 @@ func PermissionsFor(p Principal) (Permissions, error) {
// issue 356), which it answers on the request's reply: the one request a node is asked.
AskHandOverSubject(p.Node),
// And asking it for a fresh search for setuid programs (novox/hq issue 361), answered the same way.
AskSetuidSearchSubject(p.Node),
// And asking it to judge its declared directories, read-only (novox/hq issue 358), answered the same way.
AskJudgeDirectoriesSubject(p.Node)}
AskSetuidSearchSubject(p.Node)}
// The node-engine witnesses the core builds it places (novox/hq to-be 45 §8, ADR 0236; the
// contract is lease/witness.go): it asks its own machine's node tools PING, and, where the
// machine runs the controller, reads the lease's one key — read, never written.
+1 -3
View File
@@ -114,9 +114,7 @@ func TestOnlyWhatCanBeAskedMayAnswer(t *testing.T) {
node, _ := PermissionsFor(Principal{Kind: KindNode, Node: "one", PasswordHash: "x"})
if !node.AllowResponses || !slices.Contains(node.Subscribe, AskHandOverSubject("one")) ||
!slices.Contains(node.Subscribe, AskSetuidSearchSubject("one")) ||
slices.Contains(node.Subscribe, AskSetuidSearchSubject("two")) ||
!slices.Contains(node.Subscribe, AskJudgeDirectoriesSubject("one")) ||
slices.Contains(node.Subscribe, AskJudgeDirectoriesSubject("two")) {
slices.Contains(node.Subscribe, AskSetuidSearchSubject("two")) {
t.Fatalf("a node cannot answer the hand-over it is asked: %v %v", node.AllowResponses, node.Subscribe)
}
person, _ := PermissionsFor(Principal{Kind: KindPerson, Node: "one", Module: "jo", PasswordHash: "x"})
+2 -2
View File
@@ -24,7 +24,7 @@ accounts {
jetstream: enabled
users = [
{ user: "controller", password: "$2a$11$cccccccccccccccccccccc", permissions: {
publish: { allow: ["$JS.ACK.CONTROL.controller.>", "$JS.ACK.DEAD_LETTER_NOTICES.controller.>", "$JS.ACK.EVENTS.controller.>", "$JS.API.>", "$KV.SEAT_MESH_BUILD_MACHINE_cancelled.>", "$KV.SEAT_NODE_BUILD_AGENT_cancelled.>", "$KV.mesh-controller_asked.>", "$KV.mesh-controller_calls.>", "$KV.mesh-controller_condition-history.>", "$KV.mesh-controller_conditions.>", "$KV.mesh-controller_hand-acts.>", "$KV.mesh-controller_lease.>", "$SRV.INFO", "_INBOX.enrol.>", "mesh.again.>", "mesh.assignment.>", "mesh.events.dead.>", "mesh.mod.*.tool.>", "mesh.node.>", "mesh.seat.mesh-build-machine.accept.>", "mesh.seat.mesh-build-machine.tool.>", "mesh.seat.mesh-controller.event.applied", "mesh.seat.mesh-controller.event.built-before", "mesh.seat.mesh-controller.event.checked", "mesh.seat.mesh-controller.event.condition-changed", "mesh.seat.mesh-controller.event.condition-cleared", "mesh.seat.mesh-controller.event.condition-raised", "mesh.seat.mesh-controller.event.doctor-heartbeat", "mesh.seat.mesh-controller.event.healer-acted", "mesh.seat.mesh-controller.event.plan-moved", "mesh.seat.mesh-controller.event.refused", "mesh.seat.mesh-controller.event.rolled-back", "mesh.seat.mesh-controller.event.secret-replaced", "mesh.seat.mesh-controller.tool.plans", "mesh.seat.mesh-delivery.tool.close", "mesh.seat.mesh-delivery.tool.groups", "mesh.seat.mesh-delivery.tool.release", "mesh.seat.mesh-delivery.tool.stalled", "mesh.seat.mesh-delivery.tool.stop", "mesh.seat.mesh-delivery.tool.times", "mesh.seat.node-backup.tool.backed-up.*", "mesh.seat.node-backup.tool.now.*", "mesh.seat.node-build-agent.accept.>", "mesh.seat.node-build-agent.tool.>", "mesh.seat.node-intrusion-prevention.tool.banned.*", "mesh.seat.node-launcher.tool.secret.*", "mesh.seat.node-service-manager.tool.restart.*"] }
publish: { allow: ["$JS.ACK.CONTROL.controller.>", "$JS.ACK.DEAD_LETTER_NOTICES.controller.>", "$JS.ACK.EVENTS.controller.>", "$JS.API.>", "$KV.SEAT_MESH_BUILD_MACHINE_cancelled.>", "$KV.SEAT_NODE_BUILD_AGENT_cancelled.>", "$KV.mesh-controller_asked.>", "$KV.mesh-controller_calls.>", "$KV.mesh-controller_condition-history.>", "$KV.mesh-controller_conditions.>", "$KV.mesh-controller_hand-acts.>", "$KV.mesh-controller_lease.>", "$SRV.INFO", "_INBOX.enrol.>", "mesh.again.>", "mesh.assignment.>", "mesh.events.dead.>", "mesh.mod.*.tool.>", "mesh.node.>", "mesh.seat.mesh-build-machine.accept.>", "mesh.seat.mesh-build-machine.tool.>", "mesh.seat.mesh-controller.event.applied", "mesh.seat.mesh-controller.event.built-before", "mesh.seat.mesh-controller.event.checked", "mesh.seat.mesh-controller.event.condition-changed", "mesh.seat.mesh-controller.event.condition-cleared", "mesh.seat.mesh-controller.event.condition-raised", "mesh.seat.mesh-controller.event.doctor-heartbeat", "mesh.seat.mesh-controller.event.healer-acted", "mesh.seat.mesh-controller.event.plan-moved", "mesh.seat.mesh-controller.event.refused", "mesh.seat.mesh-controller.event.rolled-back", "mesh.seat.mesh-controller.event.secret-replaced", "mesh.seat.mesh-controller.tool.plans", "mesh.seat.mesh-delivery.tool.close", "mesh.seat.mesh-delivery.tool.release", "mesh.seat.mesh-delivery.tool.stalled", "mesh.seat.mesh-delivery.tool.stop", "mesh.seat.mesh-delivery.tool.times", "mesh.seat.node-backup.tool.backed-up.*", "mesh.seat.node-backup.tool.now.*", "mesh.seat.node-build-agent.accept.>", "mesh.seat.node-build-agent.tool.>", "mesh.seat.node-intrusion-prevention.tool.banned.*", "mesh.seat.node-launcher.tool.secret.*", "mesh.seat.node-service-manager.tool.restart.*"] }
subscribe: { allow: ["$JS.API.>", "$JS.EVENT.ADVISORY.CONSUMER.DELETED.>", "$JS.EVENT.ADVISORY.CONSUMER.MAX_DELIVERIES.>", "$SRV.INFO", "$SRV.INFO.mesh-controller", "$SRV.INFO.mesh-controller.>", "$SRV.PING", "$SRV.PING.mesh-controller", "$SRV.PING.mesh-controller.>", "$SRV.STATS", "$SRV.STATS.mesh-controller", "$SRV.STATS.mesh-controller.>", "_DELIVER.controller", "_DELIVER.controller.>", "_INBOX.controller.>", "mesh.control.>", "mesh.mod.*.event.provisioner.failing", "mesh.mod.*.event.provisioner.recovered", "mesh.mod.*.event.provisioner.retirement", "mesh.mod.gitea.event.pull.merged", "mesh.mod.gitea.event.pull.updated", "mesh.mod.mesh-catalog.event.catching-up", "mesh.mod.mesh-catalog.event.upgraded", "mesh.seat.mesh-build-machine.event.built", "mesh.seat.mesh-controller.tool.>", "mesh.seat.node-build-agent.event.built", "mesh.seat.operator-channel.event.decided.mesh-controller"] }
allow_responses: { max: 1, ttl: "1m" }
} }
@@ -34,7 +34,7 @@ accounts {
} }
{ user: "node.one", password: "$2a$11$nnnnnnnnnnnnnnnnnnnnnn", permissions: {
publish: { allow: ["$JS.ACK.NODES.one.>", "$JS.API.CONSUMER.INFO.NODES.one", "$SRV.PING.node-tools.one", "mesh.control.one.>"] }
subscribe: { allow: ["_DELIVER.one", "_DELIVER.one.>", "_INBOX.node.one.>", "mesh.node.one.ask.hand-over", "mesh.node.one.ask.judge-directories", "mesh.node.one.ask.report", "mesh.node.one.ask.setuid-search", "mesh.node.one.declare"] }
subscribe: { allow: ["_DELIVER.one", "_DELIVER.one.>", "_INBOX.node.one.>", "mesh.node.one.ask.hand-over", "mesh.node.one.ask.report", "mesh.node.one.ask.setuid-search", "mesh.node.one.declare"] }
allow_responses: { max: 1, ttl: "1m" }
} }
{ user: "one.nats", password: "$2a$11$bbbbbbbbbbbbbbbbbbbbbb", permissions: {
-5
View File
@@ -96,11 +96,6 @@ var WritersTable = []WriterRow{
{State: "a fresh setuid search asked of a machine", Writer: "controller, at its terminal",
KeptIn: "the machine, which throws its last search away", Others: "the engine verifies the mesh's signature and starts it, or refuses",
Subjects: []string{"mesh.node.*.ask.setuid-search"}, Writes: isController},
// A read-only judgement of a machine's declared directories asked of its engine (novox/hq issue 358): signed as a
// hand-over is, under a signing context of its own. It changes nothing on the machine.
{State: "a judgement of a machine's directories asked of it", Writer: "controller",
KeptIn: "nowhere: the engine answers it and keeps nothing", Others: "the engine verifies the mesh's signature and answers, or refuses",
Subjects: []string{"mesh.node.*.ask.judge-directories"}, Writes: isController},
{State: "a machine's applied state and its report", Writer: "the node-engine's apply queue",
KeptIn: "the machine; the report on the bus", Others: "the reconcile and a delivery enqueue, never apply",
// And its health statement between reports (novox/hq ADR 0240): the same writer stating the same
-19
View File
@@ -17,7 +17,6 @@ var designRows = []string{
"a machine's declaration",
"a hand-over asked of a machine",
"a fresh setuid search asked of a machine",
"a judgement of a machine's directories asked of it",
"a machine's applied state and its report",
"the controller lease",
"plans and their tiers",
@@ -187,21 +186,3 @@ func TestASetuidSearchAskHasOnePublisher(t *testing.T) {
}
}
}
// **A judgement of a machine's directories asked of it has one publisher, the controller** (novox/hq issue 358), as a
// hand-over has.
func TestADirectoryJudgementAskHasOnePublisher(t *testing.T) {
for _, p := range []Principal{
{Kind: KindNode, Node: "laptop"},
{Kind: KindNodeTools, Node: "laptop", Module: RuntimeModule},
{Kind: KindModule, Node: "laptop", Module: "notes"},
} {
err := CheckWriters(p, []string{AskJudgeDirectoriesSubject("laptop")})
if err == nil || !strings.Contains(err.Error(), "a judgement of a machine's directories asked of it") {
t.Errorf("%s may ask a judgement of directories: %v", p.Username(), err)
}
}
if err := CheckWriters(Principal{Kind: KindController}, []string{AskJudgeDirectoriesSubject("laptop")}); err != nil {
t.Fatalf("the controller may not ask a judgement: %v", err)
}
}
-1
View File
@@ -1718,7 +1718,6 @@ func ParseManifest(raw []byte) (Manifest, error) {
// facts about the catalogue and are checked at registration (CatalogueProblems).
problems = append(problems, declaredSeatProblems(m)...)
problems = append(problems, RunsAsProblems(m)...)
problems = append(problems, ReadsHolderProblems(m)...)
if m.Computed != "" && len(m.Resources) > 0 {
// One or the other. A module that both ships files and has them computed would leave
// nobody able to say where a given file came from.
+19 -34
View File
@@ -68,10 +68,9 @@ func TestFailedIsAnOptionalVerbOfTheServiceManager(t *testing.T) {
holder := func(serves ...string) Manifest {
return Manifest{Module: "systemd", Version: "1", Claims: []Claim{{Name: ServiceManagerSeat, Scope: ScopeNode, Serves: serves}}}
}
eight := []string{"units", "status", "start", "stop", "restart", "enable", "disable", "journal",
"reset-failed", "wanted-by", "unlink-dangling"}
eight := []string{"units", "status", "start", "stop", "restart", "enable", "disable", "journal"}
if err := CanHold(holder(eight...), seat); err != nil {
t.Fatalf("a holder without failed is refused: %v", err)
t.Fatalf("today's holder, without failed, is refused: %v", err)
}
if err := CanHold(holder(append(eight, "failed")...), seat); err != nil {
t.Fatalf("a holder serving failed is refused: %v", err)
@@ -82,7 +81,7 @@ func TestFailedIsAnOptionalVerbOfTheServiceManager(t *testing.T) {
if err := CanHold(holder(eight[1:]...), seat); err == nil || !strings.Contains(err.Error(), "does not serve units") {
t.Fatalf("a holder missing a required verb was accepted: %v", err)
}
optional := map[string]bool{"failed": true}
optional := map[string]bool{"failed": true, "reset-failed": true, "wanted-by": true, "unlink-dangling": true}
for _, v := range seat.Serves {
if v.Optional != optional[v.Name] {
t.Errorf("%s optional: %v", v.Name, v.Optional)
@@ -90,35 +89,26 @@ func TestFailedIsAnOptionalVerbOfTheServiceManager(t *testing.T) {
}
}
// **`reset-failed`, `wanted-by` and `unlink-dangling` are required** (novox/hq issue 332, ADR 0246 step 3):
// every holder serves them, so a holder serving only the nine verbs before them is refused by the verb it
// lacks; a holder serving all twelve holds the seat; each replaces the shell command it names; and read
// back from the store's row they stay required.
func TestResetFailedWantedByAndUnlinkDanglingAreRequiredVerbsOfTheServiceManager(t *testing.T) {
// **`reset-failed` and `wanted-by` join the seat optional** (novox/hq issue 332, ADR 0246 step 1): the
// holder running today, serving the nine verbs, still holds the seat; a holder serving all eleven is not
// refused; each replaces the shell command it names; and read back from the store's row they stay optional.
func TestResetFailedAndWantedByAreOptionalVerbsOfTheServiceManager(t *testing.T) {
defer UseSeats(DefaultSeats())
nine := []string{"units", "status", "start", "stop", "restart", "enable", "disable", "journal", "failed"}
all := append(slices.Clone(nine), "reset-failed", "wanted-by", "unlink-dangling")
holder := func(serves ...string) Manifest {
return Manifest{Module: "systemd", Version: "1", Claims: []Claim{{Name: ServiceManagerSeat, Scope: ScopeNode, Serves: serves}}}
}
refusedWithout := func(seat Seat) {
t.Helper()
for _, verb := range []string{"reset-failed", "wanted-by", "unlink-dangling"} {
serves := slices.DeleteFunc(slices.Clone(all), func(v string) bool { return v == verb })
if err := CanHold(holder(serves...), seat); err == nil || !strings.Contains(err.Error(), "does not serve "+verb) {
t.Errorf("a holder not serving %s holds the seat: %v", verb, err)
}
}
}
seat, _ := SeatNamed(ServiceManagerSeat)
if err := CanHold(holder(nine...), seat); err == nil {
t.Fatal("a holder serving only the nine verbs before issue 332 holds the seat")
if err := CanHold(holder(nine...), seat); err != nil {
t.Fatalf("today's holder, without the two verbs, is refused: %v", err)
}
refusedWithout(seat)
if err := CanHold(holder(all...), seat); err != nil {
t.Fatalf("a holder serving all twelve is refused: %v", err)
if err := CanHold(holder(append(nine, "reset-failed", "wanted-by")...), seat); err != nil {
t.Fatalf("a holder serving both is refused: %v", err)
}
if err := CanHold(holder(append(slices.Clone(all), "why-started")...), seat); err == nil || !strings.Contains(err.Error(), "does not promise") {
if err := CanHold(holder(append(nine, "reset-failed", "wanted-by", "unlink-dangling")...), seat); err != nil {
t.Fatalf("a holder serving unlink-dangling too is refused: %v", err)
}
if err := CanHold(holder(append(nine, "why-started")...), seat); err == nil || !strings.Contains(err.Error(), "does not promise") {
t.Fatalf("a verb the seat does not promise was accepted: %v", err)
}
replaces := map[string]string{"reset-failed": "systemctl reset-failed", "wanted-by": "systemctl list-dependencies --reverse",
@@ -128,9 +118,6 @@ func TestResetFailedWantedByAndUnlinkDanglingAreRequiredVerbsOfTheServiceManager
if !ok {
continue
}
if v.Optional {
t.Errorf("%s is still optional", v.Name)
}
if !slices.Contains(v.Replaces, want) {
t.Errorf("%s does not say it replaces %q: %v", v.Name, want, v.Replaces)
}
@@ -161,9 +148,8 @@ func TestResetFailedWantedByAndUnlinkDanglingAreRequiredVerbsOfTheServiceManager
}
UseSeats(rows)
seat, _ = SeatNamed(ServiceManagerSeat)
refusedWithout(seat)
if err := CanHold(holder(all...), seat); err != nil {
t.Fatalf("read back from the row, a holder serving all twelve is refused: %v", err)
if err := CanHold(holder(nine...), seat); err != nil {
t.Fatalf("read back from the row, the two verbs are required: %v", err)
}
}
@@ -183,9 +169,8 @@ func TestAnOptionalVerbStaysOptionalInASetReadFromTheStore(t *testing.T) {
UseSeats(rows)
seat, _ := SeatNamed(ServiceManagerSeat)
holder := Manifest{Module: "systemd", Version: "1", Claims: []Claim{{Name: ServiceManagerSeat, Scope: ScopeNode,
Serves: []string{"units", "status", "start", "stop", "restart", "enable", "disable", "journal",
"reset-failed", "wanted-by", "unlink-dangling"}}}}
Serves: []string{"units", "status", "start", "stop", "restart", "enable", "disable", "journal"}}}}
if err := CanHold(holder, seat); err != nil {
t.Fatalf("a set read from rows refuses a holder without the optional failed: %v", err)
t.Fatalf("a set read from rows refuses today's holder: %v", err)
}
}
-220
View File
@@ -1,220 +0,0 @@
package catalogue
import (
"encoding/json"
"fmt"
"path/filepath"
"sort"
"strings"
)
// A node's files and accounts, read (novox/hq ADR 0310, extending ADR 0268 §5; hq to-be 41 WP8).
//
// **A seat of its own on every node.** Reading a file, searching one, listing a directory, the owner and mode
// of each component of a path, and looking up an account or a group are the reads ADR 0268 §5 has narrow tools
// take over from the login shell's `execute`, so an approval is asked for an act and never for a read. Every
// node needs them, the control-node included, and another module could offer them instead of the tool
// runner's (ADR 0126 §9): a seat, so the mesh finds them on every node by one name.
//
// **Read as an account that holds no secret.** The holder runs as an account of its own (runs-as, ADR 0259
// §8), so the node's file modes bound what it sees — never the operator's account, which sees the
// operator's keys and the agent's credentials. On top, it refuses by name the places a secret is kept,
// which the controller names for it (secretPlaces), and every answer passes the content rule's secret class
// (mesh-sdk's outward, ADR 0310 §4).
// ReadsSeat is the role that reads a node's files and accounts (novox/hq ADR 0310).
const ReadsSeat = "node-reads"
// ReadsSecretPlaces is the word the holder of node-reads is given: the places on its node where a secret is
// kept, as a JSON list of absolute paths, each refused by name before any read (novox/hq ADR 0310 §5).
const ReadsSecretPlaces = "MESH_SECRET_PLACES"
// readsVerbs is the contract every holder of node-reads serves (novox/hq ADR 0310 §2). The bounds are the
// build's to set and each verb's description to state (ADR 0310, Consequences); the holder states them in
// every answer it cuts.
func readsVerbs() []Verb {
return []Verb{
{Name: "stat", Description: "Each component of one path or several, from / down: its type, owner and group " +
"(name and number), mode, whether it is a link and to what, and whether it is a mount point and of which " +
"file system. A link is not followed unless follow is \"true\". Read as the holder's own account, which " +
"holds no secret: a component it may not reach says so. At most 200 paths in one call.",
Input: schema(map[string]string{
"paths": "one absolute path, or several separated by line breaks",
"follow": "\"true\": also say where the path leads once every link is followed",
}, []string{"paths"}, "follow"),
Replaces: []string{"stat", "ls -ld", "namei -l", "findmnt -T"}},
{Name: "readlink", Description: "What one link points to, as written, and where the path leads once every " +
"link is followed, and whether that exists.",
Input: schema(map[string]string{"path": "an absolute path"}, []string{"path"}),
Replaces: []string{"readlink", "readlink -f", "realpath"}},
{Name: "list", Description: "Every entry of one directory with its type, owner, group, mode, size and, for a " +
"link, its target. At most 2000 entries; a longer directory is cut and says so. A place a secret is kept " +
"is refused by name.",
Input: schema(map[string]string{"path": "an absolute path to a directory"}, []string{"path"}),
Replaces: []string{"ls", "ls -la"}},
{Name: "read", Description: "One text file, or a part of it by line: at most 256 KiB in one answer " +
"(64 KiB unless more is asked), cut at a line and said so. A binary file is refused; a place a secret is " +
"kept, or a known credential file, is refused by name; a line shaped like a secret is withheld and its " +
"number said. /proc and /sys are read as far as the holder's account may.",
Input: schema(map[string]string{
"path": "an absolute path to a file",
"from": "the first line to answer, counted from 1 (optional)",
"lines": "how many lines to answer (optional)",
"bytes": "the most bytes to answer, up to 262144 (optional, 65536 unless given)",
}, []string{"path"}),
Replaces: []string{"cat", "head", "tail", "less"}},
{Name: "search", Description: "Find a fixed string (never a pattern) in one file or under one directory: " +
"every matching line with its file and number. Bounded: at most 500 matches (100 unless more is asked), " +
"8 directories deep (4 unless more is asked), 5000 files and 4 MiB per file; links are not followed and " +
"binary files are skipped. A place a secret is kept is skipped and named; a matching line shaped like a " +
"secret is withheld. The answer says which bound it met.",
Input: schema(map[string]string{
"text": "the fixed string to find",
"path": "an absolute path to a file or a directory",
"depth": "how many directories deep, up to 8 (optional)",
"matches": "the most matches to answer, up to 500 (optional)",
"case": "\"false\": match whatever the case (optional)",
}, []string{"text", "path"}, "case"),
Replaces: []string{"grep", "grep -r", "grep -F"}},
{Name: "account", Description: "One account or group by name or number, as this node's account files say: " +
"an account's number, group, home, shell and every group it is in; a group's number and members. With " +
"neither, every account and group. Never a password field.",
Input: schema(map[string]string{
"name": "an account's name or number (optional)",
"group": "a group's name or number (optional)",
}, nil),
Replaces: []string{"getent passwd", "getent group", "id", "groups"}},
}
}
// ReadsHolderProblems is what a holder of node-reads is held to (novox/hq ADR 0310 §3): it reads as an
// account of its own, so the node's file modes bound what it sees. Carried by the machine's runtime it would
// read as the operator's account, which sees the operator's keys and the agent's credentials.
func ReadsHolderProblems(m Manifest) []string {
if !m.ClaimsSeat(ReadsSeat) {
return nil
}
if m.RunsAs == "" {
return []string{fmt.Sprintf("%s claims %s and must run as an account of its own (runs-as): its reads are "+
"bounded by that account's file modes, and the machine's runtime runs as the operator's account "+
"(novox/hq ADR 0310 §3)", m.Module, ReadsSeat)}
}
// In no group beside its own: a group is a way to a secret (docker's is root's), and the account's file modes
// are what bound its reads.
for _, r := range m.Resources {
if fmt.Sprint(r["type"]) != "user" || fmt.Sprint(r["name"]) != m.RunsAs {
continue
}
if groups, said := r["groups"]; said {
if list, ok := groups.([]any); !ok || len(list) > 0 {
return []string{fmt.Sprintf("%s claims %s, and its account %s is put in groups %v: the account that "+
"reads is in no group beside its own (novox/hq ADR 0310 §3)", m.Module, ReadsSeat, m.RunsAs, groups)}
}
}
}
return nil
}
// secretPlaces is every place on this node a secret is kept, as the placed manifests say (novox/hq ADR 0310
// §5): the directory of every module's own secret, every credential file a module is given and every grant
// directory a provider is handed its consumers' credentials in, the place a module keeps the operator-sealed
// secrets, and every directory of the module that provides `secret` — the vault — wherever the node places it,
// a directory declared without a path included. Sorted, each once, and a place under another dropped, so the
// list says each refusal once.
//
// **Failure is loud.** A place still holding a placeholder, or not absolute, fails the composition with the
// module named: a list that silently shrank would be a refusal the decision promises and nothing does.
func (r Resolution) secretPlaces(with Rendering) ([]string, error) {
seen := map[string]bool{}
var problems []string
add := func(module, what, path string) {
path = strings.TrimSpace(path)
if path == "" {
return
}
if !strings.HasPrefix(path, "/") || strings.Contains(path, "${") {
problems = append(problems, fmt.Sprintf("%s's %s is %q, which is not a place on %s", module, what, path, r.Node))
return
}
path = filepath.Clean(path)
if path == "/" {
problems = append(problems, fmt.Sprintf("%s's %s is the root directory", module, what))
return
}
seen[path] = true
}
for _, m := range r.Modules {
for name, own := range m.OwnSecrets {
add(m.Module, "own secret "+name, own.Path)
if strings.HasPrefix(own.Path, "/") {
add(m.Module, "own secret "+name+"'s directory", filepath.Dir(own.Path))
}
}
for _, to := range m.SecretRequirements() {
for _, f := range m.SecretFiles(to) {
add(m.Module, "credential file for "+to, f.Path)
}
}
for to, where := range m.Grants {
add(m.Module, "grant directory for "+to, where)
}
add(m.Module, "place for the operator-sealed secrets (keeps)", m.Keeps)
if providesSecret(m) {
dirs := dirsFor(m, with)
for _, id := range sortedKeys(dirs) {
add(m.Module, "directory "+id, dirs[id])
}
}
}
if len(problems) > 0 {
sort.Strings(problems)
return nil, fmt.Errorf("the holder of %s on %s cannot be told where a secret is kept, so it would read "+
"one (novox/hq ADR 0310 §5): %s", ReadsSeat, r.Node, strings.Join(problems, "; "))
}
all := make([]string, 0, len(seen))
for p := range seen {
all = append(all, p)
}
sort.Strings(all)
var out []string
for _, p := range all {
if n := len(out); n > 0 && strings.HasPrefix(p, out[n-1]+"/") {
continue
}
out = append(out, p)
}
return out, nil
}
func providesSecret(m Manifest) bool {
for _, p := range m.Provides {
if p.Name == "secret" {
return true
}
}
return false
}
// readsWords is what the holder of node-reads is given beside its own words: the node's secret places.
func (r Resolution) readsWords(m Manifest, words map[string]string, with Rendering) (map[string]string, error) {
if !m.ClaimsSeat(ReadsSeat) {
return words, nil
}
places, err := r.secretPlaces(with)
if err != nil {
return nil, err
}
body, err := json.Marshal(places)
if err != nil {
return nil, err
}
if words == nil {
words = map[string]string{}
}
if _, has := words[ReadsSecretPlaces]; has {
return nil, fmt.Errorf("%s gives its own %s; the node's secret places are the mesh's to say (novox/hq ADR 0310 §5)",
m.Module, ReadsSecretPlaces)
}
words[ReadsSecretPlaces] = string(body)
return words, nil
}
-136
View File
@@ -1,136 +0,0 @@
package catalogue
import (
"encoding/json"
"strings"
"testing"
)
// novox/hq ADR 0310 §1, §2: node-reads is a node seat, and its verbs say the commands they replace, so
// mesh_search finds them by `cat`, `grep` and `getent passwd` (ADR 0245 §3).
func TestNodeReadsIsANodeSeatWhoseVerbsSayWhatTheyReplace(t *testing.T) {
s, ok := SeatNamed(ReadsSeat)
if !ok {
t.Fatalf("the mesh defines no seat %s", ReadsSeat)
}
if s.Scope != ScopeNode || s.Delivers != "" || !strings.Contains(s.Decision, "0310") {
t.Errorf("%s: scope %q, delivers %q, decision %q", ReadsSeat, s.Scope, s.Delivers, s.Decision)
}
replaced := map[string]string{}
for _, v := range s.Serves {
if v.Optional {
t.Errorf("%s.%s is optional: a new seat's holder serves every verb", ReadsSeat, v.Name)
}
if len(v.Replaces) == 0 {
t.Errorf("%s.%s says nothing it replaces", ReadsSeat, v.Name)
}
for _, c := range v.Replaces {
replaced[c] = v.Name
}
}
for command, verb := range map[string]string{"cat": "read", "grep": "search", "getent passwd": "account",
"getent group": "account", "id": "account", "stat": "stat", "readlink": "readlink", "ls": "list"} {
if replaced[command] != verb {
t.Errorf("%q is replaced by %q, want %s.%s", command, replaced[command], ReadsSeat, verb)
}
}
}
// novox/hq ADR 0310 §3: a holder of node-reads reads as an account of its own; one the machine's runtime would
// carry — as the operator's account — is refused at parse.
func TestAHolderOfNodeReadsWithoutAnAccountOfItsOwnIsRefused(t *testing.T) {
_, err := ParseManifest([]byte(`{"module": "reads", "version": "1",
"claims": [{"name": "node-reads", "scope": "node"}]}`))
if err == nil || !strings.Contains(err.Error(), "runs-as") || !strings.Contains(err.Error(), "0310") {
t.Errorf("a holder of node-reads without runs-as was not refused for it: %v", err)
}
if p := ReadsHolderProblems(Manifest{Module: "reads", RunsAs: "mesh-reads",
Claims: []Claim{{Name: ReadsSeat}}}); len(p) != 0 {
t.Errorf("a holder running as its own account was refused: %v", p)
}
}
// novox/hq ADR 0310 §5: the holder is told, by the composition, where its node keeps a secret — the directory
// of every module's own secret, every credential file and grant directory, the vault's directories and the
// place the operator-sealed secrets are kept — and no other module is told.
func TestTheHolderOfNodeReadsIsToldWhereItsNodeKeepsASecret(t *testing.T) {
with := Rendering{ArtifactStore: "anchor.internal:5101",
Needed: map[string]map[string]string{RuntimeModule: {"broker": "sealed-credential"},
"reads": {"broker": "own"}, "desk": {"broker": "own"}}}
goRuntime := Manifest{Module: RuntimeModule, Version: "1",
OwnSecrets: OwnSecrets{"broker": {Path: "/var/lib/mesh/" + RuntimeModule + "/broker"}},
Build: &Build{Artifacts: []Artifact{{Name: "runtime", Kind: ArtifactBundle, Language: "go",
System: "arch", From: "cmd/node-tools"}}}}
goRuntime, err := goRuntime.Resolve([]Built{{Name: "runtime", Kind: ArtifactBundle,
Reference: ArtifactStoreScheme + RuntimeModule + "/runtime/blobs/" + bundleDigest, Digest: bundleDigest}})
if err != nil {
t.Fatal(err)
}
reads := aToolsModule(t, "reads", "tools/index.js")
reads.RunsAs, reads.SecretsOwner = "mesh-reads", "mesh-reads"
reads.Claims = []Claim{{Name: ReadsSeat}}
reads.OwnSecrets = OwnSecrets{"broker": {Path: "/var/lib/mesh-reads/broker"}}
desk := aToolsModule(t, "desk", "tools/index.js")
desk.RunsAs, desk.SecretsOwner = "desk", "desk"
desk.OwnSecrets = OwnSecrets{"broker": {Path: "/var/lib/desk/broker"}}
// The vault as the catalogue declares it: its directories have no path of their own, and the node places them.
vault, err := placedManifest(catalogueManifest(t, "mesh-vault"), with)
if err != nil {
t.Fatal(err)
}
app := Manifest{Module: "app", Version: "1", Secrets: map[string]string{"postgres-database": "/etc/app/db.secret"},
OwnSecrets: OwnSecrets{"token": {Path: "/home/ops/.config/app/token"}}}
r := Resolution{Node: "anchor", Account: "ops", Modules: []Manifest{reads, desk, vault, app, goRuntime}}
owns, err := r.ownRuntimes(with)
if err != nil {
t.Fatal(err)
}
var given map[string]map[string]string
for _, p := range owns {
if p["id"] == "reads."+OwnRuntimeID() {
if err := json.Unmarshal([]byte(p["env"].(map[string]string)[RuntimeToolEnv]), &given); err != nil {
t.Fatal(err)
}
}
if p["id"] == "desk."+OwnRuntimeID() && strings.Contains(p["env"].(map[string]string)[RuntimeToolEnv], ReadsSecretPlaces) {
t.Error("a module not holding node-reads is told the node's secret places")
}
}
var places []string
if err := json.Unmarshal([]byte(given["reads"][ReadsSecretPlaces]), &places); err != nil {
t.Fatalf("the holder is not told its node's secret places: %v (%v)", err, given)
}
want := []string{"/etc/app/db.secret", "/home/ops/.config/app", "/var/lib/desk", "/var/lib/mesh-reads",
"/var/lib/mesh-vault", "/var/lib/mesh/" + RuntimeModule}
if strings.Join(places, " ") != strings.Join(want, " ") {
t.Errorf("secret places:\n got %v\nwant %v", places, want)
}
}
// The review of #257: a secret place the controller cannot resolve fails the composition, naming the module,
// rather than leaving the list one place shorter.
func TestASecretPlaceThatCannotBeResolvedFailsTheComposition(t *testing.T) {
r := Resolution{Node: "anchor", Modules: []Manifest{
{Module: "app", Version: "1", Keeps: "${dir:keep}/sealed"},
}}
if _, err := r.secretPlaces(Rendering{}); err == nil || !strings.Contains(err.Error(), "app") {
t.Errorf("an unresolved place was dropped: %v", err)
}
r.Modules[0].Keeps = "relative/place"
if _, err := r.secretPlaces(Rendering{}); err == nil {
t.Error("a relative place was dropped")
}
}
// ADR 0310 §3: the account that reads is in no group beside its own; one put in a group is refused.
func TestTheReadsAccountIsInNoGroup(t *testing.T) {
m := Manifest{Module: "reads", RunsAs: "mesh-reads", Claims: []Claim{{Name: ReadsSeat}},
Resources: []map[string]any{{"id": "account", "type": "user", "name": "mesh-reads", "groups": []any{"docker"}}}}
if p := ReadsHolderProblems(m); len(p) != 1 || !strings.Contains(p[0], "docker") {
t.Errorf("an account in docker was not refused: %v", p)
}
m.Resources[0]["groups"] = []any{}
if p := ReadsHolderProblems(m); len(p) != 0 {
t.Errorf("an account in no group was refused: %v", p)
}
}
-4
View File
@@ -303,10 +303,6 @@ func (r Resolution) ownRuntimes(with Rendering) ([]map[string]any, error) {
if err != nil {
return nil, err
}
// The holder of node-reads is told where this node keeps its secrets (novox/hq ADR 0310 §5).
if words, err = r.readsWords(m, words, with); err != nil {
return nil, err
}
if len(words) > 0 {
body, err := json.Marshal(map[string]map[string]string{m.Module: words})
if err != nil {
+7 -10
View File
@@ -310,9 +310,6 @@ var defaultSeats = append([]Seat{
// node-mounts writes a mount and an automount unit per share on a machine that asks (shares.go).
{Name: NFSServerSeat, Scope: ScopeNode, Decision: "novox/hq ADR 0263", Serves: nfsServerVerbs()},
{Name: MountsSeat, Scope: ScopeNode, Decision: "novox/hq ADR 0263", Serves: mountsVerbs()},
// A node's files and accounts, read (novox/hq ADR 0310, reads.go): by an account of the holder's own that holds
// no secret, on every node, so the reads ADR 0268 §5 takes over from the login shell's execute have a tool.
{Name: ReadsSeat, Scope: ScopeNode, Decision: "novox/hq ADR 0310", Serves: readsVerbs()},
},
// The graphical session's roles (novox/hq ADR 0208), last because they are a workstation's.
graphicalSessionSeats()...)
@@ -681,13 +678,13 @@ func serviceManagerVerbs() []Verb {
Replaces: []string{"systemctl --failed"}},
// **Clearing a failed record, and finding what starts a unit** (novox/hq issue 332): a unit whose
// file is gone stays failed in its manager until the record is reset, and what keeps asking for it
// is a dependency or an enable link no verb could show. Required since every holder serves them
// (ADR 0246 step 3).
{Name: "reset-failed", Description: "Clear one unit's failed record in its manager — " +
// is a dependency or an enable link no verb could show. Both optional while their holders catch up
// (ADR 0246 step 1); a later change requires them.
{Name: "reset-failed", Optional: true, Description: "Clear one unit's failed record in its manager — " +
"its failed state and its start-limit count — and answer its state after. It removes no file and " +
"starts nothing.",
Input: scoped(unit, []string{"unit"}), Replaces: []string{"systemctl reset-failed"}},
{Name: "wanted-by", Description: "What wants, requires or triggers one unit, read-only: the " +
{Name: "wanted-by", Optional: true, Description: "What wants, requires or triggers one unit, read-only: the " +
"manager's reverse dependencies (WantedBy, RequiredBy, UpheldBy, BoundBy, TriggeredBy and the rest) and " +
"every enable link naming it in the scope's configuration directories (*.wants, *.requires, *.upholds), " +
"each with where it points and whether it dangles — the account's own directory included in user scope.",
@@ -695,9 +692,9 @@ func serviceManagerVerbs() []Verb {
Replaces: []string{"systemctl list-dependencies --reverse", "systemctl show -p WantedBy",
"ls ~/.config/systemd/user/*.wants"}},
// **A dangling enable link removed on the person's word** (novox/hq issue 332): `systemctl disable`
// leaves a link whose unit file is gone, so the manager keeps asking for the unit. Required since
// every holder serves it (ADR 0246 step 3).
{Name: "unlink-dangling", Description: "Remove the dangling enable links named for one " +
// leaves a link whose unit file is gone, so the manager keeps asking for the unit. Optional until its
// holders serve it (ADR 0246 step 1).
{Name: "unlink-dangling", Optional: true, Description: "Remove the dangling enable links named for one " +
"unit — links in a *.wants, *.requires or *.upholds directory of the account's or the machine's own " +
"configuration whose target does not exist, which `disable` leaves once the unit's file is gone — on " +
"the person's word: `why` is required. Each is recorded (its path, its target, the reason) before it is " +
+3 -3
View File
@@ -48,7 +48,7 @@ func TestTheSeatsAreAClosedSetAndEachNamesItsDecision(t *testing.T) {
delivered[s.Delivers] = s.Name
}
}
// Forty-one with node-reads (novox/hq ADR 0310); forty with node-nfs-server and node-mounts (novox/hq ADR 0263); thirty-eight with node-resolver (novox/hq ADR 0247); thirty-seven with mesh-delivery (novox/hq ADR 0239); thirty-six since node-resolver-config retired
// Forty with node-nfs-server and node-mounts (novox/hq ADR 0263); thirty-eight with node-resolver (novox/hq ADR 0247); thirty-seven with mesh-delivery (novox/hq ADR 0239); thirty-six since node-resolver-config retired
// into node-uplink (novox/hq ADR 0223); thirty-seven
// since the retired node-dns-resolver went (novox/hq ADR 0220); thirty-eight with
// node-backup (novox/hq ADR 0214); thirty-seven with node-message-bus (novox/hq ADR 0215);
@@ -59,8 +59,8 @@ func TestTheSeatsAreAClosedSetAndEachNamesItsDecision(t *testing.T) {
// node-container-runtime (ADR 0207); nineteen with node-environment and node-login-shell (ADR 0203,
// ADR 0204); seventeen with node-build-agent (ADR 0190). One fewer once the retired
// mesh-build-machine row goes, when no registered manifest claims it.
if len(Seats()) != 41 {
t.Errorf("the mesh defines %d seats rather than 41; the set is closed, so a change here is "+
if len(Seats()) != 40 {
t.Errorf("the mesh defines %d seats rather than 40; the set is closed, so a change here is "+
"a decision (novox/hq ADR 0110): %s", len(Seats()), seatNames())
}
}
+1 -10
View File
@@ -333,9 +333,7 @@ var ControllerVerbs = []Verb{
// The build queue, controlled by hand (novox/hq ADR 0219). Every verb that drops an ask leaves a
// failed outcome for it, so a plan waiting on it fails visibly instead of hanging.
{Name: "queue", Description: "Every ask in the build queue: waiting, in flight (on which machine, for how long), " +
"and dead (handed out as often as allowed and never settled) — each with its id, repository, path, ref and when it was asked. " +
"Answers the table as text and, as data, each ask's state, kind (check or build), repository, commit, machine, since " +
"and position among the waiting (novox/hq issue 455).",
"and dead (handed out as often as allowed and never settled) — each with its id, repository, path, ref and when it was asked.",
Input: schema(nil, nil)},
{Name: "cancel", Description: "Drop one waiting or dead ask from the build queue; its outcome is recorded failed, " +
"cancelled by hand, and a plan that asked for it fails. One in flight is refused: `kill` ends it where it runs.",
@@ -492,13 +490,6 @@ var ControllerVerbs = []Verb{
"why": "with consumer or older-than: why — required, and recorded in the hand-act log",
"cause": "with consumer or older-than: the cause in a word (cleanup-waiting when absent)",
}, nil, "confirm")},
{Name: "judge-directories", Description: "Read-only: which of the directories one machine is declared its " +
"node-engine's walk that follows no link another account could make would refuse (novox/hq issue 358), one line " +
"each: placed, would be refused and why (the link and who could replace it), refused already by the placement " +
"guard, or below a home. The engine judges the declaration it keeps and makes, chmods and chowns nothing.",
Input: schema(map[string]string{
"node": "the machine's name",
}, []string{"node"})},
// What a consumer gave up on (novox/hq issue 330): kept in DEAD_LETTERS until a person acts on it.
{Name: "root-free", Description: "Whether each machine named is root-free now (novox/hq ADR 0259 §8): no agent " +
"there can become root without a person. Judged when asked, never from a condition: free only when the machine " +
+8 -40
View File
@@ -61,10 +61,6 @@ type Plan struct {
// Phases is the walk's time from its merge, phase by phase (ADR 0282 decision 6): never kept, worked out
// from the walk's own moments by whoever says the walk (`delivery walks`, `plan-moved`).
Phases *WalkPhases `json:"phases,omitempty"`
// WalkSaid is, on the save that started or ended the walk, which of the two it was (novox/hq ADR 0308
// decision 1): set by the save, never kept, read by whoever says the save (`plan-moved`). Empty on every
// other save.
WalkSaid string `json:"-"`
}
// PlanTimes are a walk's own moments beside its modules' (novox/hq ADR 0282 decision 6).
@@ -77,10 +73,6 @@ type PlanTimes struct {
// Class is the walk's module class, read at its cut: core when it moves a module on the controller's own
// path or the mesh's resolver, leaf otherwise (ADR 0282 decision 1).
Class string `json:"class,omitempty"`
// Started is when the walk was said started, and Ended when it was said ended (novox/hq ADR 0308 decision
// 1): each said once, on the save that marked it.
Started *time.Time `json:"started,omitempty"`
Ended *time.Time `json:"ended,omitempty"`
}
// PlanCommit is one repository's commit a walk carries: the latest merge of its branch in the batch.
@@ -125,14 +117,6 @@ type PlanBatch struct {
// the batch's walk does not build them.
Closed bool `json:"closed,omitempty"`
Withheld []string `json:"withheld,omitempty"`
// CutAtOnce says the batch's window closed when it was made: its merge shares nothing with a batch
// assembling and has no delivery group member still to merge, so it waits for no window (novox/hq ADR 0304
// decision 1, ADR 0306 decisions 2 and 3). A merge that joins it later opens its window again. It is not
// Closed, which is a stop's.
CutAtOnce bool `json:"cut_at_once,omitempty"`
// Waits says why a batch made for one merge waits for the window: its delivery group has a member still to
// merge, or mesh-delivery could not say whether it has (novox/hq ADR 0306 decision 2).
Waits string `json:"waits,omitempty"`
}
// OwnPath says the record is a batch of merges on the controller's own path.
@@ -199,8 +183,8 @@ type PlanDelivery struct {
Go *time.Time `json:"go,omitempty"`
By string `json:"by,omitempty"`
Why string `json:"why,omitempty"`
// Stopped is who ended the walk, through the delivery's owner or by hand (`plans stop|close`), and StoppedWhy
// why: the walk is failed, and the delivery reads it as stopped, not as a build that failed.
// Stopped is who ended the walk through the delivery's owner, and StoppedWhy why: the walk is failed,
// and the delivery reads it as stopped, not as a build that failed.
Stopped string `json:"stopped,omitempty"`
StoppedWhy string `json:"stopped_why,omitempty"`
// Merges is every merge the walk or batch answers (novox/hq ADR 0276): its own commits, and the earlier
@@ -252,12 +236,10 @@ func (p Plan) Waiting() bool {
return p.Delivery != nil && p.Delivery.Awaits != "" && p.Delivery.Go == nil
}
// PlanSaved is told every plan this process kept, after it is kept, with the inventory that kept it (novox/hq
// ADR 0239): the serving controller says it on the bus as `plan-moved`, and so does a command (the controller's
// run installs it for every verb, novox/hq ADR 0308 decision 1), so the save that starts or ends a walk is said
// whichever process made it. Nil says nothing; whoever follows a walk also asks for it, and finds an unsaid save
// by comparison.
var PlanSaved func(*Inventory, Plan)
// PlanSaved is told every plan this process kept, after it is kept (novox/hq ADR 0239): the serving
// controller says it on the bus as `plan-moved`. Nil in a command, which says nothing; whoever follows a
// walk also asks for it, so a save made by a command is found by comparison.
var PlanSaved func(Plan)
// ErrPlanMoved is a save against a plan written by somebody else since it was read.
var ErrPlanMoved = errors.New("the plan was written by somebody else since it was read")
@@ -469,7 +451,7 @@ type MergeMove struct {
// leaves a merge answered by two plans, nor a walk stopped whose merges were not moved). A plan written by
// somebody else since it was read refuses the whole act with ErrPlanMoved. Each plan is said (PlanSaved) once
// the transaction is committed, in order.
func (i *Inventory) SavePlansMoving(ctx context.Context, plans []*Plan, moves []MergeMove) (err error) {
func (i *Inventory) SavePlansMoving(ctx context.Context, plans []*Plan, moves []MergeMove) error {
epoch, err := i.actingEpoch(ctx)
if err != nil {
if len(plans) > 0 {
@@ -490,20 +472,6 @@ func (i *Inventory) SavePlansMoving(ctx context.Context, plans []*Plan, moves []
entered time.Time
}
done := make([]written, len(plans))
// **The save that starts or ends a walk is marked** (novox/hq ADR 0308 decision 1), in the same write, and
// unmarked should the write not be made, so the next save marks it again.
marked := time.Now()
undo := make([]func(), 0, len(plans))
defer func() {
if err != nil {
for _, u := range undo {
u()
}
}
}()
for _, p := range plans {
undo = append(undo, p.markWalk(marked))
}
for n, p := range plans {
revision, entered, err := writePlan(ctx, tx, p, epoch)
if err != nil {
@@ -529,7 +497,7 @@ func (i *Inventory) SavePlansMoving(ctx context.Context, plans []*Plan, moves []
p.Epoch = 0
}
if PlanSaved != nil {
PlanSaved(i, *p)
PlanSaved(*p)
}
}
return nil
+3 -4
View File
@@ -202,15 +202,14 @@ func TestASeatsVerbGainsTheArgumentsTheBinaryNames(t *testing.T) {
t.Fatal("failed was not added to the row")
}
// The optional mark is not stored; the working set read from the rows takes it from the compiled seat,
// so a holder that does not serve the optional failed still holds the seat.
// so today's holder, which does not serve failed, still holds the seat.
catalogue.UseSeats(seats)
defer catalogue.UseSeats(catalogue.DefaultSeats())
live, _ := catalogue.SeatNamed(catalogue.ServiceManagerSeat)
holder := catalogue.Manifest{Module: "systemd", Version: "1", Claims: []catalogue.Claim{{Name: catalogue.ServiceManagerSeat,
Scope: catalogue.ScopeNode, Serves: []string{"units", "status", "start", "stop", "restart", "enable", "disable", "journal",
"reset-failed", "wanted-by", "unlink-dangling"}}}}
Scope: catalogue.ScopeNode, Serves: []string{"units", "status", "start", "stop", "restart", "enable", "disable", "journal"}}}}
if err := catalogue.CanHold(holder, live); err != nil {
t.Fatalf("the seat read from the store refuses a holder without the optional failed: %v", err)
t.Fatalf("the seat read from the store refuses today's holder: %v", err)
}
// Seeding again changes nothing more.
before := verbs["journal"]
-81
View File
@@ -1,81 +0,0 @@
package inventory
import "time"
// A walk says when it starts and when it ends (novox/hq ADR 0308 decision 1): the save that starts it and the
// save that ends it are marked, so `plan-moved` names what the walk touches, its bound and its outcome on those
// two saves, and on no other. The marks are kept in the walk's times, so a controller replaced mid-walk (a core
// walk replaces it) neither says a start again nor misses the end.
// The moments of a walk `plan-moved` names.
const (
WalkStarted = "started"
WalkEnded = "ended"
)
// The outcomes of an ended walk (ADR 0308 decision 1).
const (
WalkDelivered = "delivered"
WalkFailed = "failed"
WalkStopped = "stopped"
)
// Live says the walk is walking: cut, not waiting for its delivery's word, and not ended.
func (p Plan) Live() bool { return p.Open() && !p.Batch() && !p.Waiting() }
// Ended says the walk is in a state it does not leave by itself: done, failed or superseded.
func (p Plan) Ended() bool {
return p.State == PlanDone || p.State == PlanFailed || p.State == PlanSuperseded
}
// Outcome is how an ended walk ended: delivered when done; stopped when a person or the delivery's owner stopped
// it, or a newer walk took it over; failed otherwise. Empty for a walk not ended.
func (p Plan) Outcome() string {
switch {
case p.State == PlanDone:
return WalkDelivered
case p.State == PlanSuperseded:
return WalkStopped
case p.State == PlanFailed && p.Delivery != nil && p.Delivery.Stopped != "":
return WalkStopped
case p.State == PlanFailed:
return WalkFailed
}
return ""
}
// markWalk marks the save that starts or ends the walk, in its times and in WalkSaid, and returns what undoes
// the mark should the save not be written. A walk starts on the first save that finds it live — when it is cut
// and needs no word, or when it is let go — which is before its first tier is asked, and so before anything is
// sent: what it restarts is held from its first send on. It starts again when a failed walk is retried. It ends
// on the first save that finds it ended after it started; one that ends without ever starting (a batch that
// moved nothing, a walk stopped while it waited for its word) touched nothing and says neither. A walk kept
// before its times were (ADR 0282 decision 6) is not marked; a release plan is, its times holding only these.
func (p *Plan) markWalk(now time.Time) (undo func()) {
p.WalkSaid = ""
if p.Batch() || (p.Times == nil && p.Release == nil) {
return func() {}
}
var was *PlanTimes
if p.Times != nil {
kept := *p.Times
was = &kept
}
times := PlanTimes{}
if p.Times != nil {
times = *p.Times
}
at := now.UTC()
switch {
case p.Live() && (times.Started == nil || times.Ended != nil):
times.Started, times.Ended = &at, nil
p.WalkSaid = WalkStarted
case p.Ended() && times.Started != nil && times.Ended == nil:
times.Ended = &at
p.WalkSaid = WalkEnded
default:
return func() {}
}
p.Times = &times
return func() { p.Times, p.WalkSaid = was, "" }
}
-130
View File
@@ -1,130 +0,0 @@
package inventory
import (
"testing"
"time"
)
// A walk is said started on the save that finds it live, ended on the save that finds it ended after it started,
// and neither on any other save (novox/hq ADR 0308 decision 1).
func TestAWalkIsSaidStartedOnceAndEndedOnce(t *testing.T) {
now := time.Date(2026, 10, 12, 11, 0, 0, 0, time.UTC)
cut := now.Add(-time.Second)
p := Plan{ID: "plan-1", State: PlanBuilding, Tiers: [][]string{{"messenger"}},
Modules: map[string]*PlanModule{"messenger": {}}, Times: &PlanTimes{Cut: &cut, Class: ClassLeaf}}
p.markWalk(now)
if p.WalkSaid != WalkStarted || p.Times.Started == nil || !p.Times.Started.Equal(now) {
t.Fatalf("a live walk's first save starts it: %q %+v", p.WalkSaid, p.Times)
}
p.State = PlanRolling
p.markWalk(now.Add(time.Minute))
if p.WalkSaid != "" || !p.Times.Started.Equal(now) {
t.Fatalf("a later save says nothing and keeps the start: %q %+v", p.WalkSaid, p.Times)
}
p.State = PlanDone
p.markWalk(now.Add(2 * time.Minute))
if p.WalkSaid != WalkEnded || p.Times.Ended == nil || p.Outcome() != WalkDelivered {
t.Fatalf("the save that finds it done ends it, delivered: %q %+v %q", p.WalkSaid, p.Times, p.Outcome())
}
p.markWalk(now.Add(3 * time.Minute))
if p.WalkSaid != "" {
t.Fatalf("an ended walk saved again says nothing: %q", p.WalkSaid)
}
// Retried, it walks again: a new start.
p.State = PlanBuilding
p.markWalk(now.Add(4 * time.Minute))
if p.WalkSaid != WalkStarted || p.Times.Ended != nil || !p.Times.Started.Equal(now.Add(4*time.Minute)) {
t.Fatalf("a retried walk starts again: %q %+v", p.WalkSaid, p.Times)
}
}
// What is never said: a batch, a walk waiting for its word, a walk that ends without having started, and a walk
// kept before its times were. A release plan is said.
func TestWhatIsNotAWalkStartIsNotSaid(t *testing.T) {
now := time.Now()
for name, p := range map[string]Plan{
"a batch": {State: PlanAssembling, Times: &PlanTimes{}},
"waiting for a word": {State: PlanBuilding, Times: &PlanTimes{}, Delivery: &PlanDelivery{Awaits: "mesh-delivery"}},
"ended, never begun": {State: PlanDone, Times: &PlanTimes{}},
"kept before times": {State: PlanBuilding},
"stopped while waits": {State: PlanFailed, Times: &PlanTimes{}, Delivery: &PlanDelivery{Awaits: "mesh-delivery", Stopped: "x"}},
} {
p.markWalk(now)
if p.WalkSaid != "" {
t.Errorf("%s: said %q", name, p.WalkSaid)
}
}
r := Plan{State: PlanRolling, Release: &PlanRelease{Order: []string{"ace"}}}
r.markWalk(now)
if r.WalkSaid != WalkStarted || r.Times == nil || r.Times.Started == nil || r.Times.Class != "" {
t.Fatalf("a release plan is said started, its times holding only that: %q %+v", r.WalkSaid, r.Times)
}
// Let go, the walk starts.
go1 := now
w := Plan{State: PlanBuilding, Times: &PlanTimes{}, Delivery: &PlanDelivery{Awaits: "mesh-delivery", Go: &go1}}
w.markWalk(now)
if w.WalkSaid != WalkStarted {
t.Fatalf("a walk let go starts: %q", w.WalkSaid)
}
}
// An ended walk's outcome: delivered, failed, or stopped by a person or the delivery's owner, or by a newer walk.
func TestAWalksOutcome(t *testing.T) {
for want, p := range map[string]Plan{
WalkDelivered: {State: PlanDone},
WalkFailed: {State: PlanFailed},
WalkStopped: {State: PlanFailed, Delivery: &PlanDelivery{Stopped: "mesh-delivery"}},
"": {State: PlanRolling},
} {
if got := p.Outcome(); got != want {
t.Errorf("%s: outcome %q, want %q", p.State, got, want)
}
}
if (Plan{State: PlanSuperseded}).Outcome() != WalkStopped {
t.Error("a superseded walk is stopped")
}
}
// The marks are kept with the walk, so a controller replaced mid-walk neither says its start again nor misses
// its end; and a save refused leaves the walk unmarked, so the save that is made says it.
func TestAWalksStartIsKeptAndARefusedSaveLeavesItUnsaid(t *testing.T) {
inv := ForTest(t)
ctx := t.Context()
cut := time.Now().UTC().Add(-time.Minute)
p := Plan{ID: "plan-308", Repository: "novox/mesh-catalog", Commit: "abc", Created: cut, State: PlanBuilding,
Tiers: [][]string{{"messenger"}}, Modules: map[string]*PlanModule{"messenger": {}},
Times: &PlanTimes{Cut: &cut, Class: ClassLeaf}}
var said []string
was := PlanSaved
PlanSaved = func(_ *Inventory, p Plan) { said = append(said, p.WalkSaid) }
t.Cleanup(func() { PlanSaved = was })
if err := inv.SavePlan(ctx, &p); err != nil {
t.Fatal(err)
}
back, err := inv.PlanByID(ctx, p.ID)
if err != nil || back.Times == nil || back.Times.Started == nil || back.Times.Class != ClassLeaf {
t.Fatalf("the start is kept with the walk: %v %+v", err, back.Times)
}
// Read back by another controller and saved: not said again.
back.State = PlanRolling
if err := inv.SavePlan(ctx, &back); err != nil {
t.Fatal(err)
}
// A stale copy ending it is refused, and unmarked.
stale := p
stale.Revision = 1
stale.State = PlanDone
if err := inv.SavePlan(ctx, &stale); err == nil {
t.Fatal("a stale save is refused")
}
if stale.WalkSaid != "" || stale.Times.Ended != nil {
t.Fatalf("a refused save is unmarked: %q %+v", stale.WalkSaid, stale.Times)
}
back.State = PlanDone
if err := inv.SavePlan(ctx, &back); err != nil {
t.Fatal(err)
}
if len(said) != 3 || said[0] != WalkStarted || said[1] != "" || said[2] != WalkEnded {
t.Fatalf("said: %q, want started, nothing, ended", said)
}
}
-3
View File
@@ -311,9 +311,6 @@ type ChangePlan struct {
Steps []string `json:"steps,omitempty"`
// Summary is the plan in one line, for a commit status.
Summary string `json:"summary"`
// Class is the class of the slowest-budgeted module the change moves (novox/hq ADR 0282 §1, ADR 0313 §2):
// core, leaf, or none when it moves no module at all — a fix that moves nothing has no fix budget.
Class string `json:"class,omitempty"`
}
// MachinePlan is one machine's part of a change plan.
-22
View File
@@ -148,28 +148,6 @@ func AskSetuidSearch(ctx context.Context, conn *nats.Conn, signer Signer, node,
"there", record: "a start"})
}
// JudgeDirectoriesContext is prefixed to a directory judgement ask's bytes before signing (novox/hq issue 358): never
// another ask's signature, nor a declaration's. The engine holds the same words.
const JudgeDirectoriesContext = "novox-mesh judge-directories v1\n"
// AskJudgeDirectories asks one machine's node-engine to judge, read-only, which of the directories it is declared
// the walk that follows no link another account could make would refuse (novox/hq issue 358): the ask a hand-over
// is, naming no path, signed under JudgeDirectoriesContext. The engine changes nothing and answers one line per
// directory.
func AskJudgeDirectories(ctx context.Context, conn *nats.Conn, signer Signer, node, by string,
timeout time.Duration) (HandOverAnswer, error) {
if conn == nil {
return HandOverAnswer{}, errors.New("this controller is not on the bus")
}
body, err := signAsk(ctx, signer, JudgeDirectoriesContext, HandOverAsk{Node: node, By: by})
if err != nil {
return HandOverAnswer{}, err
}
return askSigned(ctx, conn, broker.AskJudgeDirectoriesSubject(node), body, node, timeout, askWords{
what: "a judgement of its directories", nothing: "nothing was judged, and nothing is changed by one",
issue: "issue 358", unknown: "ask again: a judgement changes nothing", record: "a judgement"})
}
// SignHandOver fills the ask's expiry and nonce and signs it with the mesh's key, over HandOverContext and the
// ask's bytes exactly as they travel.
func SignHandOver(ctx context.Context, signer Signer, ask HandOverAsk) ([]byte, error) {
-60
View File
@@ -1,60 +0,0 @@
package link
import (
"context"
"crypto/ed25519"
"encoding/json"
"strings"
"testing"
"time"
"github.com/nats-io/nats.go"
"github.com/novox/mesh-controller/internal/broker"
"github.com/novox/mesh-controller/internal/testbus"
)
// A judgement of a machine's directories is asked of the machine on its own subject, signed under its own context
// (never a hand-over's), naming no path, and the engine's answer comes back (novox/hq issue 358). The engine holds the
// same subject and context (mesh-host internal/link, TestTheDirectoryJudgementAskKeepsItsSubjectAndContext).
func TestADirectoryJudgementIsAskedOfTheMachineSignedUnderItsOwnContext(t *testing.T) {
if broker.AskJudgeDirectoriesSubject("laptop") != "mesh.node.laptop.ask.judge-directories" ||
JudgeDirectoriesContext != "novox-mesh judge-directories v1\n" {
t.Fatalf("the subject %q, the context %q", broker.AskJudgeDirectoriesSubject("laptop"), JudgeDirectoriesContext)
}
conn, err := nats.Connect(testbus.URL(t))
if err != nil {
t.Fatal(err)
}
t.Cleanup(conn.Close)
signer, public := testSigner(t)
var heard HandOverAsk
engine, err := conn.Subscribe(broker.AskJudgeDirectoriesSubject("laptop"), func(msg *nats.Msg) {
var signed SignedHandOver
_ = json.Unmarshal(msg.Data, &signed)
if ed25519.Verify(public, append([]byte(HandOverContext), signed.Ask...), signed.Signature) ||
ed25519.Verify(public, append([]byte(SetuidSearchContext), signed.Ask...), signed.Signature) ||
!ed25519.Verify(public, append([]byte(JudgeDirectoriesContext), signed.Ask...), signed.Signature) {
_ = msg.Respond([]byte(`{"refused":"not signed as a judgement"}`))
return
}
_ = json.Unmarshal(signed.Ask, &heard)
body, _ := json.Marshal(HandOverAnswer{Said: "3 directories declared, asked by " + heard.By})
_ = msg.Respond(body)
})
if err != nil {
t.Fatal(err)
}
t.Cleanup(func() { _ = engine.Unsubscribe() })
a, err := AskJudgeDirectories(context.Background(), conn, signer, "laptop", "jo", 5*time.Second)
if err != nil || a.Said != "3 directories declared, asked by jo" {
t.Fatalf("answered %+v, %v", a, err)
}
if heard.Node != "laptop" || heard.Path != "" || heard.Nonce == "" || heard.Expires.IsZero() {
t.Fatalf("the engine heard %+v", heard)
}
if _, err := AskJudgeDirectories(context.Background(), conn, signer, "anchor", "jo", 5*time.Second); err == nil ||
!strings.Contains(err.Error(), "nothing was judged") {
t.Fatalf("a machine with no engine listening: %v", err)
}
}
-25
View File
@@ -7,7 +7,6 @@ import (
"fmt"
"regexp"
"sort"
"strings"
"time"
"github.com/nats-io/nats.go"
@@ -269,30 +268,6 @@ func ReadQueue(ctx context.Context, js *broker.JetStream, seat string) (Queue, e
return q, nil
}
// WithoutPassword is a repository as a listing may say it: a URL's password, should one ever be written
// into it, left out (novox/hq issue 455). Only for what is shown: the ask itself keeps what it was given,
// which a cancel's outcome and a rebuild's match are read from.
func WithoutPassword(repository string) string {
scheme, rest, found := strings.Cut(repository, "://")
if !found {
return repository
}
authority, path, _ := strings.Cut(rest, "/")
at := strings.LastIndex(authority, "@")
if at < 0 {
return repository
}
user, _, password := strings.Cut(authority[:at], ":")
if !password {
return repository
}
out := scheme + "://" + user + authority[at:]
if len(rest) > len(authority) {
out += "/" + path
}
return out
}
// ReadBuildEvents is every start and outcome the seat announced since a moment, from the events
// stream, with a consumer of its own that is gone when this returns.
func ReadBuildEvents(ctx context.Context, js *broker.JetStream, seat string, since time.Time) (BuildHeard, error) {
-1
View File
@@ -89,7 +89,6 @@
"cleanup",
"dead-letters",
"root-free",
"judge-directories",
"data",
"build",
"artifacts",
+1 -1
View File
@@ -8,7 +8,7 @@ private addresses. That is acceptable while mesh-controller is private; if it ev
a second place to clean besides the catalogue itself.
mesh-catalog b9de001833b1b61b297182b8e3bcdae1cbdeace9 modules/*/module.json, modules/nats/Dockerfile
mesh-host a76baa4b47f07a8b2bab065603414530bd02b53a examples/foundation-first-node-nats.lock
mesh-host bd5cc6980419c1bd4824be6d58dfebd2381a9de3 examples/foundation-first-node-nats.lock
mesh-sdk 33917f91ac3cc213b879b32f3c70e2aa70395f98 conformance/events/module-event.json
To move them, from this repository's root, with the two repositories checked out beside it:
@@ -161,7 +161,7 @@
"type": "file",
"path": "/var/lib/mesh-bus-conf/accounts.conf",
"mode": "0600",
"content": "// The first user list, carried by the installer because at genesis there is no mesh to\n// compose one. A bootstrap credential, rotated with the store's and replaced by the\n// controller's own composition from its first start onward.\naccounts {\n MESH {\n jetstream: enabled\n users = [\n { user: \"controller\", password: \"$2a$10$AHqJgOifIVbU41KmATiMhuXFs8xa7Wl2HuN4UVBCXdN2jIQzjqApy\", permissions: {\n publish: { allow: [\"$JS.ACK.CONTROL.controller.>\", \"$JS.ACK.EVENTS.controller.>\", \"$JS.ACK.DEAD_LETTER_NOTICES.controller.>\", \"$JS.API.>\", \"$KV.mesh-controller_asked.>\", \"$KV.mesh-controller_calls.>\", \"$KV.mesh-controller_hand-acts.>\", \"$KV.mesh-controller_conditions.>\", \"$KV.mesh-controller_condition-history.>\", \"$KV.mesh-controller_lease.>\", \"$KV.SEAT_MESH_BUILD_MACHINE_cancelled.>\", \"$KV.SEAT_NODE_BUILD_AGENT_cancelled.>\", \"_INBOX.enrol.>\", \"mesh.assignment.>\", \"mesh.mod.*.tool.>\", \"mesh.node.>\", \"mesh.seat.mesh-build-machine.accept.>\", \"mesh.seat.node-build-agent.accept.>\", \"mesh.seat.mesh-build-machine.tool.>\", \"mesh.seat.node-build-agent.tool.>\", \"mesh.seat.mesh-controller.event.applied\", \"mesh.seat.mesh-controller.event.built-before\", \"mesh.seat.mesh-controller.event.refused\", \"mesh.seat.mesh-controller.event.rolled-back\", \"mesh.seat.mesh-controller.event.checked\", \"mesh.seat.mesh-controller.event.plan-moved\", \"mesh.seat.mesh-controller.event.condition-raised\", \"mesh.seat.mesh-controller.event.condition-changed\", \"mesh.seat.mesh-controller.event.condition-cleared\", \"mesh.seat.mesh-controller.event.doctor-heartbeat\", \"mesh.seat.mesh-controller.event.secret-replaced\", \"mesh.seat.mesh-controller.event.healer-acted\", \"$SRV.INFO\", \"mesh.seat.node-intrusion-prevention.tool.banned.*\", \"mesh.seat.node-backup.tool.backed-up.*\", \"mesh.seat.node-backup.tool.now.*\", \"mesh.seat.mesh-delivery.tool.stalled\", \"mesh.seat.mesh-delivery.tool.close\", \"mesh.seat.node-launcher.tool.secret.*\", \"mesh.seat.mesh-delivery.tool.release\", \"mesh.seat.mesh-delivery.tool.stop\", \"mesh.seat.mesh-delivery.tool.times\", \"mesh.seat.mesh-delivery.tool.groups\", \"mesh.seat.node-service-manager.tool.restart.*\", \"mesh.seat.mesh-controller.tool.plans\", \"mesh.events.dead.>\", \"mesh.again.>\"] }\n subscribe: { allow: [\"$JS.API.>\", \"$JS.EVENT.ADVISORY.CONSUMER.MAX_DELIVERIES.>\", \"$JS.EVENT.ADVISORY.CONSUMER.DELETED.>\", \"_DELIVER.controller\", \"_DELIVER.controller.>\", \"_INBOX.controller.>\", \"mesh.control.>\", \"mesh.mod.*.event.provisioner.failing\", \"mesh.mod.*.event.provisioner.recovered\", \"mesh.mod.*.event.provisioner.retirement\", \"mesh.mod.gitea.event.pull.merged\", \"mesh.mod.gitea.event.pull.updated\", \"mesh.mod.mesh-catalog.event.catching-up\", \"mesh.mod.mesh-catalog.event.upgraded\", \"mesh.seat.mesh-build-machine.event.built\", \"mesh.seat.node-build-agent.event.built\", \"mesh.seat.operator-channel.event.decided.mesh-controller\", \"mesh.seat.mesh-controller.tool.>\", \"$SRV.PING\", \"$SRV.INFO\", \"$SRV.PING.mesh-controller\", \"$SRV.PING.mesh-controller.>\", \"$SRV.INFO.mesh-controller\", \"$SRV.INFO.mesh-controller.>\", \"$SRV.STATS\", \"$SRV.STATS.mesh-controller\", \"$SRV.STATS.mesh-controller.>\"] }\n allow_responses: { max: 1, ttl: \"1m\" }\n } }\n ]\n }\n}\n"
"content": "// The first user list, carried by the installer because at genesis there is no mesh to\n// compose one. A bootstrap credential, rotated with the store's and replaced by the\n// controller's own composition from its first start onward.\naccounts {\n MESH {\n jetstream: enabled\n users = [\n { user: \"controller\", password: \"$2a$10$AHqJgOifIVbU41KmATiMhuXFs8xa7Wl2HuN4UVBCXdN2jIQzjqApy\", permissions: {\n publish: { allow: [\"$JS.ACK.CONTROL.controller.>\", \"$JS.ACK.EVENTS.controller.>\", \"$JS.ACK.DEAD_LETTER_NOTICES.controller.>\", \"$JS.API.>\", \"$KV.mesh-controller_asked.>\", \"$KV.mesh-controller_calls.>\", \"$KV.mesh-controller_hand-acts.>\", \"$KV.mesh-controller_conditions.>\", \"$KV.mesh-controller_condition-history.>\", \"$KV.mesh-controller_lease.>\", \"$KV.SEAT_MESH_BUILD_MACHINE_cancelled.>\", \"$KV.SEAT_NODE_BUILD_AGENT_cancelled.>\", \"_INBOX.enrol.>\", \"mesh.assignment.>\", \"mesh.mod.*.tool.>\", \"mesh.node.>\", \"mesh.seat.mesh-build-machine.accept.>\", \"mesh.seat.node-build-agent.accept.>\", \"mesh.seat.mesh-build-machine.tool.>\", \"mesh.seat.node-build-agent.tool.>\", \"mesh.seat.mesh-controller.event.applied\", \"mesh.seat.mesh-controller.event.built-before\", \"mesh.seat.mesh-controller.event.refused\", \"mesh.seat.mesh-controller.event.rolled-back\", \"mesh.seat.mesh-controller.event.checked\", \"mesh.seat.mesh-controller.event.plan-moved\", \"mesh.seat.mesh-controller.event.condition-raised\", \"mesh.seat.mesh-controller.event.condition-changed\", \"mesh.seat.mesh-controller.event.condition-cleared\", \"mesh.seat.mesh-controller.event.doctor-heartbeat\", \"mesh.seat.mesh-controller.event.secret-replaced\", \"mesh.seat.mesh-controller.event.healer-acted\", \"$SRV.INFO\", \"mesh.seat.node-intrusion-prevention.tool.banned.*\", \"mesh.seat.node-backup.tool.backed-up.*\", \"mesh.seat.node-backup.tool.now.*\", \"mesh.seat.mesh-delivery.tool.stalled\", \"mesh.seat.mesh-delivery.tool.close\", \"mesh.seat.node-launcher.tool.secret.*\", \"mesh.seat.mesh-delivery.tool.release\", \"mesh.seat.mesh-delivery.tool.stop\", \"mesh.seat.mesh-delivery.tool.times\", \"mesh.seat.node-service-manager.tool.restart.*\", \"mesh.seat.mesh-controller.tool.plans\", \"mesh.events.dead.>\", \"mesh.again.>\"] }\n subscribe: { allow: [\"$JS.API.>\", \"$JS.EVENT.ADVISORY.CONSUMER.MAX_DELIVERIES.>\", \"$JS.EVENT.ADVISORY.CONSUMER.DELETED.>\", \"_DELIVER.controller\", \"_DELIVER.controller.>\", \"_INBOX.controller.>\", \"mesh.control.>\", \"mesh.mod.*.event.provisioner.failing\", \"mesh.mod.*.event.provisioner.recovered\", \"mesh.mod.*.event.provisioner.retirement\", \"mesh.mod.gitea.event.pull.merged\", \"mesh.mod.gitea.event.pull.updated\", \"mesh.mod.mesh-catalog.event.catching-up\", \"mesh.mod.mesh-catalog.event.upgraded\", \"mesh.seat.mesh-build-machine.event.built\", \"mesh.seat.node-build-agent.event.built\", \"mesh.seat.operator-channel.event.decided.mesh-controller\", \"mesh.seat.mesh-controller.tool.>\", \"$SRV.PING\", \"$SRV.INFO\", \"$SRV.PING.mesh-controller\", \"$SRV.PING.mesh-controller.>\", \"$SRV.INFO.mesh-controller\", \"$SRV.INFO.mesh-controller.>\", \"$SRV.STATS\", \"$SRV.STATS.mesh-controller\", \"$SRV.STATS.mesh-controller.>\"] }\n allow_responses: { max: 1, ttl: \"1m\" }\n } }\n ]\n }\n}\n"
},
{
"id": "broker",
@@ -31,13 +31,6 @@ package apply
// 5. **A mount source that is a refused directory or a refused access is refused with it**: the container
// would otherwise bind the very path the engine would not place, and the runtime creates a missing one
// as root.
// 6. **A file is judged as a directory is** (novox/hq issue 495): never one of the machine's own roots, nor
// in a tree nothing is placed in (rule 2), and never below a directory or an access refused here. A file
// or an archive below a refused path is refused with it, whichever module declares it and in whatever
// order. Rules 3 and 4 are a directory's owner and do not reach a file: a file below /etc is the mesh's
// ordinary configuration, and one below a home is judged by home_links.go and agent_home_guard.go.
// A refused directory also gates the rest of its module, as a step that did not complete does
// (apply.go's `gated`): what a module declares after its directory was written for that directory.
//
// Each is a failed resource with its reason in the node's report; nothing is touched. Paths are judged as
// declared and again with every link in them resolved, so a link at /srv/x pointing at /etc places nothing.
@@ -407,7 +400,6 @@ const (
placingDirectory placing = iota
placingAccess
placingMount
placingFile
)
// refusePath says why a path is not placed or mounted; nil when it may be. module is the resource's module,
@@ -474,7 +466,7 @@ func refuseOne(path string, kind placing, module, owner string) *PlacementRefuse
for _, part := range strings.Split(path, "/") {
ssh = ssh || part == ".ssh"
}
if ssh && (kind == placingAccess || kind == placingMount) {
if ssh && kind != placingDirectory {
return &PlacementRefusedError{Path: path, Why: "it is an account's .ssh, which holds its keys and who may " +
"log in as it, and is never an access or a mount"}
}
@@ -510,12 +502,8 @@ func moduleOfID(id string) string {
return module
}
// refusedPlaces judges every directory, access, file and archive of a declaration before anything is applied,
// and answers each refusal by path: what is refused is refused again as a container's mount source.
//
// Directories and accesses first, so a file or an archive below one of them is refused with it whatever order
// they are declared in (novox/hq issue 495): the engine refused Docker's data root as a directory and then wrote
// a file into it, because nothing judged the file's path.
// refusedPlaces judges every directory and access of a declaration before anything is applied, and answers
// each refusal by path: what is refused is refused again as a container's mount source.
func refusedPlaces(resources []declaration.Resource) map[string]error {
out := map[string]error{}
for _, r := range resources {
@@ -532,60 +520,9 @@ func refusedPlaces(resources []declaration.Resource) map[string]error {
out[filepath.Clean(r.Target())] = err
}
}
trees := make(map[string]error, len(out))
for path, err := range out {
trees[path] = err
}
for _, r := range resources {
var err error
switch res := r.(type) {
case *declaration.File:
if err = belowRefused(res.Path, trees); err == nil {
err = refusePath(res.Path, placingFile, moduleOfID(res.ID), "")
}
case *declaration.Archive:
// Only below a refused path: where an archive may unpack is otherwise the archive's own judgement
// (archive.go), and the engine's own module unpacks its versions into its own tree.
err = belowRefused(res.Path, trees)
default:
continue
}
if err != nil {
out[filepath.Clean(r.Target())] = err
}
}
return out
}
// belowRefused says why a path below a refused directory or access is refused with it; nil when it is below
// none. Judged as declared and with its links resolved, as refusePath judges.
func belowRefused(path string, refused map[string]error) error {
clean := filepath.Clean(path)
if !filepath.IsAbs(clean) {
return nil
}
for _, p := range []string{clean, resolved(clean)} {
// The deepest refused tree it is below, so the same declaration always gives the same reason.
var tree string
for t := range refused {
if below(p, t) && len(t) > len(tree) {
tree = t
}
}
if tree == "" {
continue
}
why := refused[tree]
reason := why.Error()
var refusal *PlacementRefusedError
if errors.As(why, &refusal) {
reason = refusal.Why
}
return &PlacementRefusedError{Path: clean, Why: "it is below " + tree + ", which is refused: " + reason}
}
return nil
}
// refuseMounts says why a container's mounts are not made; nil when they may be.
func refuseMounts(c *declaration.Container, refused map[string]error) error {
for _, v := range c.Volumes {
-12
View File
@@ -14,15 +14,3 @@
./internal/inventory TestAnIssuedValueIsSealedAgainAfterAKeyChangeOrAnAcceptance
./internal/inventory TestAConditionsLooksAreKeptBesideTheBucket
./cmd/mesh-controller TestTheConditionsVerbReadsTheLooksTheBucketNoLongerHolds
./internal/inventory TestAWalksStartIsKeptAndARefusedSaveLeavesItUnsaid
./cmd/mesh-controller TestAWalkLetGoAndStoppedByVerbsIsSaidStartedAndEnded
./cmd/mesh-controller TestAWalkStoppedOrClosedByAPersonIsSaidEndedStopped
./cmd/mesh-controller TestAWalkRetriedByAPersonIsSaidStartedAgain
./cmd/mesh-controller TestABacklogReleasedByAPersonIsSaidStarted
./cmd/mesh-controller TestAWalkEndedByCancelOrClearIsSaidEnded
./cmd/mesh-controller TestAWalkRestartedByARebuildIsSaidStarted
./cmd/mesh-controller TestAWalkStoppedByHandAndRetriedEndsFailedWhenItFailsAgain
./cmd/mesh-controller TestReplay237
./cmd/mesh-controller TestAnUnassignThatLeavesItsNodeUnresolvedSaysSoOnceInItsAnswer
./cmd/mesh-controller TestAnUnassignThatLeavesItsNodeResolvedSaysNothingOfIt
./cmd/mesh-controller TestAnAssignThatLeavesItsNodeUnresolvedSaysOnlyThePlansRefusal