diff --git a/modules/mesh-delivery-builder/cmd/mesh-delivery-builder/main.go b/modules/mesh-delivery-builder/cmd/mesh-delivery-builder/main.go index d602f8e..f003aae 100644 --- a/modules/mesh-delivery-builder/cmd/mesh-delivery-builder/main.go +++ b/modules/mesh-delivery-builder/cmd/mesh-delivery-builder/main.go @@ -92,7 +92,16 @@ func run(ctx context.Context, getenv func(string) string, logOut io.Writer) erro hearing := buildrun.NewDeadLetterHearing(ctx, buildrun.JetStreamDeadLetters{JS: js}, delivery.AskLanguages, dead, logger.Printf, buildrun.SayHearing(ctx, hearingKV, logger.Printf)) defer hearing.Stop() - conn.SetReconnectHandler(func(*nats.Conn) { hearing.Again() }) + // Each ask's step is heard by its own watch and, at every step end of its build module and every reconnect, read + // (buildrun.HearEnds): a watch that goes deaf loses no end (the lost check of 2026-10-28). + var buildModules []string + for _, l := range delivery.AskLanguages { + if m, err := delivery.BuildModuleOf(l); err == nil { + buildModules = append(buildModules, m) + } + } + heard := buildrun.HearEnds(ctx, asks, asks, buildModules, logger.Printf) + conn.SetReconnectHandler(func(*nats.Conn) { hearing.Again(); heard.Nudge("") }) // The builder asks the controller, as its own account, whether the artifact store still holds a done key's blobs // (the seat verb held, novox/hq issue 1937) before it leaves the key done. calls, err := process.Connect(cred, nats.Name(cred.Node+"."+cred.Module+".calls"), nats.RetryOnFailedConnect(true)) @@ -102,7 +111,7 @@ func run(ctx context.Context, getenv func(string) string, logOut io.Writer) erro defer calls.Close() b := &build.Builder{ Claimer: build.Claimer{Store: kvStore{builds}, By: cred.Node + "." + cred.Module}, - Asks: buildrun.Asker{Publisher: asks, Waiter: buildrun.LostAskWaiter{Inner: asks, Dead: dead, Hearing: hearing}, Bound: bound}, + Asks: buildrun.Asker{Publisher: asks, Waiter: buildrun.LostAskWaiter{Inner: heard, Dead: dead, Hearing: hearing}, Bound: bound}, Held: heldOnTheBus{js}, // An ask that can no longer be answered is asked again (issue 1945), read at the step bound: a context's bound. Gone: heldOnTheBus{js}, diff --git a/modules/mesh-delivery-builder/go.mod b/modules/mesh-delivery-builder/go.mod index ddfb7c0..b8b03ce 100644 --- a/modules/mesh-delivery-builder/go.mod +++ b/modules/mesh-delivery-builder/go.mod @@ -3,7 +3,7 @@ module mesh-delivery-builder go 1.26.0 require ( - git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261028174713-38dbe1d3a388 + git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261028193502-f91340fe82ef github.com/nats-io/nats-server/v2 v2.11.17 github.com/nats-io/nats.go v1.54.0 ) diff --git a/modules/mesh-delivery-builder/go.sum b/modules/mesh-delivery-builder/go.sum index 6245202..cbc4905 100644 --- a/modules/mesh-delivery-builder/go.sum +++ b/modules/mesh-delivery-builder/go.sum @@ -1,5 +1,5 @@ -git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261028174713-38dbe1d3a388 h1:ycu/sNieTdLpD3bzhZOCXdzcoqXUOxPRmqWV019REpo= -git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261028174713-38dbe1d3a388/go.mod h1:ouERNpZizzwZ0HLEtAypsY9FR20FyUgUYRni6J7kVCY= +git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261028193502-f91340fe82ef h1:ggwHXCvAOhBCKAY+ErehKEhu/IQTS4poJBRDokGYnDc= +git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261028193502-f91340fe82ef/go.mod h1:ouERNpZizzwZ0HLEtAypsY9FR20FyUgUYRni6J7kVCY= github.com/antithesishq/antithesis-sdk-go v0.7.0-default-no-op h1:Z/MZK75wC/NSrkgqeNIa7jexam9uWzhLmFTSCPI/kn0= github.com/antithesishq/antithesis-sdk-go v0.7.0-default-no-op/go.mod h1:FQyySiasQQM8735Ddel3MRojmy4dA1IqCeyJ5jmPMbI= github.com/google/go-tpm v0.9.8 h1:slArAR9Ft+1ybZu0lBwpSmpwhRXaa85hWtMinMyRAWo= diff --git a/modules/mesh-delivery-builder/internal/build/run_test.go b/modules/mesh-delivery-builder/internal/build/run_test.go index 481d925..6cbb41c 100644 --- a/modules/mesh-delivery-builder/internal/build/run_test.go +++ b/modules/mesh-delivery-builder/internal/build/run_test.go @@ -691,6 +691,7 @@ func TestABuildAskWaitingInItsStreamIsNotBounded(t *testing.T) { byHand bool always bool // Gone says every ask cannot be answered, not only the first dead bool // DEAD_LETTERS keeps the first ask: the seat gave it up (issue 734) + deaf bool // the ask's own watch hears nothing though its step ends (the lost check of 2026-10-28) puts int done bool asking int // the asking the event says, 0 when none is said @@ -739,6 +740,7 @@ func TestABuildAskWaitingInItsStreamIsNotBounded(t *testing.T) { {name: "given up by its stream: asked again under a new id and done from it", puts: 2, done: true, asking: 2}, {name: "asked again by hand: the same, with no check bound", byHand: true, puts: 2, done: true, asking: 2}, {name: "given up into DEAD_LETTERS: its wait ends failed with the words and it is asked again at once", dead: true, puts: 2, done: true, asking: 2}, + {name: "its step ended while its watch was deaf: read at its build module's next step end, done with no new ask", deaf: true, puts: 1, done: true}, {name: "never answerable: failed after its askings", askings: 2, always: true, puts: 2}, {name: "taken over at its last asking: failed, not asked again", askings: 3, always: true, step: "asked mesh-build-go again (asking 3): x", puts: 0}, } { @@ -829,7 +831,12 @@ func TestABuildAskWaitingInItsStreamIsNotBounded(t *testing.T) { if c.dead { r.b.Asks = buildrun.Asker{Publisher: r.asks, Waiter: buildrun.LostAskWaiter{Inner: r.asks, Dead: dead}, Bound: 2 * time.Second} } - if !c.byHand && !c.dead { + var heard *buildrun.HeardEnds + if c.deaf { + heard = &buildrun.HeardEnds{Inner: silentWatch{}, Read: r.asks} + r.b.Asks = buildrun.Asker{Publisher: r.asks, Waiter: heard, Bound: 2 * time.Second} + } + if !c.byHand && !c.dead && !c.deaf { gone.why = func(a delivery.StepAsk) string { if c.always || a.ID == first || first == "" { return "it waits first in line while a node took a later ask" @@ -851,7 +858,16 @@ func TestABuildAskWaitingInItsStreamIsNotBounded(t *testing.T) { } } } - if c.done { + if c.deaf { + r.asks.End(r.answer(waitForAsks(t, r, 1)[0])) + for deadline := time.Now().Add(2 * time.Second); heard.Waiting() == 0; time.Sleep(time.Millisecond) { + if time.Now().After(deadline) { + t.Fatal("no ask is waited on") + } + } + heard.Nudge(buildrun.GoBuildModule) // a step of mesh-build-go ended + } + if c.done && !c.deaf { asks := waitForAsks(t, r, c.puts) if first == "" && !c.byHand { first = asks[0].ID @@ -876,7 +892,7 @@ func TestABuildAskWaitingInItsStreamIsNotBounded(t *testing.T) { mu.Lock() defer mu.Unlock() // Note 62: the old message of an ask asked again because its stream gave it up is dropped from the stream. - if gone.mu.Lock(); c.done && !c.byHand && !c.dead && (len(gone.dropped) != 1 || gone.dropped[0] != first) { + if gone.mu.Lock(); c.done && !c.byHand && !c.dead && !c.deaf && (len(gone.dropped) != 1 || gone.dropped[0] != first) { t.Errorf("dropped %v from the stream, want the old ask %s", gone.dropped, first) } gone.mu.Unlock() @@ -1086,3 +1102,10 @@ func TestATakeOverThatCannotReadTheStreamWaitsForTheAsk(t *testing.T) { t.Fatalf("the key = %+v after %d asks, want done from the ask's step, none put", v, len(r.asks.Asks())) } } + +// silentWatch is a watch of an ask's step that stays open and hears nothing. +type silentWatch struct{} + +func (silentWatch) WatchAsk(context.Context, string, string) (<-chan delivery.Step, error) { + return make(chan delivery.Step), nil +} diff --git a/modules/mesh-delivery-checker/cmd/mesh-delivery-checker-tools/main.go b/modules/mesh-delivery-checker/cmd/mesh-delivery-checker-tools/main.go index a6a6936..660b6d5 100644 --- a/modules/mesh-delivery-checker/cmd/mesh-delivery-checker-tools/main.go +++ b/modules/mesh-delivery-checker/cmd/mesh-delivery-checker-tools/main.go @@ -1,6 +1,6 @@ // Command mesh-delivery-checker-tools serves the checker's read tools (novox/hq ADR 0484 clause 13, issue 1686): the runtime // launches it for a call, it reads the checker's verdicts and kept states and the indexer's candidates through the checker's -// state and reads, and writes nothing. The checker is the other program: it serves no tool (ADR 0437 §4). +// state and reads. It writes only the tries (the try's tools) and, asking a check again by hand, one verdict. The checker is the other program: it serves no tool (ADR 0437 §4). package main import ( @@ -235,6 +235,24 @@ func Tools(r check.Reader) []stdio.Tool { } } +// RecoveryTools are the tools that steer a check by hand (tools-are-how-a-module-is-spoken-to): ask a check again whose +// wait judged nothing (the lost check of 2026-10-28). They write the checker's verdicts through w. +func RecoveryTools(r check.Reader, w check.VerdictEntry) []stdio.Tool { + str := func(args map[string]any, k string) string { s, _ := args[k].(string); return s } + return []stdio.Tool{{Name: check.AskAgainTool, + Description: "Ask a candidate's check again by hand, whose verdict stays running while nothing runs for it (" + check.StatusReadTool + " names it " + + "under lost): its verdict is ended as asked again, saying why, and the checker, which hears its verdicts, stops the wait that judged nothing " + + "and asks the check anew, whole. Refused for a group with no candidate, a verdict that is not running (a pass or failure stands until a push or " + + "a trunk move), and while a step of its pull requests can still run on a build module (its end judges it). The checker reads a step that " + + "ended while its watch was deaf by itself at the next step end of its build module; this is for what that does not reach.", + Input: map[string]any{"type": "object", "required": []string{"group", "why"}, "properties": map[string]any{ + "group": map[string]any{"type": "string", "description": "the delivery group's branch name"}, + "why": map[string]any{"type": "string", "description": "why it is asked again, in words; kept in the verdict it ends"}}}, + Run: func(args map[string]any) (any, error) { + return r.AskAgain(w, str(args, "group"), str(args, "why")) + }}} +} + // stepBound is the checker's step bound as the checker reads it (MESH_CHECKER_STEP_BOUND), its default when unset or not a // duration. func stepBound() time.Duration { @@ -249,7 +267,8 @@ func main() { PreviewState: read(stdio.State("previews")), StepStates: map[string]check.StateRead{"mesh-build-go": read(stdio.State("mesh-build-go.steps")), "mesh-build-node": read(stdio.State("mesh-build-node.steps"))}, HaveState: read(stdio.State("node-engine.have")), StepBound: stepBound(), - TurnState: read(stdio.State("mesh-delivery-gate.turns")), HearingState: read(stdio.State(buildrun.HearingState))} + TurnState: read(stdio.State("mesh-delivery-gate.turns")), HearingState: read(stdio.State(buildrun.HearingState)), + AskState: read(stdio.State(check.AsksState))} r.Runs = runsOf{read(stdio.State("mesh-delivery-indexer.modules"))} // the node-engine at the commit the mesh runs, as the checker reads it tries := stdio.State(check.TriesState) source := stdio.State("mesh-delivery-gate.source") @@ -277,7 +296,20 @@ func main() { return err }} trying := Trying{Tries: store, Ender: store, Trunks: trunks} - if err := stdio.Serve("", logged(append(Tools(r), TryTools(trying)...))); err != nil { + verdicts := stdio.State("verdicts") + written := stateStore{entry: func(key string) (json.RawMessage, uint64, error) { + reads.Add(1) + e, err := verdicts.Get(key) + if err != nil || e == nil { + return nil, 0, err + } + return e.Value, e.Revision, nil + }, update: func(key string, value []byte, revision uint64) error { + _, err := verdicts.Update(key, json.RawMessage(value), revision) + return err + }} + tools := append(append(Tools(r), TryTools(trying)...), RecoveryTools(r, written)...) + if err := stdio.Serve("", logged(tools)); err != nil { fmt.Fprintf(os.Stderr, "[mesh-delivery-checker-tools] %v\n", err) os.Exit(1) } diff --git a/modules/mesh-delivery-checker/cmd/mesh-delivery-checker-tools/main_test.go b/modules/mesh-delivery-checker/cmd/mesh-delivery-checker-tools/main_test.go index 9f250df..282db23 100644 --- a/modules/mesh-delivery-checker/cmd/mesh-delivery-checker-tools/main_test.go +++ b/modules/mesh-delivery-checker/cmd/mesh-delivery-checker-tools/main_test.go @@ -23,6 +23,14 @@ func TestTheToolsServedAreTheFiveReadTools(t *testing.T) { if !slices.Equal(names, want) { t.Errorf("tools = %v, want %v", names, want) } + // The recovery tool beside them asks a lost check again; with nothing to write it refuses. + recovery := RecoveryTools(check.Reader{}, nil) + if len(recovery) != 1 || recovery[0].Name != check.AskAgainTool || recovery[0].Description == "" { + t.Errorf("recovery tools = %+v", recovery) + } + if _, err := recovery[0].Run(map[string]any{"group": "feat/x", "why": "lost"}); err == nil { + t.Errorf("%s answered with no state to write", check.AskAgainTool) + } // With nothing to read from a tool says so and changes nothing. for _, tl := range Tools(check.Reader{}) { if tl.Name == check.StatusReadTool { diff --git a/modules/mesh-delivery-checker/cmd/mesh-delivery-checker/bus.go b/modules/mesh-delivery-checker/cmd/mesh-delivery-checker/bus.go index d81d219..a5453a6 100644 --- a/modules/mesh-delivery-checker/cmd/mesh-delivery-checker/bus.go +++ b/modules/mesh-delivery-checker/cmd/mesh-delivery-checker/bus.go @@ -9,6 +9,7 @@ import ( "git.novox.be/novox/mesh-sdk/go/catalogue" "git.novox.be/novox/mesh-sdk/go/delivery" + "git.novox.be/novox/mesh-sdk/go/process" "mesh-delivery-checker/internal/check" ) @@ -130,3 +131,55 @@ func (m manifestReader) Manifest(ctx context.Context, digest string) (catalogue. func parseManifest(raw string) (catalogue.Manifest, error) { return catalogue.ParseManifestForInputs([]byte(raw)) } + +// awaitedKV is a bucket that may appear after the start (process.AwaitBucket) as a check.KV: a call while it is not on the +// bus fails saying so. +type awaitedKV struct{ b *process.AwaitedBucket } + +func (a awaitedKV) kv() (kvStore, error) { + kv := a.b.KV() + if kv == nil { + return kvStore{}, errors.New("the bucket is not on the bus yet") + } + return kvStore{kv}, nil +} + +func (a awaitedKV) Get(ctx context.Context, key string) ([]byte, uint64, bool, error) { + s, err := a.kv() + if err != nil { + return nil, 0, false, err + } + return s.Get(ctx, key) +} + +func (a awaitedKV) Create(ctx context.Context, key string, value []byte) (uint64, error) { + s, err := a.kv() + if err != nil { + return 0, err + } + return s.Create(ctx, key, value) +} + +func (a awaitedKV) Update(ctx context.Context, key string, value []byte, revision uint64) (uint64, error) { + s, err := a.kv() + if err != nil { + return 0, err + } + return s.Update(ctx, key, value, revision) +} + +func (a awaitedKV) Keys(ctx context.Context) ([]string, error) { + s, err := a.kv() + if err != nil { + return nil, err + } + return s.Keys(ctx) +} + +func (a awaitedKV) Delete(ctx context.Context, key string) error { + s, err := a.kv() + if err != nil { + return err + } + return s.Delete(ctx, key) +} diff --git a/modules/mesh-delivery-checker/cmd/mesh-delivery-checker/integration_test.go b/modules/mesh-delivery-checker/cmd/mesh-delivery-checker/integration_test.go index 6b39ca3..a3bf800 100644 --- a/modules/mesh-delivery-checker/cmd/mesh-delivery-checker/integration_test.go +++ b/modules/mesh-delivery-checker/cmd/mesh-delivery-checker/integration_test.go @@ -89,6 +89,8 @@ type fakeBuildModules struct { // beside is, by workspace, the siblings the fetch placed in it as ` `, sorted: a digest echoes them // (1929/AC2; mesh-sdk buildstep.besideOf), or the level runs whole and keeps nothing. beside map[string][]string + // names are the nodes' names the last check ask carried, for the names check (ADR 0567 §12). + names []string } func (f *fakeBuildModules) count(tool string) int { @@ -191,7 +193,14 @@ func (f *fakeBuildModules) serve(t *testing.T, module string, kept jetstream.Key } p := &buildstep.Puller{Source: &buildstep.JetStreamAsks{JS: f.js, Language: language}, Language: language, Node: "n1", Put: put, Capacity: func() int { return 2 }, PullWait: 200 * time.Millisecond, - Run: func(ctx context.Context, a delivery.StepAsk) (any, error) { return buildstep.RunAsk(ctx, steps, a) }} + Run: func(ctx context.Context, a delivery.StepAsk) (any, error) { + if a.Check != nil { + f.mu.Lock() + f.names = a.Check.NodeNames + f.mu.Unlock() + } + return buildstep.RunAsk(ctx, steps, a) + }} go func() { _ = p.Pull(f.ctx) }() } @@ -334,6 +343,7 @@ func startBed(t *testing.T) *bed { t.Fatal(err) } b.setOnline(t, "n1", true) + b.setNode(t, "n1") for _, module := range []string{"mesh-build-go", "mesh-build-node"} { b.setHealth(t, "n1", module) } @@ -366,6 +376,20 @@ func (b *bed) setOnline(t *testing.T, node string, online bool) { } } +// setNode writes the node's record in the node-engine's have, as the node-engine does, so the checker names it in each +// check ask (ADR 0567 §12); with no record the checker asks no check. +func (b *bed) setNode(t *testing.T, node string) { + t.Helper() + data, err := delivery.EncodeNodeRecord(delivery.NodeRecord{V: 1, Node: node}) + if err != nil { + t.Fatal(err) + } + key, _ := delivery.HaveNodeKey(node) + if _, err := b.buckets[delivery.HaveBucket].Put(b.ctx, key, data); err != nil { + t.Fatal(err) + } +} + func (b *bed) setHealth(t *testing.T, node, module string) { t.Helper() data, err := delivery.EncodeHave(delivery.Have{Phase: delivery.PhaseRunning, Health: delivery.HealthOK}) @@ -493,6 +517,12 @@ func TestCheckerJudgesACandidateAndOwesItsStatus(t *testing.T) { // N6/AC5, 1300 if v.Composition == nil || v.Composition.State != delivery.CompositionNotRun || len(v.Machines) != 1 || v.Machines[0] != "n1" { t.Errorf("composition %+v machines %v", v.Composition, v.Machines) } + b.fake.mu.Lock() + names := b.fake.names + b.fake.mu.Unlock() + if len(names) != 1 || names[0] != "n1" { + t.Errorf("the check ask named the nodes %v, want [n1] from the have's node record", names) + } o := b.owed(t, 7, head1, "success") if o.Context != delivery.StatusContextCheck || !strings.HasPrefix(o.Text, "pass 111111111111 on aaaaaaaaaaaa") || !strings.Contains(o.Text, "unit 2 run") { t.Errorf("owed = %+v", o) @@ -797,7 +827,8 @@ func TestTheCheckerSaysOwedReadableOnTheBus(t *testing.T) { // R2-1 break } if said.Module != "mesh-delivery-checker" || said.Node != "n1" || !said.Keeps("owed") || !said.Readable("owed") || - !said.Readable("previews") || !said.Readable("verdicts") || !said.Readable("kept") || !said.Readable("tries") || said.Readable("hearing") || len(said.States) != 6 { - t.Fatalf("the checker said %+v, want its six states with kept, owed, previews, tries and verdicts readable, tries by the delivery view (1929/AC4; 1887 A5b; build_usage)", said) + !said.Readable("previews") || !said.Readable("verdicts") || !said.Readable("kept") || !said.Readable("tries") || said.Readable("hearing") || + !said.Keeps("asks") || said.Readable("asks") || len(said.States) != 7 { + t.Fatalf("the checker said %+v, want its seven states, asks and hearing its own, with kept, owed, previews, tries and verdicts readable, tries by the delivery view (1929/AC4; 1887 A5b; build_usage)", said) } } diff --git a/modules/mesh-delivery-checker/cmd/mesh-delivery-checker/main.go b/modules/mesh-delivery-checker/cmd/mesh-delivery-checker/main.go index 52530d5..a485138 100644 --- a/modules/mesh-delivery-checker/cmd/mesh-delivery-checker/main.go +++ b/modules/mesh-delivery-checker/cmd/mesh-delivery-checker/main.go @@ -69,6 +69,8 @@ var keptStates = []announce.State{ // design limit 1); the checker alone writes them (ADR 0444 clause 5). // Whether DEAD_LETTERS is heard (issue 734): read by the checker's own status tool alone. {Name: "hearing"}, + // The asks each running check put (check.AsksState): read by the checker's own checker_ask_again alone. + {Name: "asks"}, {Name: "kept", Readable: true}, {Name: "owed", Readable: true}, {Name: "previews", Readable: true}, @@ -144,9 +146,14 @@ func run(ctx context.Context, getenv func(string) string, logOut io.Writer) erro hearing := buildrun.NewDeadLetterHearing(ctx, buildrun.JetStreamDeadLetters{JS: js}, []string{delivery.AskGo, delivery.AskNode}, dead, logger.Printf, buildrun.SayHearing(ctx, hearingKV, logger.Printf)) defer hearing.Stop() - conn.SetReconnectHandler(func(*nats.Conn) { hearing.Again() }) - waiter := buildrun.LostAskWaiter{Inner: asks, Dead: dead, Hearing: hearing} + // Each ask's step is heard by its own watch and, at every step end of its build module and every reconnect, read + // (buildrun.HearEnds): a watch that goes deaf loses no end (the lost check of 2026-10-28). + heard := buildrun.HearEnds(ctx, asks, asks, []string{buildrun.GoBuildModule, buildrun.NodeBuildModule}, logger.Printf) + conn.SetReconnectHandler(func(*nats.Conn) { hearing.Again(); heard.Nudge("") }) + waiter := buildrun.LostAskWaiter{Inner: heard, Dead: dead, Hearing: hearing} + asksKV := process.AwaitBucket(ctx, js, conn, check.AsksBucket, "checker_ask_again refuses every check, as it cannot tell whether its ask waits in a stream", logger.Printf) ch := &check.Checker{ + Asks: awaitedKV{asksKV}, Verdicts: kvStore{buckets[delivery.CheckerVerdictsBucket]}, Owed: kvStore{buckets[delivery.CheckerOwedBucket]}, Trunks: trunks, @@ -331,6 +338,18 @@ func run(ctx context.Context, getenv func(string) string, logOut io.Writer) erro } }) }() + // The checker's own verdicts, updates only: one checker_ask_again wrote asks its check again (Checker.VerdictWritten). + vw, err := buckets[delivery.CheckerVerdictsBucket].WatchAll(ctx, jetstream.UpdatesOnly()) + if err != nil { + return fmt.Errorf("the checker's verdicts cannot be watched, so no check can be asked again by hand: %w", err) + } + go func() { + errs <- follow(ctx, vw, func(e jetstream.KeyValueEntry) { + if opOf(e) { + ch.VerdictWritten(ctx, e.Key(), e.Value()) + } + }) + }() logger.Printf("started on %s", cred.Node) go func() { errs <- follow(ctx, w, each) }() select { diff --git a/modules/mesh-delivery-checker/go.mod b/modules/mesh-delivery-checker/go.mod index 85ac234..0eb617e 100644 --- a/modules/mesh-delivery-checker/go.mod +++ b/modules/mesh-delivery-checker/go.mod @@ -3,7 +3,7 @@ module mesh-delivery-checker go 1.26.0 require ( - git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261028174713-38dbe1d3a388 + git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261028193502-f91340fe82ef github.com/nats-io/nats-server/v2 v2.11.17 github.com/nats-io/nats.go v1.54.0 ) diff --git a/modules/mesh-delivery-checker/go.sum b/modules/mesh-delivery-checker/go.sum index 6245202..cbc4905 100644 --- a/modules/mesh-delivery-checker/go.sum +++ b/modules/mesh-delivery-checker/go.sum @@ -1,5 +1,5 @@ -git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261028174713-38dbe1d3a388 h1:ycu/sNieTdLpD3bzhZOCXdzcoqXUOxPRmqWV019REpo= -git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261028174713-38dbe1d3a388/go.mod h1:ouERNpZizzwZ0HLEtAypsY9FR20FyUgUYRni6J7kVCY= +git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261028193502-f91340fe82ef h1:ggwHXCvAOhBCKAY+ErehKEhu/IQTS4poJBRDokGYnDc= +git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261028193502-f91340fe82ef/go.mod h1:ouERNpZizzwZ0HLEtAypsY9FR20FyUgUYRni6J7kVCY= github.com/antithesishq/antithesis-sdk-go v0.7.0-default-no-op h1:Z/MZK75wC/NSrkgqeNIa7jexam9uWzhLmFTSCPI/kn0= github.com/antithesishq/antithesis-sdk-go v0.7.0-default-no-op/go.mod h1:FQyySiasQQM8735Ddel3MRojmy4dA1IqCeyJ5jmPMbI= github.com/google/go-tpm v0.9.8 h1:slArAR9Ft+1ybZu0lBwpSmpwhRXaa85hWtMinMyRAWo= diff --git a/modules/mesh-delivery-checker/internal/check/askagain.go b/modules/mesh-delivery-checker/internal/check/askagain.go new file mode 100644 index 0000000..7540bbe --- /dev/null +++ b/modules/mesh-delivery-checker/internal/check/askagain.go @@ -0,0 +1,198 @@ +package check + +import ( + "context" + "encoding/json" + "errors" + "fmt" + "strings" + + "git.novox.be/novox/mesh-sdk/go/delivery" +) + +// **A check is asked again by hand** (the lost check of 2026-10-28; tools-are-how-a-module-is-spoken-to: every recovery +// has a tool). checker_ask_again ends a candidate's running verdict, whose wait judged nothing, with AskedAgainWords and +// the why; the checker hears it on its watch of its verdicts (Checker.VerdictWritten), ends the check of those heads +// running in it, and claims and asks it anew, a whole check (IsEnded). It is refused while a step of the candidate's pull +// requests can still run (checker_status's running_steps): that step's end judges it; and while an ask the check put is +// still in its build seat's stream, taken by no node (it has no step key yet): asking again then would run the check twice +// (issue 1791's kind). The checker keeps the asks each running check put in its state asks (AsksState, by verdict key). +// An ask is not put again under its own id instead: the stream de-duplicates an id within its window, so the copy waiting +// stays and the new one is dropped, and past the window both would run; nothing takes a put ask back (buildrun.Asker). + +// AsksState is the checker's state of the asks each running check put, by verdict key (CheckAsks); AsksBucket its bucket. +const ( + AsksState = "asks" + AsksBucket = delivery.CheckerModule + "_" + AsksState +) + +// CheckAsks are the asks a check put, in order, as the state asks keeps them while it runs; its end deletes the key. +type CheckAsks struct { + Asks []string `json:"asks"` +} + +// AsksKV is the state asks: a KV whose key a check's end deletes, so the state holds only the checks that run. +type AsksKV interface { + KV + Delete(ctx context.Context, key string) error +} + +// forgetAsks deletes the asks a check put at its end; one that cannot be deleted is said, and the next check of the same +// heads writes the key anew. +func (ch *Checker) forgetAsks(ctx context.Context, key string) { + if err := ch.Asks.Delete(ctx, key); err != nil { + ch.logf("%s: the asks it put could not be forgotten at its end: %v", key, err) + } +} + +// recordAsks keeps the asks a check put under its verdict key; nil Asks keeps nothing. A record that cannot be written +// is said: checker_ask_again then refuses the check, as it cannot tell whether its ask waits in a stream. +func (ch *Checker) recordAsks(ctx context.Context, key string, asks []string) { + if ch.Asks == nil { + return + } + data, err := json.Marshal(CheckAsks{Asks: asks}) + if err == nil { + _, err = putOnce(ctx, ch.Asks, key, data, func(cur []byte) bool { return string(cur) == string(data) }) + } + if err != nil { + ch.logf("%s: the asks it put cannot be kept (%v), so %s refuses it", key, err, AskAgainTool) + } +} + +// AskAgainTool asks a candidate's check again by hand. +const AskAgainTool = "checker_ask_again" + +// AskedAgainWords open the words of a verdict AskAgainTool wrote; the why follows. +const AskedAgainWords = EndedWords + "asked again by hand (" + AskAgainTool + "): " + +// errAskedAgain is the cause a running check is ended with when its verdict was asked again by hand. +var errAskedAgain = errors.New("its verdict was asked again by hand (" + AskAgainTool + ")") + +// IsAskedAgain says whether a verdict was written by AskAgainTool. +func IsAskedAgain(v delivery.Verdict) bool { + return IsEnded(v) && strings.HasPrefix(v.Failed.Words, AskedAgainWords) +} + +// VerdictEntry is the verdicts state as the ask-again tool writes it: a key's value and revision (nil and 0 for none), +// and a compare-and-set. +type VerdictEntry interface { + Entry(key string) (json.RawMessage, uint64, error) + Update(key string, value []byte, revision uint64) error +} + +// AskedAgain is the answer of AskAgainTool. +type AskedAgain struct { + Key string `json:"key"` + Was string `json:"was"` + Said string `json:"said"` + Note string `json:"note"` +} + +// AskAgain ends the running verdict of the group's candidate as asked again by hand, saying why. It refuses a group with +// no candidate, a verdict that is not running (a pass or a failure stands until a push or a trunk move), one a step of +// whose pull requests can still run, and one whose asks are not known or one of which no node took yet. +func (r Reader) AskAgain(w VerdictEntry, group, why string) (AskedAgain, error) { + why = strings.TrimSpace(why) + if group == "" || why == "" { + return AskedAgain{}, fmt.Errorf("give the group and why it is asked again") + } + if w == nil { + return AskedAgain{}, fmt.Errorf("the verdicts state cannot be written here") + } + c, ok := r.candidate(group) + if !ok { + return AskedAgain{}, fmt.Errorf("no candidate is held for the group %q", group) + } + key, err := delivery.CheckerVerdictKey(c.Group, c.HeadsHash) + if err != nil { + return AskedAgain{}, err + } + raw, rev, err := w.Entry(key) + if err != nil { + return AskedAgain{}, fmt.Errorf("%s cannot be read: %w", key, err) + } + if len(raw) == 0 { + return AskedAgain{}, fmt.Errorf("%s holds no verdict: the checker claims its check when it looks at the candidate (%s)", key, StatusReadTool) + } + v, err := delivery.DecodeVerdict(raw) + if err != nil { + return AskedAgain{}, fmt.Errorf("%s holds what is not a verdict: %w", key, err) + } + if v.State != delivery.VerdictRunning { + return AskedAgain{}, fmt.Errorf("%s is %s, not running: a verdict stands until a push or a trunk move asks it again", key, v.State) + } + steps := r.readSteps() + for _, rs := range steps.running { + if asksOf(c, rs.What) { + return AskedAgain{}, fmt.Errorf("a step of it runs: %s %s on %s since %s (%s); its end judges it", rs.Module, rs.ID, rs.Node, rs.Since, rs.What) + } + } + if r.AskState.Get == nil { + return AskedAgain{}, fmt.Errorf("the checker's asks are not readable here, so whether its ask waits in a build seat's stream cannot be told") + } + kept, err := r.AskState.Get(key) + var put CheckAsks + if err == nil && len(kept) > 0 { + err = json.Unmarshal(kept, &put) + } + if err != nil || len(put.Asks) == 0 { + return AskedAgain{}, fmt.Errorf("the checker names no ask of %s (%v), so whether one waits in a build seat's stream cannot be told; asking again could run it twice", key, err) + } + taken := map[string]bool{} + for _, s := range steps.all { + taken[s.step.ID] = true + } + for _, id := range put.Asks { + if !taken[id] { + return AskedAgain{}, fmt.Errorf("its ask %s waits in its build seat's stream, taken by no node yet: asking again would run it twice; "+ + "the seats' backlog is in mesh-delivery-view.build_usage", id) + } + } + words := AskedAgainWords + why + ended := delivery.Verdict{Group: v.Group, Heads: v.Heads, Trunk: v.Trunk, State: delivery.VerdictFail, + Failed: delivery.FailedFirst{Machine: "checker", Words: words}} + data, err := delivery.EncodeVerdict(ended) + if err != nil { + return AskedAgain{}, err + } + if err := w.Update(key, data, rev); err != nil { + return AskedAgain{}, fmt.Errorf("%s changed while it was asked again, so it was not; read it again: %w", key, err) + } + return AskedAgain{Key: key, Was: v.State, Said: words, + Note: "the checker hears it on its watch of its verdicts, ends the wait that judged nothing and asks the check anew, whole; " + + VerdictsReadTool + " shows it running again"}, nil +} + +// VerdictWritten takes a change of the checker's verdicts in (its watch, updates only): a verdict AskAgainTool wrote ends +// the check of those heads running in this process, which then considers them again; with none running, the candidate +// that holds them is considered at once. Any other verdict is the checker's own, and left. +func (ch *Checker) VerdictWritten(ctx context.Context, key string, value []byte) { + v, err := delivery.DecodeVerdict(value) + if err != nil || !IsAskedAgain(v) { + return + } + ch.init() + ch.mu.Lock() + if l, ok := ch.live[key]; ok { + l.end(errAskedAgain) + ch.mu.Unlock() + ch.logf("%s: %s; the check running for it is ended and asked again", key, v.Failed.Words) + return + } + var group string + var cand delivery.Candidate + for k, c := range ch.known { + if vk, err := delivery.CheckerVerdictKey(c.Group, c.HeadsHash); err == nil && vk == key { + group, cand = k, c + break + } + } + ch.mu.Unlock() + if group == "" { + ch.logf("%s: %s, but no candidate holds these heads, so nothing is asked", key, v.Failed.Words) + return + } + ch.logf("%s: %s; asked again", key, v.Failed.Words) + ch.consider(ctx, group, cand) +} diff --git a/modules/mesh-delivery-checker/internal/check/checker.go b/modules/mesh-delivery-checker/internal/check/checker.go index 3e5b1da..da952d3 100644 --- a/modules/mesh-delivery-checker/internal/check/checker.go +++ b/modules/mesh-delivery-checker/internal/check/checker.go @@ -79,6 +79,8 @@ type Checker struct { } // Bound is how long one check may run; none when 0 (DefaultBound). Bound time.Duration + // Asks keeps the asks each running check put, by verdict key (AsksState), for checker_ask_again; nil keeps none. + Asks AsksKV // Link is the base of the address a status points at; the verdict key follows. Link string // Announce says a status was written (EventOwedWritten); nil says nothing. @@ -328,7 +330,11 @@ func (ch *Checker) consider(ctx context.Context, key string, c delivery.Candidat delete(ch.again, vkey) delete(ch.live, vkey) ch.mu.Unlock() + again := errors.Is(context.Cause(run), errAskedAgain) end(nil) + if again && ctx.Err() == nil { + ch.consider(ctx, key, ch.candidate(key, c)) // asked again by hand (AskAgainTool): claimed anew + } }() for { // Every check is asked at once: the build seats' streams hold the backlog, a new head's check and a check after a @@ -711,10 +717,20 @@ func (ch *Checker) try(ctx, run context.Context, key string, cs *Case) { return } began := ch.now() + if cs.Watch == nil && ch.Asks != nil { + cs.Watch = func(_ string, step *delivery.Step) { + if step == nil { // put: kept before its wait starts + ch.recordAsks(ctx, cs.Key, cs.Asks()) + } + } + defer ch.forgetAsks(ctx, cs.Key) + } ch.writeOwed(ctx, cs, delivery.Verdict{State: delivery.VerdictRunning}, Outcome{}) out := ch.judge(run, cs) - // An ask the build seat gave up on judged nothing (issue 734): the check is asked again under the same claim, its status - // pending, and after LostAskTries it fails as not heard, judged again when the nodes change. + // An ask the build seat gave up on, or whose step the build module's next process ended because it was replaced under + // it, judged nothing (issue 734, IsLostAsk): the check is asked again under the same claim, its status pending, and after + // LostAskTries it fails as not heard, judged again when the nodes change. A step that ended while its watch was deaf is + // read at the next nudge (HeardEnds) and judged. for try := 1; IsLostAsk(out.Verdict) && run.Err() == nil; try++ { if try >= LostAskTries { out.Verdict.Failed.Words = strings.TrimSpace(out.Verdict.Failed.Words + "\nasked " + fmt.Sprint(LostAskTries) + @@ -724,8 +740,8 @@ func (ch *Checker) try(ctx, run context.Context, key string, cs *Case) { ch.logf("%s: %s; asked again (%d of %d)", cs.Key, out.Verdict.Failed.Words, try+1, LostAskTries) out = ch.judge(run, cs) } - if ctx.Err() != nil { - return + if ctx.Err() != nil || errors.Is(context.Cause(run), errAskedAgain) { + return // the checker stops, or the verdict was asked again by hand, which wrote it: its next check claims it anew } var why superseded if errors.As(context.Cause(run), &why) { diff --git a/modules/mesh-delivery-checker/internal/check/fakes_test.go b/modules/mesh-delivery-checker/internal/check/fakes_test.go index 2965b72..d53f2a1 100644 --- a/modules/mesh-delivery-checker/internal/check/fakes_test.go +++ b/modules/mesh-delivery-checker/internal/check/fakes_test.go @@ -60,3 +60,11 @@ func (m *memKV) Keys(context.Context) ([]string, error) { sort.Strings(keys) return keys, nil } + +func (m *memKV) Delete(_ context.Context, key string) error { + m.mu.Lock() + defer m.mu.Unlock() + delete(m.vals, key) + delete(m.revs, key) + return nil +} diff --git a/modules/mesh-delivery-checker/internal/check/lostask.go b/modules/mesh-delivery-checker/internal/check/lostask.go index 4db60c6..8328e46 100644 --- a/modules/mesh-delivery-checker/internal/check/lostask.go +++ b/modules/mesh-delivery-checker/internal/check/lostask.go @@ -3,6 +3,7 @@ package check import ( "strings" + "git.novox.be/novox/mesh-sdk/go/buildstep" "git.novox.be/novox/mesh-sdk/go/delivery" "git.novox.be/novox/mesh-sdk/go/delivery/buildrun" ) @@ -19,9 +20,13 @@ import ( // judged again when the nodes change. const LostAskTries = 3 -// IsLostAsk says whether a verdict failed because the build seat gave its ask up (buildrun.LostWords). +// IsLostAsk says whether a verdict failed because its ask judged nothing: the build seat gave it up (buildrun.LostWords), or +// the build module that ran its step was replaced under it, and its next process ended the step it left running +// (buildstep.RestartReason; a delivery of the build module, as on 2026-10-28). Neither is the change's failure: the check +// is asked again, as for a given-up ask. func IsLostAsk(v delivery.Verdict) bool { - return v.State == delivery.VerdictFail && strings.Contains(v.Failed.Words, buildrun.LostWords) + return v.State == delivery.VerdictFail && (strings.Contains(v.Failed.Words, buildrun.LostWords) || + strings.Contains(v.Failed.Words, buildstep.RestartReason)) } // IsNotTaken says whether a verdict failed because no build node took its ask within the bound (buildrun.NotTakenWords). diff --git a/modules/mesh-delivery-checker/internal/check/lostask_test.go b/modules/mesh-delivery-checker/internal/check/lostask_test.go index 35ea6a5..ddf4d33 100644 --- a/modules/mesh-delivery-checker/internal/check/lostask_test.go +++ b/modules/mesh-delivery-checker/internal/check/lostask_test.go @@ -8,6 +8,7 @@ import ( "testing" "time" + "git.novox.be/novox/mesh-sdk/go/buildstep" "git.novox.be/novox/mesh-sdk/go/delivery" "git.novox.be/novox/mesh-sdk/go/delivery/buildrun" ) @@ -141,30 +142,206 @@ func TestAnAskGivenUpOrNeverTakenEndsItsTryAsErrorAndItsHeadIsAskedAnew(t *testi }) } -// Issue 734: a pull request's check whose ask the build seat gave up on is asked again under its claim, its status -// pending, and judged; one given up every time fails as not heard and is judged again when the nodes change. -func TestACheckWhoseAskWasGivenUpIsAskedAgain(t *testing.T) { +// troubled is the build seat as a check meets it when its step's end does not reach its wait: the first `restarts` asks' +// steps are ended by the build module's next process (buildstep.RestartReason), and the first `deaf` asks' watches hear +// nothing though their steps end (the lost check of 2026-10-28). Its steps state is read through AskSteps and Steps. +type troubled struct { + *buildrun.FakeAsks + answer func(delivery.StepAsk) delivery.Step + + mu sync.Mutex + restarts, deaf int + deafIDs map[string]bool + steps map[string]delivery.Step +} + +func (tr *troubled) PublishAsk(ctx context.Context, subject, id string, data []byte) error { + if err := tr.FakeAsks.PublishAsk(ctx, subject, id, data); err != nil { + return err + } + a, err := delivery.DecodeStepAsk(data) + if err != nil { + return err + } + step := tr.answer(a) + step.What = buildstep.AskWhat(a) + tr.mu.Lock() + if tr.restarts > 0 { + tr.restarts-- + step.State, step.Reason, step.Result = delivery.StepFailed, buildstep.RestartReason, nil + } + deaf := tr.deaf > 0 + if deaf { + tr.deaf-- + tr.deafIDs[id] = true + } + tr.steps[id] = step + tr.mu.Unlock() + if !deaf { + tr.Write(step) + } + return nil +} + +func (tr *troubled) WatchAsk(ctx context.Context, module, askID string) (<-chan delivery.Step, error) { + tr.mu.Lock() + deaf := tr.deafIDs[askID] + tr.mu.Unlock() + if deaf { + return make(chan delivery.Step), nil // open, and silent for good + } + return tr.FakeAsks.WatchAsk(ctx, module, askID) +} + +func (tr *troubled) AskSteps(_ context.Context, _, askID string) ([]delivery.Step, error) { + tr.mu.Lock() + defer tr.mu.Unlock() + if s, ok := tr.steps[askID]; ok { + return []delivery.Step{s}, nil + } + return nil, nil +} + +// Steps is the steps state as the read tools read it, with running in place of every step the hand has not let end. +func (tr *troubled) Steps(running bool) StateRead { + tr.mu.Lock() + defer tr.mu.Unlock() + vals := map[string]json.RawMessage{} + for id, s := range tr.steps { + if running { + s.State, s.Ended, s.Started = delivery.StepRunning, time.Time{}, time.Now() + } + raw, _ := delivery.EncodeStep(s) + vals[s.Node+"."+id] = raw + } + return StateRead{Keys: func() ([]string, error) { + var out []string + for k := range vals { + out = append(out, k) + } + return out, nil + }, Get: func(k string) (json.RawMessage, error) { return vals[k], nil }} +} + +// kvRead is a bucket in memory as the read tools read it, live. +func kvRead(kv *memKV) StateRead { + return StateRead{Keys: func() ([]string, error) { return kv.Keys(context.Background()) }, + Get: func(k string) (json.RawMessage, error) { + v, _, _, err := kv.Get(context.Background(), k) + return v, err + }} +} + +// asVerdicts is the rig's verdicts as the ask-again tool reads and writes them. +type asVerdicts struct{ kv *memKV } + +func (a asVerdicts) Entry(key string) (json.RawMessage, uint64, error) { + v, rev, _, err := a.kv.Get(context.Background(), key) + return v, rev, err +} +func (a asVerdicts) Update(key string, value []byte, revision uint64) error { + _, err := a.kv.Update(context.Background(), key, value, revision) + return err +} + +// Issue 734 and the lost check of 2026-10-28: a check whose ask judged nothing is asked again, and one whose step ended +// unheard is judged. Given up by the build seat once, or its step ended by the build module's next process after a +// delivery replaced it, the check is asked again under its claim and passes; given up every time it fails loudly as not +// heard, judged again when the nodes change. A step whose watch went deaf is read at the next step end of its build module +// (a nudge) and judged with no new ask; one no event reaches is named lost by checker_status, refused by checker_ask_again +// while its step still runs, and asked again by it once its step ended. +func TestACheckWhoseAskJudgedNothingIsAskedAgainOrRead(t *testing.T) { ctx := context.Background() for _, row := range []struct { - lose int - state string - asks int + name string + lose, restarts, deaf int + how string // "nudge": a step of the build module ends; "hand": checker_ask_again + state string + asks int }{ - {1, delivery.VerdictPass, 2}, - {LostAskTries, delivery.VerdictFail, LostAskTries}, + {name: "given up once", lose: 1, state: delivery.VerdictPass, asks: 2}, + {name: "given up every time", lose: LostAskTries, state: delivery.VerdictFail, asks: LostAskTries}, + {name: "its build module replaced under it", restarts: 1, state: delivery.VerdictPass, asks: 2}, + {name: "replaced under every ask", restarts: LostAskTries, state: delivery.VerdictFail, asks: LostAskTries}, + {name: "its watch deaf, a step of its build module ends", deaf: 1, how: "nudge", state: delivery.VerdictPass, asks: 1}, + {name: "its watch deaf, asked again by hand", deaf: 1, how: "hand", state: delivery.VerdictPass, asks: 2}, + {name: "its watch deaf, asked again by hand after its build module replaced it", deaf: 1, restarts: 1, how: "hand", state: delivery.VerdictPass, asks: 2}, } { - b := newBench(t) - l := losing(b, row.lose) - r := newRig(t, b.ex) - cand := candidateOf(t, "feat/x", pullOf(repoA, 7, head1)) - r.ch.Candidate(ctx, "feat%2Fx", cand) - r.ch.Wait() - v := r.verdict(t, keyOf(t, "feat/x", cand)) - if v.State != row.state || len(l.Asks()) != row.asks { - t.Errorf("lose %d: verdict %s (%s) after %d asks, want %s after %d", row.lose, v.State, v.Failed.Words, len(l.Asks()), row.state, row.asks) - } - if row.state == delivery.VerdictFail && (!IsLostAsk(v) || !IsNodesFailure(v)) { - t.Errorf("a check given up every time = %q, want lost and judged again when the nodes change", v.Failed.Words) - } + t.Run(row.name, func(t *testing.T) { + b := newBench(t) + var asked func() int + var heard *buildrun.HeardEnds + var tr *troubled + if row.lose > 0 { + l := losing(b, row.lose) + asked = func() int { return len(l.Asks()) } + } else { + tr = &troubled{FakeAsks: &buildrun.FakeAsks{}, answer: b.answer, restarts: row.restarts, deaf: row.deaf, + deafIDs: map[string]bool{}, steps: map[string]delivery.Step{}} + heard = &buildrun.HeardEnds{Inner: tr, Read: tr} + b.ex.Asks = buildrun.Asker{Publisher: tr, Waiter: heard, Bound: 5 * time.Second} + asked = func() int { return len(tr.Asks()) } + } + r := newRig(t, b.ex) + asksKept := newMemKV() + r.ch.Asks = asksKept + cand := candidateOf(t, "feat/x", pullOf(repoA, 7, head1)) + key := keyOf(t, "feat/x", cand) + r.ch.Candidate(ctx, "feat%2Fx", cand) + if row.deaf > 0 { + for deadline := time.Now().Add(2 * time.Second); heard.Waiting() == 0 && time.Now().Before(deadline); { + time.Sleep(2 * time.Millisecond) + } + if v := r.verdict(t, key); v.State != delivery.VerdictRunning { + t.Fatalf("a check whose step ended unheard = %s, want running until it is read", v.State) + } + } + switch row.how { + case "nudge": + heard.Nudge(buildrun.NodeBuildModule) // another build module's step: not this one's to read + heard.Nudge(buildrun.GoBuildModule) + case "hand": + cands := newMemKV() + ckey, _ := delivery.CandidatesKey("feat/x") + _, _ = cands.Create(ctx, ckey, cand) + none := StateRead{Keys: func() ([]string, error) { return nil, nil }, Get: func(string) (json.RawMessage, error) { return nil, nil }} + rd := Reader{CandidateState: kvRead(cands), VerdictState: kvRead(r.verdicts), AskState: kvRead(asksKept), + StepStates: map[string]StateRead{buildrun.GoBuildModule: none}} // no node took its ask yet + if _, err := rd.AskAgain(asVerdicts{r.verdicts}, "feat/x", "its watch went deaf"); err == nil || !strings.Contains(err.Error(), "waits in its build seat's stream") { + t.Errorf("asked again while its ask waits in the stream (issue 1791's kind): %v", err) + } + rd.StepStates[buildrun.GoBuildModule] = tr.Steps(true) + if _, err := rd.AskAgain(asVerdicts{r.verdicts}, "feat/x", "its watch went deaf"); err == nil || !strings.Contains(err.Error(), "a step of it runs") { + t.Errorf("asked again while its step runs: %v", err) + } + rd.StepStates[buildrun.GoBuildModule] = tr.Steps(false) + if st, _ := rd.Status(); !strings.Contains(st.Lost["feat/x"], AskAgainTool) { + t.Errorf("status lost = %v, want feat/x named with %s", st.Lost, AskAgainTool) + } + got, err := rd.AskAgain(asVerdicts{r.verdicts}, "feat/x", "its watch went deaf") + if err != nil || got.Key != key || !strings.HasPrefix(got.Said, AskedAgainWords) { + t.Fatalf("asked again = %+v, %v", got, err) + } + raw, _, _, _ := r.verdicts.Get(ctx, key) + r.ch.VerdictWritten(ctx, key, raw) // the checker's watch of its verdicts hands it over + } + r.ch.Wait() + v := r.verdict(t, key) + if v.State != row.state || asked() != row.asks { + t.Errorf("verdict %s (%s) after %d asks, want %s after %d", v.State, v.Failed.Words, asked(), row.state, row.asks) + } + if _, _, kept, _ := asksKept.Get(ctx, key); kept { + t.Errorf("the asks of the ended check are still kept under %s", key) + } + if row.state == delivery.VerdictFail && (!IsLostAsk(v) || !IsNodesFailure(v)) { + t.Errorf("a check that judged nothing every time = %q, want lost and judged again when the nodes change", v.Failed.Words) + } + if row.how == "hand" { + rd := Reader{VerdictState: kvRead(r.verdicts), CandidateState: kvRead(newMemKV())} + if _, err := rd.AskAgain(asVerdicts{r.verdicts}, "feat/x", "again"); err == nil { + t.Error("a judged check was asked again") + } + } + }) } } diff --git a/modules/mesh-delivery-checker/internal/check/read.go b/modules/mesh-delivery-checker/internal/check/read.go index cbe4581..250b6b9 100644 --- a/modules/mesh-delivery-checker/internal/check/read.go +++ b/modules/mesh-delivery-checker/internal/check/read.go @@ -47,7 +47,9 @@ type Reader struct { Runs interface{ CommitOf(module string) string } // HearingState is the checker's state hearing: whether it hears DEAD_LETTERS (issue 734). HearingState StateRead - Now func() time.Time + // AskState is the checker's state asks: the asks each running check put (AsksState), which checker_ask_again reads. + AskState StateRead + Now func() time.Time } // VerdictRead is a verdict as stored with the full report of the status of each pull request it judged (Report), when the @@ -306,6 +308,8 @@ type RunningStep struct { ID string `json:"id"` Tool string `json:"tool"` Since string `json:"since,omitempty"` + // What says what the step is (buildstep.AskWhat): an ask's kind, repository@head and levels. + What string `json:"what,omitempty"` } // LeftStep is a key a build module left running that no step behind it runs any more, and why. @@ -331,6 +335,9 @@ type Status struct { // CannotBeJudged are the candidates no pull request of which can be judged, by group, with why: the gate's source.main // names no trunk head of their repositories (issue 1422). They are judged once it does; until then their status is error. CannotBeJudged map[string]string `json:"cannot_be_judged"` + // Lost are the candidates whose verdict is running while no step of theirs can still run and their newest step ended, by + // group, with that step: nothing will judge them (the lost check of 2026-10-28); checker_ask_again asks one again. + Lost map[string]string `json:"lost"` // DeadLetters says whether the checker hears the asks the build seats give up on (issue 734): deaf, a try or check // whose ask is given up waits until its bound. DeadLetters DeadLettersHeard `json:"dead_letters"` @@ -394,63 +401,11 @@ func heldBy(t *Turns, c delivery.Candidate, heads map[string]string) string { // Status reads the build modules' steps and the candidates against their verdicts. func (r Reader) Status() (Status, error) { - st := Status{RunningByNode: map[string]int{}} - mods := make([]string, 0, len(r.StepStates)) - for m := range r.StepStates { - mods = append(mods, m) - } - sort.Strings(mods) - st.Running, st.LeftRunning = []RunningStep{}, []LeftStep{} - now, bound := time.Now(), r.StepBound - if r.Now != nil { - now = r.Now() - } - if bound <= 0 { - bound = DefaultStepBound - } - for _, m := range mods { - sr := r.StepStates[m] - if sr.Keys == nil || sr.Get == nil { - continue - } - keys, err := sr.Keys() - if err != nil { - st.Notes = append(st.Notes, "the steps of "+m+" cannot be listed: "+err.Error()) - continue - } - // A step that runs started lately: the newest ids are read first, at most MaxReads of them. - newestFirst(keys) - keys, cut := capKeys(keys, "") - if cut != "" { - st.Notes = append(st.Notes, "the steps of "+m+": read the newest "+fmt.Sprint(MaxReads)+" of its keys; a step older than those is not shown") - } - steps := make([]delivery.Step, len(keys)) - isRunning := make([]bool, len(keys)) - _ = parallel(len(keys), func(i int) error { - raw, err := sr.Get(keys[i]) - if err != nil || len(raw) == 0 { - return nil - } - step, err := delivery.DecodeStep(raw) - steps[i], isRunning[i] = step, err == nil && step.State == delivery.StepRunning - return nil - }) - for i := range keys { - if !isRunning[i] { - continue - } - step := steps[i] - rs := RunningStep{Module: m, Node: step.Node, ID: step.ID, Tool: step.Tool} - if !step.Started.IsZero() { - rs.Since = step.Started.UTC().Format("2006-01-02T15:04:05Z") - } - if why := r.leftWhy(m, step, now, bound); why != "" { - st.LeftRunning = append(st.LeftRunning, LeftStep{RunningStep: rs, Why: why}) - continue - } - st.Running = append(st.Running, rs) - st.RunningByNode[step.Node]++ - } + st := Status{RunningByNode: map[string]int{}, Lost: map[string]string{}} + read := r.readSteps() + st.Running, st.LeftRunning, st.Notes = read.running, read.left, read.notes + for _, rs := range st.Running { + st.RunningByNode[rs.Node]++ } if r.HaveState.Get == nil { st.Notes = append(st.Notes, "the node-engine's have is not readable here, so a step is not checked against its build module being on its node") @@ -530,7 +485,11 @@ func (r Reader) Status() (Status, error) { } v, err := delivery.DecodeVerdict(raw) switch { - case err != nil || v.State == delivery.VerdictRunning: + case err != nil: + case v.State == delivery.VerdictRunning: + if why := read.lostWhy(c); why != "" { + st.Lost[c.Group] = why + } case IsNodesFailure(v): st.Waiting[KindNodes] = append(st.Waiting[KindNodes], c.Group) case IsUntrunked(v): @@ -551,6 +510,118 @@ func (r Reader) Status() (Status, error) { return st, nil } +// stepsRead is what the build modules' steps states hold: the steps that can still run, those left running, and every +// ask step read, by module, for the candidate it belongs to (stepsOf). +type stepsRead struct { + running []RunningStep + left []LeftStep + all []moduleStep + notes []string +} + +type moduleStep struct { + module string + step delivery.Step +} + +// readSteps reads the newest MaxReads keys of each build module's steps state. +func (r Reader) readSteps() stepsRead { + out := stepsRead{running: []RunningStep{}, left: []LeftStep{}} + mods := make([]string, 0, len(r.StepStates)) + for m := range r.StepStates { + mods = append(mods, m) + } + sort.Strings(mods) + now, bound := time.Now(), r.StepBound + if r.Now != nil { + now = r.Now() + } + if bound <= 0 { + bound = DefaultStepBound + } + for _, m := range mods { + sr := r.StepStates[m] + if sr.Keys == nil || sr.Get == nil { + continue + } + keys, err := sr.Keys() + if err != nil { + out.notes = append(out.notes, "the steps of "+m+" cannot be listed: "+err.Error()) + continue + } + // A step that runs started lately: the newest ids are read first, at most MaxReads of them. + newestFirst(keys) + keys, cut := capKeys(keys, "") + if cut != "" { + out.notes = append(out.notes, "the steps of "+m+": read the newest "+fmt.Sprint(MaxReads)+" of its keys; a step older than those is not shown") + } + steps := make([]delivery.Step, len(keys)) + decoded := make([]bool, len(keys)) + _ = parallel(len(keys), func(i int) error { + raw, err := sr.Get(keys[i]) + if err != nil || len(raw) == 0 { + return nil + } + step, err := delivery.DecodeStep(raw) + steps[i], decoded[i] = step, err == nil + return nil + }) + for i := range keys { + if !decoded[i] { + continue + } + step := steps[i] + out.all = append(out.all, moduleStep{module: m, step: step}) + if step.State != delivery.StepRunning { + continue + } + rs := RunningStep{Module: m, Node: step.Node, ID: step.ID, Tool: step.Tool, What: step.What} + if !step.Started.IsZero() { + rs.Since = step.Started.UTC().Format("2006-01-02T15:04:05Z") + } + if why := r.leftWhy(m, step, now, bound); why != "" { + out.left = append(out.left, LeftStep{RunningStep: rs, Why: why}) + continue + } + out.running = append(out.running, rs) + } + } + return out +} + +// asksOf says whether a step is an ask of one of the candidate's pull requests: its What names `@` +// (buildstep.AskWhat). +func asksOf(c delivery.Candidate, what string) bool { + for _, p := range c.Pulls { + if p.Repository != "" && strings.Contains(what, p.Repository+"@"+short12(p.Head.Head)) { + return true + } + } + return false +} + +// lostWhy says why a candidate whose verdict is running has a check that nothing will judge, or "": no step of its pull +// requests can still run, and its newest one ended. +func (s stepsRead) lostWhy(c delivery.Candidate) string { + for _, rs := range s.running { + if asksOf(c, rs.What) { + return "" + } + } + var last *delivery.Step + for i := range s.all { + st := s.all[i].step + if st.State != delivery.StepRunning && asksOf(c, st.What) && (last == nil || st.Ended.After(last.Ended)) { + last = &s.all[i].step + } + } + if last == nil { + return "" // its ask waits in its build seat's stream: no node took it yet + } + return fmt.Sprintf("its verdict is running, but no step of it runs: its last step %s on %s ended %s at %s and no verdict followed; %s asks it again", + last.ID, last.Node, last.State, last.Ended.UTC().Format(time.RFC3339), AskAgainTool) +} + // DefaultStepBound is how long one check ask's step may run once a build node took it (its key written running; the fetch, // the digests and the levels), never counting its wait in the stream; past it the check fails naming the node. const DefaultStepBound = 30 * time.Minute diff --git a/modules/mesh-delivery-checker/manifest_test.go b/modules/mesh-delivery-checker/manifest_test.go index 815ce91..404988d 100644 --- a/modules/mesh-delivery-checker/manifest_test.go +++ b/modules/mesh-delivery-checker/manifest_test.go @@ -93,7 +93,7 @@ func TestManifestDeclarations(t *testing.T) { // 1678/AC1 t.Errorf("module = %q", m.Module) } // delivery.CheckerKeptHistory, CheckerOwedHistory, PreviewsHistory, CheckerVerdictsHistory; the names follow the SDK's buckets. - if want := []state{{Name: "hearing", History: 1}, {Name: "kept", History: 1}, {Name: "owed", History: 5}, {Name: "previews", History: 5}, {Name: "tries", History: 1}, {Name: "verdicts", History: 5}}; !reflect.DeepEqual(m.State, want) { + if want := []state{{Name: "asks", History: 1}, {Name: "hearing", History: 1}, {Name: "kept", History: 1}, {Name: "owed", History: 5}, {Name: "previews", History: 5}, {Name: "tries", History: 1}, {Name: "verdicts", History: 5}}; !reflect.DeepEqual(m.State, want) { t.Errorf("state = %+v, want %+v", m.State, want) } if want := []string{"mesh-build-go.steps", "mesh-build-go.toolchains", "mesh-build-node.steps", "mesh-build-node.toolchains", "mesh-controller.assignments", @@ -124,8 +124,9 @@ func TestManifestDeclarations(t *testing.T) { // 1678/AC1 t.Errorf("streams = %+v, want %+v", m.Streams, want) } // The read tools (issue 1686) are served by the tools bundle, not by the checker's process. - // The try's tools (ADR 0501 §5; the end by hand, issue 734) beside them: mesh-controller's try calls them. - if want := []string{"checker_kept", "checker_previews", "checker_pull", "checker_status", "checker_try", "checker_try_end", "checker_try_read", "checker_verdicts"}; !reflect.DeepEqual(sorted(m.Tools), want) { + // The try's tools (ADR 0501 §5; the end by hand, issue 734) beside them: mesh-controller's try calls them. A lost check + // is asked again by hand (checker_ask_again). + if want := []string{"checker_ask_again", "checker_kept", "checker_previews", "checker_pull", "checker_status", "checker_try", "checker_try_end", "checker_try_read", "checker_verdicts"}; !reflect.DeepEqual(sorted(m.Tools), want) { t.Errorf("tools = %v, want %v", m.Tools, want) } for _, k := range []string{"logs", "emits", "claims", "provides", "requires", "defines-seats", "seat", "seats", "bus", "config"} { diff --git a/modules/mesh-delivery-checker/module.json b/modules/mesh-delivery-checker/module.json index a968770..6d12e3b 100644 --- a/modules/mesh-delivery-checker/module.json +++ b/modules/mesh-delivery-checker/module.json @@ -10,6 +10,7 @@ { "name": "checks", "events": ["preview.**", "owed.**"] } ], "state": [ + { "name": "asks", "history": 1 }, { "name": "hearing", "history": 1 }, { "name": "kept", "history": 1 }, { "name": "owed", "history": 5 }, @@ -38,6 +39,7 @@ "node-build-node" ], "tools": [ + "checker_ask_again", "checker_kept", "checker_previews", "checker_pull",