Checker: put every node's name on each check ask for the names check, so no repository lists them (ADR 0567 §12, issue 1126)

2026-10-28 18:34:02 +01:00
parent deda4c985e
commit 9db9499267
7 changed files with 93 additions and 7 deletions
@@ -2,12 +2,16 @@ package main

 import (
 	"context"
+	"fmt"
 	"sort"
 	"strings"
 	"sync"

+	"github.com/nats-io/nats.go/jetstream"
+
 	"git.novox.be/novox/mesh-sdk/go/delivery"
 	"git.novox.be/novox/mesh-sdk/go/delivery/buildrun"
+	"git.novox.be/novox/mesh-sdk/go/process"

 	"mesh-delivery-checker/internal/check"
 )
@@ -25,11 +29,46 @@ type judgeDeps struct {
 	builds   check.BuildStates
 	// compositions is the assigner's bucket of compositions; nil leaves every composition not run.
 	compositions check.CompositionReader
-	logf         func(format string, args ...any)
+	// nodes names every node with a record; nil hands no names.
+	nodes *nodeNames
+	logf  func(format string, args ...any)
+}
+
+// nodeNames reads every node's name from the node-engine's have, one key `<node>.node` per node with a record (novox/hq
+// ADR 0567 §12), at each ask: a node enrolled since is named in the next check.
+type nodeNames struct{ kv jetstream.KeyValue }
+
+// openNodeNames opens the node-engine's have for the nodes' names alone: it is not watched, so no check waits on a node.
+func openNodeNames(ctx context.Context, js process.BucketOpener, logf func(string, ...any)) *nodeNames {
+	return &nodeNames{kv: process.OptionalBucket(ctx, js, delivery.HaveBucket, "no check is asked until it is: the names check needs the nodes' names", logf)}
+}
+
+func (n nodeNames) Names(ctx context.Context) ([]string, error) {
+	if n.kv == nil {
+		return nil, fmt.Errorf("the bucket %s could not be opened at the checker's start", delivery.HaveBucket)
+	}
+	lister, err := n.kv.ListKeysFiltered(ctx, "*."+delivery.HaveNodeWord)
+	if err != nil {
+		return nil, err
+	}
+	var out []string
+	for key := range lister.Keys() {
+		if node, _, isNode, err := delivery.ParseHaveKey(key); err == nil && isNode {
+			out = append(out, node)
+		}
+	}
+	sort.Strings(out)
+	return out, nil
 }

 func newJudge(d judgeDeps) check.Judge {
-	return &check.Examiner{Compositions: d.compositions, Asks: d.asks, Toolchains: d.tools,
+	var nodes interface {
+		Names(ctx context.Context) ([]string, error)
+	}
+	if d.nodes != nil {
+		nodes = d.nodes
+	}
+	return &check.Examiner{Nodes: nodes, Compositions: d.compositions, Asks: d.asks, Toolchains: d.tools,
 		Kept: check.Kept{Store: d.kept}, Previews: d.previews, Modules: d.repos, Packages: d.repos, Forge: d.forge, Runs: d.repos, Builds: d.builds, Announce: d.announce, Trunks: d.trunks, Logf: d.logf}
 }

@@ -194,6 +194,7 @@ func run(ctx context.Context, getenv func(string) string, logOut io.Writer) erro
 		kept: kvStore{buckets[delivery.CheckerKeptBucket]}, previews: kvStore{buckets[delivery.PreviewsBucket]},
 		repos: repos, builds: builds, forge: forgeReads{call: caller.Call}, logf: logger.Printf,
 		announce: announce, compositions: compositions,
+		nodes: openNodeNames(ctx, js, logger.Printf),
 	})
 	ch.Announce = announce
 	tryer.Judge = ch.Judge
@@ -7,7 +7,8 @@ import (
 )

 // 1912: with checks as asks on the build seats' streams, the stream redelivers a lost node's ask (ADR 0525 §6), so the
-// checker program opens no node-engine have to start again a check that failed for want of a node.
+// checker program watches no node-engine have to start again a check that failed for want of a node. It reads the have's
+// keys only for the nodes' names at each ask (judge.go, novox/hq ADR 0567 §12).
 func TestTheCheckerWatchesNoHave(t *testing.T) {
 	raw, err := os.ReadFile("main.go")
 	if err != nil {
@@ -20,3 +20,5 @@ require (
 	golang.org/x/sys v0.48.0 // indirect
 	golang.org/x/time v0.15.0 // indirect
 )
+
+replace git.novox.be/novox/mesh-sdk/go => /home/jochen/projects/novox/mesh-sdk/go
@@ -1,5 +1,3 @@
-git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261027193820-8ad9372b1952 h1:TmveT3Bija643RGWkilvkzP/h8UWlVvHFZZtQfJK5oU=
-git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261027193820-8ad9372b1952/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=
@@ -5,6 +5,7 @@ import (
 	"crypto/sha256"
 	"encoding/hex"
 	"encoding/json"
+	"errors"
 	"fmt"
 	"os"
 	"path/filepath"
@@ -272,8 +273,36 @@ func TestACleanMergeIsFetchedAtItsTrunkAndBothLevelsPass(t *testing.T) { // 1679
 			t.Errorf("%s was not kept", k)
 		}
 	}
+
+	// ADR 0567 §12: every check ask carries every node's name for the names check; a check whose names cannot be read, or
+	// that reads none, is not asked and fails saying so.
+	for _, c := range []struct {
+		names []string
+		err   error
+		fails string
+	}{{[]string{"anchor", "laptop"}, nil, ""}, {nil, nil, "no node record"}, {nil, errors.New("no bucket"), "no bucket"}} {
+		b := newBench(t)
+		b.ex.Nodes = namesOf{c.names, c.err}
+		out := b.judge(t, caseOf(t, pullOf(repoA, 7, head1)))
+		asks := b.asks.Asks()
+		if c.fails != "" {
+			if out.Verdict.State != delivery.VerdictFail || len(asks) != 0 || !strings.Contains(out.Verdict.Failed.Words, c.fails) {
+				t.Errorf("names %v, %v: verdict %+v, %d asks", c.names, c.err, out.Verdict, len(asks))
+			}
+		} else if len(asks) == 0 || strings.Join(asks[0].Check.NodeNames, ",") != "anchor,laptop" {
+			t.Errorf("the check ask carries the names %v", asks)
+		}
+	}
 }

+// namesOf is the nodes' names as a test gives them.
+type namesOf struct {
+	names []string
+	err   error
+}
+
+func (n namesOf) Names(context.Context) ([]string, error) { return n.names, n.err }
+
 func TestOnlyThePackageWithoutAKeptVerdictRuns(t *testing.T) { // 1288/AC1
 	b := newBench(t)
 	b.digest[delivery.LevelUnit] = Digested{Level: "unit", Packages: map[string]string{"fixture/slow": digA, "fixture/other": digC}}
@@ -110,8 +110,14 @@ type Examiner struct {
 	// waiting until the assigner wrote a verdict that does not wait, or ctx ends (ADR 0528 clause 5, issue 1297); nil
 	// leaves the composition not run.
 	Compositions CompositionReader
-	Now          func() time.Time
-	Logf         func(format string, args ...any)
+	// Nodes names every node with a record, read from each `<node>.node` of the node-engine's have (novox/hq ADR 0567
+	// §12): every check ask carries them (CheckJob.NodeNames) for the names check, so no repository lists them. A check
+	// whose names cannot be read, or that reads none, is not asked and fails saying so; nil hands no names.
+	Nodes interface {
+		Names(ctx context.Context) ([]string, error)
+	}
+	Now  func() time.Time
+	Logf func(format string, args ...any)
 }

 // CompositionReader answers the assigner's composition of a check by the check's key, waiting until the assigner wrote
@@ -403,6 +409,16 @@ func (st *state) askNeeding(ctx context.Context, t *target, merged *[]Fetched, l
 	p := t.pull
 	placed := len(needs) > 0
 	job := &delivery.CheckJob{Fetch: t.fetchArgs, Levels: levels, Kept: true, Packages: packages}
+	if st.j.Nodes != nil {
+		names, err := st.j.Nodes.Names(ctx)
+		if err == nil && len(names) == 0 {
+			err = fmt.Errorf("no node record is on the bus")
+		}
+		if err != nil {
+			return fail(t.module, fmt.Sprintf("the check of %s#%d is not asked: the nodes' names the names check needs cannot be read: %v", p.Repository, p.Number, err))
+		}
+		job.NodeNames = names
+	}
 	if t.runner != "" {
 		job.Runner, job.RunnerWhen = t.runner, buildGoDir
 	}