Compare commits

...
9 Commits
Author SHA1 Message Date
jschoubben d83156fb21 Add checker_previews and checker_status read tools so the live acceptance of issues 1680 and 1685 can be read (C1, C2) 2026-10-22 17:25:11 +02:00
jschoubben 16ca51dc1f Bound builder_builds by key prefix, limit and read budget, list unreadable keys, refuse fp2 with commit, add candidate reads (issue 1827 V1-V3, 1818, 1681) 2026-10-22 17:23:46 +02:00
mesh-tools 0e372c87f1 Merge pull request 'Read a go.mod the head does not hold at the trunk, so a branch older than a new Go module passes the pin check (issue 1845)' (#21) from fix/1845-pin-read-at-trunk into main 2026-10-22 13:44:08 +00:00
jschoubben 4a0c771059 Match the forge's 404 by its status, not by digits a path's sha may hold (issue 1845)
mesh/repo-check head 4a0c77105943 merged into trunk 2b635e2138ae — pass: its merge-check.sh passed
mesh/merge-gate head 4a0c77105943 merged into trunk 2b635e2138ae — pass: builds mesh-delivery-checker → novox; no bus step; every machine composes with the…
mesh/delivery delivered
mesh/check pass 4a0c77105943 on 2b635e2138ae | unit 371 run 0 kept | int 410 run 0 kept | clone 13s unit 206ms int 14s+45s | composition not yet run
2026-10-22 15:09:25 +02:00
jschoubben 14c78e485f Read a Go module's go.mod at the trunk when the head does not hold it, so a branch cut before the module was added passes the pin check (issue 1845) 2026-10-22 15:00:58 +02:00
mesh-tools 2b635e2138 Merge pull request 'Send image artifacts to mesh-build-image, one node, publishing only from the trunk (issue 1705)' (#20) from feat/r4c9-image-build into main 2026-10-22 08:57:21 +00:00
jschoubben db62e82e26 Write a failed publish of a merged image to the key; read mesh-build-image's captured steps (review r2)
mesh/repo-check head db62e82e26d7 merged into trunk 47ab8cd3cf45 beside mesh-catalog#435@7c5d11e5 — pass: its merge-check.sh passed
mesh/merge-gate head db62e82e26d7 merged into trunk 47ab8cd3cf45 — pass: group feat/r4c9-image-build composed: every machine composes with the change as it…
mesh/delivery delivered
mesh/delivery-group group feat/r4c9-image-build merged: every member is merged
mesh/check pass db62e82e26d7 on 2b635e2138ae | unit 366 run 0 kept | int 405 run 0 kept | clone 9.2s unit 191ms int 6.7s+44s | composition not yet run
2026-10-22 10:37:21 +02:00
jschoubben 12f61998c5 Publish a merged candidate's image once; a retaken key builds only what is missing (review r1) 2026-10-22 10:33:52 +02:00
jschoubben bbc690539b Build an image on one node through mesh-build-image; only a trunk key publishes (issue 1705) 2026-10-22 10:19:26 +02:00
30 changed files with 1298 additions and 64 deletions
@@ -57,6 +57,7 @@ type fakeBuildModules struct {
mu sync.Mutex
calls map[string]int // by `<module>.<tool>`
fetches []map[string]any
builds []map[string]any // the arguments of every build call
}
func (f *fakeBuildModules) count(tool string) int {
@@ -88,6 +89,10 @@ func (f *fakeBuildModules) serve(t *testing.T, nc *nats.Conn, module string) {
f.mu.Lock()
f.fetches = append(f.fetches, args)
f.mu.Unlock()
} else {
f.mu.Lock()
f.builds = append(f.builds, args)
f.mu.Unlock()
}
id := fmt.Sprintf("s%d", f.n.Add(1))
key, _ := delivery.StepKey(node, id)
@@ -116,6 +121,9 @@ func (f *fakeBuildModules) serve(t *testing.T, nc *nats.Conn, module string) {
step.State, step.Result = delivery.StepPassed, json.RawMessage(`{"workspace":"w`+id+`","commit":"`+commit+`"`+merge+`}`)
case f.failBuild.Load() && node == "n1":
step.State, step.Reason = delivery.StepFailed, fmt.Sprintf("go build of %v: boom", args["artifact"])
case tool == "build_image_build" && args["publish"] == true: // a trunk image is pushed: the digest and the reference
d := digestOf(fmt.Sprint(args["artifact"]))
step.State, step.Result = delivery.StepPassed, json.RawMessage(`{"digest":"`+d+`","reference":"registry.example/imaged/server@`+d+`"}`)
default:
step.State, step.Result = delivery.StepPassed, json.RawMessage(`{"digest":"`+digestOf(fmt.Sprint(args["artifact"]))+`"}`)
}
@@ -218,6 +226,8 @@ func startBed(t *testing.T) *bed {
b.fake = &fakeBuildModules{js: js, ctx: ctx, calls: map[string]int{}}
b.fake.serve(t, ctl, "mesh-build-go")
b.fake.serve(t, ctl, "mesh-build-node")
b.fake.serve(t, ctl, "mesh-build-image")
b.setHealth(t, "n1", "mesh-build-image", delivery.HealthOK) // the image build module runs on n1 only
b.report(t, "mesh-build-go", "n1", "go", "go1.27.1", "1")
b.report(t, "mesh-build-go", "n2", "go", "go1.27.1", "1")
b.report(t, "mesh-build-node", "n1", "typescript", "tsc5", "1")
@@ -582,3 +592,85 @@ func TestBuilderBuildsACandidatesFingerprintFromTheHeadMergedOntoTheTrunk(t *tes
t.Errorf("fetches = %v, want one of the candidate's head with its ref and the trunk commit", b.fake.fetches)
}
}
// TestAnImageIsBuiltOnOneNodeAndOnlyATrunkKeyPublishes: modules.imaged (one image artifact) is built on n1, where
// mesh-build-image runs: a trunk record's key is done with the digest and the reference, its build call carrying publish; a
// candidate's key for the same module is built first with no publish and no reference; when the pull request is merged and the
// trunk's record names the candidate's fingerprint, the key is built again with publish and ends with a reference
// (ADR 0487 clauses 5 and 12).
func TestAnImageIsBuiltOnOneNodeAndOnlyATrunkKeyPublishes(t *testing.T) { // 1705
b := startBed(t)
other := "src2:" + strings.Repeat("e", 64)
digest := b.moduleCommit(t, "imaged", "catalogue-a67f0196-imaged.module.json", "modules/imaged", nil, commit)
// The trunk carries `other`; its key is built and published.
trunk := func(fp2 string) {
data, err := delivery.EncodeModule(delivery.Module{Repository: "novox/mesh-catalog", Commit: commit, FP: "src1:" + strings.Repeat("f", 64), FP2: fp2,
Manifest: digest, Path: "modules/imaged"})
if err != nil {
t.Fatal(err)
}
if _, err := b.modules.Put(b.ctx, "imaged", data); err != nil {
t.Fatal(err)
}
}
trunk(other)
b.start(t, "n1", nil)
okey, _ := delivery.BuilderBuildKey("imaged", other)
awaitKey := func(key string, pred func(delivery.BuilderBuild) bool) delivery.BuilderBuild {
var last delivery.BuilderBuild
for deadline := time.Now().Add(20 * time.Second); time.Now().Before(deadline); time.Sleep(50 * time.Millisecond) {
if e, err := b.builds.Get(b.ctx, key); err == nil {
if last, err = delivery.DecodeBuilderBuild(e.Value()); err == nil && pred(last) {
return last
}
}
}
t.Fatalf("builds.%s = %+v within 20 s", key, last)
return last
}
v := awaitKey(okey, isState(delivery.BuildDone))
if len(v.Artifacts) != 1 || v.Artifacts[0].Digest != digestOf("server") || !strings.HasSuffix(v.Artifacts[0].Reference, "@"+digestOf("server")) {
t.Fatalf("trunk build = %+v, want the digest and the reference", v)
}
// The candidate carries fp: built, not published.
const head = "1111111111111111111111111111111111111111"
pulls := []delivery.CandidatePull{{Head: delivery.Head{Repository: "novox/mesh-catalog", Number: 7, Head: head}, Modules: []string{"imaged"},
Fps: map[string]delivery.CandidateModule{"imaged": {FP2: fp, Manifest: digest}}}}
hash, _ := delivery.HeadsHash([]delivery.Head{pulls[0].Head})
cand, err := delivery.EncodeCandidate(delivery.Candidate{V: delivery.Version, Group: "feat/x", HeadsHash: hash, Pulls: pulls, FPSet: delivery.FingerprintSet(pulls)})
if err != nil {
t.Fatal(err)
}
ckey, _ := delivery.CandidatesKey("feat/x")
if _, err := b.candidates.Put(b.ctx, ckey, cand); err != nil {
t.Fatal(err)
}
v = b.await(t, "imaged", isState(delivery.BuildDone))
if len(v.Artifacts) != 1 || v.Artifacts[0].Reference != "" {
t.Fatalf("candidate build = %+v, want done with no reference", v)
}
b.fake.mu.Lock()
if len(b.fake.builds) != 2 || b.fake.builds[0]["publish"] != true || b.fake.builds[1]["publish"] != nil {
t.Errorf("builds = %v, want the trunk's with publish, then the candidate's with none", b.fake.builds)
}
b.fake.mu.Unlock()
// The pull request is merged: the trunk's record names fp, and its key ends published, built once more with publish.
trunk(fp)
v = b.await(t, "imaged", func(v delivery.BuilderBuild) bool {
return v.State == delivery.BuildDone && len(v.Artifacts) == 1 && v.Artifacts[0].Reference != ""
})
if v.Artifacts[0].Digest != digestOf("server") {
t.Errorf("merged build = %+v", v)
}
b.fake.mu.Lock()
defer b.fake.mu.Unlock()
published := 0
for _, a := range b.fake.builds {
if a["publish"] == true {
published++
}
}
if len(b.fake.builds) != 3 || published != 2 {
t.Errorf("builds = %v, want three, two of them with publish (the trunk's two fingerprints)", b.fake.builds)
}
}
@@ -0,0 +1,14 @@
{
"module": "imaged",
"version": "1",
"slug": "imaged",
"build": {
"artifacts": [
{
"name": "server",
"kind": "image",
"from": "Dockerfile"
}
]
}
}
@@ -63,6 +63,26 @@ type ClaimOptions struct {
// qualifies now and the key may be built again (it is not held back after a failed second build, issue 1664). Nil means
// none does.
MoreNodes func(modules []string) bool
// ImageBuilder says whether a node runs a healthy image build module now: a key failed for NoImageBuilderPrefix is taken
// again only then. Nil means none does.
ImageBuilder func() bool
// Trunk is whether the trunk's record names this fingerprint. A done key whose image has no reference was built as a
// candidate's, which never pushes (ADR 0487 clause 12); on the trunk it is taken again to publish the image, when an image
// builder runs (ImageBuilder).
Trunk bool
}
// Unpublished is whether a done build holds an image built without a push: it has no reference.
func Unpublished(b delivery.BuilderBuild) bool {
if b.State != delivery.BuildDone {
return false
}
for _, a := range b.Artifacts {
if a.Kind == "image" && a.Reference == "" {
return true
}
}
return false
}
// Claim takes the build of module at fingerprint, or answers nil when it is not this builder's to build now:
@@ -72,7 +92,8 @@ type ClaimOptions struct {
// builder writes the new revision when the second build ends (ADR 0478 clause 4);
// - a failed key is taken again as a new revision of the same key (ADR 0429 clause 18), except one failed for a kind no
// builder builds yet (RefusedPrefix, ADR 0478 clause 2) or for digests that differ (buildrun.DigestsDifferPrefix, clause 4),
// which wait for another fingerprint;
// which wait for another fingerprint, and one failed for want of an image builder (NoImageBuilderPrefix), which waits for
// another fingerprint or a node that runs the image build module (ClaimOptions.ImageBuilder);
// - a key left queued or building by this builder is taken as it stands (ADR 0478 clause 5: a stopped builder takes its
// own again when it starts), and so is one left by another builder when ClaimOptions.TakeOver (clause 6).
func (c Claimer) Claim(ctx context.Context, module, fingerprint, manifest string, opt ClaimOptions) (*Claim, error) {
@@ -97,9 +118,14 @@ func (c Claimer) Claim(ctx context.Context, module, fingerprint, manifest string
if modules := OneNodeModules(cur); len(modules) > 0 && opt.MoreNodes != nil && opt.MoreNodes(modules) {
return &Claim{Key: key, Rev: rev, Build: cur}, nil
}
if opt.Trunk && Unpublished(cur) && opt.ImageBuilder != nil && opt.ImageBuilder() {
return &Claim{Key: key, Rev: rev, Build: cur}, nil
}
return nil, nil
case cur.State == delivery.BuildFailed && (strings.HasPrefix(cur.Error, RefusedPrefix) || strings.HasPrefix(cur.Error, buildrun.DigestsDifferPrefix)):
return nil, nil
case cur.State == delivery.BuildFailed && strings.HasPrefix(cur.Error, NoImageBuilderPrefix) && (opt.ImageBuilder == nil || !opt.ImageBuilder()):
return nil, nil
case cur.State == delivery.BuildFailed:
return c.write(ctx, key, building, func(data []byte) (uint64, error) { return c.Store.Update(ctx, key, data, rev) })
case cur.By == c.By || opt.TakeOver:
@@ -155,6 +155,22 @@ func TestAFailedKeyIsTakenAgainAsANewRevisionExceptARefusedKind(t *testing.T) {
}
}
func TestAKeyFailedForNoImageBuilderIsTakenAgainOnlyWhenANodeHasTheModule(t *testing.T) { // 1705b
st := newMem()
key := seed(t, st, delivery.BuilderBuild{State: delivery.BuildFailed, By: "novox.a", Error: NoImageBuilderPrefix + " no node has mesh-build-image"})
writes := st.writes
c := Claimer{Store: st, By: "novox.a"}
for _, opt := range []ClaimOptions{{}, {ImageBuilder: func() bool { return false }}} {
if got, err := c.Claim(context.Background(), "m", fp1, "", opt); err != nil || got != nil || st.writes != writes {
t.Errorf("claim = %v, %v, writes %d (was %d), want none and no write", got, err, st.writes, writes)
}
}
got, err := c.Claim(context.Background(), "m", fp1, hex64('a'), ClaimOptions{ImageBuilder: func() bool { return true }})
if err != nil || got == nil || valueOf(t, st, key).State != delivery.BuildBuilding {
t.Errorf("claim = %v, %v, want a claim with the key building", got, err)
}
}
func TestFinishMovesTheKeyByCompareAndSetAndWritesOnlyADifferentValue(t *testing.T) { // 1607/AC3
st := newMem()
c := Claimer{Store: st, By: "novox.a"}
@@ -0,0 +1,41 @@
package build
import (
"encoding/json"
"os"
"testing"
"git.novox.be/novox/mesh-sdk/go/delivery"
)
// result reads a captured step value of mesh-build-image (testdata/captured/README) and returns its result.
func captured(t *testing.T, name string) json.RawMessage {
t.Helper()
raw, err := os.ReadFile("testdata/captured/" + name)
if err != nil {
t.Fatal(err)
}
var step delivery.Step
if err := json.Unmarshal(raw, &step); err != nil {
t.Fatalf("%s: %v", name, err)
}
if step.State != delivery.StepPassed || len(step.Result) == 0 {
t.Fatalf("%s: state %q, result %s, want a passed step with a result", name, step.State, step.Result)
}
return step.Result
}
func TestCapturedImageStepsDecodeWithTheBuildersOwnTypes(t *testing.T) { // review r2, mesh-catalog 2; ADR 0487 clause 1
var f fetchResult
if err := json.Unmarshal(captured(t, "fetch.json"), &f); err != nil || f.Workspace == "" {
t.Errorf("fetch = %+v, %v, want a workspace (the field the builder reads)", f, err)
}
var trunk buildResult
if err := json.Unmarshal(captured(t, "build-trunk.json"), &trunk); err != nil || trunk.Digest == "" || trunk.Reference == "" {
t.Errorf("trunk build = %+v, %v, want a digest and a reference", trunk, err)
}
var cand buildResult
if err := json.Unmarshal(captured(t, "build-candidate.json"), &cand); err != nil || cand.Digest == "" || cand.Reference != "" {
t.Errorf("candidate build = %+v, %v, want a digest and no reference", cand, err)
}
}
@@ -15,6 +15,15 @@ import (
// a key is not built again as a new revision.
const RefusedPrefix = "refused kind:"
// ImageBuildModule is the build module that builds an image artifact (novox/hq ADR 0487): buildah, rootless, on the nodes that
// run it. It has no toolchain language; the builder finds its nodes from the node-engine's have.
const ImageBuildModule = "mesh-build-image"
// NoImageBuilderPrefix opens the error of a build key failed because no node runs ImageBuildModule (ADR 0487 clause 5): such a
// key is not built again as a new revision, only when a node reports the module (ClaimOptions.ImageBuilder) or the fingerprint
// changes.
const NoImageBuilderPrefix = "no image builder:"
// Task is one artifact to build: its name and kind in the manifest, the build module that builds it and the language
// of the toolchain it is built with.
type Task struct {
@@ -45,7 +54,7 @@ func (p Plan) Modules() []string {
// (the indexer gives an archive no language, so a fingerprint names no toolchain for it; ADR 0478 clause 1).
func (p Plan) NeedsToolchain(module string) bool {
for _, t := range p.Tasks {
if t.Module == module && t.Kind != catalogue.ArtifactArchive {
if t.Module == module && t.Kind != catalogue.ArtifactArchive && t.Kind != catalogue.ArtifactImage {
return true
}
}
@@ -61,7 +70,7 @@ func (r *Refused) Error() string {
}
// PlanOf is the plan of a manifest (ADR 0478 clauses 1 and 2): a Go bundle and an archive are built by the Go build
// module, a TypeScript bundle by the Node one, each in the order of the artifacts' names. A manifest with an image,
// module, an image by the image build module (ADR 0487), a TypeScript bundle by the Node one, each in the order of the artifacts' names. A manifest with an
// upstream or package artifact, or a bundle of another language, is refused as a whole, naming the first such artifact
// by name. A manifest with no artifact has an empty plan.
func PlanOf(m catalogue.Manifest) (Plan, error) {
@@ -79,6 +88,8 @@ func PlanOf(m catalogue.Manifest) (Plan, error) {
p.Tasks = append(p.Tasks, Task{Artifact: a.Name, Kind: a.Kind, Module: buildrun.GoBuildModule, Language: "go"})
case a.Kind == catalogue.ArtifactBundle && a.Language == "typescript":
p.Tasks = append(p.Tasks, Task{Artifact: a.Name, Kind: a.Kind, Module: buildrun.NodeBuildModule, Language: "typescript"})
case a.Kind == catalogue.ArtifactImage:
p.Tasks = append(p.Tasks, Task{Artifact: a.Name, Kind: a.Kind, Module: ImageBuildModule})
case a.Kind == catalogue.ArtifactBundle:
return Plan{}, &Refused{Artifact: a.Name, What: fmt.Sprintf("bundle of language %q", a.Language)}
default:
@@ -41,12 +41,11 @@ func TestPlanRoutesEachKindToItsBuildModule(t *testing.T) { // 1607/AC2
}
}
func TestPlanRefusesImageUpstreamAndPackageByName(t *testing.T) { // 1607/AC2, ADR 0478 clause 2
func TestPlanRefusesUpstreamAndPackageByName(t *testing.T) { // 1607/AC2, ADR 0478 clause 2
for _, c := range []struct {
artifact catalogue.Artifact
kind string
}{
{catalogue.Artifact{Name: "img", Kind: "image"}, "image"},
{catalogue.Artifact{Name: "up", Kind: "upstream"}, "upstream"},
{catalogue.Artifact{Name: "pkg", Kind: "package", Language: "typescript"}, "package"},
} {
@@ -74,3 +73,16 @@ func TestPlanRefusesABundleOfAnotherLanguageAndAModuleWithNoArtifact(t *testing.
}
func asRefused(err error, target **Refused) bool { return errors.As(err, target) }
func TestPlanSendsAnImageToMeshBuildImageWithNoToolchain(t *testing.T) { // 1705a, ADR 0487 clause 5
p, err := PlanOf(manifestOf(catalogue.Artifact{Name: "img", Kind: "image"}, catalogue.Artifact{Name: "files", Kind: "archive"}))
if err != nil || len(p.Tasks) != 2 {
t.Fatalf("plan %+v, error %v", p, err)
}
if p.Tasks[1].Artifact != "img" || p.Tasks[1].Module != ImageBuildModule {
t.Errorf("task = %+v, want the image on %s", p.Tasks[1], ImageBuildModule)
}
if p.NeedsToolchain(ImageBuildModule) {
t.Error("an image needs no toolchain")
}
}
@@ -10,6 +10,7 @@ import (
"strings"
"sync"
"git.novox.be/novox/mesh-sdk/go/catalogue"
"git.novox.be/novox/mesh-sdk/go/delivery"
)
@@ -19,7 +20,7 @@ type ToolchainEntries interface {
}
// toolPrefix is the start of each build module's tool names: <prefix>fetch and <prefix>build.
var toolPrefix = map[string]string{buildrun.GoBuildModule: "build_go_", buildrun.NodeBuildModule: "build_node_"}
var toolPrefix = map[string]string{buildrun.GoBuildModule: "build_go_", buildrun.NodeBuildModule: "build_node_", ImageBuildModule: "build_image_"}
// Builder builds, dark, every new-form fingerprint the indexer writes (novox/hq ADR 0453 clause 4, ADR 0478): it is
// handed each modules value as the watch of the indexer's bucket sees it, and for each module with a fingerprint and an
@@ -287,6 +288,7 @@ func (b *Builder) try(ctx context.Context, module string, m delivery.Module) {
}
key, _ := delivery.BuilderBuildKey(module, m.FP2)
b.mu.Lock()
trunk := b.trunkFP[key]
first := !b.tried[key]
b.tried[key] = true
epoch := b.epoch
@@ -296,7 +298,7 @@ func (b *Builder) try(ctx context.Context, module string, m delivery.Module) {
// A second build that failed is not tried again until the nodes change (issue 1664).
return (!failedBefore || epoch > failedAt) && b.moreNodes(modules)
}
cl, err := b.Claimer.Claim(ctx, module, m.FP2, m.Manifest, ClaimOptions{TakeOver: first, MoreNodes: moreNodes})
cl, err := b.Claimer.Claim(ctx, module, m.FP2, m.Manifest, ClaimOptions{TakeOver: first, MoreNodes: moreNodes, ImageBuilder: b.imageBuilderRuns, Trunk: trunk})
if err != nil {
b.logf("%s: %v", module, err)
return
@@ -304,7 +306,22 @@ func (b *Builder) try(ctx context.Context, module string, m delivery.Module) {
if cl == nil {
return
}
result := b.build(ctx, module, m, plan, planErr)
// A done key taken again builds only what is missing: the build modules that ran on one node, and the image when it was
// built as a candidate's; the other artifacts stay as the done key has them (ADR 0487 clauses 5 and 8).
var prior *delivery.BuilderBuild
var only map[string]bool
publishing := false
if cl.Build.State == delivery.BuildDone {
prior, only = &cl.Build, map[string]bool{}
for _, bm := range OneNodeModules(cl.Build) {
only[bm] = true
}
if trunk && Unpublished(cl.Build) {
only[ImageBuildModule] = true
publishing = true
}
}
result := b.build(ctx, module, m, plan, planErr, prior, only)
if ctx.Err() != nil {
return
}
@@ -313,7 +330,11 @@ func (b *Builder) try(ctx context.Context, module string, m delivery.Module) {
return
}
result.By, result.Manifest = b.Claimer.By, m.Manifest
if cl.Build.State == delivery.BuildDone && result.State == delivery.BuildFailed && !strings.HasPrefix(result.Error, buildrun.DigestsDifferPrefix) {
if publishing && result.State == delivery.BuildFailed {
// The trunk's image was built only as a candidate's and its push failed: the key says so, so the builds view, the
// checker and the failed-key retake see it, and a look does not build the image again for nothing.
result.Error = "publishing the image of the merged commit failed: " + result.Error
} else if cl.Build.State == delivery.BuildDone && result.State == delivery.BuildFailed && !strings.HasPrefix(result.Error, buildrun.DigestsDifferPrefix) {
// A done key built again on a second node keeps its done value when the new build fails for another reason than
// the digests: the first build stands, and a later change of the nodes looks again.
b.logf("%s: built again on a second node and failed, the done build stands: %s", cl.Key, result.Error)
@@ -360,10 +381,11 @@ type lane struct {
module, node string
tasks []Task
digests map[string]string // artifact -> digest
references map[string]string // artifact -> the reference an image was pushed to (a trunk build only)
err error
}
func (b *Builder) build(ctx context.Context, module string, m delivery.Module, plan Plan, planErr error) delivery.BuilderBuild {
func (b *Builder) build(ctx context.Context, module string, m delivery.Module, plan Plan, planErr error, prior *delivery.BuilderBuild, only map[string]bool) delivery.BuilderBuild {
switch {
case planErr != nil:
return failed("%s", planErr)
@@ -386,12 +408,27 @@ func (b *Builder) build(ctx context.Context, module string, m delivery.Module, p
b.Places.Cancel(l.node)
}
}
var kept []string // build modules whose artifacts stay as the prior done key has them
for _, bm := range plan.Modules() {
if prior != nil && len(only) > 0 && !only[bm] {
kept = append(kept, bm)
continue
}
language := buildrun.LanguageOf[bm]
entries := b.Toolchains.Entries(language)
qualifies := func(node string) bool { return b.qualifies(node, bm) }
var nodes []string
if plan.NeedsToolchain(bm) {
if bm == ImageBuildModule {
// An image is built on one node, chosen from the nodes whose image build module runs healthy (ADR 0487 clause 8):
// the module has no toolchain language, so no toolchain entry names its nodes, and a second build would only
// push the image again.
ns, err := buildrun.ChooseAnyNodes("image", b.imageEntries(), b.Places, qualifies, 1)
if err != nil {
giveUpLanes()
return failed("%s no node has %s, so the image cannot be built: the provision rootless-image-build is held by the module buildah; assign buildah and %s to a node (%v)", NoImageBuilderPrefix, ImageBuildModule, ImageBuildModule, err)
}
nodes = ns
} else if plan.NeedsToolchain(bm) {
ns, tc, err := buildrun.ChooseNodes(language, entries, b.Places, qualifies, b.Nodes)
if err != nil {
giveUpLanes()
@@ -413,7 +450,9 @@ func (b *Builder) build(ctx context.Context, module string, m delivery.Module, p
}
nodes = ns
}
if len(nodes) == 1 {
if bm == ImageBuildModule {
steps = append(steps, fmt.Sprintf("%s on %s", bm, nodes[0]))
} else if len(nodes) == 1 {
oneNode = append(oneNode, bm)
steps = append(steps, fmt.Sprintf("%s on one node, %s", bm, nodes[0]))
} else {
@@ -428,7 +467,7 @@ func (b *Builder) build(ctx context.Context, module string, m delivery.Module, p
}
}
for _, n := range nodes {
lanes = append(lanes, &lane{module: bm, node: n, tasks: tasks, digests: map[string]string{}})
lanes = append(lanes, &lane{module: bm, node: n, tasks: tasks, digests: map[string]string{}, references: map[string]string{}})
}
}
var wg sync.WaitGroup
@@ -447,7 +486,23 @@ func (b *Builder) build(ctx context.Context, module string, m delivery.Module, p
return failed("%s", strings.Join(errs, "; "))
}
var artifacts []delivery.BuiltArtifact
keptModule := map[string]bool{}
for _, bm := range kept {
keptModule[bm] = true
}
for _, t := range plan.Tasks {
if keptModule[t.Module] {
found := false
for _, a := range prior.Artifacts {
if a.Name == t.Artifact {
artifacts, found = append(artifacts, a), true
}
}
if !found {
return failed("the done build holds no artifact %s to keep", t.Artifact)
}
continue
}
byNode := map[string]string{}
for _, l := range lanes {
if d, ok := l.digests[t.Artifact]; ok && l.module == t.Module {
@@ -458,7 +513,21 @@ func (b *Builder) build(ctx context.Context, module string, m delivery.Module, p
if err != nil {
return failed("%s", err)
}
artifacts = append(artifacts, delivery.BuiltArtifact{Name: t.Artifact, Kind: t.Kind, Digest: d})
built := delivery.BuiltArtifact{Name: t.Artifact, Kind: t.Kind, Digest: d}
for _, l := range lanes {
if r := l.references[t.Artifact]; r != "" && l.module == t.Module {
built.Reference = r
}
}
artifacts = append(artifacts, built)
}
for _, bm := range kept {
steps = append(steps, bm+" kept")
for lang, u := range prior.Toolchains {
if _, ok := used[lang]; !ok && buildrun.LanguageOf[bm] == lang {
used[lang] = u
}
}
}
step := "built " + strings.Join(steps, "; ")
if len(oneNode) > 0 {
@@ -478,6 +547,39 @@ func (b *Builder) qualifies(node, bm string) bool {
return b.Places.CapacityOf(node) > 0 && b.online(node) && (b.Health == nil || b.Health.Healthy(node, bm))
}
// imageEntries are the nodes an image may be built on, as toolchain entries for the chooser: every node the builder has a
// capacity for or a build module toolchain from. Whether the image build module runs there is qualifies', from the have.
func (b *Builder) imageEntries() []delivery.NodeToolchain {
seen := map[string]bool{}
var entries []delivery.NodeToolchain
add := func(n string) {
if !seen[n] {
seen[n] = true
entries = append(entries, delivery.NodeToolchain{Node: n})
}
}
for n := range b.Places.Capacity {
add(n)
}
for _, language := range []string{"go", "typescript"} {
for _, e := range b.Toolchains.Entries(language) {
add(e.Node)
}
}
sort.Slice(entries, func(i, j int) bool { return entries[i].Node < entries[j].Node })
return entries
}
// imageBuilderRuns is whether a node can build an image now.
func (b *Builder) imageBuilderRuns() bool {
for _, e := range b.imageEntries() {
if b.qualifies(e.Node, ImageBuildModule) {
return true
}
}
return false
}
// moreNodes is whether any of these build modules has two nodes that qualify now.
func (b *Builder) moreNodes(modules []string) bool {
for _, bm := range modules {
@@ -501,6 +603,18 @@ func (b *Builder) step(ctx context.Context, bm, node, tool string, args map[stri
return b.Runner.Run(ctx, bm, node, toolPrefix[bm]+tool, args)
}
// fetchResult and buildResult are the results of a build module's fetch and build steps as the builder reads them.
type fetchResult struct {
Workspace string `json:"workspace"`
Merge string `json:"merge"`
Conflicts []string `json:"conflicts"`
}
type buildResult struct {
Digest string `json:"digest"`
Reference string `json:"reference"`
}
// runLane takes a place on the node, fetches the commit there and builds each of the lane's artifacts, one step at a time.
func (b *Builder) runLane(ctx context.Context, l *lane, repository string, m delivery.Module, module string) {
release, err := b.Places.Acquire(ctx, l.node)
@@ -523,18 +637,15 @@ func (b *Builder) runLane(ctx context.Context, l *lane, repository string, m del
l.err = err
return
}
var fetched struct {
Workspace string `json:"workspace"`
Merge string `json:"merge"`
Conflicts []string `json:"conflicts"`
}
var fetched fetchResult
if err := json.Unmarshal(raw, &fetched); err != nil || fetched.Workspace == "" {
l.err = fmt.Errorf("the fetch on %s answered no workspace: %s", l.node, raw)
return
}
// A candidate is built from its head merged onto the trunk. A head that does not merge ends the fetch passed with the tree at
// the trunk, and building that would store the trunk's build under the candidate's fingerprint.
if _, candidate := fetchArgs["base"]; candidate {
_, candidate := fetchArgs["base"]
if candidate {
if len(fetched.Conflicts) > 0 {
l.err = fmt.Errorf("the head does not merge into the trunk on %s: files in conflict: %s", l.node, strings.Join(fetched.Conflicts, ", "))
return
@@ -545,18 +656,24 @@ func (b *Builder) runLane(ctx context.Context, l *lane, repository string, m del
}
}
for _, t := range l.tasks {
raw, err := b.step(ctx, l.module, l.node, "build", map[string]any{"workspace": fetched.Workspace, "module": m.Path, "artifact": t.Artifact})
args := map[string]any{"workspace": fetched.Workspace, "module": m.Path, "artifact": t.Artifact}
if t.Kind == catalogue.ArtifactImage && !candidate {
// Only a trunk key pushes the image to the registry; a candidate's build never does (ADR 0487 clause 12).
args["publish"] = true
}
raw, err := b.step(ctx, l.module, l.node, "build", args)
if err != nil {
l.err = err
return
}
var built struct {
Digest string `json:"digest"`
}
var built buildResult
if err := json.Unmarshal(raw, &built); err != nil || built.Digest == "" {
l.err = fmt.Errorf("the build of %s of %s on %s answered no digest: %s", t.Artifact, module, l.node, raw)
return
}
l.digests[t.Artifact] = built.Digest
if built.Reference != "" && !candidate {
l.references[t.Artifact] = built.Reference
}
}
}
@@ -67,7 +67,11 @@ func (b *buildModules) CallOn(node, key string, body any) (json.RawMessage, erro
if v, ok := b.digests[node+"/"+fmt.Sprint(args["artifact"])]; ok {
d = v
}
step.Result = json.RawMessage(`{"digest":"` + d + `"}`)
if tool == "build_image_build" && args["publish"] == true {
step.Result = json.RawMessage(`{"digest":"` + d + `","reference":"registry.example/m/img@` + d + `"}`)
} else {
step.Result = json.RawMessage(`{"digest":"` + d + `"}`)
}
}
sk, _ := delivery.StepKey(node, id)
b.steps.mu.Lock()
@@ -238,11 +242,126 @@ func TestAFailingStepFailsTheBuildWithItsReasonAndNodeAndIsTriedAgainAsANewRevis
}
}
func TestAModuleWithAnImageGetsARefusedKeyNeverBuiltAgain(t *testing.T) { // 1607/AC2, ADR 0478 clause 2
r := newRig(t, archiveA, imageArt)
// imageHave marks mesh-build-image running and healthy on these nodes.
func imageHave(t *testing.T, nodes ...string) *buildrun.HaveSet {
t.Helper()
have := &buildrun.HaveSet{}
for _, n := range nodes {
have.Put(n+".mesh-build-go", haveValue(t, delivery.PhaseRunning, delivery.HealthOK), false)
have.Put(n+"."+ImageBuildModule, haveValue(t, delivery.PhaseRunning, delivery.HealthOK), false)
}
return have
}
func TestAnImageGoesToOneNodeAndGetsOneDoneKeyWithItsReference(t *testing.T) { // 1705a, ADR 0487 clause 5
r := newRig(t, imageArt)
r.b.Health = imageHave(t, "ace", "novox") // two nodes qualify; an image still builds on one
v := r.consider(t, "modules/m")
if v.State != delivery.BuildFailed || !strings.HasPrefix(v.Error, RefusedPrefix) || !strings.Contains(v.Error, "image") || !strings.Contains(v.Error, "build-agent") {
t.Fatalf("build = %+v, want failed 'refused kind: image' naming build-agent", v)
if v.State != delivery.BuildDone || len(v.Artifacts) != 1 || v.Artifacts[0].Kind != "image" || v.Artifacts[0].Digest != digest {
t.Fatalf("build = %+v, want done with one image artifact and its digest", v)
}
if v.Artifacts[0].Reference == "" {
t.Errorf("a trunk image has no reference: %+v", v.Artifacts[0])
}
if strings.HasPrefix(v.Step, OneNodePrefix) || len(OneNodeModules(v)) != 0 {
t.Errorf("step = %q, want no one-node mark: an image is never built again on a second node", v.Step)
}
if n := len(r.bm.callsOf("build_image_fetch")); n != 1 {
t.Errorf("%d image fetches, want one", n)
}
writes := r.st.writes
r.consider(t, "modules/m")
if r.st.writes != writes || len(r.bm.callsOf("build_image_build")) != 1 {
t.Errorf("a done image key was built again")
}
}
func TestAnImageIsBuiltOnlyWhereMeshBuildImageIsHealthy(t *testing.T) { // 1705a
r := newRig(t, imageArt)
r.b.Health = imageHave(t, "novox")
r.consider(t, "modules/m")
c := r.bm.callsOf("build_image_build")
if len(c) != 1 || c[0].node != "novox" {
t.Errorf("calls = %+v, want one on novox", c)
}
}
func TestABundleAndAnImageOfOneModuleBuildOnTwoNodesAndOne(t *testing.T) { // 1705a
r := newRig(t, goBundle, imageArt)
r.b.Health = imageHave(t, "ace", "novox")
v := r.consider(t, "modules/m")
if v.State != delivery.BuildDone || len(v.Artifacts) != 2 {
t.Fatalf("build = %+v", v)
}
if n := len(r.bm.callsOf("build_go_build")); n != 2 {
t.Errorf("%d go builds, want 2", n)
}
if n := len(r.bm.callsOf("build_image_build")); n != 1 {
t.Errorf("%d image builds, want 1", n)
}
if modules := OneNodeModules(v); len(modules) != 0 {
t.Errorf("one-node modules = %v, want none", modules)
}
}
func TestWithNoImageNodeTheKeyFailsNamingTheProvisionAndIsNotRetakenUntilANodeReportsTheModule(t *testing.T) { // 1705b, lead's decision
r := newRig(t, imageArt)
r.b.Health = imageHave(t) // mesh-build-image runs nowhere
v := r.consider(t, "modules/m")
if v.State != delivery.BuildFailed || !strings.HasPrefix(v.Error, NoImageBuilderPrefix) || !strings.Contains(v.Error, "rootless-image-build") || !strings.Contains(v.Error, "buildah") || !strings.Contains(v.Error, ImageBuildModule) {
t.Fatalf("build = %+v, want failed naming rootless-image-build, buildah and mesh-build-image", v)
}
if len(r.bm.calls) != 0 {
t.Errorf("%d calls, want none", len(r.bm.calls))
}
writes := r.st.writes
r.consider(t, "modules/m")
r.consider(t, "modules/m")
if r.st.writes != writes {
t.Errorf("the failed key was written again (%d writes, was %d)", r.st.writes, writes)
}
// A node reports the module: the key is taken again.
r.b.Health = imageHave(t, "ace")
v = r.consider(t, "modules/m")
if v.State != delivery.BuildDone {
t.Errorf("build = %+v, want done once a node reports mesh-build-image", v)
}
}
func TestACandidatesImageCallCarriesNoPublishAndItsKeyNoReference(t *testing.T) { // 1705b, lead's decision
r := newRig(t, imageArt)
r.b.Health = imageHave(t, "ace")
trunkModule(t, r)
r.b.Candidate(context.Background(), "feat%2Fx", candidateValue(t, "feat/x", 7, headX))
r.b.Wait()
v := valueOf(t, r.st, r.key)
if v.State != delivery.BuildDone || len(v.Artifacts) != 1 || v.Artifacts[0].Reference != "" {
t.Fatalf("build = %+v, want done with no reference", v)
}
calls := r.bm.callsOf("build_image_build")
if len(calls) != 1 {
t.Fatalf("%d image builds, want 1", len(calls))
}
if _, has := calls[0].body.(map[string]any)["publish"]; has {
t.Errorf("a candidate's image call carries publish: %+v", calls[0].body)
}
}
func TestATrunkImageCallCarriesPublish(t *testing.T) { // 1705b
r := newRig(t, imageArt)
r.b.Health = imageHave(t, "ace")
r.consider(t, "modules/m")
calls := r.bm.callsOf("build_image_build")
if len(calls) != 1 || calls[0].body.(map[string]any)["publish"] != true {
t.Errorf("calls = %+v, want publish true", calls)
}
}
func TestAnUpstreamArtifactIsStillRefusedKeyNeverBuiltAgain(t *testing.T) { // 1607/AC2, ADR 0478 clause 2
r := newRig(t, archiveA, catalogue.Artifact{Name: "up", Kind: "upstream"})
v := r.consider(t, "modules/m")
if v.State != delivery.BuildFailed || !strings.HasPrefix(v.Error, RefusedPrefix) || !strings.Contains(v.Error, "upstream") || !strings.Contains(v.Error, "build-agent") {
t.Fatalf("build = %+v, want failed 'refused kind: upstream' naming build-agent", v)
}
if len(r.bm.calls) != 0 {
t.Errorf("%d calls, want none for a refused kind", len(r.bm.calls))
@@ -411,3 +530,104 @@ func TestANodeThatIsNotOnlineIsNotChosenAndComingBackWakesTheBuild(t *testing.T)
t.Errorf("build = %+v, want done once a node is online", v)
}
}
func TestACandidatesImageIsPublishedOnceWhenTheTrunkNamesItsFingerprint(t *testing.T) { // review r1, mesh-delivery 1; ADR 0487 clause 5
r := newRig(t, imageArt)
r.b.Health = imageHave(t, "ace")
trunkModule(t, r) // the trunk carries another fingerprint; fp1 is the candidate's
r.b.Candidate(context.Background(), "feat%2Fx", candidateValue(t, "feat/x", 7, headX))
r.b.Wait()
v := valueOf(t, r.st, r.key)
if v.State != delivery.BuildDone || v.Artifacts[0].Reference != "" {
t.Fatalf("candidate build = %+v, want done with no reference", v)
}
if n := len(r.bm.callsOf("build_image_build")); n != 1 {
t.Fatalf("%d image builds after the candidate, want 1", n)
}
// The pull request is merged: the trunk's record names the candidate's fingerprint.
r.b.Module(context.Background(), "m", moduleValue(t, "modules/m"))
r.b.Wait()
v = valueOf(t, r.st, r.key)
if v.State != delivery.BuildDone || len(v.Artifacts) != 1 || v.Artifacts[0].Reference == "" {
t.Fatalf("trunk build = %+v, want done with a reference", v)
}
calls := r.bm.callsOf("build_image_build")
published := 0
for _, c := range calls {
if c.body.(map[string]any)["publish"] == true {
published++
}
}
if len(calls) != 2 || published != 1 {
t.Errorf("%d image builds, %d with publish, want 2 and exactly 1", len(calls), published)
}
// Written once more only: looking again builds nothing.
rev := r.st.revs[r.key]
r.b.Module(context.Background(), "m", moduleValue(t, "modules/m"))
r.b.Wait()
if r.st.revs[r.key] != rev || len(r.bm.callsOf("build_image_build")) != 2 {
t.Error("a published key was built again")
}
}
func TestASecondGoNodeDoesNotBuildOrPushTheImageAgain(t *testing.T) { // review r1, mesh-delivery 2; ADR 0487 clause 8
r := newRig(t, goBundle, imageArt)
r.b.Health = imageHave(t, "ace", "novox")
r.pres.Put("ace", presenceValue(t, false), false) // only novox qualifies for Go (and the image)
v := r.consider(t, "modules/m")
if v.State != delivery.BuildDone || len(OneNodeModules(v)) != 1 {
t.Fatalf("build = %+v, want done with the Go bundle on one node", v)
}
var image delivery.BuiltArtifact
for _, a := range v.Artifacts {
if a.Kind == "image" {
image = a
}
}
if image.Reference == "" {
t.Fatalf("artifacts = %+v, want a published image", v.Artifacts)
}
r.pres.Put("ace", presenceValue(t, true), false)
r.b.Reconsider(context.Background())
r.b.Wait()
v = valueOf(t, r.st, r.key)
if len(OneNodeModules(v)) != 0 || len(v.Artifacts) != 2 {
t.Fatalf("build = %+v, want done on two Go nodes", v)
}
if n := len(r.bm.callsOf("build_image_build")); n != 1 {
t.Errorf("%d image builds, want the one of the first build only", n)
}
for _, a := range v.Artifacts {
if a.Kind == "image" && a != image {
t.Errorf("image = %+v, was %+v: the done key was rewritten with another image", a, image)
}
}
if n := len(r.bm.callsOf("build_go_build")); n != 3 { // one, then two
t.Errorf("%d go builds, want 3", n)
}
}
func TestAFailedPublishOfACandidatesImageIsWrittenToTheKey(t *testing.T) { // review r2, mesh-delivery 1; ADR 0487 clause 5
r := newRig(t, imageArt)
r.b.Health = imageHave(t, "ace")
trunkModule(t, r)
r.b.Candidate(context.Background(), "feat%2Fx", candidateValue(t, "feat/x", 7, headX))
r.b.Wait()
if v := valueOf(t, r.st, r.key); v.State != delivery.BuildDone {
t.Fatalf("candidate build = %+v", v)
}
r.bm.fails["ace/build_image_build"] = "push to the registry: connection refused"
r.b.Module(context.Background(), "m", moduleValue(t, "modules/m")) // the merge: the trunk names the fingerprint
r.b.Wait()
v := valueOf(t, r.st, r.key)
if v.State != delivery.BuildFailed || !strings.Contains(v.Error, "connection refused") || !strings.Contains(v.Error, "publish") {
t.Fatalf("build = %+v, want failed naming the publish and its reason", v)
}
// The failed key is retaken as any failed key is, and ends published once the registry answers.
delete(r.bm.fails, "ace/build_image_build")
r.b.Module(context.Background(), "m", moduleValue(t, "modules/m"))
r.b.Wait()
if v := valueOf(t, r.st, r.key); v.State != delivery.BuildDone || v.Artifacts[0].Reference == "" {
t.Errorf("build = %+v, want done with a reference", v)
}
}
@@ -0,0 +1,4 @@
Captured step values of mesh-build-image (fetch, a candidate's build, a trunk's build), copied from
novox/mesh-catalog modules/mesh-build-image/cmd/mesh-build-image/testdata/captured/. Both copies must change together: the
module's capture test writes them, and the builder's TestCapturedImageStepsDecodeWithTheBuildersOwnTypes (internal/build,
fixtures_test.go) decodes these with the types the builder reads results with and fails on a missing field.
@@ -0,0 +1,14 @@
{
"ended": "2026-10-22T08:00:01Z",
"id": "STEPID",
"node": "ace",
"result": {
"artifact": "server",
"digest": "sha256:1111111111111111111111111111111111111111111111111111111111111111",
"pushed": false
},
"started": "2026-10-22T08:00:00Z",
"state": "passed",
"tool": "build_image_build",
"v": 1
}
@@ -0,0 +1,15 @@
{
"ended": "2026-10-22T08:00:01Z",
"id": "STEPID",
"node": "ace",
"result": {
"artifact": "server",
"digest": "sha256:1111111111111111111111111111111111111111111111111111111111111111",
"pushed": true,
"reference": "REGISTRY/fixture-image/server@sha256:1111111111111111111111111111111111111111111111111111111111111111"
},
"started": "2026-10-22T08:00:00Z",
"state": "passed",
"tool": "build_image_build",
"v": 1
}
@@ -0,0 +1,13 @@
{
"ended": "2026-10-22T08:00:01Z",
"id": "STEPID",
"node": "ace",
"result": {
"commit": "COMMIT",
"workspace": "WORKSPACE"
},
"started": "2026-10-22T08:00:00Z",
"state": "passed",
"tool": "build_image_fetch",
"v": 1
}
@@ -86,12 +86,12 @@ func TestManifestDeclarations(t *testing.T) { // 1607/AC1
if want := []state{{Name: "builds", History: 5}}; !reflect.DeepEqual(m.State, want) { // delivery.BuilderBuildsHistory
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",
if want := []string{"mesh-build-go.steps", "mesh-build-go.toolchains", "mesh-build-image.steps", "mesh-build-node.steps", "mesh-build-node.toolchains",
"mesh-delivery-indexer.candidates", "mesh-delivery-indexer.manifests", "mesh-delivery-indexer.modules", "mesh-delivery-watchman.presence", "node-engine.have"}; !reflect.DeepEqual(sorted(m.Reads), want) {
t.Errorf("reads = %v, want %v", m.Reads, want)
}
if want := []string{"mesh-build-go.build_go_build", "mesh-build-go.build_go_fetch", "mesh-build-node.build_node_build", "mesh-build-node.build_node_fetch"}; !reflect.DeepEqual(sorted(m.Invokes), want) {
t.Errorf("invokes = %v, want only the build modules' fetch and build", m.Invokes)
if want := []string{"mesh-build-go.build_go_build", "mesh-build-go.build_go_fetch", "mesh-build-image.build_image_build", "mesh-build-image.build_image_fetch", "mesh-build-node.build_node_build", "mesh-build-node.build_node_fetch"}; !reflect.DeepEqual(sorted(m.Invokes), want) {
t.Errorf("invokes = %v, want only the build modules' fetch and build (go, image, node)", m.Invokes)
}
// The builder is woken by a build module's report of a toolchain, as the indexer is: the bucket may not exist when it starts.
if want := []string{"mesh-build-go.toolchain.reported", "mesh-build-node.toolchain.reported"}; !reflect.DeepEqual(sorted(m.Consumes), want) {
@@ -12,6 +12,7 @@
"reads": [
"mesh-build-go.steps",
"mesh-build-go.toolchains",
"mesh-build-image.steps",
"mesh-build-node.steps",
"mesh-build-node.toolchains",
"mesh-delivery-indexer.candidates",
@@ -23,6 +24,8 @@
"invokes": [
"mesh-build-go.build_go_build",
"mesh-build-go.build_go_fetch",
"mesh-build-image.build_image_build",
"mesh-build-image.build_image_fetch",
"mesh-build-node.build_node_build",
"mesh-build-node.build_node_fetch"
],
@@ -59,11 +59,52 @@ func Tools(r check.Reader) []stdio.Tool {
kept, err := r.Kept(level, digest)
return map[string]any{"kept": kept}, err
}},
{Name: check.PreviewsReadTool,
Description: "The merge previews the checker holds, each as stored under previews.<repository>.<head>.<trunk>: the merge commit, per module directory " +
"its tree, manifest digest and lock hashes, or the files in conflict. With a repository, that repository's; with a head (7 or more characters) " +
"only that head's. Keys that are no preview key are listed as unreadable. Read-only.",
Input: map[string]any{"type": "object", "properties": map[string]any{
"repository": map[string]any{"type": "string", "description": "<owner>/<name>"},
"head": map[string]any{"type": "string", "description": "a pull request head commit, or a prefix of at least 7 characters"}}},
Run: func(args map[string]any) (any, error) {
repository, _ := args["repository"].(string)
head, _ := args["head"].(string)
if head != "" && len(head) < 7 {
return nil, fmt.Errorf("the head %q is too short: give at least 7 characters", head)
}
ps, bad, err := r.Previews(repository, head)
return map[string]any{"previews": ps, "unreadable": bad}, err
}},
{Name: check.StatusReadTool,
Description: "What holds the checker back and what runs: the capacity per node (the setting, the default one step per node), whether the controller's " +
"delivery plans in their build phase hold a key (no new check starts while one does), the steps in flight on the build modules by node, and the " +
"candidates without a verdict for their heads. The steps the checker holds waiting for a place are in its process, not in a bucket, and the " +
"answer says so. Read-only.",
Input: map[string]any{"type": "object", "properties": map[string]any{}},
Run: func(map[string]any) (any, error) { return r.Status() }},
}
}
func capacity() (string, error) {
path := os.Getenv("MESH_CHECKER_SETTINGS")
if path == "" {
return os.Getenv("MESH_CHECKER_CAPACITY"), nil
}
raw, err := os.ReadFile(path)
if err != nil {
return "", err
}
var s struct {
Capacity string `json:"capacity"`
}
return s.Capacity, json.Unmarshal(raw, &s)
}
func main() {
r := check.Reader{VerdictState: read(stdio.State("verdicts")), KeptState: read(stdio.State("kept")), CandidateState: read(stdio.State("mesh-delivery-indexer.candidates"))}
r := check.Reader{VerdictState: read(stdio.State("verdicts")), KeptState: read(stdio.State("kept")), CandidateState: read(stdio.State("mesh-delivery-indexer.candidates")),
PreviewState: read(stdio.State("previews")), PlansState: read(stdio.State("mesh-controller.plans-building")),
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"))},
Capacity: capacity}
if err := stdio.Serve("", Tools(r)); err != nil {
fmt.Fprintf(os.Stderr, "[mesh-delivery-checker-tools] %v\n", err)
os.Exit(1)
@@ -1,12 +1,13 @@
package main
import (
"slices"
"testing"
"mesh-delivery-checker/internal/check"
)
func TestTheToolsServedAreTheThreeReadTools(t *testing.T) {
func TestTheToolsServedAreTheFiveReadTools(t *testing.T) {
var names []string
for _, tl := range Tools(check.Reader{}) {
names = append(names, tl.Name)
@@ -14,12 +15,15 @@ func TestTheToolsServedAreTheThreeReadTools(t *testing.T) {
t.Errorf("%s has no description or no run", tl.Name)
}
}
want := []string{check.VerdictsReadTool, check.PullReadTool, check.KeptReadTool}
if len(names) != 3 || names[0] != want[0] || names[1] != want[1] || names[2] != want[2] {
want := []string{check.VerdictsReadTool, check.PullReadTool, check.KeptReadTool, check.PreviewsReadTool, check.StatusReadTool}
if !slices.Equal(names, want) {
t.Errorf("tools = %v, want %v", names, want)
}
// With nothing to read from a tool says so and changes nothing.
for _, tl := range Tools(check.Reader{}) {
if tl.Name == check.StatusReadTool {
continue // it answers from what it can read, and says what it could not
}
if _, err := tl.Run(map[string]any{"repository": "novox/x", "number": float64(1)}); err == nil {
t.Errorf("%s answered with no state to read", tl.Name)
}
@@ -4,7 +4,10 @@ import (
"context"
"encoding/json"
"fmt"
"regexp"
"strings"
"mesh-delivery-checker/internal/check"
)
// The forge's tools the checker reads with (mesh-catalog modules/gitea): gitea_get_file answers {file: {content}}, the text
@@ -16,6 +19,9 @@ const (
commitsTool = "gitea.gitea_commits"
)
// notFoundStatus is the 404 of the forge's error, `Gitea API <path>: <status> <body>`.
var notFoundStatus = regexp.MustCompile(`: 404( |$)`)
// forgeReads reads the forge through call (mesh-sdk process.Conn.Call as the checker's own account).
type forgeReads struct {
call func(key string, body any) (json.RawMessage, error)
@@ -31,6 +37,11 @@ func (f forgeReads) File(_ context.Context, repository, path, ref string) (strin
owner, repo := ownerRepo(repository)
raw, err := f.call(getFileTool, map[string]string{"owner": owner, "repo": repo, "path": path, "ref": ref})
if err != nil {
if notFoundStatus.MatchString(err.Error()) {
// The forge answers 404 for a file the ref does not hold (issue 1845). The status is matched in its own place,
// after the path's colon: the path carries a sha that may hold the digits 404.
return "", fmt.Errorf("%w: %v", check.ErrNotFound, err)
}
return "", err
}
var a struct {
@@ -3,10 +3,13 @@ package main
import (
"context"
"encoding/json"
"errors"
"os"
"path/filepath"
"strings"
"testing"
"mesh-delivery-checker/internal/check"
)
// capturedAnswer is what the forge's tool answered (internal/check/testdata/captured/README).
@@ -68,3 +71,18 @@ func TestTheForgeNamesTheWholeShaOfAShortCommit(t *testing.T) { // review D2
t.Error("a commit that does not start with the pin was taken")
}
}
func TestAFileTheRefDoesNotHoldIsNotFoundAndOtherFailuresAreNot(t *testing.T) { // 1845/AC1, AC4
f := forgeReads{call: func(string, any) (json.RawMessage, error) {
return nil, errors.New("Gitea API contents/checks/particulars/go.mod?ref=98ca97fc: 404 object does not exist")
}}
if _, err := f.File(context.Background(), "novox/mesh-catalog", "checks/particulars/go.mod", "98ca97fc"); !errors.Is(err, check.ErrNotFound) {
t.Errorf("a 404 is %v, want ErrNotFound", err)
}
f = forgeReads{call: func(string, any) (json.RawMessage, error) {
return nil, errors.New("Gitea API contents/go.mod?ref=1111111111111111111111111111111404abcde: 500 internal error")
}}
if _, err := f.File(context.Background(), "novox/mesh-catalog", "go.mod", "main"); err == nil || errors.Is(err, check.ErrNotFound) {
t.Errorf("a 500 is %v, want a failure that is not ErrNotFound", err)
}
}
@@ -2,6 +2,7 @@ package check
import (
"context"
"errors"
"fmt"
"path"
"regexp"
@@ -22,6 +23,10 @@ const (
// Issue1148 is why a pin that only a head carries fails the check.
const Issue1148 = "issue 1148"
// ErrNotFound is what Forge.File wraps when the ref holds no such file (the forge answered 404): a file the ref does not hold,
// told from a forge that could not be read (issue 1845).
var ErrNotFound = errors.New("the ref holds no such file")
// Forge reads a file of a repository at a ref, and says whether a commit is on a repository's trunk.
type Forge interface {
// File is the text of a file at a ref (a branch, a tag or a commit).
@@ -51,8 +56,9 @@ func SDKPin(goMod string) (commit string, ok bool) {
}
// checkPins refuses a Go member whose go.mod names a mesh-sdk commit that is neither on mesh-sdk's trunk nor the head of the
// group's mesh-sdk pull request. It reads each go.mod the fetch named at the member's head from the forge. It answers nil
// when every pin is the group's.
// group's mesh-sdk pull request. It reads each go.mod the fetch named from the forge: the one the check builds, which is the
// head's when the head holds the file and the trunk's when it does not, since a module added on the trunk after the branch was
// cut is in the merge and not at the head (issue 1845). It answers nil when every pin is the group's.
func (st *state) checkPins(ctx context.Context) verdictPtr {
if st.j.Forge == nil {
return nil
@@ -66,6 +72,10 @@ func (st *state) checkPins(ctx context.Context) verdictPtr {
file := path.Join(dir, "go.mod")
st.c.Progress.Set(fmt.Sprintf("read %s of %s#%d", file, t.pull.Repository, t.pull.Number), t.node)
text, err := st.j.Forge.File(ctx, t.pull.Repository, file, t.pull.Head)
if errors.Is(err, ErrNotFound) && t.pull.Trunk != "" {
// Only a file the head does not hold is read at the trunk; any other failure fails the check as it did.
text, err = st.j.Forge.File(ctx, t.pull.Repository, file, t.pull.Trunk)
}
if err != nil {
return failed(forgeMachine(err, t.node), fmt.Sprintf("%s#%d: %s cannot be read to check its mesh-sdk pin: %v", t.pull.Repository, t.pull.Number, file, err))
}
@@ -17,16 +17,20 @@ type fakeForge struct {
goMods map[string]string // `<repository> <path> <ref>` -> text
onTrunk map[string]bool // by commit prefix
err error
errAt map[string]error // by ref: a read at that ref fails with it
}
func (f *fakeForge) File(_ context.Context, repository, path, ref string) (string, error) {
if f.err != nil {
return "", f.err
}
if e := f.errAt[ref]; e != nil {
return "", e
}
if s, ok := f.goMods[repository+" "+path+" "+ref]; ok {
return s, nil
}
return "", fmt.Errorf("no file %s of %s at %s", path, repository, ref)
return "", fmt.Errorf("no file %s of %s at %s: %w", path, repository, ref, ErrNotFound)
}
func (f *fakeForge) FullSHA(_ context.Context, _ string, commit string) (string, error) {
@@ -153,6 +157,53 @@ func TestAPinThatCannotBeCheckedFailsAndNeverPasses(t *testing.T) { // ADR 0453
}
}
// trunkOnlyBench is a group of mesh-delivery#7 whose fetch holds two Go modules: modules/m, which the head holds, and
// modules/new, which only the trunk holds (added on the trunk after the branch was cut). The SDK pin of each go.mod is given.
func trunkOnlyBench(t *testing.T, headPin, trunkPin string) *bench {
b := newBench(t)
b.fetch.Modules = []string{"modules/m", "modules/new"}
forge := &fakeForge{goMods: map[string]string{
repoA + " modules/m/go.mod " + head1: capturedGoMod(t, headPin),
repoA + " modules/m/go.mod " + trunkA: capturedGoMod(t, headPin),
repoA + " modules/new/go.mod " + trunkA: capturedGoMod(t, trunkPin),
}, onTrunk: map[string]bool{"cb54756c3865": true}}
b.ex.Forge = forge
return b
}
func TestAModuleOnlyTheTrunkHoldsIsReadAtTheTrunkAndPasses(t *testing.T) { // 1845/AC1
b := trunkOnlyBench(t, "cb54756c3865", "cb54756c3865")
if v := b.judge(t, caseOf(t, pullOf(repoA, 7, head1))).Verdict; v.State != delivery.VerdictPass {
t.Fatalf("verdict = %+v", v)
}
}
func TestAStalePinOfAModuleOnlyTheTrunkHoldsStillFailsNamingTheFileAndTheCommit(t *testing.T) { // 1845/AC2
b := trunkOnlyBench(t, "cb54756c3865", "9aaa5c80ac5c")
v := b.judge(t, caseOf(t, pullOf(repoA, 7, head1))).Verdict
if v.State != delivery.VerdictFail || !strings.Contains(v.Failed.Words, repoA+"#7") || !strings.Contains(v.Failed.Words, "modules/new/go.mod") || !strings.Contains(v.Failed.Words, "9aaa5c80ac5c") {
t.Fatalf("verdict = %+v", v)
}
}
func TestAModuleTheHeadHoldsIsJudgedByTheHeadsPin(t *testing.T) { // 1845/AC3
b := trunkOnlyBench(t, "9aaa5c80ac5c", "cb54756c3865") // the head's pin is stale, the trunk's go.mod of the same module is fine
b.ex.Forge.(*fakeForge).goMods[repoA+" modules/m/go.mod "+trunkA] = capturedGoMod(t, "cb54756c3865")
v := b.judge(t, caseOf(t, pullOf(repoA, 7, head1))).Verdict
if v.State != delivery.VerdictFail || !strings.Contains(v.Failed.Words, "modules/m/go.mod") || !strings.Contains(v.Failed.Words, "9aaa5c80ac5c") {
t.Fatalf("verdict = %+v", v)
}
}
func TestAReadThatFailsForAnotherReasonStillFailsAndIsNotTriedAtTheTrunk(t *testing.T) { // 1845/AC4
b := trunkOnlyBench(t, "cb54756c3865", "cb54756c3865")
b.ex.Forge.(*fakeForge).errAt = map[string]error{head1: fmt.Errorf("the forge answered 500")}
v := b.judge(t, caseOf(t, pullOf(repoA, 7, head1))).Verdict
if v.State != delivery.VerdictFail || !strings.Contains(v.Failed.Words, "modules/m/go.mod") || !strings.Contains(v.Failed.Words, "the forge answered 500") {
t.Fatalf("verdict = %+v", v)
}
}
type runsAt map[string]string
func (r runsAt) CommitOf(module string) string { return r[module] }
@@ -7,6 +7,7 @@ import (
"strings"
"git.novox.be/novox/mesh-sdk/go/delivery"
"git.novox.be/novox/mesh-sdk/go/delivery/buildrun"
)
// The read tools (novox/hq ADR 0484 clauses 8 and 13, issue 1686): what the checker stored, as stored, with the line of the
@@ -17,6 +18,9 @@ const (
VerdictsReadTool = "checker_verdicts"
PullReadTool = "checker_pull"
KeptReadTool = "checker_kept"
// PreviewsReadTool reads the previews state (issue 1680); StatusReadTool reads what the checker is held by and what it runs (issue 1685).
PreviewsReadTool = "checker_previews"
StatusReadTool = "checker_status"
)
// StateRead reads one state: its keys and a key's stored value (nil for a key with none).
@@ -26,7 +30,14 @@ type StateRead struct {
}
// Reader answers the read tools from the checker's verdicts and kept states and the indexer's candidates.
type Reader struct{ VerdictState, KeptState, CandidateState StateRead }
type Reader struct {
VerdictState, KeptState, CandidateState StateRead
PreviewState StateRead // the checker's merge previews
PlansState StateRead // the controller's delivery plans in their build phase; zero where the bucket is absent
StepStates map[string]StateRead // the build modules' steps states, by module
Capacity func() (string, error) // the capacity setting as written, `node=steps,...`
}
// VerdictRead is a verdict as stored with the full report of the status of each pull request it judged (Report), when the
// candidate still holds those heads; without it the report is that of the verdict alone.
@@ -191,3 +202,153 @@ func (r Reader) Kept(level, digest string) (map[string]json.RawMessage, error) {
}
return out, nil
}
// PreviewRead is one preview as stored, with the parts of its key.
type PreviewRead struct {
Key string `json:"key"`
Repository string `json:"repository"`
Head string `json:"head"`
Trunk string `json:"trunk"`
Preview json.RawMessage `json:"preview"`
}
// Previews are the previews the checker holds, each as stored. With a repository only that repository's; with a head (a
// prefix of at least 7 characters is enough) only previews of that head. A key that is no preview key is listed as unreadable.
func (r Reader) Previews(repository, head string) ([]PreviewRead, []string, error) {
if r.PreviewState.Keys == nil || r.PreviewState.Get == nil {
return nil, nil, fmt.Errorf("the previews state cannot be read here")
}
keys, err := r.PreviewState.Keys()
if err != nil {
return nil, nil, err
}
sort.Strings(keys)
out := []PreviewRead{}
var bad []string
for _, k := range keys {
repo, h, trunk, err := delivery.ParsePreviewKey(k)
if err != nil {
bad = append(bad, k)
continue
}
if (repository != "" && repo != repository) || (head != "" && !strings.HasPrefix(h, head)) {
continue
}
raw, err := r.PreviewState.Get(k)
if err != nil {
return nil, nil, err
}
if len(raw) > 0 {
out = append(out, PreviewRead{Key: k, Repository: repo, Head: h, Trunk: trunk, Preview: raw})
}
}
return out, bad, nil
}
// RunningStep is a step in flight on a build module.
type RunningStep struct {
Module string `json:"module"`
Node string `json:"node"`
ID string `json:"id"`
Tool string `json:"tool"`
Since string `json:"since,omitempty"`
}
// Status is what holds the checker back and what runs now, read from the buckets: the checker's held and running steps live in
// its process, so they are shown as what the buckets say (the steps in flight on the build modules, the candidates without a
// verdict for their heads, and the delivery plans in their build phase), not as the process's own counters.
type Status struct {
Capacity map[string]int `json:"capacity"`
CapacityNote string `json:"capacity_note,omitempty"`
DefaultPerNode int `json:"default_per_node"`
PlansBuilding struct {
Readable bool `json:"readable"`
Keys []string `json:"keys"`
Holds bool `json:"holds"`
} `json:"plans_building"`
Running []RunningStep `json:"running_steps"`
RunningByNode map[string]int `json:"running_by_node"`
Unjudged []string `json:"unjudged_candidates"`
Notes []string `json:"notes,omitempty"`
}
// Status reads the capacity, the plan bucket, the build modules' steps and the candidates against their verdicts.
func (r Reader) Status() (Status, error) {
st := Status{DefaultPerNode: buildrun.DefaultCapacity, Capacity: map[string]int{}, RunningByNode: map[string]int{}}
if r.Capacity == nil {
st.CapacityNote = "the capacity setting cannot be read from here"
} else if setting, err := r.Capacity(); err != nil {
st.CapacityNote = "the capacity setting cannot be read: " + err.Error()
} else if st.Capacity, err = buildrun.ParseCapacity(setting); err != nil {
st.Capacity, st.CapacityNote = map[string]int{}, "the capacity setting is not valid: "+err.Error()
}
if r.PlansState.Keys == nil {
st.Notes = append(st.Notes, PlansBuildingBucket+" is not readable here (absent), so it is read as empty: no delivery holds the checker")
} else if keys, err := r.PlansState.Keys(); err != nil {
st.Notes = append(st.Notes, PlansBuildingBucket+" cannot be listed, so it is read as empty: "+err.Error())
} else {
sort.Strings(keys)
st.PlansBuilding.Readable, st.PlansBuilding.Keys, st.PlansBuilding.Holds = true, keys, len(keys) > 0
}
mods := make([]string, 0, len(r.StepStates))
for m := range r.StepStates {
mods = append(mods, m)
}
sort.Strings(mods)
st.Running = []RunningStep{}
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
}
sort.Strings(keys)
for _, k := range keys {
raw, err := sr.Get(k)
if err != nil || len(raw) == 0 {
continue
}
step, err := delivery.DecodeStep(raw)
if err != nil || step.State != delivery.StepRunning {
continue
}
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")
}
st.Running = append(st.Running, rs)
st.RunningByNode[step.Node]++
}
}
st.Unjudged = []string{}
if r.CandidateState.Keys != nil && r.CandidateState.Get != nil && r.VerdictState.Get != nil {
keys, err := r.CandidateState.Keys()
if err != nil {
return st, err
}
sort.Strings(keys)
for _, k := range keys {
raw, err := r.CandidateState.Get(k)
if err != nil || len(raw) == 0 {
continue
}
c, err := delivery.DecodeCandidate(raw)
if err != nil {
continue
}
vkey, err := delivery.CheckerVerdictKey(c.Group, c.HeadsHash)
if err != nil {
continue
}
if v, err := r.VerdictState.Get(vkey); err == nil && len(v) == 0 {
st.Unjudged = append(st.Unjudged, c.Group)
}
}
}
st.Notes = append(st.Notes, "the steps the checker holds waiting for a place are in its process and in no bucket: a candidate without a verdict while a plan key exists, or while its node runs as many steps as its capacity, is held")
return st, nil
}
@@ -3,8 +3,10 @@ package check
import (
"context"
"encoding/json"
"os"
"strings"
"testing"
"time"
"git.novox.be/novox/mesh-sdk/go/delivery"
)
@@ -102,3 +104,64 @@ func TestTheKeptToolAnswersTheKeysAsStoredByLevelAndByDigest(t *testing.T) { //
t.Error("a digest nothing kept was answered")
}
}
// 1680 live acceptance: checker_previews shows the preview key of an open pull request, as stored, narrowed by repository and head.
func TestThePreviewsToolShowsTheStoredPreviewOfAPullRequest(t *testing.T) {
pv := delivery.Preview{Repository: repoA, Head: head1, Trunk: head2, Merge: "m1", Modules: map[string]delivery.PreviewModule{}}
data, err := delivery.EncodePreview(pv)
if err != nil {
t.Fatal(err)
}
key, _ := delivery.PreviewKey(repoA, head1, head2)
rd := Reader{PreviewState: fakeState{key: data, "junk": []byte("{}")}.read()}
got, bad, err := rd.Previews(repoA, head1[:8])
if err != nil || len(got) != 1 || got[0].Key != key || got[0].Head != head1 || got[0].Trunk != head2 || string(got[0].Preview) != string(data) {
t.Fatalf("previews = %+v, %v", got, err)
}
if len(bad) != 1 || bad[0] != "junk" {
t.Errorf("unreadable = %v", bad)
}
if got, _, _ := rd.Previews("novox/other", ""); len(got) != 0 {
t.Errorf("another repository's = %+v", got)
}
if _, _, err := (Reader{}).Previews("", ""); err == nil {
t.Error("answered with no state to read")
}
}
// 1685 live acceptance: checker_status reads the capacity, whether a plan key holds the checker, the steps in flight by node and
// the candidates without a verdict.
func TestTheStatusToolReadsCapacityHoldsAndRunningSteps(t *testing.T) {
running, _ := delivery.EncodeStep(delivery.Step{ID: "abc1", Tool: "build_go_test", Node: "shanks", State: delivery.StepRunning, Started: time.Date(2026, 10, 22, 15, 0, 0, 0, time.UTC)})
passed, _ := delivery.EncodeStep(delivery.Step{ID: "abc2", Tool: "build_go_test", Node: "ace", State: delivery.StepPassed})
cand := candidateOf(t, "feat/x", pullOf(repoA, 7, head1))
ckey, _ := delivery.CandidatesKey("feat/x")
rd := Reader{
Capacity: func() (string, error) { return "shanks=2,ace=0", nil },
PlansState: fakeState{"p1": []byte("{}")}.read(),
StepStates: map[string]StateRead{"mesh-build-go": fakeState{"shanks.abc1": running, "ace.abc2": passed}.read()},
CandidateState: fakeState{ckey: cand}.read(),
VerdictState: fakeState{}.read(),
}
st, err := rd.Status()
if err != nil {
t.Fatal(err)
}
if st.Capacity["shanks"] != 2 || st.Capacity["ace"] != 0 || st.DefaultPerNode != 1 {
t.Errorf("capacity = %v default %d", st.Capacity, st.DefaultPerNode)
}
if !st.PlansBuilding.Holds || len(st.PlansBuilding.Keys) != 1 {
t.Errorf("plans = %+v", st.PlansBuilding)
}
if len(st.Running) != 1 || st.Running[0].Node != "shanks" || st.RunningByNode["shanks"] != 1 || st.RunningByNode["ace"] != 0 {
t.Errorf("running = %+v %v", st.Running, st.RunningByNode)
}
if len(st.Unjudged) != 1 || st.Unjudged[0] != "feat/x" {
t.Errorf("unjudged = %v", st.Unjudged)
}
// An absent plan bucket is read as empty and said; an unreadable capacity is said, not guessed.
st, err = Reader{Capacity: func() (string, error) { return "", os.ErrNotExist }}.Status()
if err != nil || st.PlansBuilding.Holds || st.CapacityNote == "" || len(st.Notes) == 0 {
t.Errorf("empty status = %+v, %v", st, err)
}
}
@@ -118,7 +118,7 @@ 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.
if want := []string{"checker_kept", "checker_pull", "checker_verdicts"}; !reflect.DeepEqual(sorted(m.Tools), want) {
if want := []string{"checker_kept", "checker_previews", "checker_pull", "checker_status", "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", "uses", "defines-seats", "seat", "seats", "bus"} {
@@ -31,7 +31,9 @@
],
"tools": [
"checker_kept",
"checker_previews",
"checker_pull",
"checker_status",
"checker_verdicts"
],
"invokes": [
@@ -35,18 +35,39 @@ func Tools(r view.Reader) []stdio.Tool {
mods, err := r.Modules(only)
return map[string]any{"modules": mods}, err
}},
{Name: view.CandidateReadTool,
Description: "What the indexer stored for one candidate (the open pull requests of a branch) under candidates.<group>, as stored: " +
"the pull requests and heads, the base, and per pull request the touched modules with their new-form fingerprint (fp2) or why " +
"they have none (none2). Read-only.",
Input: map[string]any{"type": "object", "required": []string{"group"}, "properties": map[string]any{
"group": map[string]any{"type": "string", "description": "the candidate's group, the branch name its pull requests share"}}},
Run: func(args map[string]any) (any, error) {
group, _ := args["group"].(string)
return r.Candidate(group)
}},
{Name: view.CandidatesReadTool,
Description: "Every candidate the indexer holds, by group, each as stored under candidates.<group>; with module, only those with a " +
"pull request touching that module. Keys that cannot be read are listed as unreadable. Read-only.",
Input: map[string]any{"type": "object", "properties": map[string]any{
"module": map[string]any{"type": "string", "description": "only candidates touching this module"}}},
Run: func(args map[string]any) (any, error) {
module, _ := args["module"].(string)
c, bad, err := r.Candidates(module)
return map[string]any{"candidates": c, "unreadable": bad}, err
}},
{Name: view.BuilderBuildsReadTool,
Description: "The builder's build keys, each as stored in mesh-delivery-builder_builds: key, module, fingerprint (src2) and build " +
"(state, by, step with the nodes it was built on, manifest, artifacts with their digests, toolchains, error). Narrow by module " +
"or state (queued, building, done, failed). Read-only.",
"or state (queued, building, done, failed); at most limit builds (default 50), newest revision first for a module, and the answer says when it was cut and lists keys that are no build key (unreadable). Without a module, give one to get its newest. Read-only.",
Input: map[string]any{"type": "object", "properties": map[string]any{
"module": map[string]any{"type": "string", "description": "only this module's builds"},
"state": map[string]any{"type": "string", "description": "only builds in this state"}}},
"state": map[string]any{"type": "string", "description": "only builds in this state"},
"limit": map[string]any{"type": "integer", "description": "at most this many builds (default 50), newest revision first"}}},
Run: func(args map[string]any) (any, error) {
module, _ := args["module"].(string)
state, _ := args["state"].(string)
rows, err := r.BuilderBuilds(module, state)
return map[string]any{"builds": rows}, err
limit, _ := args["limit"].(float64)
return r.BuilderBuilds(module, state, int(limit))
}},
{Name: view.BuilderBuildReadTool,
Description: "One build of the builder as stored. Give the module and its fingerprint (fp2, src2:...), or the module alone for the build " +
@@ -65,7 +86,13 @@ func Tools(r view.Reader) []stdio.Tool {
}
func read(state stdio.KeptState) view.StateRead {
return view.StateRead{Keys: state.Keys, Get: func(key string) (json.RawMessage, error) {
return view.StateRead{Keys: state.Keys, GetEntry: func(key string) (json.RawMessage, uint64, error) {
e, err := state.Get(key)
if err != nil || e == nil {
return nil, 0, err
}
return e.Value, e.Revision, nil
}, Get: func(key string) (json.RawMessage, error) {
e, err := state.Get(key)
if err != nil || e == nil {
return nil, err
@@ -75,7 +102,7 @@ func read(state stdio.KeptState) view.StateRead {
}
func main() {
r := view.Reader{State: read(stdio.State("mesh-delivery-indexer.modules")), Builds: read(stdio.State("mesh-delivery-builder.builds"))}
r := view.Reader{State: read(stdio.State("mesh-delivery-indexer.modules")), Builds: read(stdio.State("mesh-delivery-builder.builds")), CandidatesState: read(stdio.State("mesh-delivery-indexer.candidates"))}
if err := stdio.Serve("", Tools(r)); err != nil {
fmt.Fprintf(os.Stderr, "[mesh-delivery-view-tools] %v\n", err)
os.Exit(1)
@@ -2,6 +2,7 @@ package main
import (
"encoding/json"
"fmt"
"strings"
"testing"
@@ -117,13 +118,16 @@ func TestBuilderBuildsListsKeysAsStored(t *testing.T) {
if err != nil {
t.Fatal(err)
}
rows := out.(map[string]any)["builds"].([]view.BuilderRow)
rows := out.(view.BuildsAnswer).Builds
if u := out.(view.BuildsAnswer).Unreadable; len(u) != 1 || u[0] != "junk" {
t.Errorf("unreadable = %v, want [junk] (issue 1818)", u)
}
if len(rows) != 2 || rows[0].Key != keyA || rows[0].Module != "netcheck" || rows[0].Fingerprint != fp2A || string(rows[0].Build) != doneBuild || string(rows[1].Build) != failBuild {
t.Errorf("rows = %+v", rows)
}
for args, want := range map[string]string{"state": keyB, "module": keyA} {
out, _ := run(t, r, view.BuilderBuildsReadTool, map[string]any{args: map[string]string{keyB: "failed", keyA: "netcheck"}[want]})
got := out.(map[string]any)["builds"].([]view.BuilderRow)
got := out.(view.BuildsAnswer).Builds
if len(got) != 1 || got[0].Key != want {
t.Errorf("%s filter = %+v, want %s", args, got, want)
}
@@ -156,3 +160,107 @@ func TestBuilderBuildJoinsTheIndexersFingerprint(t *testing.T) {
t.Errorf("an unbuilt fingerprint: %v", err)
}
}
// bigBuilds is a bucket of n keys over 100 modules that counts the values read.
type bigBuilds struct {
fake fake
reads *int
}
func newBig(n int) bigBuilds {
f := fake{}
for i := 0; i < n; i++ {
f[fmt.Sprintf("mod%02d.%064x", i%100, i)] = doneBuild
}
return bigBuilds{fake: f, reads: new(int)}
}
func (b bigBuilds) reader() view.Reader {
r := b.fake.reader()
get := r.State.Get
r.Builds = view.StateRead{Keys: r.State.Keys, Get: func(k string) (json.RawMessage, error) { *b.reads++; return get(k) },
GetEntry: func(k string) (json.RawMessage, uint64, error) {
*b.reads++
raw, err := get(k)
var rev uint64
fmt.Sscanf(k[strings.Index(k, ".")+1:], "%x", &rev) // the fake's revision is the key's number
return raw, rev + 1, err
}}
return r
}
// 1827/AC1: with 2,000 keys, a module's builds are found by key prefix, so only that module's values are read (20, not 2,000),
// newest revision first, within the limit, and the answer says it was cut.
func TestBuilderBuildsFiltersByPrefixBeforeAnyGet(t *testing.T) {
b := newBig(2000)
out, err := run(t, b.reader(), view.BuilderBuildsReadTool, map[string]any{"module": "mod07", "limit": float64(5)})
if err != nil {
t.Fatal(err)
}
a := out.(view.BuildsAnswer)
if *b.reads != 20 {
t.Errorf("read %d values for a module of 20 keys, want 20", *b.reads)
}
if len(a.Builds) != 5 || !a.Cut || !strings.Contains(a.Note, "5") {
t.Errorf("answer = %d rows, cut %v, note %q", len(a.Builds), a.Cut, a.Note)
}
for i := 1; i < len(a.Builds); i++ {
if a.Builds[i-1].Revision < a.Builds[i].Revision {
t.Errorf("not newest first: %d before %d", a.Builds[i-1].Revision, a.Builds[i].Revision)
}
}
if a.Builds[0].Revision != 1908 {
t.Errorf("newest revision = %d, want 1908", a.Builds[0].Revision)
}
}
// 1827/AC2: with no module the answer reads at most the limit's worth in key order (default 50), never the 2,000.
func TestBuilderBuildsWithoutAModuleIsBounded(t *testing.T) {
b := newBig(2000)
out, err := run(t, b.reader(), view.BuilderBuildsReadTool, map[string]any{})
if err != nil {
t.Fatal(err)
}
a := out.(view.BuildsAnswer)
if len(a.Builds) != view.DefaultBuildsLimit || !a.Cut || *b.reads > view.DefaultBuildsLimit {
t.Errorf("%d rows, cut %v, %d reads", len(a.Builds), a.Cut, *b.reads)
}
b = newBig(2000)
out, _ = run(t, b.reader(), view.BuilderBuildsReadTool, map[string]any{"state": "failed"})
if a := out.(view.BuildsAnswer); *b.reads != view.MaxBuildReads || !a.Cut || len(a.Builds) != 0 {
t.Errorf("a state matching nothing: %d reads (want the bound %d), cut %v", *b.reads, view.MaxBuildReads, a.Cut)
}
}
// 1818: fp2 together with commit is refused, naming both.
func TestBuilderBuildRefusesFP2WithCommit(t *testing.T) {
r := both(fake{keyA: doneBuild}, fake{"netcheck": `{"v":3,"fp2":"` + fp2A + `","commit":"c1","path":"."}`})
_, err := run(t, r, view.BuilderBuildReadTool, map[string]any{"module": "netcheck", "fp2": fp2A, "commit": "c1"})
if err == nil || !strings.Contains(err.Error(), "fp2") || !strings.Contains(err.Error(), "commit") || !strings.Contains(err.Error(), "not both") {
t.Errorf("err = %v", err)
}
}
// 1681: indexer_candidates and indexer_candidate answer the stored value; a pull request's fp2 per touched module shows.
func TestCandidateToolsAnswerTheStoredValue(t *testing.T) {
cand := `{"v":1,"group":"feat/x","base":3,"heads":"h","pulls":[{"modules":["zsh"],"fps":{"zsh":{"fp2":"` + fp2B + `","manifest":"m"}}}]}`
other := `{"v":1,"group":"fix","base":3,"heads":"h","pulls":[{"modules":["netcheck"]}]}`
r := fake{"feat/x": cand, "fix": other, "bad": "{"}.reader()
r.CandidatesState = r.State
out, err := run(t, r, view.CandidateReadTool, map[string]any{"group": "feat/x"})
if err != nil || string(out.(json.RawMessage)) != cand || !strings.Contains(string(out.(json.RawMessage)), fp2B) {
t.Fatalf("candidate = %v, %v", out, err)
}
if _, err := run(t, r, view.CandidateReadTool, map[string]any{"group": "gone"}); err == nil || !strings.Contains(err.Error(), "no candidate gone") {
t.Errorf("err = %v", err)
}
out, err = run(t, r, view.CandidatesReadTool, map[string]any{})
m := out.(map[string]any)
if err != nil || len(m["candidates"].(map[string]json.RawMessage)) != 2 || len(m["unreadable"].([]string)) != 1 {
t.Errorf("all = %v, %v", m, err)
}
out, _ = run(t, r, view.CandidatesReadTool, map[string]any{"module": "zsh"})
if c := out.(map[string]any)["candidates"].(map[string]json.RawMessage); len(c) != 1 || c["feat/x"] == nil {
t.Errorf("by module = %v", c)
}
}
+152 -14
View File
@@ -7,6 +7,7 @@ package view
import (
"encoding/json"
"fmt"
"slices"
"sort"
"strings"
@@ -23,12 +24,16 @@ const (
type StateRead struct {
Keys func() ([]string, error)
Get func(key string) (json.RawMessage, error)
// GetEntry, when set, also gives the revision of the value; builder_builds orders by it.
GetEntry func(key string) (json.RawMessage, uint64, error)
}
// Reader answers the read tools from a modules state.
type Reader struct {
State StateRead // the indexer's modules
Builds StateRead // the builder's builds
CandidatesState StateRead // the indexer's candidates
}
// Module is the stored value of modules.<module>, exactly as the indexer wrote it.
@@ -84,6 +89,67 @@ func (r Reader) Modules(none2 bool) (map[string]json.RawMessage, error) {
return out, nil
}
// The read tools of the indexer's candidates (issue 1681): what the indexer stored under candidates.<group>, as stored, so the
// new-form fingerprint of each touched module of an open pull request (pulls[].fps) can be read live.
const (
CandidateReadTool = "indexer_candidate"
CandidatesReadTool = "indexer_candidates"
)
// Candidate is the stored value of the candidates key of a group, exactly as the indexer wrote it.
func (r Reader) Candidate(group string) (json.RawMessage, error) {
key, err := delivery.CandidatesKey(strings.TrimSpace(group))
if err != nil {
return nil, err
}
if r.CandidatesState.Get == nil {
return nil, fmt.Errorf("the candidates state cannot be read here")
}
raw, err := r.CandidatesState.Get(key)
if err != nil {
return nil, err
}
if len(raw) == 0 {
return nil, fmt.Errorf("no candidate %s in the candidates state", group)
}
return raw, nil
}
// Candidates is every candidate, by group, each as stored; with a module only the candidates with a pull request touching it.
// A value that is not readable is listed under unreadable with its key, not skipped.
func (r Reader) Candidates(module string) (map[string]json.RawMessage, []string, error) {
if r.CandidatesState.Keys == nil || r.CandidatesState.Get == nil {
return nil, nil, fmt.Errorf("the candidates state cannot be read here")
}
keys, err := r.CandidatesState.Keys()
if err != nil {
return nil, nil, err
}
sort.Strings(keys)
out := map[string]json.RawMessage{}
var unreadable []string
for _, k := range keys {
raw, err := r.CandidatesState.Get(k)
if err != nil {
return nil, nil, err
}
if len(raw) == 0 {
continue
}
group, perr := delivery.ParseCandidatesKey(k)
var c delivery.Candidate
if perr != nil || json.Unmarshal(raw, &c) != nil {
unreadable = append(unreadable, k)
continue
}
if module != "" && !slices.ContainsFunc(c.Pulls, func(p delivery.CandidatePull) bool { return slices.Contains(p.Modules, module) }) {
continue
}
out[group] = raw
}
return out, unreadable, nil
}
// The read tools of the builder's builds (novox/hq issue 1723): what the builder stored under `<module>.<fingerprint hex>`
// in mesh-delivery-builder_builds, answered as stored, so its states, nodes (in the step) and digests can be checked live.
const (
@@ -91,48 +157,100 @@ const (
BuilderBuildsReadTool = "builder_builds"
)
// BuilderRow is one key of the builder's builds: the key, the module and the fingerprint it parses to, and the stored value
// as the builder wrote it (state, by, step, manifest, artifacts with digests, toolchains, error).
// BuilderRow is one key of the builder's builds: the key, the module and the fingerprint it parses to, the revision of its
// stored value (when the read gives one) and the stored value as the builder wrote it.
type BuilderRow struct {
Key string `json:"key"`
Module string `json:"module"`
Fingerprint string `json:"fingerprint"`
Revision uint64 `json:"revision,omitempty"`
Build json.RawMessage `json:"build"`
}
// The bounds of builder_builds (issue 1827): the rows it returns when no limit is given, and the values it reads in one call.
// Reading a value is a bus round trip, so the answer must not read the whole bucket (it timed out at 30 s on the live one).
const (
DefaultBuildsLimit = 50
MaxBuildReads = 200
)
// BuildsAnswer is the answer of builder_builds: the rows, newest revision first, whether the answer was cut and why, and
// the keys that are no build key (Unreadable), which are listed rather than silently skipped (issue 1818).
type BuildsAnswer struct {
Builds []BuilderRow `json:"builds"`
Cut bool `json:"cut,omitempty"`
Note string `json:"note,omitempty"`
Unreadable []string `json:"unreadable,omitempty"`
}
func (r Reader) get(key string) (json.RawMessage, uint64, error) {
if r.Builds.GetEntry != nil {
return r.Builds.GetEntry(key)
}
raw, err := r.Builds.Get(key)
return raw, 0, err
}
func (r Reader) builderRow(key string) (BuilderRow, bool, error) {
module, fp, err := delivery.ParseBuilderBuildKey(key)
if err != nil {
return BuilderRow{}, false, nil // a key that is no build key is not a build
}
raw, err := r.Builds.Get(key)
raw, rev, err := r.get(key)
if err != nil {
return BuilderRow{}, false, err
}
if len(raw) == 0 {
return BuilderRow{}, false, nil
}
return BuilderRow{Key: key, Module: module, Fingerprint: fp, Build: raw}, true, nil
return BuilderRow{Key: key, Module: module, Fingerprint: fp, Revision: rev, Build: raw}, true, nil
}
// BuilderBuilds lists the builder's keys, each as stored, sorted by key; module and state, when given, keep only the builds
// of that module or in that state.
func (r Reader) BuilderBuilds(module, state string) ([]BuilderRow, error) {
// BuilderBuilds lists the builder's keys, each as stored, newest revision first. With a module it considers only the keys
// that begin `<module>.`, before any value is read; with a state it keeps the builds in that state. It returns at most limit
// rows (DefaultBuildsLimit when limit is not above zero) and reads at most MaxBuildReads values, and says when it cut the
// answer. Keys that are no build key are listed as unreadable. Without a module the keys are walked in key order, so the
// answer is the first rows found, not the newest of the bucket: give a module to get its newest.
func (r Reader) BuilderBuilds(module, state string, limit int) (BuildsAnswer, error) {
if r.Builds.Keys == nil || r.Builds.Get == nil {
return nil, fmt.Errorf("the builder's builds cannot be read here")
return BuildsAnswer{}, fmt.Errorf("the builder's builds cannot be read here")
}
if limit <= 0 {
limit = DefaultBuildsLimit
}
keys, err := r.Builds.Keys()
if err != nil {
return nil, err
return BuildsAnswer{}, err
}
sort.Strings(keys)
rows := []BuilderRow{}
prefix := ""
if module = strings.TrimSpace(module); module != "" {
prefix = module + "."
}
out := BuildsAnswer{Builds: []BuilderRow{}}
var candidates []string
for _, k := range keys {
if prefix != "" && !strings.HasPrefix(k, prefix) {
continue
}
if _, _, err := delivery.ParseBuilderBuildKey(k); err != nil {
out.Unreadable = append(out.Unreadable, k)
continue
}
candidates = append(candidates, k)
}
reads := 0
for _, k := range candidates {
if reads >= MaxBuildReads {
out.Cut, out.Note = true, fmt.Sprintf("read %d values and stopped; give a module (and a state) to narrow the answer", MaxBuildReads)
break
}
reads++
row, ok, err := r.builderRow(k)
if err != nil {
return nil, err
return BuildsAnswer{}, err
}
if !ok || (module != "" && row.Module != module) {
if !ok {
continue
}
if state != "" {
@@ -143,9 +261,26 @@ func (r Reader) BuilderBuilds(module, state string) ([]BuilderRow, error) {
continue
}
}
rows = append(rows, row)
out.Builds = append(out.Builds, row)
// Without a module the walk is in key order and stops at the limit; with one, all its (few) keys are read to order them.
if prefix == "" && len(out.Builds) >= limit {
if reads < len(candidates) {
out.Cut, out.Note = true, fmt.Sprintf("stopped at the limit of %d builds in key order, not newest first; give a module for its newest", limit)
}
break
}
}
return rows, nil
sort.SliceStable(out.Builds, func(i, j int) bool {
if out.Builds[i].Revision != out.Builds[j].Revision {
return out.Builds[i].Revision > out.Builds[j].Revision
}
return out.Builds[i].Key < out.Builds[j].Key
})
if len(out.Builds) > limit {
out.Builds = out.Builds[:limit]
out.Cut, out.Note = true, fmt.Sprintf("cut to the newest %d builds of %s", limit, module)
}
return out, nil
}
// BuilderBuild is the build of module at the new-form fingerprint fp2; with an empty fp2 it is the build at the fingerprint
@@ -156,6 +291,9 @@ func (r Reader) BuilderBuild(module, fp2, commit string) (BuilderRow, error) {
if r.Builds.Get == nil {
return BuilderRow{}, fmt.Errorf("the builder's builds cannot be read here")
}
if fp2 != "" && commit != "" {
return BuilderRow{}, fmt.Errorf("give fp2 or commit, not both: fp2 %s names a build directly, commit %s asks for the build at the indexer's fingerprint of that commit", fp2, commit)
}
if fp2 == "" {
raw, err := r.Module(module)
if err != nil {
+1 -1
View File
@@ -95,7 +95,7 @@ func TestManifestIsTakenAndReadsOnly(t *testing.T) { // 1134/AC7
}
// The two read tools of the indexer's modules (issue 1562), carried by a bundle the runtime launches; the indexer
// itself serves no tool (ADR 0437 §4). Carrying them gives the tool runner read access to every bucket the view reads.
if want := []string{"indexer_module", "indexer_modules", "builder_build", "builder_builds"}; !reflect.DeepEqual(m.Tools, want) {
if want := []string{"indexer_module", "indexer_modules", "indexer_candidate", "indexer_candidates", "builder_build", "builder_builds"}; !reflect.DeepEqual(m.Tools, want) {
t.Errorf("tools = %v, want %v", m.Tools, want)
}
for _, a := range m.Build.Artifacts {
+2
View File
@@ -6,6 +6,8 @@
"tools": [
"indexer_module",
"indexer_modules",
"indexer_candidate",
"indexer_candidates",
"builder_build",
"builder_builds"
],