mesh-delivery/modules/mesh-delivery-checker/internal/check/try_test.go

package check

import (
	"context"
	"encoding/json"
	"errors"
	"fmt"
	"strings"
	"testing"
	"time"

	"git.novox.be/novox/mesh-delivery/sdk/tryevent"
	"git.novox.be/novox/mesh-sdk/go/delivery"
)

// memTries is the tries state as the tools see it, over a memKV.
type memTries struct{ kv *memKV }

func (m memTries) Keys() ([]string, error) { return m.kv.Keys(context.Background()) }
func (m memTries) Get(key string) (json.RawMessage, error) {
	v, _, _, err := m.kv.Get(context.Background(), key)
	return v, err
}
func (m memTries) Create(key string, value []byte) error {
	_, err := m.kv.Create(context.Background(), key, value)
	return err
}

// writtenTries is a memKV that keeps every running try it was given to write, in order.
type writtenTries struct {
	*memKV
	running []Try
}

func (w *writtenTries) Update(ctx context.Context, key string, value []byte, rev uint64) (uint64, error) {
	if t, err := DecodeTry(value); err == nil && !t.Over() {
		w.running = append(w.running, t)
	}
	return w.memKV.Update(ctx, key, value, rev)
}

var tryTrunks = map[string]string{repoA: trunkA, repoSDK: trunkS, hqRepo: trunkA}

func readTry(t testing.TB, kv *memKV, id string) Try {
	t.Helper()
	raw, _, found, _ := kv.Get(context.Background(), id)
	if !found {
		t.Fatalf("no try %s", id)
	}
	tr, err := DecodeTry(raw)
	if err != nil {
		t.Fatal(err)
	}
	return tr
}

func TestATryIsAskedQueuedOncePerHeadAndAtMostFourAtOnce(t *testing.T) { // ADR 0501 §5
	kv := newMemKV()
	store := memTries{kv}
	at := time.Date(2026, 10, 22, 18, 0, 0, 0, time.UTC)
	id, err := AskTry(store, tryTrunks, TryAsk{Repository: repoA, Head: head1, Trunk: "main"}, at)
	if err != nil || !strings.HasPrefix(id, "try-") {
		t.Fatalf("id %q, %v", id, err)
	}
	tr := readTry(t, kv, id)
	if tr.State != TryQueued || tr.Trunk != trunkA || tr.Branch != "main" || tr.Head != head1 || tr.Repository != repoA {
		t.Errorf("try = %+v, want queued on the trunk's head", tr)
	}
	again, err := AskTry(store, tryTrunks, TryAsk{Repository: repoA, Head: head1, Trunk: "main"}, at.Add(time.Second))
	if err != nil || again != id {
		t.Errorf("a second ask of the same head answered %q, %v, want %q", again, err, id)
	}
	// Issue 1890: tries on a build node (a step of theirs running, or none named yet) and tries waiting for one (queued, or
	// their asks not taken) are bounded apart, MaxTries and MaxTriesWaiting; the refusal names both counts.
	// A group try is the same try whatever the order of its members; the commits asked are the commits tried.
	group := TryAsk{Members: []TryAskMember{{Repository: repoSDK, Head: head2}, {Repository: repoA, Head: head1}}}
	gid, err := AskTry(store, tryTrunks, group, at.Add(time.Second))
	if err != nil || gid == id {
		t.Fatalf("the group try = %q, %v, want a try of its own", gid, err)
	}
	group.Members[0], group.Members[1] = group.Members[1], group.Members[0]
	if again, err := AskTry(store, tryTrunks, group, at.Add(time.Minute)); err != nil || again != gid {
		t.Errorf("the group asked in another order answered %q, %v, want %q", again, err, gid)
	}
	if g := readTry(t, kv, gid); len(g.Members) != 2 || g.Members[0].Repository != repoA || g.Members[0].Head != head1 || g.Members[1].Trunk != trunkS {
		t.Errorf("group try = %+v, want its members by repository at the commits asked", g.Members)
	}
	if open, err := OpenTries(store); err != nil || len(open) != 2 || !open[0].Whole || len(open[1].Members) != 2 && len(open[0].Members) != 2 {
		t.Errorf("open tries = %+v, %v, want the two queued", open, err)
	}
	if !IsTryGroup(gid) || IsTryGroup("feat/x") || IsTryGroup("fix/1921-try-1") {
		t.Errorf("which candidates keys are a try's group: %s is, a branch is not", gid)
	}
	onNode := func(i int) Try {
		return Try{ID: fmt.Sprintf("try-%d", i), Repository: repoA, Head: fmt.Sprintf("%040x", i), Trunk: trunkA, State: TryRunning,
			Steps: []TryStep{{Ask: "a", State: delivery.StepRunning}}}
	}
	waitingFor := func(i int) Try {
		return Try{ID: fmt.Sprintf("try-%d", i), Repository: repoA, Head: fmt.Sprintf("%040x", i), Trunk: trunkA, State: TryRunning,
			Steps: []TryStep{{Ask: "a", State: TryAsked}}}
	}
	for _, c := range []struct {
		what          string
		holding, wait int
		refused       string
	}{
		{"four queued behind the checks, none on a node: a fifth is taken", 0, 4, ""},
		{"four on a node", MaxTries, 0, "now 4 run and 0 wait"},
		{"three on a node, eight waiting", 3, MaxTriesWaiting, "a new try is refused while 4 tries run on a build node or 8 wait for one; now 3 run and 8 wait"},
	} {
		kv := newMemKV()
		for i := range c.holding + c.wait {
			tr := waitingFor(i + 1)
			if i < c.holding {
				tr = onNode(i + 1)
			}
			data, _ := encodeTry(tr)
			_, _ = kv.Create(context.Background(), tr.ID, data)
		}
		_, err := AskTry(memTries{kv}, tryTrunks, TryAsk{Repository: repoSDK, Head: head1}, at.Add(time.Minute))
		if (c.refused == "") != (err == nil) || (err != nil && !strings.Contains(err.Error(), c.refused)) {
			t.Errorf("%s: answered %v, want refused %q", c.what, err, c.refused)
		}
	}
}

func TestATryOfARepositoryWithNoCheckedLevelIsRefused(t *testing.T) { // the agreed error of the try
	store := memTries{newMemKV()}
	for _, repo := range []string{"novox/no-trunk", "novox/mesh-lab"} { // hq is checked since R4g (ADR 0527): see tryTrunks
		_, err := AskTry(store, tryTrunks, TryAsk{Repository: repo, Head: head1, Trunk: "main"}, time.Now())
		if err == nil || err.Error() != "no level of "+repo+" is checked by the checker" {
			t.Errorf("%s: %v", repo, err)
		}
	}
	for _, bad := range []TryAsk{{Repository: repoA, Head: "abc"}, {Repository: repoA, Head: head1, Level: "e2e"},
		{Repository: repoA, Head: head1, Tests: "a b"}, {Repository: "x", Head: head1}, {Repository: repoA, Head: head1, Trunk: "-x"},
		// A group try (issue 1921): members or one repository, never both or none; one commit per repository; every member checked.
		{},
		{Repository: repoA, Head: head1, Members: []TryAskMember{{Repository: repoSDK, Head: head2}}},
		{Members: []TryAskMember{{Repository: repoA, Head: head1}, {Repository: repoA, Head: head2}}},
		{Members: []TryAskMember{{Repository: repoA, Head: head1}, {Repository: repoSDK, Head: "main"}}},
		{Members: []TryAskMember{{Repository: repoA, Head: head1}, {Repository: "novox/no-trunk", Head: head2}}}} {
		if _, err := AskTry(store, tryTrunks, bad, time.Now()); err == nil {
			t.Errorf("%+v was taken", bad)
		}
	}
}

// fakeTryCandidates answers the indexer's candidate of a try's group from memory, recording the keys asked.
type fakeTryCandidates struct {
	cand  delivery.Candidate
	err   error
	asked []string
}

func (f *fakeTryCandidates) TryCandidate(_ context.Context, group, heads string, _ time.Duration) (delivery.Candidate, error) {
	f.asked = append(f.asked, group+"."+heads)
	return f.cand, f.err
}

// wholeBench makes the bench judge a whole try as the checker does: the composition on every placed node and the
// indexer's candidate of the try's group.
func wholeBench(b *bench, cand delivery.Candidate) (*fakeCompositions, *fakeTryCandidates) {
	comps := &fakeCompositions{v: delivery.CompositionVerdict{State: delivery.CompositionPass, SDK: "v0.1.14-x", Machines: []string{"g14", "shanks"}, Took: 40}}
	cands := &fakeTryCandidates{cand: cand}
	b.ex.Compositions, b.ex.Candidates = comps, cands
	return comps, cands
}

// A group try (issue 1921): several repositories each at the exact commit asked, judged by the code of a group's pull-request
// check; the two cannot drift, and a later check of the same heads keeps what the try passed.
func TestATryIsJudgedAsAGroupsCheckAndOwesTheForgeNothing(t *testing.T) { // ADR 0501 §5, issue 1921
	ctx := context.Background()
	kv := newMemKV()
	id, err := AskTry(memTries{kv}, tryTrunks, TryAsk{Members: []TryAskMember{{Repository: repoSDK, Head: head2, Trunk: trunkS}, {Repository: repoA, Head: head1, Trunk: trunkA}}}, time.Now())
	if err != nil {
		t.Fatal(err)
	}
	b := newBench(t)
	comps, cands := wholeBench(b, delivery.Candidate{FPSet: "fps-of-the-try"})
	written := &writtenTries{memKV: kv}
	var said []string
	tr := &Tryer{Tries: written, Judge: b.ex, Say: func(_ context.Context, event string, e tryevent.Event) {
		said = append(said, fmt.Sprintf("%s %s %d", event, e.ID, len(e.Members)))
	}}
	raw, _, _, _ := kv.Get(ctx, id)
	tr.Put(ctx, id, raw)
	tr.Wait()
	// The indexer hears the start with the members at their commits, and the end (it writes and deletes the group's candidate).
	if len(said) != 2 || said[0] != "try.started "+id+" 2" || said[1] != "try.ended "+id+" 0" {
		t.Errorf("events = %v, want the start with 2 members and the end", said)
	}
	got := readTry(t, kv, id)
	if open, err := OpenTries(memTries{kv}); err != nil || len(open) != 0 {
		t.Errorf("open tries after the end = %v, %v", open, err)
	}
	if got.State != TryPass || got.Took == "" || len(got.Members) != 2 || got.Members[0].Repository != repoA || got.Members[1].Head != head2 ||
		got.Said == "" || got.Levels[delivery.LevelUnit].Run+got.Levels[delivery.LevelUnit].Kept != 4 { // the bench gives both members the same digests
		t.Fatalf("try = %+v", got)
	}
	if got.Composition == nil || got.Composition.State != delivery.CompositionPass || len(got.Machines) == 0 {
		t.Errorf("the try's composition = %+v, want the composition on every placed node, as a check's", got.Composition)
	}
	// The same key the indexer's candidate of the group has: the try's id and the heads of its members.
	if len(comps.asked) != 1 || comps.asked[0] != id || len(cands.asked) != 1 || !strings.HasPrefix(cands.asked[0], id+".") {
		t.Errorf("composed %v, candidate asked %v, want the try's key %s", comps.asked, cands.asked, id)
	}
	// Issue 1890: while it runs, the try names its asks as soon as they are put, and then where each step stands.
	if len(written.running) < 3 || len(written.running[1].Asks) != 1 || written.running[1].Steps[0].State != TryAsked {
		t.Errorf("the running try's writes = %+v, want its ask named while it ran", written.running)
	}
	if len(got.Steps) != 2 || got.Steps[0].Node != "shanks" || got.Steps[0].State != delivery.StepPassed || len(got.Asks) != 2 {
		t.Errorf("the ended try's steps = %+v, asks %v", got.Steps, got.Asks)
	}
	for _, a := range got.Asks { // the delivery view counts their steps as a try's (build_usage)
		if _, err := delivery.AskStepKey("shanks", a); err != nil {
			t.Errorf("the try names %q, which is no ask id: %v", a, err)
		}
	}
	// Each member is fetched at the exact commit asked, merged onto its own trunk, with no pull request's ref.
	fetch := b.steps.tool("fetch")
	if len(fetch) != 2 {
		t.Fatalf("fetch = %+v, want one per member", fetch)
	}
	for _, f := range fetch {
		want := map[string][2]string{repoA: {head1, trunkA}, repoSDK: {head2, trunkS}}[f.args["repository"].(string)]
		if f.args["commit"] != want[0] || f.args["base"] != want[1] || f.args["ref"] != "" {
			t.Errorf("fetch = %+v, want the exact commit %s merged onto %s", f.args, want[0], want[1])
		}
	}
	// A whole try writes the merge previews the indexer makes its candidate from; it writes no status and asks no Approve.
	if keys, _ := b.prev.Keys(ctx); len(keys) != 2 {
		t.Errorf("a whole try wrote the previews %v, want one per member", keys)
	}
	// An ended try is not run again.
	raw, _, _, _ = kv.Get(ctx, id)
	tr.Put(ctx, id, raw)
	tr.Wait()
	if n := len(b.steps.tool("fetch")); n != 2 {
		t.Errorf("an ended try was fetched again: %d fetches", n)
	}
	// The kept verdicts: what the try passed is kept under the digests of the merged trees, so the pull-request check of
	// the same head on the same trunk runs none of it again (and a push of other code runs only what changed).
	before := len(b.steps.tool("test"))
	out := b.judge(t, caseOf(t, pullOf(repoA, 7, head1)))
	if out.Verdict.State != delivery.VerdictPass || out.Verdict.Levels[delivery.LevelUnit].Kept == 0 || out.Verdict.Levels[delivery.LevelUnit].Run != 0 ||
		out.Verdict.Levels[delivery.LevelIntegration].Run != 0 {
		t.Errorf("the check of the tried head = %+v, want everything the try passed kept and nothing run", out.Verdict.Levels)
	}
	if after := len(b.steps.tool("test")); after != before {
		t.Errorf("the check of the tried head ran %d test steps, want none: the try's passes are kept", after-before)
	}
}

func TestATryOfOneLevelAndSomeTestsRunsThemAloneAndKeepsNothing(t *testing.T) {
	ctx := context.Background()
	kv := newMemKV()
	id, err := AskTry(memTries{kv}, tryTrunks, TryAsk{Repository: repoA, Head: head1, Level: delivery.LevelIntegration, Tests: "TestBus|TestStore"}, time.Now())
	if err != nil {
		t.Fatal(err)
	}
	b := newBench(t)
	tr := &Tryer{Tries: kv, Judge: b.ex, Say: func(context.Context, string, tryevent.Event) {
		t.Error("a try of one level and some tests said an event: it has no candidate")
	}}
	raw, _, _, _ := kv.Get(ctx, id)
	tr.Put(ctx, id, raw)
	tr.Wait()
	if open, _ := OpenTries(memTries{kv}); len(open) != 0 {
		t.Errorf("open = %v", open)
	}
	tests := b.steps.tool("test")
	if len(tests) != 1 || tests[0].args["level"] != delivery.LevelIntegration || tests[0].args["run"] != "TestBus|TestStore" {
		t.Fatalf("tests = %+v, want the integration level alone with the run pattern", tests)
	}
	if n := len(b.steps.tool("digest")); n != 0 {
		t.Errorf("%d digests for a try of some tests", n)
	}
	if keys, _ := b.kept.Keys(ctx); len(keys) != 0 {
		t.Errorf("kept %v from a try of some tests", keys)
	}
	if got := readTry(t, kv, id); got.State != TryPass || !strings.Contains(got.Said, "only the tests TestBus|TestStore") {
		t.Errorf("try = %+v", got)
	}
}

func TestATryOfOneLevelKeepsOnlyThatLevel(t *testing.T) {
	ctx := context.Background()
	kv := newMemKV()
	id, _ := AskTry(memTries{kv}, tryTrunks, TryAsk{Repository: repoA, Head: head1, Level: delivery.LevelUnit}, time.Now())
	b := newBench(t)
	tr := &Tryer{Tries: kv, Judge: b.ex}
	raw, _, _, _ := kv.Get(ctx, id)
	tr.Put(ctx, id, raw)
	tr.Wait()
	keys, _ := b.kept.Keys(ctx)
	if got := readTry(t, kv, id); got.State != TryPass || len(keys) == 0 {
		t.Fatalf("try = %+v, kept %v", got, keys)
	}
	for _, k := range keys {
		if !strings.HasPrefix(k, delivery.LevelUnit+".") {
			t.Errorf("a try of the unit level kept %s", k)
		}
	}
}

func TestAFailingTryNamesWhatFailedAndAStepThatCannotRunIsAnError(t *testing.T) {
	ctx := context.Background()
	kv := newMemKV()
	b := newBench(t)
	b.test = func(c stepCall) (any, error) { return captured[Tested](t, "go-test-failing"), nil }
	id, _ := AskTry(memTries{kv}, tryTrunks, TryAsk{Repository: repoA, Head: head1}, time.Now())
	tr := &Tryer{Tries: kv, Judge: b.ex}
	raw, _, _, _ := kv.Get(ctx, id)
	tr.Put(ctx, id, raw)
	tr.Wait()
	if got := readTry(t, kv, id); got.State != TryFail || len(got.Failed) != 2 || !strings.Contains(got.Failed[0], "unit: fixture/failing/bad.TestThreeIsFour") ||
		!strings.Contains(got.Failed[1], "integration: fixture/failing/bad.TestThreeIsFour") { // both levels ran (the operator, 2026-11-02)
		t.Errorf("try = %+v", got)
	}
	// A whole try that could not judge the manifests and the composition is no pass; a failed composition is named beside
	// the failed tests (the group's check does as much), and a candidate of other heads is not the try's.
	for _, row := range []struct {
		name        string
		cand        *fakeTryCandidates
		comp        delivery.CompositionVerdict
		state, said string
	}{
		{name: "the indexer wrote no candidate", cand: &fakeTryCandidates{err: errors.New("the indexer wrote no candidate within 5m0s")}, state: TryError, said: "the indexer wrote no candidate within 5m0s"},
		{name: "a node that gave no composition answer", cand: &fakeTryCandidates{}, comp: delivery.CompositionVerdict{State: delivery.CompositionPass, SDK: "x", Warnings: []string{"g14: " + delivery.ComposeNoAnswer}},
			state: TryError, said: "g14: " + delivery.ComposeNoAnswer},
		{name: "a composition refused on a node", cand: &fakeTryCandidates{}, comp: delivery.CompositionVerdict{State: delivery.CompositionFail, Machine: "g14", Words: "not composed on g14: web: needs a state mail does not keep"},
			state: TryFail, said: "not composed on g14: web: needs a state mail does not keep"},
	} {
		kv := newMemKV()
		b := newBench(t)
		comps, _ := wholeBench(b, delivery.Candidate{})
		b.ex.Candidates, comps.v = row.cand, row.comp
		if row.comp.State == "" {
			comps.v.State = delivery.CompositionPass
		}
		id, _ := AskTry(memTries{kv}, tryTrunks, TryAsk{Repository: repoA, Head: head1}, time.Now())
		tr := &Tryer{Tries: kv, Judge: b.ex}
		raw, _, _, _ := kv.Get(ctx, id)
		tr.Put(ctx, id, raw)
		tr.Wait()
		if got := readTry(t, kv, id); got.State != row.state || !strings.Contains(strings.Join(got.Failed, " | ")+got.Said, row.said) {
			t.Errorf("%s: try = %s, failed %v, said %q, want %s naming %q", row.name, got.State, got.Failed, got.Said, row.state, row.said)
		}
	}
	// No build node is no error since R4g: the try's ask waits in the check stream until a node pulls it (ADR 0525 §4).
}

func TestATryLeftRunningIsTakenOver(t *testing.T) {
	ctx := context.Background()
	kv := newMemKV()
	id, _ := AskTry(memTries{kv}, tryTrunks, TryAsk{Repository: repoA, Head: head1}, time.Now())
	// Left running by a checker that stopped.
	raw, rev, _, _ := kv.Get(ctx, id)
	cur, _ := DecodeTry(raw)
	cur.State = TryRunning
	data, _ := encodeTry(cur)
	if _, err := kv.Update(ctx, id, data, rev); err != nil {
		t.Fatal(err)
	}
	b := newBench(t)
	wholeBench(b, delivery.Candidate{})
	tr := &Tryer{Tries: kv, Judge: b.ex}
	tr.Reconsider(ctx)
	tr.Wait()
	if got := readTry(t, kv, id); got.State != TryPass {
		t.Errorf("the try left running = %+v, want taken over and passed", got)
	}
}