nomadcode/services/core/internal/gitosync/scanner_test.go

package gitosync

import (
	"context"
	"errors"
	"os"
	"os/exec"
	"path/filepath"
	"strings"
	"testing"

	"github.com/nomadcode/nomadcode-core/internal/authoring"
	"github.com/nomadcode/nomadcode-core/internal/gitoevents"
	"github.com/nomadcode/nomadcode-core/internal/roadmapsync"
	"github.com/nomadcode/nomadcode-core/internal/roadmapsyncpipeline"
)

const milestonePath = "agent-roadmap/phase/p1/milestones/m1.md"
const archivedMilestonePath = "agent-roadmap/archive/phase/p1/milestones/old-m1.md"

const milestoneMarkdownWithIdentity = `# Milestone m1

## Provider identity
- provider: plane
- tenant: acme
- project: proj-1
- work item id: wi-123
`

const milestoneMarkdownNoIdentity = `# Milestone m2

Just a body, no provider identity block.
`

// fakeRunner returns scripted stdout per (args joined) command and records the
// ordered sequence of commands it ran.
type fakeRunner struct {
	responses map[string]string
	errs      map[string]error
	calls     []string
}

func newFakeRunner() *fakeRunner {
	return &fakeRunner{responses: map[string]string{}, errs: map[string]error{}}
}

func (f *fakeRunner) Run(_ context.Context, _ string, name string, args ...string) (string, error) {
	key := name + " " + strings.Join(args, " ")
	f.calls = append(f.calls, key)
	if err, ok := f.errs[key]; ok {
		return "", err
	}
	return f.responses[key], nil
}

func newScanEvent() gitoevents.BranchUpdatedEvent {
	return gitoevents.BranchUpdatedEvent{
		RepoID: "nomadcode",
		Branch: "develop",
		Before: "aaaa",
		After:  "bbbb",
	}
}

func newTestScanner(t *testing.T, runner CommandRunner) *BranchRevisionScanner {
	t.Helper()
	s, err := NewBranchRevisionScanner(runner, ScannerConfig{
		DevelopRepoPath: "/repo",
		RemoteName:      "origin",
		Branch:          "develop",
	})
	if err != nil {
		t.Fatalf("NewBranchRevisionScanner: %v", err)
	}
	return s
}

func TestScanRunsFetchRevParseActiveIndexShowInOrder(t *testing.T) {
	runner := newFakeRunner()
	runner.responses["git rev-parse refs/remotes/origin/develop"] = "bbbb\n"
	runner.responses["git ls-tree -r --name-only bbbb -- agent-roadmap/phase agent-roadmap/archive"] = milestonePath + "\n"
	runner.responses["git show bbbb:"+milestonePath] = milestoneMarkdownWithIdentity

	out, err := newTestScanner(t, runner).Scan(context.Background(), newScanEvent())
	if err != nil {
		t.Fatalf("Scan: %v", err)
	}

	wantOrder := []string{
		"git fetch --prune origin develop",
		"git rev-parse refs/remotes/origin/develop",
		"git ls-tree -r --name-only bbbb -- agent-roadmap/phase agent-roadmap/archive",
		"git show bbbb:" + milestonePath,
		"git show -s --format=%B bbbb",
	}
	if len(runner.calls) != len(wantOrder) {
		t.Fatalf("call count: got %d (%v), want %d", len(runner.calls), runner.calls, len(wantOrder))
	}
	for i, want := range wantOrder {
		if runner.calls[i] != want {
			t.Fatalf("call[%d]: got %q, want %q", i, runner.calls[i], want)
		}
	}

	if out.Result.Revision.Revision != "bbbb" {
		t.Fatalf("revision: got %q, want bbbb", out.Result.Revision.Revision)
	}
	if len(out.Result.ScannedMilestones) != 1 || out.Result.ScannedMilestones[0].Path != milestonePath {
		t.Fatalf("scanned milestones: got %+v", out.Result.ScannedMilestones)
	}
	if got := out.Result.ScannedMilestones[0].Identity.WorkItemID; got != "wi-123" {
		t.Fatalf("identity work item id: got %q, want wi-123", got)
	}
	if len(out.Docs) != 1 || out.Docs[0].Markdown != milestoneMarkdownWithIdentity {
		t.Fatalf("docs: got %+v", out.Docs)
	}
}

func TestScanReturnsNotReadyOnRevisionMismatch(t *testing.T) {
	runner := newFakeRunner()
	// Remote develop has not caught up to the event's `after`.
	runner.responses["git rev-parse refs/remotes/origin/develop"] = "cccc\n"

	_, err := newTestScanner(t, runner).Scan(context.Background(), newScanEvent())
	if !errors.Is(err, ErrNotReady) {
		t.Fatalf("Scan: got %v, want ErrNotReady", err)
	}
	// It must not diff/show once it knows the revision is stale.
	for _, c := range runner.calls {
		if strings.HasPrefix(c, "git ls-tree") || strings.HasPrefix(c, "git show") {
			t.Fatalf("unexpected command after mismatch: %q", c)
		}
	}
}

func TestScanPreservesMilestoneWithoutProviderIdentity(t *testing.T) {
	runner := newFakeRunner()
	runner.responses["git rev-parse refs/remotes/origin/develop"] = "bbbb"
	runner.responses["git ls-tree -r --name-only bbbb -- agent-roadmap/phase agent-roadmap/archive"] = milestonePath
	runner.responses["git show bbbb:"+milestonePath] = milestoneMarkdownNoIdentity

	out, err := newTestScanner(t, runner).Scan(context.Background(), newScanEvent())
	if err != nil {
		t.Fatalf("Scan: %v", err)
	}
	// Kept in ChangedFiles (so the match gate's reason stays accurate) and preserved in Docs for missing-create.
	if len(out.Result.ChangedFiles) != 1 {
		t.Fatalf("changed files: got %v", out.Result.ChangedFiles)
	}
	if len(out.Result.ScannedMilestones) != 0 {
		t.Fatalf("scanned milestones: want none, got %+v", out.Result.ScannedMilestones)
	}
	if len(out.Docs) != 1 {
		t.Fatalf("docs: got %d, want 1", len(out.Docs))
	}
	doc := out.Docs[0]
	if doc.Path != milestonePath || doc.MilestoneID != "m1" || doc.Markdown != milestoneMarkdownNoIdentity || doc.HasIdentity {
		t.Fatalf("doc mismatch: %+v", doc)
	}
}

func TestScanIndexesOnlyActiveMilestonesAndKeepsArchiveCandidates(t *testing.T) {
	runner := newFakeRunner()
	runner.responses["git rev-parse refs/remotes/origin/develop"] = "bbbb"
	runner.responses["git ls-tree -r --name-only bbbb -- agent-roadmap/phase agent-roadmap/archive"] =
		"agent-roadmap/phase/p1/PHASE.md\n" +
			milestonePath + "\n" +
			archivedMilestonePath + "\n"
	runner.responses["git show bbbb:"+milestonePath] = milestoneMarkdownWithIdentity

	out, err := newTestScanner(t, runner).Scan(context.Background(), newScanEvent())
	if err != nil {
		t.Fatalf("Scan: %v", err)
	}
	if len(out.Result.ChangedFiles) != 1 || out.Result.ChangedFiles[0] != milestonePath {
		t.Fatalf("changed files: got %v, want only the milestone path", out.Result.ChangedFiles)
	}
	if len(out.ArchiveCandidates) != 1 {
		t.Fatalf("archive candidates: got %+v, want one", out.ArchiveCandidates)
	}
	if out.ArchiveCandidates[0].Path != archivedMilestonePath || out.ArchiveCandidates[0].MilestoneID != "old-m1" {
		t.Fatalf("archive candidate mismatch: %+v", out.ArchiveCandidates[0])
	}
}

func TestScanIndexesRemoteRevisionRegardlessOfBefore(t *testing.T) {
	runner := newFakeRunner()
	runner.responses["git rev-parse refs/remotes/origin/develop"] = "bbbb"
	runner.responses["git ls-tree -r --name-only bbbb -- agent-roadmap/phase agent-roadmap/archive"] = ""

	ev := newScanEvent()
	ev.Before = "0000000000000000000000000000000000000000"

	if _, err := newTestScanner(t, runner).Scan(context.Background(), ev); err != nil {
		t.Fatalf("Scan: %v", err)
	}
	for _, c := range runner.calls {
		if strings.HasPrefix(c, "git diff") {
			t.Fatalf("active index must not use diff range, got %q", c)
		}
		if strings.HasPrefix(c, "git ls-tree") && !strings.Contains(c, "bbbb -- ") {
			t.Fatalf("expected ls-tree at remote revision, got %q", c)
		}
	}
}

func TestScanRegressionWithIdentityWriter(t *testing.T) {
	// 1. Create a temporary git repo to run the real LocalIdentityWriter on it.
	tmpDir, err := os.MkdirTemp("", "nomadcode-scanner-regression-*")
	if err != nil {
		t.Fatalf("failed to create temp dir: %v", err)
	}
	defer os.RemoveAll(tmpDir)

	// git init
	cmd := exec.Command("git", "init")
	cmd.Dir = tmpDir
	if err := cmd.Run(); err != nil {
		t.Fatalf("failed to git init: %v", err)
	}

	// git config user.name and user.email (just in case)
	cmd = exec.Command("git", "config", "user.name", "test")
	cmd.Dir = tmpDir
	_ = cmd.Run()
	cmd = exec.Command("git", "config", "user.email", "test@test.com")
	cmd.Dir = tmpDir
	_ = cmd.Run()

	milestoneRelPath := "agent-roadmap/phase/p1/milestones/m1.md"
	milestoneDir := filepath.Join(tmpDir, "agent-roadmap", "phase", "p1", "milestones")
	if err := os.MkdirAll(milestoneDir, 0755); err != nil {
		t.Fatalf("failed to create milestone dir: %v", err)
	}

	milestoneFullPath := filepath.Join(milestoneDir, "m1.md")
	// write identity-less milestone markdown
	if err := os.WriteFile(milestoneFullPath, []byte(milestoneMarkdownNoIdentity), 0644); err != nil {
		t.Fatalf("failed to write milestone file: %v", err)
	}

	// 2. Run LocalIdentityWriter to inject identity block.
	writer := authoring.NewLocalIdentityWriter()
	ident := roadmapsync.Identity{
		Provider:   "plane",
		WorkItemID: "wi-123",
		Tenant:     "acme",
		Project:    "proj-1",
	}
	res, err := writer.EnsureProviderIdentity(context.Background(), authoring.EnsureProviderIdentityInput{
		WorkspacePath: tmpDir,
		Identity:      ident,
	})
	if err != nil {
		t.Fatalf("EnsureProviderIdentity failed: %v", err)
	}
	if len(res.InjectedPaths) != 1 || res.InjectedPaths[0] != milestoneRelPath {
		t.Fatalf("unexpected injected paths: %v", res.InjectedPaths)
	}

	// Read the modified markdown (which now has identity)
	injectedMarkdownBytes, err := os.ReadFile(milestoneFullPath)
	if err != nil {
		t.Fatalf("failed to read injected file: %v", err)
	}
	injectedMarkdown := string(injectedMarkdownBytes)

	// 3. Mock the runner with the injected markdown as the output of `git show`
	runner := newFakeRunner()
	runner.responses["git rev-parse refs/remotes/origin/develop"] = "bbbb\n"
	runner.responses["git ls-tree -r --name-only bbbb -- agent-roadmap/phase agent-roadmap/archive"] = milestoneRelPath + "\n"
	runner.responses["git show bbbb:"+milestoneRelPath] = injectedMarkdown

	out, err := newTestScanner(t, runner).Scan(context.Background(), newScanEvent())
	if err != nil {
		t.Fatalf("Scan regression failed: %v", err)
	}

	// 4. Verify that the scanner now successfully parses it
	if len(out.Result.ScannedMilestones) != 1 || out.Result.ScannedMilestones[0].Path != milestoneRelPath {
		t.Fatalf("expected 1 scanned milestone, got %+v", out.Result.ScannedMilestones)
	}
	parsedIdent := out.Result.ScannedMilestones[0].Identity
	if parsedIdent.Provider != "plane" || parsedIdent.WorkItemID != "wi-123" || parsedIdent.Tenant != "acme" || parsedIdent.Project != "proj-1" {
		t.Errorf("unexpected parsed identity: %+v", parsedIdent)
	}
	if len(out.Docs) != 1 || out.Docs[0].Markdown != injectedMarkdown {
		t.Fatalf("expected 1 doc with injected markdown, got %+v", out.Docs)
	}
}

// TestScanChangedFilesHintDoesNotGateActiveIndexScan verifies that
// ev.ChangedFiles (the wakeup hint) is not consulted to decide what gets
// scanned: even when the hint names an unrelated file, or is empty, the full
// active Milestone index at the verified revision is the source of truth.
func TestScanChangedFilesHintDoesNotGateActiveIndexScan(t *testing.T) {
	runner := newFakeRunner()
	runner.responses["git rev-parse refs/remotes/origin/develop"] = "bbbb"
	runner.responses["git ls-tree -r --name-only bbbb -- agent-roadmap/phase agent-roadmap/archive"] = milestonePath
	runner.responses["git show bbbb:"+milestonePath] = milestoneMarkdownWithIdentity

	ev := newScanEvent()
	ev.ChangedFiles = []gitoevents.ChangedFile{{Path: "README.md", ChangeType: "modified"}}

	out, err := newTestScanner(t, runner).Scan(context.Background(), ev)
	if err != nil {
		t.Fatalf("Scan: %v", err)
	}
	if len(out.Result.ScannedMilestones) != 1 || out.Result.ScannedMilestones[0].Path != milestonePath {
		t.Fatalf("expected active index milestone regardless of unrelated hint, got %+v", out.Result.ScannedMilestones)
	}
	for _, c := range runner.calls {
		if strings.HasPrefix(c, "git diff") {
			t.Fatalf("hint must not be used to build a diff range, got %q", c)
		}
	}
}

// TestScanFlagsSelfAuthoredBackfillCommitAsHintOnly verifies that a tip commit
// carrying the Core identity-backfill marker sets ScanOutput.SelfAuthored, but
// the hint does not change what gets scanned: the full active Milestone index at
// the verified revision is still the source of truth (S05 — the self-loop
// wakeup is recognized without bypassing the active scan).
func TestScanFlagsSelfAuthoredBackfillCommitAsHintOnly(t *testing.T) {
	runner := newFakeRunner()
	runner.responses["git rev-parse refs/remotes/origin/develop"] = "bbbb"
	runner.responses["git ls-tree -r --name-only bbbb -- agent-roadmap/phase agent-roadmap/archive"] = milestonePath
	runner.responses["git show bbbb:"+milestonePath] = milestoneMarkdownWithIdentity
	runner.responses["git show -s --format=%B bbbb"] =
		"chore(roadmap): backfill provider identity for m1\n\n" + roadmapsyncpipeline.CommitMarker + "\n"

	out, err := newTestScanner(t, runner).Scan(context.Background(), newScanEvent())
	if err != nil {
		t.Fatalf("Scan: %v", err)
	}
	if !out.SelfAuthored {
		t.Fatal("expected SelfAuthored hint for a Core backfill tip commit")
	}
	// The hint must not suppress the active-index scan.
	if len(out.Result.ScannedMilestones) != 1 || out.Result.ScannedMilestones[0].Path != milestonePath {
		t.Fatalf("self-authored hint must not bypass active scan, got %+v", out.Result.ScannedMilestones)
	}
	if len(out.Docs) != 1 {
		t.Fatalf("docs: got %d, want 1", len(out.Docs))
	}
}

// TestScanDoesNotFlagSelfAuthoredForOrdinaryCommit verifies an ordinary tip
// commit (no Core marker) leaves the hint false.
func TestScanDoesNotFlagSelfAuthoredForOrdinaryCommit(t *testing.T) {
	runner := newFakeRunner()
	runner.responses["git rev-parse refs/remotes/origin/develop"] = "bbbb"
	runner.responses["git ls-tree -r --name-only bbbb -- agent-roadmap/phase agent-roadmap/archive"] = milestonePath
	runner.responses["git show bbbb:"+milestonePath] = milestoneMarkdownWithIdentity
	runner.responses["git show -s --format=%B bbbb"] = "feat: an ordinary user push\n"

	out, err := newTestScanner(t, runner).Scan(context.Background(), newScanEvent())
	if err != nil {
		t.Fatalf("Scan: %v", err)
	}
	if out.SelfAuthored {
		t.Fatal("expected SelfAuthored to stay false for an ordinary commit")
	}
}

func TestScanReturnsErrorOnDuplicateActiveSlugs(t *testing.T) {
	runner := newFakeRunner()
	runner.responses["git rev-parse refs/remotes/origin/develop"] = "bbbb"
	runner.responses["git ls-tree -r --name-only bbbb -- agent-roadmap/phase agent-roadmap/archive"] =
		"agent-roadmap/phase/p1/milestones/m1.md\n" +
			"agent-roadmap/phase/p2/milestones/m1.md\n"

	_, err := newTestScanner(t, runner).Scan(context.Background(), newScanEvent())
	if !errors.Is(err, ErrDuplicateActiveSlug) {
		t.Fatalf("Scan: got %v, want ErrDuplicateActiveSlug", err)
	}
}

func TestScanAllowsSameSlugInActiveAndArchive(t *testing.T) {
	runner := newFakeRunner()
	runner.responses["git rev-parse refs/remotes/origin/develop"] = "bbbb"
	runner.responses["git ls-tree -r --name-only bbbb -- agent-roadmap/phase agent-roadmap/archive"] =
		"agent-roadmap/phase/p1/milestones/m1.md\n" +
			"agent-roadmap/archive/phase/p2/milestones/m1.md\n"
	runner.responses["git show bbbb:agent-roadmap/phase/p1/milestones/m1.md"] = milestoneMarkdownWithIdentity

	out, err := newTestScanner(t, runner).Scan(context.Background(), newScanEvent())
	if err != nil {
		t.Fatalf("Scan: unexpected error: %v", err)
	}
	if len(out.Result.ChangedFiles) != 1 || out.Result.ChangedFiles[0] != "agent-roadmap/phase/p1/milestones/m1.md" {
		t.Fatalf("expected 1 active file, got %v", out.Result.ChangedFiles)
	}
	if len(out.ArchiveCandidates) != 1 || out.ArchiveCandidates[0].Path != "agent-roadmap/archive/phase/p2/milestones/m1.md" {
		t.Fatalf("expected 1 archive candidate, got %v", out.ArchiveCandidates)
	}
}