feat(usecase): read stored transcript before fetching (ADR-021)
The engine now resolves transcripts store-first: a stored transcript — including a stored SourceNone — is summarized without touching YouTube, so re-analysis never re-fetches. On a miss it fetches through the source (caption call still gated, ADR-014) and persists the terminal outcome for the next analysis by any user. A transient SourceRateLimited is surfaced to the runner for per-user backoff but never cached, so persistence can never mask a 429 as a permanent "no transcript". The TranscriptStore is optional (nil → fetch every time), keeping the pure-core and scaffold wiring valid. cmd/tapir wires the store as both summary sink and transcript cache, so `tapir run` and the web summarize path (incl. paste + onboarding) all share the dedup. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Claude Opus 4.8
@@ -0,0 +1,187 @@
|
||||
package usecase
|
||||
|
||||
import (
|
||||
"context"
|
||||
"testing"
|
||||
|
||||
"gitea.d-ma.be/mathias/tapir/internal/domain"
|
||||
)
|
||||
|
||||
// These tests pin the ADR-021 read-stored-first behaviour at the engine core:
|
||||
// a stored transcript is summarized without re-touching the source, a miss
|
||||
// fetches once and persists, and a transient rate-limit is never cached.
|
||||
|
||||
type recordingSource struct {
|
||||
transcript domain.Transcript
|
||||
fetchCalls int
|
||||
}
|
||||
|
||||
func (s *recordingSource) ListSubscriptions(context.Context, string) ([]domain.Subscription, error) {
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
func (s *recordingSource) NewVideos(context.Context, domain.Subscription) ([]domain.Video, error) {
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
func (s *recordingSource) FetchTranscript(context.Context, domain.Video) (domain.Transcript, error) {
|
||||
s.fetchCalls++
|
||||
return s.transcript, nil
|
||||
}
|
||||
|
||||
type fakeTranscriptStore struct {
|
||||
stored map[string]domain.Transcript
|
||||
saves int
|
||||
}
|
||||
|
||||
func newFakeTranscriptStore() *fakeTranscriptStore {
|
||||
return &fakeTranscriptStore{stored: make(map[string]domain.Transcript)}
|
||||
}
|
||||
|
||||
func (f *fakeTranscriptStore) key(provider, id string) string { return provider + "|" + id }
|
||||
|
||||
func (f *fakeTranscriptStore) GetTranscript(_ context.Context, provider, id string) (domain.Transcript, bool, error) {
|
||||
t, ok := f.stored[f.key(provider, id)]
|
||||
return t, ok, nil
|
||||
}
|
||||
|
||||
func (f *fakeTranscriptStore) SaveTranscript(_ context.Context, provider, id string, t domain.Transcript) error {
|
||||
f.saves++
|
||||
f.stored[f.key(provider, id)] = t
|
||||
return nil
|
||||
}
|
||||
|
||||
type countingSummarizer struct{ calls int }
|
||||
|
||||
func (c *countingSummarizer) Summarize(_ context.Context, v domain.Video, _ domain.Transcript) (domain.Summary, error) {
|
||||
c.calls++
|
||||
return domain.Summary{VideoID: v.ID, UserID: v.UserID, Summary: "s", AIProvider: "local"}, nil
|
||||
}
|
||||
|
||||
type nopSink struct{}
|
||||
|
||||
func (nopSink) Name() string { return "nop" }
|
||||
func (nopSink) Deliver(context.Context, domain.Summary) error { return nil }
|
||||
|
||||
func testVideo() domain.Video {
|
||||
return domain.Video{ID: "v1", UserID: "u1", Provider: domain.ProviderYouTube, ProviderVideoID: "yt1"}
|
||||
}
|
||||
|
||||
func TestProcessNewVideo_StoredTranscriptSkipsFetch(t *testing.T) {
|
||||
src := &recordingSource{}
|
||||
ts := newFakeTranscriptStore()
|
||||
ts.stored[ts.key("youtube", "yt1")] = domain.Transcript{Source: domain.SourceCaptions, Content: "stored words"}
|
||||
sum := &countingSummarizer{}
|
||||
eng := NewEngine(src, sum, nopSink{})
|
||||
eng.Transcripts = ts
|
||||
|
||||
res, err := eng.ProcessNewVideo(context.Background(), testVideo())
|
||||
if err != nil {
|
||||
t.Fatalf("ProcessNewVideo: %v", err)
|
||||
}
|
||||
if src.fetchCalls != 0 {
|
||||
t.Fatalf("stored transcript must not re-fetch from source; got %d fetches", src.fetchCalls)
|
||||
}
|
||||
if ts.saves != 0 {
|
||||
t.Fatalf("a store hit must not re-save; got %d saves", ts.saves)
|
||||
}
|
||||
if sum.calls != 1 || res.Summary == nil {
|
||||
t.Fatalf("expected a summary from the stored transcript; calls=%d summary=%v", sum.calls, res.Summary)
|
||||
}
|
||||
}
|
||||
|
||||
func TestProcessNewVideo_StoreMissFetchesAndPersists(t *testing.T) {
|
||||
src := &recordingSource{transcript: domain.Transcript{Source: domain.SourceCaptions, Language: "en", Content: "fetched words"}}
|
||||
ts := newFakeTranscriptStore()
|
||||
sum := &countingSummarizer{}
|
||||
eng := NewEngine(src, sum, nopSink{})
|
||||
eng.Transcripts = ts
|
||||
|
||||
if _, err := eng.ProcessNewVideo(context.Background(), testVideo()); err != nil {
|
||||
t.Fatalf("ProcessNewVideo: %v", err)
|
||||
}
|
||||
if src.fetchCalls != 1 {
|
||||
t.Fatalf("a store miss must fetch exactly once; got %d", src.fetchCalls)
|
||||
}
|
||||
if ts.saves != 1 {
|
||||
t.Fatalf("a fetched transcript must be persisted; got %d saves", ts.saves)
|
||||
}
|
||||
got, ok, _ := ts.GetTranscript(context.Background(), "youtube", "yt1")
|
||||
if !ok || got.Content != "fetched words" {
|
||||
t.Fatalf("persisted transcript not readable back: ok=%v content=%q", ok, got.Content)
|
||||
}
|
||||
}
|
||||
|
||||
// The second summarize of the same video reads the persisted transcript and does
|
||||
// NOT re-fetch — the primary ADR-021 win, proven end to end at the engine.
|
||||
func TestProcessNewVideo_SecondSummarizeDoesNotRefetch(t *testing.T) {
|
||||
src := &recordingSource{transcript: domain.Transcript{Source: domain.SourceCaptions, Content: "words"}}
|
||||
ts := newFakeTranscriptStore()
|
||||
eng := NewEngine(src, &countingSummarizer{}, nopSink{})
|
||||
eng.Transcripts = ts
|
||||
|
||||
for i := 0; i < 2; i++ {
|
||||
if _, err := eng.ProcessNewVideo(context.Background(), testVideo()); err != nil {
|
||||
t.Fatalf("pass %d: %v", i, err)
|
||||
}
|
||||
}
|
||||
if src.fetchCalls != 1 {
|
||||
t.Fatalf("the second summarize must reuse the stored transcript; got %d fetches", src.fetchCalls)
|
||||
}
|
||||
}
|
||||
|
||||
// A stored "no captions" outcome short-circuits before both fetch and summarize.
|
||||
func TestProcessNewVideo_StoredNoneSkipsFetchAndSummarize(t *testing.T) {
|
||||
src := &recordingSource{}
|
||||
ts := newFakeTranscriptStore()
|
||||
ts.stored[ts.key("youtube", "yt1")] = domain.Transcript{Source: domain.SourceNone}
|
||||
sum := &countingSummarizer{}
|
||||
eng := NewEngine(src, sum, nopSink{})
|
||||
eng.Transcripts = ts
|
||||
|
||||
res, err := eng.ProcessNewVideo(context.Background(), testVideo())
|
||||
if err != nil {
|
||||
t.Fatalf("ProcessNewVideo: %v", err)
|
||||
}
|
||||
if !res.Skipped {
|
||||
t.Fatal("a stored SourceNone must skip")
|
||||
}
|
||||
if src.fetchCalls != 0 || sum.calls != 0 {
|
||||
t.Fatalf("stored none must neither fetch nor summarize; fetches=%d calls=%d", src.fetchCalls, sum.calls)
|
||||
}
|
||||
}
|
||||
|
||||
// A transient 429 is surfaced (so the runner backs off per-user) but never cached
|
||||
// as a shared terminal state — otherwise it would mask a rate-limit as permanent.
|
||||
func TestProcessNewVideo_RateLimitedIsNotPersisted(t *testing.T) {
|
||||
src := &recordingSource{transcript: domain.Transcript{Source: domain.SourceRateLimited}}
|
||||
ts := newFakeTranscriptStore()
|
||||
eng := NewEngine(src, &countingSummarizer{}, nopSink{})
|
||||
eng.Transcripts = ts
|
||||
|
||||
res, err := eng.ProcessNewVideo(context.Background(), testVideo())
|
||||
if err != nil {
|
||||
t.Fatalf("ProcessNewVideo: %v", err)
|
||||
}
|
||||
if !res.Skipped || res.TranscriptSource != string(domain.SourceRateLimited) {
|
||||
t.Fatalf("expected a rate-limited skip; skipped=%v source=%q", res.Skipped, res.TranscriptSource)
|
||||
}
|
||||
if ts.saves != 0 {
|
||||
t.Fatalf("a transient rate-limit must not be persisted; got %d saves", ts.saves)
|
||||
}
|
||||
}
|
||||
|
||||
// With no TranscriptStore wired the engine fetches every time (back-compat).
|
||||
func TestProcessNewVideo_NilStoreFetchesEveryTime(t *testing.T) {
|
||||
src := &recordingSource{transcript: domain.Transcript{Source: domain.SourceCaptions, Content: "words"}}
|
||||
eng := NewEngine(src, &countingSummarizer{}, nopSink{})
|
||||
|
||||
for i := 0; i < 2; i++ {
|
||||
if _, err := eng.ProcessNewVideo(context.Background(), testVideo()); err != nil {
|
||||
t.Fatalf("pass %d: %v", i, err)
|
||||
}
|
||||
}
|
||||
if src.fetchCalls != 2 {
|
||||
t.Fatalf("nil store must fetch every time; got %d", src.fetchCalls)
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user