feat(runner): end-to-end run loop with durable dedup
RunOnce walks the user's subscriptions, upserts each candidate video (assigning its durable store id), skips videos already summarized via the store's SeenVideoIDs (cross-restart dedup the engine's in-memory map can't provide), and processes the rest through the engine. Loop adds an optional poll cadence; per-item errors are collected, not fatal. Tested with fakes — no live deps. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -0,0 +1,161 @@
|
||||
package runner_test
|
||||
|
||||
import (
|
||||
"context"
|
||||
"io"
|
||||
"log/slog"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/require"
|
||||
|
||||
"gitea.d-ma.be/mathias/tapir/internal/domain"
|
||||
"gitea.d-ma.be/mathias/tapir/internal/runner"
|
||||
"gitea.d-ma.be/mathias/tapir/internal/usecase"
|
||||
)
|
||||
|
||||
const testUser = "11111111-1111-1111-1111-111111111111"
|
||||
|
||||
// --- fakes -----------------------------------------------------------------
|
||||
|
||||
type fakeSource struct {
|
||||
subs []domain.Subscription
|
||||
videos map[string][]domain.Video // keyed by channel id
|
||||
transcripts map[string]domain.Transcript
|
||||
}
|
||||
|
||||
func (f *fakeSource) ListSubscriptions(_ context.Context, _ string) ([]domain.Subscription, error) {
|
||||
return f.subs, nil
|
||||
}
|
||||
|
||||
func (f *fakeSource) NewVideos(_ context.Context, sub domain.Subscription) ([]domain.Video, error) {
|
||||
return f.videos[sub.ChannelID], nil
|
||||
}
|
||||
|
||||
func (f *fakeSource) FetchTranscript(_ context.Context, v domain.Video) (domain.Transcript, error) {
|
||||
if t, ok := f.transcripts[v.ProviderVideoID]; ok {
|
||||
return t, nil
|
||||
}
|
||||
return domain.Transcript{VideoID: v.ID, UserID: v.UserID, Source: domain.SourceCaptions, Content: "default transcript text"}, nil
|
||||
}
|
||||
|
||||
// fakeStore assigns deterministic ids ("id-"+provider video id) so a pre-seeded
|
||||
// seen set lines up with UpsertVideo output, modelling cross-restart dedup.
|
||||
type fakeStore struct {
|
||||
seen map[string]bool
|
||||
upserted []domain.Video
|
||||
}
|
||||
|
||||
func (f *fakeStore) UpsertVideo(_ context.Context, v domain.Video) (string, error) {
|
||||
f.upserted = append(f.upserted, v)
|
||||
return "id-" + v.ProviderVideoID, nil
|
||||
}
|
||||
|
||||
func (f *fakeStore) SeenVideoIDs(_ context.Context, _ string) (map[string]bool, error) {
|
||||
cp := make(map[string]bool, len(f.seen))
|
||||
for k, v := range f.seen {
|
||||
cp[k] = v
|
||||
}
|
||||
return cp, nil
|
||||
}
|
||||
|
||||
type fakeSummarizer struct{}
|
||||
|
||||
func (fakeSummarizer) Summarize(_ context.Context, v domain.Video, _ domain.Transcript) (domain.Summary, error) {
|
||||
return domain.Summary{UserID: v.UserID, VideoID: v.ID, Summary: "s", AIProvider: "local", AIModel: "koala/phi4-mini"}, nil
|
||||
}
|
||||
|
||||
type recordingSink struct{ delivered []domain.Summary }
|
||||
|
||||
func (s *recordingSink) Name() string { return "store" }
|
||||
func (s *recordingSink) Deliver(_ context.Context, sum domain.Summary) error {
|
||||
s.delivered = append(s.delivered, sum)
|
||||
return nil
|
||||
}
|
||||
|
||||
func sub(channelID, title string) domain.Subscription {
|
||||
return domain.Subscription{UserID: testUser, ChannelID: channelID, ChannelTitle: title, Active: true}
|
||||
}
|
||||
|
||||
func vid(provID, title string) domain.Video {
|
||||
return domain.Video{UserID: testUser, Provider: domain.ProviderYouTube, ProviderVideoID: provID, Title: title}
|
||||
}
|
||||
|
||||
func quietLogger() *slog.Logger {
|
||||
return slog.New(slog.NewTextHandler(io.Discard, nil))
|
||||
}
|
||||
|
||||
// --- tests -----------------------------------------------------------------
|
||||
|
||||
func TestRunOnce_SummarizesNewVideos(t *testing.T) {
|
||||
src := &fakeSource{
|
||||
subs: []domain.Subscription{sub("chan1", "Channel One")},
|
||||
videos: map[string][]domain.Video{"chan1": {vid("v1", "Video 1"), vid("v2", "Video 2")}},
|
||||
}
|
||||
st := &fakeStore{seen: map[string]bool{}}
|
||||
sink := &recordingSink{}
|
||||
eng := usecase.NewEngine(src, fakeSummarizer{}, sink)
|
||||
r := runner.New(src, st, eng, testUser, quietLogger())
|
||||
|
||||
stats, err := r.RunOnce(context.Background())
|
||||
require.NoError(t, err)
|
||||
require.Equal(t, 2, stats.Candidates)
|
||||
require.Equal(t, 2, stats.Summarized)
|
||||
require.Equal(t, 0, stats.SkippedSeen)
|
||||
require.Len(t, sink.delivered, 2)
|
||||
|
||||
// Each delivered summary must carry the durable store id as its video id.
|
||||
require.Equal(t, "id-v1", sink.delivered[0].VideoID)
|
||||
require.Equal(t, "id-v2", sink.delivered[1].VideoID)
|
||||
}
|
||||
|
||||
func TestRunOnce_SkipsAlreadySummarized(t *testing.T) {
|
||||
src := &fakeSource{
|
||||
subs: []domain.Subscription{sub("chan1", "Channel One")},
|
||||
videos: map[string][]domain.Video{"chan1": {vid("v1", "Video 1"), vid("v2", "Video 2")}},
|
||||
}
|
||||
// v1 was summarized in a prior run (durable seen set).
|
||||
st := &fakeStore{seen: map[string]bool{"id-v1": true}}
|
||||
sink := &recordingSink{}
|
||||
eng := usecase.NewEngine(src, fakeSummarizer{}, sink)
|
||||
r := runner.New(src, st, eng, testUser, quietLogger())
|
||||
|
||||
stats, err := r.RunOnce(context.Background())
|
||||
require.NoError(t, err)
|
||||
require.Equal(t, 1, stats.SkippedSeen)
|
||||
require.Equal(t, 1, stats.Summarized)
|
||||
require.Len(t, sink.delivered, 1)
|
||||
require.Equal(t, "id-v2", sink.delivered[0].VideoID, "only the unseen video is summarized")
|
||||
}
|
||||
|
||||
func TestRunOnce_SkipsVideosWithoutTranscript(t *testing.T) {
|
||||
src := &fakeSource{
|
||||
subs: []domain.Subscription{sub("chan1", "Channel One")},
|
||||
videos: map[string][]domain.Video{"chan1": {vid("v1", "Video 1")}},
|
||||
transcripts: map[string]domain.Transcript{"v1": {Source: domain.SourceNone}},
|
||||
}
|
||||
st := &fakeStore{seen: map[string]bool{}}
|
||||
sink := &recordingSink{}
|
||||
eng := usecase.NewEngine(src, fakeSummarizer{}, sink)
|
||||
r := runner.New(src, st, eng, testUser, quietLogger())
|
||||
|
||||
stats, err := r.RunOnce(context.Background())
|
||||
require.NoError(t, err)
|
||||
require.Equal(t, 1, stats.SkippedNoText)
|
||||
require.Equal(t, 0, stats.Summarized)
|
||||
require.Empty(t, sink.delivered, "no summary delivered when there is no transcript")
|
||||
}
|
||||
|
||||
func TestRunOnce_UpsertsEveryCandidate(t *testing.T) {
|
||||
src := &fakeSource{
|
||||
subs: []domain.Subscription{sub("chan1", "Channel One")},
|
||||
videos: map[string][]domain.Video{"chan1": {vid("v1", "Video 1"), vid("v2", "Video 2")}},
|
||||
}
|
||||
// Even an already-seen video gets upserted so its metadata stays fresh.
|
||||
st := &fakeStore{seen: map[string]bool{"id-v1": true}}
|
||||
eng := usecase.NewEngine(src, fakeSummarizer{}, &recordingSink{})
|
||||
r := runner.New(src, st, eng, testUser, quietLogger())
|
||||
|
||||
_, err := r.RunOnce(context.Background())
|
||||
require.NoError(t, err)
|
||||
require.Len(t, st.upserted, 2, "every candidate is upserted, including seen ones")
|
||||
}
|
||||
Reference in New Issue
Block a user