feat(discovery): trigger a discovery pass on YouTube connect

A newly connected account showed no videos until the next 2h scheduled pass —
the gap that made onboarding look broken (a second user connected, saw nothing,
read as failure). The connect callback now fires an out-of-band discovery pass
for the connecting user, so videos appear promptly.

Concurrency: scheduled and connect-triggered passes share one lock (serialize),
preserving the single-fetcher invariant (ADR-018). A trigger interleaves between
the scheduler's per-user passes rather than fetching concurrently or waiting for
a whole pass. The trigger runs on the server ctx (survives the redirect) and is
non-blocking for the request goroutine.

Scope: connect-trigger only. The optional login-refresh / "Discover now" button
from #6 are intentionally not built — an unconditional login hook risks 429
storms (per the ticket's own recommendation); defer until wanted.

TDD: TestCallbackTriggersDiscovery, TestSerializeRunsOneAtATime,
TestDiscoveryTriggerEnqueueRunsUser; new BDD scenario mapped.

Refs #6

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-06-09 21:15:46 +02:00
co-authored by Claude Opus 4.8
parent b527db9739
commit ddf719d179
7 changed files with 189 additions and 1 deletions
+44
View File
@@ -0,0 +1,44 @@
package main
import (
"context"
"log/slog"
"sync"
"gitea.d-ma.be/mathias/tapir/internal/runner"
)
// discoveryRunner runs one user's discovery pass.
type discoveryRunner func(ctx context.Context, userID string) (runner.Stats, error)
// serialize wraps run so calls never overlap: every discovery pass — scheduled
// or connect-triggered (#6) — acquires the same lock, preserving the
// one-fetcher-at-a-time invariant the scheduler relies on (ADR-018, the
// single-replica assumption). Locking is per-user, so a connect-triggered pass
// interleaves between the scheduler's users instead of waiting for a whole pass.
func serialize(mu *sync.Mutex, run discoveryRunner) discoveryRunner {
return func(ctx context.Context, userID string) (runner.Stats, error) {
mu.Lock()
defer mu.Unlock()
return run(ctx, userID)
}
}
// discoveryTrigger fires an out-of-band discovery pass for one user without
// blocking the caller (the connect HTTP handler). The pass runs on the server's
// long-lived ctx — not the request ctx — so it survives the post-connect
// redirect. run is the serialized runner, so a trigger never overlaps the
// scheduler. Satisfies web.DiscoveryTrigger.
type discoveryTrigger struct {
ctx context.Context
run discoveryRunner
log *slog.Logger
}
func (t *discoveryTrigger) Enqueue(userID string) {
go func() {
if _, err := t.run(t.ctx, userID); err != nil {
t.log.Warn("discovery: connect-triggered pass had errors", "user", userID, "err", err)
}
}()
}
+62
View File
@@ -0,0 +1,62 @@
package main
import (
"context"
"fmt"
"sync"
"sync/atomic"
"testing"
"time"
"github.com/stretchr/testify/require"
"gitea.d-ma.be/mathias/tapir/internal/runner"
)
// serialize must guarantee at most one discovery pass runs at a time, so a
// connect-triggered pass never fetches concurrently with the scheduler.
func TestSerializeRunsOneAtATime(t *testing.T) {
var active, maxActive int32
run := func(_ context.Context, _ string) (runner.Stats, error) {
n := atomic.AddInt32(&active, 1)
for { // record the high-water mark of concurrent runs
m := atomic.LoadInt32(&maxActive)
if n <= m || atomic.CompareAndSwapInt32(&maxActive, m, n) {
break
}
}
time.Sleep(2 * time.Millisecond)
atomic.AddInt32(&active, -1)
return runner.Stats{}, nil
}
s := serialize(&sync.Mutex{}, run)
var wg sync.WaitGroup
for i := 0; i < 20; i++ {
wg.Add(1)
go func(i int) { defer wg.Done(); _, _ = s(context.Background(), fmt.Sprintf("u%d", i)) }(i)
}
wg.Wait()
require.Equal(t, int32(1), atomic.LoadInt32(&maxActive),
"serialize must run at most one pass at a time")
}
// Enqueue runs the user's pass out-of-band (non-blocking) on the trigger's ctx.
func TestDiscoveryTriggerEnqueueRunsUser(t *testing.T) {
done := make(chan string, 1)
run := func(_ context.Context, userID string) (runner.Stats, error) {
done <- userID
return runner.Stats{}, nil
}
tr := &discoveryTrigger{ctx: context.Background(), run: run, log: quietLog()}
tr.Enqueue("u1")
select {
case got := <-done:
require.Equal(t, "u1", got)
case <-time.After(2 * time.Second):
t.Fatal("Enqueue did not run the user's pass")
}
}
+9 -1
View File
@@ -20,6 +20,7 @@ import (
"net/http"
"os"
"os/signal"
"sync"
"time"
"gitea.d-ma.be/mathias/tapir/internal/adapters/secrets"
@@ -238,13 +239,20 @@ func cmdServe(ctx context.Context, log *slog.Logger) error {
if cfg.DiscoveryInterval > 0 {
log.Info("scheduled discovery enabled", "interval", cfg.DiscoveryInterval, "fetch_rate", cfg.FetchRate)
log.Warn("scheduled discovery assumes a SINGLE replica — running serve at >1 replica double-runs discovery (ADR-018)")
runUser := func(ctx context.Context, userID string) (runner.Stats, error) {
rawRunUser := func(ctx context.Context, userID string) (runner.Stats, error) {
r, err := buildUserRunner(cfg, st, secretStore, userID, log)
if err != nil {
return runner.Stats{}, err
}
return r.RunOnce(ctx)
}
// One lock shared by the scheduler and connect-triggered passes (#6) so
// they never fetch concurrently — the single-fetcher invariant (ADR-018).
runUser := serialize(&sync.Mutex{}, rawRunUser)
if app.Connect != nil {
app.Connect.Discovery = &discoveryTrigger{ctx: ctx, run: runUser, log: log}
log.Info("connect-triggered discovery enabled")
}
go runScheduler(ctx, cfg.DiscoveryInterval, st, runUser, log)
} else {
log.Info("scheduled discovery disabled (TAPIR_DISCOVERY_INTERVAL unset or 0)")
+6
View File
@@ -18,6 +18,12 @@ Feature: Connect and manage video accounts
Then the connection is stored with status "active"
And my subscriptions are synced
Scenario: Connecting an account discovers videos immediately
Given I have no connected video accounts
When I connect my YouTube account
Then a discovery pass for my account is triggered right away
And I do not have to wait for the next scheduled pass to see my videos
Scenario: Tokens are never stored in the clear
When I connect any video account
Then no OAuth token value is stored in the database
+19
View File
@@ -23,6 +23,15 @@ type Connections interface {
UpsertConnection(ctx context.Context, userID string, c store.Connection) error
}
// DiscoveryTrigger requests an out-of-band discovery pass for a user. The connect
// flow fires it the moment a YouTube account is linked so videos appear promptly
// instead of waiting for the next scheduled pass (#6). Enqueue must be
// non-blocking and safe to call from the request goroutine; the implementation
// owns serialization with the scheduler (one pass at a time). nil = no trigger.
type DiscoveryTrigger interface {
Enqueue(userID string)
}
// connectStateTTL bounds how long a generated CSRF state is valid between the
// connect redirect and the provider callback.
const connectStateTTL = 10 * time.Minute
@@ -43,6 +52,10 @@ type ConnectHandler struct {
Conns Connections
Log *slog.Logger
// Discovery, when set, is fired after a successful connect so the new
// connection's videos are discovered immediately (#6). Optional.
Discovery DiscoveryTrigger
states *connectStateStore
now func() time.Time
}
@@ -134,6 +147,12 @@ func (h *ConnectHandler) handleCallback(w http.ResponseWriter, r *http.Request)
return
}
// Discover this user's videos now rather than waiting for the next scheduled
// pass (#6). Non-blocking; the trigger serializes with the scheduler.
if h.Discovery != nil {
h.Discovery.Enqueue(userID)
}
setFlash(w, flashConnected)
http.Redirect(w, r, "/", http.StatusSeeOther)
}
+48
View File
@@ -45,6 +45,24 @@ func (c *fakeConns) UpsertConnection(_ context.Context, userID string, conn stor
return nil
}
// fakeTrigger records Enqueue calls so a test can assert connect fired discovery.
type fakeTrigger struct {
mu sync.Mutex
users []string
}
func (f *fakeTrigger) Enqueue(userID string) {
f.mu.Lock()
defer f.mu.Unlock()
f.users = append(f.users, userID)
}
func (f *fakeTrigger) seen() []string {
f.mu.Lock()
defer f.mu.Unlock()
return append([]string(nil), f.users...)
}
// tokenServer fakes Google's token endpoint, returning body for any POST.
func tokenServer(t *testing.T, body string) *httptest.Server {
t.Helper()
@@ -126,6 +144,36 @@ func TestCallbackExchangesAndRecordsConnection(t *testing.T) {
require.Equal(t, wantRef, conns.conn.TokenRef)
}
func TestCallbackTriggersDiscovery(t *testing.T) {
srv := tokenServer(t,
`{"access_token":"at","refresh_token":"rt-secret","token_type":"Bearer","expires_in":3600}`)
app := newConnectApp(t, srv.URL, &fakeWriter{}, &fakeConns{})
trig := &fakeTrigger{}
app.Connect.Discovery = trig
state := connectState(t, app)
rec := do(t, app, httptest.NewRequest(http.MethodGet,
"/oauth/youtube/callback?state="+state+"&code=the-code", nil))
require.Equal(t, http.StatusSeeOther, rec.Code)
require.Equal(t, []string{userID}, trig.seen(),
"a successful connect must trigger discovery for the connecting user")
}
func TestCallbackNoDiscoveryOnFailedConnect(t *testing.T) {
srv := tokenServer(t,
`{"access_token":"at","refresh_token":"rt","token_type":"Bearer","expires_in":3600}`)
app := newConnectApp(t, srv.URL, &fakeWriter{}, &fakeConns{})
trig := &fakeTrigger{}
app.Connect.Discovery = trig
// No state → CSRF reject → nothing connected, so no discovery.
rec := do(t, app, httptest.NewRequest(http.MethodGet,
"/oauth/youtube/callback?code=the-code", nil))
require.Equal(t, http.StatusBadRequest, rec.Code)
require.Empty(t, trig.seen(), "a failed connect must not trigger discovery")
}
func TestCallbackRejectsMissingState(t *testing.T) {
srv := tokenServer(t,
`{"access_token":"at","refresh_token":"rt","token_type":"Bearer","expires_in":3600}`)
@@ -38,6 +38,7 @@ var scenarioCoverage = map[string]string{
// connect_account.feature
"Connect a YouTube account": "TestCallbackExchangesAndRecordsConnection",
"Connecting an account discovers videos immediately": "TestCallbackTriggersDiscovery",
"Tokens are never stored in the clear": "TestCallbackExchangesAndRecordsConnection",
"Revoking a connection stops watching but keeps history": "TestDisconnectRemovesTokenAndConnectionKeepsAccount",