feat(admin): observability — job history, live now-analyzing, durations & metrics (0.84.0) (#6)

backend/tests/api_admin_crawler.rs

@@ -612,6 +612,265 @@ async fn requeue_all_audit_omits_target_id_but_logs_count(pool: PgPool) {
     assert_eq!(payload["requeued"], 1);
 }
 
+// ---------------------------------------------------------------------------
+// Job history: unified, searchable, filterable list over all states/kinds.
+// ---------------------------------------------------------------------------
+
+/// Seed a chapter-content job in a given state and return its (manga, chapter).
+async fn seed_history_chapter_job(
+    pool: &PgPool,
+    title: &str,
+    number: i32,
+    state: &str,
+) -> (Uuid, Uuid) {
+    let manga_id = Uuid::new_v4();
+    let chapter_id = Uuid::new_v4();
+    sqlx::query("INSERT INTO mangas (id, title) VALUES ($1, $2)")
+        .bind(manga_id)
+        .bind(title)
+        .execute(pool)
+        .await
+        .unwrap();
+    sqlx::query("INSERT INTO chapters (id, manga_id, number) VALUES ($1, $2, $3)")
+        .bind(chapter_id)
+        .bind(manga_id)
+        .bind(number)
+        .execute(pool)
+        .await
+        .unwrap();
+    sqlx::query("INSERT INTO crawler_jobs (id, payload, state) VALUES ($1, $2, $3)")
+        .bind(Uuid::new_v4())
+        .bind(json!({
+            "kind": "sync_chapter_content",
+            "source_id": "target",
+            "chapter_id": chapter_id,
+            "source_chapter_key": "k",
+        }))
+        .bind(state)
+        .execute(pool)
+        .await
+        .unwrap();
+    (manga_id, chapter_id)
+}
+
+/// Seed a `done` analyze_page job pointing at a real page so the history
+/// row resolves manga/chapter/page-number through the page breadcrumb.
+async fn seed_history_analyze_job(pool: &PgPool, title: &str, page_number: i32) {
+    let manga_id = Uuid::new_v4();
+    let chapter_id = Uuid::new_v4();
+    let page_id = Uuid::new_v4();
+    sqlx::query("INSERT INTO mangas (id, title) VALUES ($1, $2)")
+        .bind(manga_id)
+        .bind(title)
+        .execute(pool)
+        .await
+        .unwrap();
+    sqlx::query("INSERT INTO chapters (id, manga_id, number) VALUES ($1, $2, 3)")
+        .bind(chapter_id)
+        .bind(manga_id)
+        .execute(pool)
+        .await
+        .unwrap();
+    sqlx::query(
+        "INSERT INTO pages (id, chapter_id, page_number, storage_key, content_type) \
+         VALUES ($1, $2, $3, 'k', 'image/png')",
+    )
+    .bind(page_id)
+    .bind(chapter_id)
+    .bind(page_number)
+    .execute(pool)
+    .await
+    .unwrap();
+    sqlx::query("INSERT INTO crawler_jobs (id, payload, state) VALUES ($1, $2, 'done')")
+        .bind(Uuid::new_v4())
+        .bind(json!({ "kind": "analyze_page", "page_id": page_id, "force": false }))
+        .execute(pool)
+        .await
+        .unwrap();
+}
+
+#[sqlx::test(migrations = "./migrations")]
+async fn job_history_lists_filters_and_paginates(pool: PgPool) {
+    seed_history_chapter_job(&pool, "Naruto", 1, "done").await;
+    seed_history_chapter_job(&pool, "Bleach", 2, "running").await;
+    seed_dead_job(&pool, "Vinland").await; // dead sync_chapter_content
+    seed_history_analyze_job(&pool, "One Piece", 7).await;
+    let h = harness(pool.clone());
+    let cookie = seed_admin(&pool, &h.app).await;
+
+    // Unfiltered: all four jobs.
+    let resp = h
+        .app
+        .clone()
+        .oneshot(get_with_cookie("/api/v1/admin/crawler/history", &cookie))
+        .await
+        .unwrap();
+    assert_eq!(resp.status(), StatusCode::OK);
+    let body = body_json(resp).await;
+    assert_eq!(body["page"]["total"], 4);
+
+    // Filter by state.
+    let resp = h
+        .app
+        .clone()
+        .oneshot(get_with_cookie(
+            "/api/v1/admin/crawler/history?state=done",
+            &cookie,
+        ))
+        .await
+        .unwrap();
+    let body = body_json(resp).await;
+    // Naruto (sync_chapter done) + One Piece (analyze_page done).
+    assert_eq!(body["page"]["total"], 2);
+
+    // Filter by kind.
+    let resp = h
+        .app
+        .clone()
+        .oneshot(get_with_cookie(
+            "/api/v1/admin/crawler/history?kind=analyze_page",
+            &cookie,
+        ))
+        .await
+        .unwrap();
+    let body = body_json(resp).await;
+    assert_eq!(body["page"]["total"], 1);
+    assert_eq!(body["items"][0]["manga_title"], "One Piece");
+    assert_eq!(body["items"][0]["page_number"], 7);
+    assert_eq!(body["items"][0]["chapter_number"], 3);
+
+    // Search by manga title.
+    let resp = h
+        .app
+        .clone()
+        .oneshot(get_with_cookie(
+            "/api/v1/admin/crawler/history?search=Bleach",
+            &cookie,
+        ))
+        .await
+        .unwrap();
+    let body = body_json(resp).await;
+    assert_eq!(body["page"]["total"], 1);
+    assert_eq!(body["items"][0]["manga_title"], "Bleach");
+    assert_eq!(body["items"][0]["state"], "running");
+
+    // Pagination: limit clamps the page slice but total reflects the full set.
+    let resp = h
+        .app
+        .clone()
+        .oneshot(get_with_cookie(
+            "/api/v1/admin/crawler/history?limit=1",
+            &cookie,
+        ))
+        .await
+        .unwrap();
+    let body = body_json(resp).await;
+    assert_eq!(body["items"].as_array().unwrap().len(), 1);
+    assert_eq!(body["page"]["total"], 4);
+
+    // Admin-gated.
+    let (_u, plain) = register_user(&h.app).await;
+    let resp = h
+        .app
+        .clone()
+        .oneshot(get_with_cookie("/api/v1/admin/crawler/history", &plain))
+        .await
+        .unwrap();
+    assert_eq!(resp.status(), StatusCode::FORBIDDEN);
+}
+
+// ---------------------------------------------------------------------------
+// Operation metrics: durations, averages, recent-ops log.
+// ---------------------------------------------------------------------------
+
+async fn record_metric(
+    pool: &PgPool,
+    op: &str,
+    manga_id: Option<Uuid>,
+    chapter_id: Option<Uuid>,
+    outcome: &str,
+    duration_ms: i64,
+    items: Option<i32>,
+) {
+    mangalord::repo::crawl_metrics::record(
+        pool, op, manga_id, chapter_id, outcome, duration_ms, items, None,
+    )
+    .await
+    .unwrap();
+}
+
+#[sqlx::test(migrations = "./migrations")]
+async fn crawler_metrics_summary_and_ops_over_http(pool: PgPool) {
+    // Two chapter ops (one failed) + a cover op.
+    record_metric(&pool, "chapter", None, None, "ok", 6000, Some(20)).await;
+    record_metric(&pool, "chapter", None, None, "failed", 8000, Some(10)).await;
+    record_metric(&pool, "manga_cover", None, None, "ok", 500, None).await;
+    let h = harness(pool.clone());
+    let cookie = seed_admin(&pool, &h.app).await;
+
+    // Summary: per-type averages + success split.
+    let resp = h
+        .app
+        .clone()
+        .oneshot(get_with_cookie("/api/v1/admin/crawler/metrics", &cookie))
+        .await
+        .unwrap();
+    assert_eq!(resp.status(), StatusCode::OK);
+    let body = body_json(resp).await;
+    let summary = body["summary"].as_array().unwrap();
+    let chapter = summary.iter().find(|s| s["op"] == "chapter").unwrap();
+    assert_eq!(chapter["n"], 2);
+    assert_eq!(chapter["ok"], 1);
+    assert_eq!(chapter["failed"], 1);
+    assert_eq!(chapter["avg_ms"], 7000.0);
+
+    // Recent-ops log + outcome filter.
+    let resp = h
+        .app
+        .clone()
+        .oneshot(get_with_cookie(
+            "/api/v1/admin/crawler/metrics/ops?outcome=failed",
+            &cookie,
+        ))
+        .await
+        .unwrap();
+    let body = body_json(resp).await;
+    assert_eq!(body["page"]["total"], 1);
+    assert_eq!(body["items"][0]["op"], "chapter");
+    assert_eq!(body["items"][0]["outcome"], "failed");
+
+    // Admin-gated.
+    let (_u, plain) = register_user(&h.app).await;
+    let resp = h
+        .app
+        .clone()
+        .oneshot(get_with_cookie("/api/v1/admin/crawler/metrics", &plain))
+        .await
+        .unwrap();
+    assert_eq!(resp.status(), StatusCode::FORBIDDEN);
+}
+
+#[sqlx::test(migrations = "./migrations")]
+async fn job_history_includes_chapter_duration(pool: PgPool) {
+    let (_m, chapter_id) = seed_history_chapter_job(&pool, "Berserk", 12, "done").await;
+    // A chapter metric for that chapter → history row should surface its duration.
+    record_metric(&pool, "chapter", None, Some(chapter_id), "ok", 6100, Some(20)).await;
+    let h = harness(pool.clone());
+    let cookie = seed_admin(&pool, &h.app).await;
+
+    let resp = h
+        .app
+        .clone()
+        .oneshot(get_with_cookie(
+            "/api/v1/admin/crawler/history?kind=sync_chapter_content",
+            &cookie,
+        ))
+        .await
+        .unwrap();
+    let body = body_json(resp).await;
+    assert_eq!(body["items"][0]["duration_ms"], 6100);
+}
+
 #[sqlx::test(migrations = "./migrations")]
 async fn dead_jobs_list_and_requeue_over_http(pool: PgPool) {
     let job_id = seed_dead_job(&pool, "Bleach").await;