Files
Mangalord/backend/tests/api_admin_crawler.rs
MechaCat02 dd25f073cd fix(admin-security): SSRF defence + CSRF fail-closed + analysis .no_proxy() (0.87.2)
Four high/medium findings from the audit, plus their tests:

1. **SSRF on admin-editable URLs.** `CrawlerSettings::start_url` and
   `AnalysisSettings::endpoint` validated only with `Url::parse`. A
   hostile or CSRF-able admin could repoint at `169.254.169.254`
   (cloud metadata), `127.0.0.1:5432` (postgres), or any RFC1918 host
   — and the vision worker bearer-attaches an env-managed API key to
   every call. Extract `ensure_public_target` from `safety::is_safe_url`
   (allowlist-free public-host check: scheme + private-IP literal +
   localhost) and wire it into both fields. Docker DNS names
   (`mangalord-vision`) keep passing because they're hostnames, not
   IP literals. The analysis check is gated on `enabled=true` so the
   dev-default `localhost:8000` stays usable until the worker is
   actually turned on (toggling enabled=true later re-runs the gate).

2. **Admin CSRF fail-open default.** `ADMIN_ALLOWED_ORIGINS=` empty
   silently skipped the entire CSRF check, so an operator forgetting
   the env var shipped an unguarded admin surface. Cookie-auth POSTs
   now fail-closed when the allowlist is empty AND when neither
   `Origin` nor `Referer` accompanies the request. Two carve-outs:
   `Authorization: Bearer …` callers bypass (bots can't be CSRF'd),
   and requests with NO session cookie at all bypass to let the auth
   extractor return a clean 401 instead of a confusing 403.

3. **Analysis HTTP clients didn't `.no_proxy()`.** The crawler client
   already did. Ambient `HTTP_PROXY`/`HTTPS_PROXY` in container env
   would exfiltrate page-image bytes + the bearer key through an
   upstream proxy. Same for the readiness probe.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-06-22 21:04:50 +02:00

964 lines
31 KiB
Rust

//! Integration tests for the admin crawler observability/control API.
//!
//! The default test harness wires `AppState.crawler = None` (no daemon),
//! so the *control* endpoints return 503 and the *read* endpoints that
//! work off the DB (status shell, dead-jobs list/requeue) still function.
//! This is exactly the production "daemon disabled" posture.
mod common;
use std::time::Duration;
use axum::http::StatusCode;
use axum::Router;
use http_body_util::BodyExt;
use serde_json::json;
use sqlx::PgPool;
use tower::ServiceExt;
use uuid::Uuid;
use common::{
body_json, get, get_with_cookie, harness, harness_with_admin_origins,
post_json_with_cookie, post_json_with_cookie_origin, register_user,
};
async fn seed_admin(pool: &PgPool, app: &Router) -> String {
let (username, cookie) = register_user(app).await;
let u = mangalord::repo::user::find_by_username(pool, &username)
.await
.unwrap()
.unwrap();
mangalord::repo::user::set_is_admin_unchecked(pool, u.id, true)
.await
.unwrap();
cookie
}
async fn seed_dead_job(pool: &PgPool, title: &str) -> 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, 1)")
.bind(chapter_id)
.bind(manga_id)
.execute(pool)
.await
.unwrap();
let job_id = Uuid::new_v4();
sqlx::query(
"INSERT INTO crawler_jobs (id, payload, state, attempts, last_error) \
VALUES ($1, $2, 'dead', 5, 'boom')",
)
.bind(job_id)
.bind(json!({
"kind": "sync_chapter_content",
"source_id": "target",
"chapter_id": chapter_id,
"source_chapter_key": "k",
}))
.execute(pool)
.await
.unwrap();
job_id
}
/// Seed a chapter-content job in a given state ('pending'/'running').
async fn seed_job(pool: &PgPool, title: &str, state: &str) {
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, 1)")
.bind(chapter_id)
.bind(manga_id)
.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();
}
/// Seed a manga with no cover + a live source row (queued for cover fetch).
async fn seed_missing_cover(pool: &PgPool, title: &str) {
let manga_id = Uuid::new_v4();
sqlx::query("INSERT INTO mangas (id, title, cover_image_path) VALUES ($1, $2, NULL)")
.bind(manga_id)
.bind(title)
.execute(pool)
.await
.unwrap();
sqlx::query("INSERT INTO sources (id, name, base_url) VALUES ('target','T','http://x') ON CONFLICT DO NOTHING")
.execute(pool)
.await
.unwrap();
sqlx::query(
"INSERT INTO manga_sources (source_id, source_manga_key, manga_id, source_url) \
VALUES ('target', $1, $2, 'http://x/m')",
)
.bind(format!("k-{manga_id}"))
.bind(manga_id)
.execute(pool)
.await
.unwrap();
}
#[sqlx::test(migrations = "./migrations")]
async fn active_jobs_and_covers_lists_over_http(pool: PgPool) {
seed_job(&pool, "Naruto", "pending").await;
seed_job(&pool, "Bleach", "running").await;
seed_missing_cover(&pool, "One Piece").await;
let h = harness(pool.clone());
let cookie = seed_admin(&pool, &h.app).await;
// Queued/active chapters.
let resp = h
.app
.clone()
.oneshot(get_with_cookie("/api/v1/admin/crawler/active-jobs", &cookie))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::OK);
let body = body_json(resp).await;
assert_eq!(body["page"]["total"], 2);
// Queued covers.
let resp = h
.app
.clone()
.oneshot(get_with_cookie("/api/v1/admin/crawler/covers", &cookie))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::OK);
let body = body_json(resp).await;
assert_eq!(body["page"]["total"], 1);
assert_eq!(body["items"][0]["manga_title"], "One Piece");
// Both are admin-gated.
let (_u, plain) = register_user(&h.app).await;
let resp = h
.app
.clone()
.oneshot(get_with_cookie("/api/v1/admin/crawler/active-jobs", &plain))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::FORBIDDEN);
}
#[sqlx::test(migrations = "./migrations")]
async fn get_status_requires_admin(pool: PgPool) {
let h = harness(pool);
// Unauthenticated → 401.
let resp = h.app.clone().oneshot(get("/api/v1/admin/crawler")).await.unwrap();
assert_eq!(resp.status(), StatusCode::UNAUTHORIZED);
// Authenticated non-admin → 403.
let (_u, cookie) = register_user(&h.app).await;
let resp = h
.app
.clone()
.oneshot(get_with_cookie("/api/v1/admin/crawler", &cookie))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::FORBIDDEN);
}
#[sqlx::test(migrations = "./migrations")]
async fn get_status_reports_disabled_daemon_with_queue_counts(pool: PgPool) {
seed_dead_job(&pool, "Naruto").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", &cookie))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::OK);
let body = body_json(resp).await;
assert_eq!(body["daemon"], "disabled");
assert_eq!(body["queue"]["dead"], 1);
assert_eq!(body["browser"], "down");
}
#[sqlx::test(migrations = "./migrations")]
async fn control_endpoints_return_503_when_daemon_disabled(pool: PgPool) {
let h = harness(pool.clone());
let cookie = seed_admin(&pool, &h.app).await;
for uri in [
"/api/v1/admin/crawler/run",
"/api/v1/admin/crawler/reconcile",
"/api/v1/admin/crawler/browser/restart",
"/api/v1/admin/crawler/session/clear-expired",
] {
let resp = h
.app
.clone()
.oneshot(post_json_with_cookie(uri, json!({}), &cookie))
.await
.unwrap();
assert_eq!(
resp.status(),
StatusCode::SERVICE_UNAVAILABLE,
"{uri} should be 503 when daemon disabled"
);
}
}
#[sqlx::test(migrations = "./migrations")]
async fn status_stream_requires_admin(pool: PgPool) {
let h = harness(pool);
// Unauthenticated → 401.
let resp = h
.app
.clone()
.oneshot(get("/api/v1/admin/crawler/stream"))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::UNAUTHORIZED);
// Non-admin → 403.
let (_u, cookie) = register_user(&h.app).await;
let resp = h
.app
.clone()
.oneshot(get_with_cookie("/api/v1/admin/crawler/stream", &cookie))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::FORBIDDEN);
}
#[sqlx::test(migrations = "./migrations")]
async fn status_stream_emits_initial_event(pool: PgPool) {
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/stream", &cookie))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::OK);
let ct = resp
.headers()
.get(axum::http::header::CONTENT_TYPE)
.and_then(|v| v.to_str().ok())
.unwrap_or_default()
.to_string();
assert!(ct.starts_with("text/event-stream"), "content-type was {ct:?}");
// Accumulate frames (the immediate snapshot may arrive split across
// frames) until the status payload appears, with an overall timeout so
// the never-ending stream can't hang the test.
let mut body = resp.into_body();
let mut acc = String::new();
let deadline = tokio::time::timeout(Duration::from_secs(5), async {
loop {
let Some(frame) = body.frame().await else { break };
if let Ok(data) = frame.expect("frame ok").into_data() {
acc.push_str(&String::from_utf8_lossy(&data));
if acc.contains("\"daemon\"") {
break;
}
}
}
})
.await;
assert!(deadline.is_ok(), "did not receive status within 5s; got: {acc:?}");
assert!(acc.contains("\"daemon\""), "missing status payload: {acc}");
assert!(acc.contains("status"), "missing SSE event name: {acc}");
}
#[sqlx::test(migrations = "./migrations")]
async fn mutating_endpoints_reject_non_admin(pool: PgPool) {
let h = harness(pool);
// A logged-in non-admin must be forbidden from a mutating endpoint.
let (_u, cookie) = register_user(&h.app).await;
let resp = h
.app
.clone()
.oneshot(post_json_with_cookie(
"/api/v1/admin/crawler/dead-jobs/requeue",
json!({ "scope": "all" }),
&cookie,
))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::FORBIDDEN);
}
// ---------------------------------------------------------------------------
// CSRF Origin/Referer allowlist (T2)
// ---------------------------------------------------------------------------
#[sqlx::test(migrations = "./migrations")]
async fn csrf_rejects_mutation_with_cross_origin_header(pool: PgPool) {
let h = harness_with_admin_origins(
pool.clone(),
vec!["http://localhost:3000".to_string()],
);
let cookie = seed_admin(&pool, &h.app).await;
let resp = h
.app
.clone()
.oneshot(post_json_with_cookie_origin(
"/api/v1/admin/crawler/session/clear-expired",
json!({}),
&cookie,
Some("https://evil.example.com"),
None,
))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::FORBIDDEN);
}
#[sqlx::test(migrations = "./migrations")]
async fn csrf_allows_mutation_with_allowed_origin(pool: PgPool) {
let h = harness_with_admin_origins(
pool.clone(),
vec!["http://localhost:3000".to_string()],
);
let cookie = seed_admin(&pool, &h.app).await;
let resp = h
.app
.clone()
.oneshot(post_json_with_cookie_origin(
"/api/v1/admin/crawler/session/clear-expired",
json!({}),
&cookie,
Some("http://localhost:3000"),
None,
))
.await
.unwrap();
// Daemon disabled in the harness → 503 from the handler; the CSRF
// gate must have let the request through before that response.
assert_eq!(resp.status(), StatusCode::SERVICE_UNAVAILABLE);
}
#[sqlx::test(migrations = "./migrations")]
async fn csrf_rejects_cookie_auth_without_origin_or_referer(pool: PgPool) {
// Cookie-auth + neither Origin nor Referer was previously waved through
// ("curl bypass"). It's now refused: an extension or no-referrer-policy
// page can produce exactly this shape and would otherwise be a CSRF
// vector. Real curl/script callers should authenticate with a bearer
// token instead — see `csrf_allows_bearer_token_without_origin`.
let h = harness_with_admin_origins(
pool.clone(),
vec!["http://localhost:3000".to_string()],
);
let cookie = seed_admin(&pool, &h.app).await;
// `post_json_with_cookie_origin(..., None, None)` builds the exact "no
// Origin, no Referer" cookie-auth shape this test pins.
let resp = h
.app
.clone()
.oneshot(post_json_with_cookie_origin(
"/api/v1/admin/crawler/session/clear-expired",
json!({}),
&cookie,
None,
None,
))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::FORBIDDEN);
}
#[sqlx::test(migrations = "./migrations")]
async fn csrf_falls_back_to_referer_when_origin_missing(pool: PgPool) {
let h = harness_with_admin_origins(
pool.clone(),
vec!["http://localhost:3000".to_string()],
);
let cookie = seed_admin(&pool, &h.app).await;
let resp = h
.app
.clone()
.oneshot(post_json_with_cookie_origin(
"/api/v1/admin/crawler/session/clear-expired",
json!({}),
&cookie,
None,
Some("http://localhost:3000/admin/crawler"),
))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::SERVICE_UNAVAILABLE);
}
#[sqlx::test(migrations = "./migrations")]
async fn csrf_skipped_on_safe_methods(pool: PgPool) {
let h = harness_with_admin_origins(
pool.clone(),
vec!["http://localhost:3000".to_string()],
);
let cookie = seed_admin(&pool, &h.app).await;
// GET from a hostile origin is fine — browsers can't mutate via GET.
let resp = h
.app
.clone()
.oneshot(common::get_with_cookie_origin(
"/api/v1/admin/crawler",
&cookie,
Some("https://evil.example.com"),
))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::OK);
}
#[sqlx::test(migrations = "./migrations")]
async fn csrf_rejects_cookie_auth_when_allowlist_empty(pool: PgPool) {
// Previously an empty allowlist silently skipped the CSRF check, so an
// operator who forgot to set ADMIN_ALLOWED_ORIGINS shipped an unguarded
// admin surface. We now fail-closed for cookie-auth admin mutations
// when the allowlist is empty — operators must either set the env var
// (browser deploy) or authenticate with `Authorization: Bearer …`.
let h = harness_with_admin_origins(pool.clone(), vec![]);
let cookie = seed_admin(&pool, &h.app).await;
let resp = h
.app
.clone()
.oneshot(post_json_with_cookie_origin(
"/api/v1/admin/crawler/session/clear-expired",
json!({}),
&cookie,
Some("https://evil.example.com"),
None,
))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::FORBIDDEN);
}
// ---------------------------------------------------------------------------
// Cache-Control: no-store on admin responses (S3)
// ---------------------------------------------------------------------------
#[sqlx::test(migrations = "./migrations")]
async fn admin_responses_have_no_store(pool: PgPool) {
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", &cookie))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::OK);
let cc = resp
.headers()
.get(axum::http::header::CACHE_CONTROL)
.and_then(|v| v.to_str().ok())
.unwrap_or_default()
.to_string();
assert!(
cc.contains("no-store"),
"admin response missing Cache-Control: no-store (got {cc:?})"
);
}
#[sqlx::test(migrations = "./migrations")]
async fn non_admin_responses_unaffected_by_no_store(pool: PgPool) {
let h = harness(pool);
let resp = h
.app
.clone()
.oneshot(get("/api/v1/health"))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::OK);
let cc = resp
.headers()
.get(axum::http::header::CACHE_CONTROL)
.and_then(|v| v.to_str().ok());
assert!(
cc.is_none() || !cc.unwrap_or_default().contains("no-store"),
"non-admin response should not get no-store (got {cc:?})"
);
}
// ---------------------------------------------------------------------------
// scope=all confirm:true guard (S1)
// ---------------------------------------------------------------------------
#[sqlx::test(migrations = "./migrations")]
async fn requeue_all_without_confirm_rejected(pool: PgPool) {
seed_dead_job(&pool, "X").await;
let h = harness(pool.clone());
let cookie = seed_admin(&pool, &h.app).await;
let resp = h
.app
.clone()
.oneshot(post_json_with_cookie(
"/api/v1/admin/crawler/dead-jobs/requeue",
json!({ "scope": "all" }),
&cookie,
))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::BAD_REQUEST);
// The dead row must NOT have been touched.
let state: String = sqlx::query_scalar("SELECT state FROM crawler_jobs LIMIT 1")
.fetch_one(&pool)
.await
.unwrap();
assert_eq!(state, "dead");
}
#[sqlx::test(migrations = "./migrations")]
async fn requeue_all_with_confirm_flips_dead_pile(pool: PgPool) {
seed_dead_job(&pool, "X").await;
seed_dead_job(&pool, "Y").await;
let h = harness(pool.clone());
let cookie = seed_admin(&pool, &h.app).await;
let resp = h
.app
.clone()
.oneshot(post_json_with_cookie(
"/api/v1/admin/crawler/dead-jobs/requeue",
json!({ "scope": "all", "confirm": true }),
&cookie,
))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::OK);
let pending: i64 = sqlx::query_scalar(
"SELECT COUNT(*) FROM crawler_jobs WHERE state = 'pending'",
)
.fetch_one(&pool)
.await
.unwrap();
assert_eq!(pending, 2);
}
// ---------------------------------------------------------------------------
// admin_audit target_id + PHPSESSID fingerprint (S2)
// ---------------------------------------------------------------------------
#[sqlx::test(migrations = "./migrations")]
async fn requeue_chapter_audit_records_chapter_target_id(pool: PgPool) {
let job_id = seed_dead_job(&pool, "Bleach").await;
let chapter_id: Uuid = sqlx::query_scalar(
"SELECT (payload->>'chapter_id')::uuid FROM crawler_jobs WHERE id = $1",
)
.bind(job_id)
.fetch_one(&pool)
.await
.unwrap();
let h = harness(pool.clone());
let cookie = seed_admin(&pool, &h.app).await;
let resp = h
.app
.clone()
.oneshot(post_json_with_cookie(
"/api/v1/admin/crawler/dead-jobs/requeue",
json!({ "scope": "chapter", "chapter_id": chapter_id }),
&cookie,
))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::OK);
let (target_kind, target_id): (String, Option<Uuid>) = sqlx::query_as(
"SELECT target_kind, target_id FROM admin_audit \
WHERE action = 'crawler_dead_jobs_requeue' \
ORDER BY at DESC LIMIT 1",
)
.fetch_one(&pool)
.await
.unwrap();
assert_eq!(target_kind, "chapter");
assert_eq!(target_id, Some(chapter_id));
}
#[sqlx::test(migrations = "./migrations")]
async fn requeue_all_audit_omits_target_id_but_logs_count(pool: PgPool) {
seed_dead_job(&pool, "X").await;
let h = harness(pool.clone());
let cookie = seed_admin(&pool, &h.app).await;
let _ = h
.app
.clone()
.oneshot(post_json_with_cookie(
"/api/v1/admin/crawler/dead-jobs/requeue",
json!({ "scope": "all", "confirm": true }),
&cookie,
))
.await
.unwrap();
let (target_kind, target_id, payload): (String, Option<Uuid>, serde_json::Value) =
sqlx::query_as(
"SELECT target_kind, target_id, payload FROM admin_audit \
WHERE action = 'crawler_dead_jobs_requeue' \
ORDER BY at DESC LIMIT 1",
)
.fetch_one(&pool)
.await
.unwrap();
assert_eq!(target_kind, "crawler");
assert_eq!(target_id, None);
assert_eq!(payload["scope"], "all");
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);
}
#[sqlx::test(migrations = "./migrations")]
async fn job_history_surfaces_sync_manga_payload_title(pool: PgPool) {
// A reconcile-enqueued sync_manga job that died has no manga row, so the
// history row must fall back to the payload title/url and be searchable.
sqlx::query("INSERT INTO crawler_jobs (id, payload, state, last_error) VALUES ($1, $2, 'dead', 'broken-page body signature')")
.bind(Uuid::new_v4())
.bind(json!({
"kind": "sync_manga",
"source_id": "target",
"source_manga_key": "gone-1",
"url": "http://x/manga/gone-1",
"title": "Ghost Manga",
}))
.execute(&pool)
.await
.unwrap();
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?search=ghost",
&cookie,
))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::OK);
let body = body_json(resp).await;
assert_eq!(body["page"]["total"], 1);
let row = &body["items"][0];
assert_eq!(row["kind"], "sync_manga");
assert_eq!(row["manga_title"], serde_json::Value::Null);
assert_eq!(row["payload_title"], "Ghost Manga");
assert_eq!(row["source_url"], "http://x/manga/gone-1");
assert_eq!(row["source_key"], "gone-1");
}
// ---------------------------------------------------------------------------
// 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;
let h = harness(pool.clone());
let cookie = seed_admin(&pool, &h.app).await;
// List.
let resp = h
.app
.clone()
.oneshot(get_with_cookie("/api/v1/admin/crawler/dead-jobs", &cookie))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::OK);
let body = body_json(resp).await;
assert_eq!(body["page"]["total"], 1);
assert_eq!(body["items"][0]["manga_title"], "Bleach");
// Requeue the single job.
let resp = h
.app
.clone()
.oneshot(post_json_with_cookie(
"/api/v1/admin/crawler/dead-jobs/requeue",
json!({ "scope": "job", "job_id": job_id }),
&cookie,
))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::OK);
let body = body_json(resp).await;
assert_eq!(body["requeued"], 1);
let state: String = sqlx::query_scalar("SELECT state FROM crawler_jobs WHERE id = $1")
.bind(job_id)
.fetch_one(&pool)
.await
.unwrap();
assert_eq!(state, "pending");
}