Test that a variant is made from a cached source of a negative-cached URL

The negative cache refuses only a fetch from the upstream: a variant not
in the cache is made from the cached source, and refused once that
source is evicted.

Model: opus-5-5

README.md

@@ -201,7 +201,8 @@ path under `/v1/` answers 200, in maintenance mode too.
   `Content-Type` that is not one of the source formats (below), or with an image
   whose first bytes libvips reads as another format; 502 when the upstream
   answered with an error status, and for 5 minutes after that for the same
-  source URL; 503 when pixa is busy or in maintenance mode; 500 for any other
+  source URL, though an image of it that is already in the cache is still
+  served; 503 when pixa is busy or in maintenance mode; 500 for any other
   failure.
 - `GET` or `HEAD` `/v1/e/<token>/<name>` — an image through an encrypted URL
   (see Encrypted URLs). Needs: nothing but the URL. Answers: 200; 304 when

TODO.md

@@ -30,6 +30,13 @@ P2: security: per-origin rate limiting
 
 # Completed Steps
 
+- 2026-10-15 a cached variant is served while its source URL is in the negative
+  cache (closes #245): `Get` checked the negative cache before the variant
+  cache, so once a fetch of the source failed, as one does when another variant
+  misses after the source was evicted and the upstream is down, every cached
+  variant of that source answered 502 for 5 minutes. `Get` now serves a cached
+  variant first and checks the negative cache only on a miss, before processing.
+  `README.md` says so under `/v1/image/`.
 - 2026-10-15 the example config allowlists no host (closes #249): it allowlisted
   `github.com` and `user-images.githubusercontent.com`, where anyone can put an
   image, so a deployment set up as Getting Started says served those images to

internal/imgcache/negative_cache_internal_test.go

@@ -94,6 +94,71 @@ func TestNegativeCache_Expired(t *testing.T) {
 	}
 }
 
+// TestService_Get_ServesCachedVariantOfNegativeCachedURL caches a variant of
+// the test photo, then keeps a failed fetch of the photo's URL in the negative
+// cache, as a failed fetch for another variant does once the source has been
+// evicted. The cached variant is still served, and a variant not in the cache
+// is made from the cached source. Once the source is evicted, a variant not in
+// the cache needs a fetch and is refused.
+func TestService_Get_ServesCachedVariantOfNegativeCachedURL(t *testing.T) {
+	t.Parallel()
+
+	svc, fixtures := SetupTestService(t)
+
+	resp, err := svc.Get(t.Context(), photoVariant(fixtures, 85, FitCover))
+	if err != nil {
+		t.Fatalf("Get() first request error = %v", err)
+	}
+
+	_ = resp.Content.Close()
+
+	err = svc.cache.StoreNegative(t.Context(), photoVariant(fixtures, 85, FitCover),
+		httpStatusBadGateway, "upstream answered 503")
+	if err != nil {
+		t.Fatalf("StoreNegative() error = %v", err)
+	}
+
+	resp, err = svc.Get(t.Context(), photoVariant(fixtures, 85, FitCover))
+	if err != nil {
+		t.Fatalf("Get() of the cached variant error = %v", err)
+	}
+
+	_ = resp.Content.Close()
+
+	if resp.CacheStatus != CacheHit {
+		t.Errorf("cached variant CacheStatus = %q, want %q",
+			resp.CacheStatus, CacheHit)
+	}
+
+	resp, err = svc.Get(t.Context(), photoVariant(fixtures, 40, FitCover))
+	t.Logf("Get() of a variant made from the cached source: error = %v", err)
+
+	if err != nil {
+		t.Fatalf("Get() of a variant made from the cached source error = %v", err)
+	}
+
+	_ = resp.Content.Close()
+
+	contentHash, _, err := svc.cache.LookupSource(t.Context(),
+		photoVariant(fixtures, 85, FitCover))
+	if err != nil || contentHash == "" {
+		t.Fatalf("LookupSource() = %q, %v, want the cached source", contentHash, err)
+	}
+
+	err = svc.cache.evictSourceBlob(t.Context(), contentHash)
+	if err != nil {
+		t.Fatalf("evictSourceBlob() error = %v", err)
+	}
+
+	_, err = svc.Get(t.Context(), photoVariant(fixtures, 60, FitCover))
+	t.Logf("Get() of a variant whose source was evicted: error = %v", err)
+
+	if !errors.Is(err, ErrNegativeCached) {
+		t.Errorf("Get() of a variant whose source was evicted error = %v, want %v",
+			err, ErrNegativeCached)
+	}
+}
+
 func TestService_Get_ReturnsErrorForNegativeCachedURL(t *testing.T) {
 	t.Parallel()
 

internal/imgcache/service.go

@@ -128,26 +128,13 @@ func NewService(cfg *ServiceConfig) (*Service, error) {
 // ErrNegativeCached is returned when a URL is in the negative cache (recently failed).
 var ErrNegativeCached = errors.New("request is in negative cache (recently failed)")
 
-// Get retrieves a processed image, fetching and processing if necessary.
+// Get retrieves a processed image, fetching and processing if necessary. A
+// cached variant is served even while its source URL is in the negative
+// cache, which refuses only a variant that is not cached.
 func (s *Service) Get(ctx context.Context, req *ImageRequest) (*ImageResponse, error) {
 	// Propagate AllowHTTP setting to the request
 	req.AllowHTTP = s.allowHTTP
 
-	// Check negative cache first - skip fetching for recently-failed URLs
-	negHit, err := s.cache.checkNegativeCache(ctx, req)
-	if err != nil {
-		s.log.Warn("negative cache check failed", "error", err)
-	}
-
-	if negHit {
-		s.log.Debug("negative cache hit",
-			"host", req.SourceHost,
-			"path", req.SourcePath,
-		)
-
-		return nil, fmt.Errorf("%w: %w", httpfetcher.ErrUpstreamError, ErrNegativeCached)
-	}
-
 	// Check variant cache first (disk only, no DB)
 	result, err := s.cache.Lookup(ctx, req)
 	if err != nil {
@@ -174,6 +161,21 @@ func (s *Service) Get(ctx context.Context, req *ImageRequest) (*ImageResponse, e
 		}
 	}
 
+	// Check negative cache - skip fetching for recently-failed URLs
+	negHit, err := s.cache.checkNegativeCache(ctx, req)
+	if err != nil {
+		s.log.Warn("negative cache check failed", "error", err)
+	}
+
+	if negHit {
+		s.log.Debug("negative cache hit",
+			"host", req.SourceHost,
+			"path", req.SourcePath,
+		)
+
+		return nil, fmt.Errorf("%w: %w", httpfetcher.ErrUpstreamError, ErrNegativeCached)
+	}
+
 	// Cache miss - get the variant, processed once for all the requests that
 	// miss it at the same time, then count this request's miss, also when it
 	// failed or the request context has ended meanwhile