diff --git a/docs/CPU_DATA_ANALYSIS.md b/docs/CPU_DATA_ANALYSIS.md
index feafef4e..cdc3c0ca 100644
--- a/docs/CPU_DATA_ANALYSIS.md
+++ b/docs/CPU_DATA_ANALYSIS.md
@@ -201,7 +201,7 @@ where $k_\mathrm{Poisson}(\mu_b,p)$ is the smallest count whose Poisson$(\mu_b)$
 
 Because detection reads the pixel's ring, a pixel that falls outside the azimuthal-integration $q$ range has no ring and can never be strong: the integration range bounds what adaptive detection can see. Both upper limits are therefore optional and default to the detector itself — the azimuthal integration runs to the highest $q$ any pixel of the detector reaches (`--azim-max-q` unset), and spot finding is not clipped in resolution (`--spot-high-resolution` unset), for rotation data as well as stills. Setting either one narrows detection accordingly — appropriate for weak, high-background data, where the spots admitted at the detector edge are dominated by noise.
 
-**Fused GPU engine.** The per-ring reduction the adaptive threshold needs is the *same* reduction the azimuthal integrator performs. On the GPU path the two are fused into a single image pass (`AdaptiveSpotFinderGPU`): one reduction accumulates the corrected per-ring sums for the azimuthal profile (§2) *and* the raw per-ring statistics for the threshold, after which a light kernel flags the strong pixels. One GPU pass therefore replaces both the separate azimuthal-integration pass and the host-side adaptive spot-finding pass, at a small fraction of the CPU finder's cost per frame and producing the same spot list and azimuthal profile. It is enabled by default in the offline `rugnux` path and the interactive viewer; the online receiver uses the CPU adaptive finder.
+**Fused GPU engine.** The per-ring reduction the adaptive threshold needs is the *same* reduction the azimuthal integrator performs. On the GPU path the two are fused into a single image pass (`AdaptiveSpotFinderGPU`): one reduction accumulates the corrected per-ring sums for the azimuthal profile (§2) *and* the raw per-ring statistics for the threshold, after which a light kernel flags the strong pixels. One GPU pass therefore replaces both the separate azimuthal-integration pass and the host-side adaptive spot-finding pass, at a small fraction of the CPU finder's cost per frame and producing the same spot list and azimuthal profile. It is enabled by default in the offline `rugnux` path, the interactive viewer and the online receiver. Note that adaptive detection is not currently reachable online — `spot_finding_settings` in the REST API exposes no `adaptive_threshold`, so the receiver runs the fixed-threshold finder and the fused engine is held ready rather than used.
 
 ### 3.3 Resolution and ice-ring handling
 
diff --git a/image_analysis/MXAnalysisWithoutFPGA.h b/image_analysis/MXAnalysisWithoutFPGA.h
index a018c0b1..a4134cd2 100644
--- a/image_analysis/MXAnalysisWithoutFPGA.h
+++ b/image_analysis/MXAnalysisWithoutFPGA.h
@@ -69,8 +69,10 @@ class MXAnalysisWithoutFPGA {
 public:
     // enable_fused_adaptive_gpu turns on the fused GPU azint+adaptive spot finder (only takes effect on
     // the GPU path with adaptive detection). The rugnux offline path and the interactive viewer enable
-    // it by default; the online receiver leaves it off and keeps the CPU adaptive finder + separate
-    // azint. It only changes performance - the fused engine reproduces the CPU finder's spots.
+    // it by default, as does the online receiver. It only changes performance - the fused engine
+    // reproduces the CPU finder's spots. Note it also decides whether the preprocessed image is copied
+    // back to the host each frame: that copy exists only for a CPU engine to read, and while adaptive
+    // detection is not reachable through the REST API the copy is the flag's only effect online.
     MXAnalysisWithoutFPGA(const DiffractionExperiment &experiment, const AzimuthalIntegrationMapping &integration,
                      const PixelMask &mask, IndexAndRefine &indexer, bool enable_fused_adaptive_gpu = false);
     void Analyze(DataMessage &output, AzimuthalIntegrationProfile &profile, const SpotFindingSettings &spot_finding_settings);
diff --git a/receiver/JFJochReceiverLite.cpp b/receiver/JFJochReceiverLite.cpp
index b2faa9db..9b5dde20 100644
--- a/receiver/JFJochReceiverLite.cpp
+++ b/receiver/JFJochReceiverLite.cpp
@@ -276,7 +276,8 @@ void JFJochReceiverLite::DataAnalysisThread(uint32_t id) {
     measurement_started.wait();
 
     try {
-        analysis = std::make_unique<MXAnalysisWithoutFPGA>(experiment, *az_int_mapping, pixel_mask, indexer);
+        analysis = std::make_unique<MXAnalysisWithoutFPGA>(experiment, *az_int_mapping, pixel_mask, indexer,
+                                                           /*enable_fused_adaptive_gpu=*/true);
     } catch (const JFJochException &e) {
         Cancel(e);
         return;