diff --git a/src/soup_cli/utils/layer_shard.py b/src/soup_cli/utils/layer_shard.py
index c3faa07..3d3cea7 100644
--- a/src/soup_cli/utils/layer_shard.py
+++ b/src/soup_cli/utils/layer_shard.py
@@ -1,4 +1,4 @@
-"""soup train --stream-layers — checkpoint sharder (v0.72.0 BETA).
+"""training.stream_layers — checkpoint sharder (v0.72.0 BETA).
 
 Rewrites an HF checkpoint into one ``layer_NNN.safetensors`` per decoder layer
 plus a single ``extras.safetensors`` (embeddings / final norm / untied head),
diff --git a/src/soup_cli/utils/layer_stream.py b/src/soup_cli/utils/layer_stream.py
index e78f7c8..8f5acab 100644
--- a/src/soup_cli/utils/layer_stream.py
+++ b/src/soup_cli/utils/layer_stream.py
@@ -1,4 +1,4 @@
-"""soup train --stream-layers — layer streaming planner (v0.72.0 BETA).
+"""training.stream_layers — layer streaming planner (v0.72.0 BETA).
 
 The pure half: tier choice, pinned-vs-pageable decision, the architecture
 allowlist, and the VRAM / throughput arithmetic. **No top-level torch** — this
@@ -856,4 +856,4 @@ def render_stream_panel(plan: StreamPlan, extra_lines: Sequence[str] = ()) -> Pa
     lines.extend(extra_lines)
     for note in plan.notes:
         lines.append(f"  [yellow]![/] {note}")
-    return Panel("\n".join(lines), title="soup train --stream-layers", border_style="cyan")
+    return Panel("\n".join(lines), title="training.stream_layers", border_style="cyan")
diff --git a/src/soup_cli/utils/layer_stream_runtime.py b/src/soup_cli/utils/layer_stream_runtime.py
index 4e56d3c..dc89782 100644
--- a/src/soup_cli/utils/layer_stream_runtime.py
+++ b/src/soup_cli/utils/layer_stream_runtime.py
@@ -1,4 +1,4 @@
-"""soup train --stream-layers — streaming runtime (v0.72.0 BETA).
+"""training.stream_layers — streaming runtime (v0.72.0 BETA).
 
 The torch half: pre-allocated VRAM buffer pool, the CPU-RAM weight source, the
 prefetch scheduler, the layer wrapper, and the meta-device model build.
diff --git a/tests/test_v07202.py b/tests/test_v07202.py
index bbe69db..917f03a 100644
--- a/tests/test_v07202.py
+++ b/tests/test_v07202.py
@@ -1501,7 +1501,7 @@ training:
 
 class TestReportedParameterCount:
     """Found by the step-6 smoke, not by any unit test: a real
-    ``soup train --stream-layers`` with ``quantization: 4bit`` printed
+    ``training.stream_layers`` run with ``quantization: 4bit`` printed
     "878,154,048 total" for SmolLM2-135M (true count 134,515,008), while the
     RESIDENT NF4 path printed 134,975,808. PEFT special-cases ``Params4bit`` as
     ``numel * 2 * quant_storage.itemsize`` — correct for a resident one, whose