fix stale batch dropdown when the slider moves; label regex hits as signatures

app.py

@@ -144,7 +144,10 @@ def batch_label(batch, i, n_batches, runtime=None):
     kind = ("marker regions" if n_marker == len(batch) else
             "sweep of the document" if n_marker == 0 else
             f"{n_marker} marker + {len(batch) - n_marker} sweep")
-    tail = f" · {', '.join(fams)}" if fams else ""
+    # "signature:" and not the bare family name. The regex has only seen a token like `/JS (` in
+    # the text; plenty of harmless PDFs contain one. Printing "javascript_injection" on its own
+    # before the model has read anything reads as a verdict the app has not made.
+    tail = f" · signature: {', '.join(fams)}" if fams else ""
     return (f"Batch {i + 1} of {n_batches} — {len(batch)} region(s), {kind} · {where}{tail} · "
             f"~{fmt_eta(len(batch), runtime)}")
 
@@ -162,7 +165,13 @@ def on_upload(path, per_batch, cover_all, runtime):
                 gr.update(choices=[], value=None, interactive=False))
 
     groups = batches_of(candidates, per_batch)
-    choices = [(batch_label(b, i, len(groups), runtime), i) for i, b in enumerate(groups)]
+
+    # Plain label strings, NOT (label, index) pairs. The dropdown allows custom values so the API
+    # can name a batch before any PDF has been uploaded, and that turns it into a free-text
+    # combobox: a programmatic integer value of 0 is falsy, so the displayed text refused to
+    # refresh and the box kept showing the previous split after the slider moved. Strings are
+    # never falsy here, and `resolve_batch` reads the index straight back out of "Batch N of M".
+    choices = [batch_label(b, i, len(groups), runtime) for i, b in enumerate(groups)]
 
     lines = [
         f"**{len(data):,} bytes** on disk, rendered to a **{len(skeleton):,}-character skeleton**"
@@ -201,7 +210,7 @@ def on_upload(path, per_batch, cover_all, runtime):
                  f"batches as you like, one at a time.")
 
     return ((skeleton, candidates), "\n\n".join(lines),
-            gr.update(choices=choices, value=0, interactive=True))
+            gr.update(choices=choices, value=choices[0], interactive=True))
 
 
 def resolve_batch(value, n_batches: int) -> int:
@@ -411,9 +420,12 @@ with gr.Blocks(title="PDF Injection Detector") as demo:
                       "unlimited."))
             per_batch = gr.Slider(1, MAX_PER_BATCH, value=DEFAULT_PER_BATCH, step=1,
                                   label="Regions per batch",
-                                  info=f"One batch is one run of the model. The "
-                                       f"{mimo.BACKEND.upper()} runtime tops out at "
-                                       f"{MAX_PER_BATCH}.")
+                                  info=(f"How many regions one run of the model reads — it just "
+                                        f"re-cuts the same list, so fewer per batch means more "
+                                        f"batches. A run reserves the same GPU time whatever this "
+                                        f"is set to, so lowering it inspects less of the file for "
+                                        f"the same quota. Leave it at {MAX_PER_BATCH} unless you "
+                                        f"want a faster single run."))
             # allow_custom_value: the choices are empty until a PDF is uploaded, and without this
             # Gradio validates any incoming value against that empty list and rejects it - which
             # makes the batch un-selectable over the API even though the UI had populated it.