[fix.ligand.mu.D8+] Ivan: 我都根本看不到 — I put it in the tab where its data lives, not the tab where the question is asked

He could not find the halogen audit. He was on PHYSICS, looking at the σ-hole
Compute button; the audit was rendering in LIGAND, two tabs away, and on the default
structure it said "No halogen" anyway.

I placed it by implementation adjacency: it needs the ligand molfile, so I put it with
the other things that need the ligand molfile. That is a reason about my code, not
about the person using it. Someone asking whether a halogen is doing a job is standing
in front of the σ-hole panel, because that is where the question is being asked.

The two halves are now one block: "σ-hole · surface electrostatics" answers how deep,
and directly under it "…and is it aimed at anything?" answers at what — with the greyed
PLIP row under each verdict. Nothing about the code changed; this is markup placement,
which is the whole point. A feature in the wrong tab is not a discoverability problem,
it is an unshipped feature with a commit hash.

Verified in the built app rather than assumed: switch to 1XKK, open PHYSICS, and the
panel measures 319x412 on screen with both lapatinib halogens listed.

Third time today the defect has been reachability rather than correctness — a dead
server, a default structure with no ligand, and now a panel in the wrong tab. The code
was right in all three. Nobody could see any of it.

Author: ivanicu

src/app.frontend.facets.molstar-rdkit.editable/index.html

@@ -790,7 +790,7 @@
         }
         .ligand-depiction svg { display: block; max-width: 100%; height: auto; cursor: pointer; border-radius: 5px; }
         .bond-atlas-block { margin-top: var(--sp-4, 16px); padding-top: var(--sp-3, 12px); border-top: 1px solid var(--border); }
-        .halogen-block { margin-top: var(--sp-4, 16px); padding-top: var(--sp-3, 12px); border-top: 1px solid var(--border); }
+        .halogen-block { margin-top: var(--sp-3, 12px); padding-top: var(--sp-3, 12px); border-top: 1px dashed var(--border); }
         .halogen-note-inline { color: var(--text-3); font-size: var(--fs-2xs, 9px); letter-spacing: var(--track-wide, .08em); text-transform: uppercase; }
         .halogen-row { border-left: 2px solid var(--border-strong); padding: var(--sp-2, 8px) 0 var(--sp-2, 8px) var(--sp-2, 8px); margin-bottom: var(--sp-2, 8px); }
         .halogen-row[data-tone="ok"] { border-left-color: var(--accent); }
@@ -1475,6 +1475,24 @@ <h3>σ-hole · surface electrostatics</h3>
                            below 150° from the C–X axis a positive cap is not a σ-hole.</p>
                         <div id="phys-surface-status" class="field-status" data-tone="idle">Load a ligand first.</div>
                         <div id="phys-surface-body"></div>
+
+                        <!-- The aiming half, directly under the depth half. The two were built in
+                             parallel by two sessions and first shipped in two different tabs, which
+                             is placement by implementation adjacency rather than by the question
+                             being asked: someone wondering whether a halogen is doing a job is
+                             standing here, not in the Ligand tab. -->
+                        <div class="halogen-block">
+                            <div class="phys-block-head">
+                                <h3>…and is it aimed at anything?</h3>
+                                <span class="halogen-note-inline">electronics vs geometry</span>
+                            </div>
+                            <p class="phys-why">Depth alone does not make a halogen bond; the hole has
+                               to point at a Lewis base. Under each verdict, greyed, is what a purely
+                               geometric profiler would report — PLIP's own constants, and PLIP accepts
+                               fluorine as a halogen-bond donor on geometry alone. Where the two rows
+                               disagree is the point.</p>
+                            <div id="halogen-audit" class="halogen-audit"></div>
+                        </div>
                     </div>
 
                     <div class="phys-block">
@@ -1556,14 +1574,6 @@ <h2>2D Ligand depiction</h2>
                     <div id="ligand-depiction" class="ligand-depiction">
                         <p class="ledger-empty">Switch to a structure with a deposited ligand to see the 2D depiction.</p>
                     </div>
-                    <div class="halogen-block">
-                        <div class="ligand-meta">
-                            <span>Halogen audit</span>
-                            <span class="halogen-note-inline">electronics vs geometry</span>
-                        </div>
-                        <p class="bond-atlas-note">A σ-hole is directional. The row under each verdict is what a purely geometric profiler would report — PLIP's own constants, and PLIP accepts fluorine as a halogen-bond donor on geometry alone. Where the two rows disagree is the point.</p>
-                        <div id="halogen-audit" class="halogen-audit"></div>
-                    </div>
                     <div class="bond-atlas-block">
                         <div class="ligand-meta">
                             <span id="bond-atlas-title">Bond atlas</span>