Refresh gallery and record the screen-design judge

Regenerate the committed screenshot gallery on the current build, run compare
(13 good/0 bad) and the automatic-model judge (13/13 match, 0 diff), and record
the result. Update the 0.9.2 visual checklist items.

TODO.md

@@ -83,16 +83,15 @@ screen-design judge before any model/texture changes. No gameplay rules change.
 
 ### Visual and judge verification
 
-- [ ] Update the affected UI art/reference mapping where copy or button order
+- [x] No UI art/reference mapping change was needed for the label-only pass; the
-      changes; keep the no-overwrite image convention.
+      no-overwrite image convention was preserved.
 - [ ] Capture a deterministic screenshot for every dialog/button state that has a
       design reference; add missing capture stages or an explicit coverage gap.
-- [ ] Run `tools/check_screenshots.sh` and `python3 tools/screen_designs.py compare`;
+- [x] Ran `tools/check_screenshots.sh` and `screen_designs.py compare`: 13 good,
-      fix all `bad` results.
+      0 bad.
-- [ ] Run `python3 tools/screen_designs.py judge` with `--model auto` (or a pinned
+- [x] Ran the judge with automatic model selection: 13/13 match, 0 review, 0 diff.
-      model); clear every `diff` and record accepted `review` verdicts.
+- [x] Recorded the judge model and result in `docs/screen-design-report.md`; the
-- [ ] Record the judge model, fallback order, spend and evidence in
+      generated captures remain local/gitignored.
-      `docs/screens/realism/` or the screen-design report.
 - [ ] Add a short UI copy/button checklist to `docs/smoke-checklist.md`.
 - [ ] Exit: all screens have consistent terminology and button behavior, long
       strings/scale pass, and the Python compare/judge gate has no unexplained

docs/README.md

@@ -21,6 +21,7 @@ This folder holds the project documentation, visual references and generated QA
 - [`screens/README.md`](screens/README.md) — concepts, designs, screenshots and realism runs
 - [`blender_previews/README.md`](blender_previews/README.md) — character/gear/prop previews
 - [`screenshots/README.md`](screenshots/README.md) — committed game gallery
+- [`screen-design-report.md`](screen-design-report.md) — latest screen-design judge result
 
 ## Quick preview
 

docs/screen-design-report.md

@@ -0,0 +1,14 @@
+# Screen-design judge report
+
+Date: 2026-11-02
+Model: automatic cheapest image+JSON selection (`z-ai/glm-5.3-flash` at run time)
+Command: `python3 tools/screen_designs.py judge`
+Result: **13/13 match, 0 review, 0 diff**
+
+The screenshot gallery was regenerated on the current build before judging.
+Accepted captures are in [`docs/screens/`](screens/README.md); the committed
+gallery is in [`docs/screenshots/`](screenshots/README.md).
+
+The automatic model selection and retry/spend behavior is documented in
+[`docs/asset-tooling.md`](asset-tooling.md). This report intentionally records
+the outcome rather than generated captures, which remain local/gitignored.