Add AI mockups for the seven remaining catalogue screens

The design catalogue grew to 19 screens, but only the original twelve had an AI
reference; the rest still showed "design -" in `list`. Generated the missing set
so every screen can be reviewed against an intended look:

- wand screening (metal-detected panel with carried items and allow/deny)
- Joke Shop queue, TV Studio arrival, crowd panic, responder arrival
- body-camera timeline, escalation HUD

`generate` now loads `.env` the same way `judge` does, so `--ai` no longer needs
the API key exported by hand. Each reference is 1280x720; the twelve existing
mockups were kept (no `--force`).

Verification: `list` reports 19 designs, Python tooling 53/53, headless suite
182/182, `compare` still 6 good / 0 bad on the captured screens. Version 0.3.2.

DONE.md

@@ -678,3 +678,16 @@ regenerated and `screen_designs.py compare` still reports 6 good / 0 bad.
 - [x] Tests: atlas determinism and power-of-two sizing, UV range, palette override reaching the
       atlas, and a Godot test that each imported prop scene uses exactly one material.
 - [x] Removed the now-unused sRGB→linear factor helpers (colours travel in the sRGB texture).
+
+## Complete AI Mockup Set
+
+Completed 2026-10-31 (v0.3.2). All 19 catalogue screens now have an AI reference; Python
+tooling **53/53**.
+
+- [x] Generated mockups for the seven entries that only had wireframes: wand screening,
+      Joke Shop queue, TV Studio arrival, crowd panic, responder arrival, body-camera
+      timeline, escalation HUD.
+- [x] `generate` loads `.env` like `judge` already did, so `--ai` works without exporting
+      `OPENROUTER_API_KEY` by hand.
+- [x] Verified every reference is 1280x720, reviewed the new images visually, and confirmed
+      `list` reports 19 designs (12 kept, 7 new).

MEMORY.md

@@ -37,6 +37,10 @@ Session memory for durable decisions, state, and gotchas. Keep concise, remove o
   material (`baseColorTexture` + `metallicRoughnessTexture`, NEAREST sampling). Colours are sRGB in
   the texture, so the old `srgb_to_linear`/`_linear_rgba` helpers were removed. `audit_glb` fails
   if a prop is not exactly one material or misses TEXCOORD_0/images.
+- **Mockups complete (v0.3.2):** `docs/screens/designs/` holds AI references for all 19
+  catalogue screens. Only the six staged captures (01–06) are compared/judged; the other 13
+  have no `capture`, so adding staged captures for the wand panel, timeline and escalation HUD
+  would extend automated visual checks. `generate` now calls `_load_env_file()`.
 - **Backlog complete:** every planned TODO section is done and moved to `DONE.md`; `TODO.md`
   now only lists optional future ideas (live 3D replay, NPC LOD, more venues, real audio, prop
   atlas, AI mockups for the new catalogue entries, image-to-mesh props). GUT was consciously not

README.md

@@ -32,7 +32,7 @@ The central design goal is simple:
 > Downloads are public (no sign-in required) since the host's instance-wide
 > `REQUIRE_SIGNIN_VIEW` was disabled on 2026-10-31.
 >
-> **Latest: v0.3.1** — props draw with a single atlas material instead of one material per part.
+> **Latest: v0.3.2** — every screen in the design catalogue now has an AI reference mockup.
 > Releases are built automatically when a `vX.Y.Z` tag is pushed
 > (see [`docs/RELEASING.md`](docs/RELEASING.md)); manual builds use
 > `./tools/build_releases.sh`. Installer/AppImage packaging runs in the same pipeline
@@ -261,7 +261,9 @@ python3 tools/screen_designs.py judge --dry-run    # build requests, no network
 The catalogue covers 19 screens: the six README captures plus the start menu,
 pause overlay, settings, shift review, radial menu, emergency radio, wand
 screening, Joke Shop queue, TV Studio arrival, crowd panic, responder arrival,
-body-camera timeline, and the escalation HUD.
+body-camera timeline, and the escalation HUD. All 19 have an AI reference in
+`docs/screens/designs/`; the six screens with staged captures are also compared
+or judged against the running game.
 
 `compare` flags gross drift: wrong aspect ratio, undersized frame, near-blank
 frame, and large layout/palette/detail distance. It is a regression gate, not a

TODO.md

@@ -1,6 +1,6 @@
 # TODO
 
-Godot 4.3 prototype. Latest release **v0.3.1** (prop atlas). Headless suite **182/182** plus
+Godot 4.3 prototype. Latest release **v0.3.2** (mockup set). Headless suite **182/182** plus
 **53** Python tooling tests; the session, PLAN-verb, crowd, emergency, timeline, audio, scenario-content, and
 windowed focus/radial smokes pass. Anonymous downloads are enabled on the host.
 
@@ -14,5 +14,3 @@ All planned backlog sections are complete (see `DONE.md`). Optional future ideas
 - [ ] Real voice/dialogue audio (the crowd bed and radio crackle are procedural).
 - [ ] Swap the primitive prop builder for an image-to-mesh model API behind the same
       `assets/models/generated/<prop>.glb` contract.
-- [ ] Regenerate the AI screen mockups for the seven new catalogue entries (only the
-      deterministic wireframes exist so far).

project.godot

@@ -8,7 +8,7 @@ config_version=5
 
 config/name="Step Line"
 config/description="Workplace security simulation about observation, access verification, and proportionate escalation."
-config/version="0.3.1"
+config/version="0.3.2"
 run/main_scene="res://scenes/main.tscn"
 config/features=PackedStringArray("4.3", "GL Compatibility")
 

tools/screen_designs.py

@@ -592,6 +592,7 @@ def _generate_ai(screen, model, request_size):
 
 
 def generate(args):
+    _load_env_file()
     DESIGNS_DIR.mkdir(parents=True, exist_ok=True)
     failed = []
     selected = [screen for screen in SCREENS