Export venues as editor-authorable .tres resources

- tools/export_venues.gd (SceneTree script) saves the three factory scenarios to
  content/venues/<id>.tres via ResourceSaver. The factory stays the source of truth;
  the exported files are what an editor workflow would edit and ship.
- New tests load the files back and check that id, name, event pool, profiles,
  policy (ID/wand), equipment, door-staff lines, shift phases, and locations all
  survive. They also fail when the exported files are missing or stale, so the
  export is re-run after content changes.
- GUT is consciously not adopted: the custom headless runner already covers 157
  assertions without an editor plugin and keeps CI dependency-free. Recorded in
  DONE.md.
- TODO: the planned backlog is complete; only optional future ideas remain.
- README/MEMORY updated. Version 0.2.16.

DONE.md

@@ -568,3 +568,30 @@ Completed 2026-10-31 (working tree). Headless **153/153**.
 
 
 - [x] Keep `%` placeholders stable in `Strings.fmt` when adding keys (positional formatting).
+
+## Screen design references (QA tooling)
+
+Completed 2026-10-31 (working tree). 30 Python tooling tests pass; the live judge run classed 3 captures as match and 3 as review (concept mockups are more stylised), with no confident mismatch.
+
+
+- [x] `tools/screen_designs.py generate` writes one reference design per screen
+      (from the `docs/` descriptions) to `docs/screens/designs/`, with an offline
+      `--draft` wireframe mode and an OpenRouter `--ai` mockup mode.
+- [x] `tools/screen_designs.py compare` checks `docs/screenshots/*.png` against the
+      designs (aspect ratio, size, blank-frame, and layout/palette/detail drift).
+- [x] Vision-model judge for semantic screenshot comparison: `judge` sends the
+      capture + reference design to a vision model, classes verdicts as
+      match/review/diff with a confidence threshold, supports `--dry-run`, `--json`,
+      `--only`, and `--model`, and reads the repo `.env` for the API key.
+
+## Tooling (when an editor workflow exists)
+
+Completed 2026-10-31 (working tree). Headless **157/157**; the exported `.tres` venues round-trip through the resource loader.
+
+
+- [x] Author venues as `.tres` resources: `tools/export_venues.gd` writes
+      `content/venues/<id>.tres` from the factory, and a test loads them back to check
+      nothing is lost (events, profiles, policy, phases, door lines, locations).
+- [x] GUT decision: **not adopted.** The custom headless runner (`src/test/test_runner.gd`)
+      already covers 157 assertions without an editor plugin, runs in CI, and keeps the
+      project dependency-free; adding GUT would duplicate coverage and require the editor.

MEMORY.md

@@ -21,8 +21,9 @@ Session memory for durable decisions, state, and gotchas. Keep concise, remove o
   Windowed control smoke: `godot --path . --script res://src/test/smoke_focus_radial.gd` → exit 0.
 - `main` is in sync with origin. **v0.2.2** tags the session-shell + world-follow-up commit;
   CI builds the portable binaries, NSIS installer, and AppImage on the tag push.
-- Next work: the two remaining TODO sections — the vision-model screenshot judge
+- **Backlog complete:** every planned TODO section is done and moved to `DONE.md`; `TODO.md`
-  (`tools/screen_designs.py`, OpenRouter key in `.env`) and editor tooling (GUT / `.tres` venues).
+  now only lists optional future ideas (live 3D replay, NPC LOD, more venues, real audio, web
+  export). GUT was consciously not adopted (custom runner covers it without an editor plugin).
 - Do not re-open `override_access`. Do not bind wand to `W`. Do not remove the radio easter egg.
 
 ## Current State
@@ -95,6 +96,19 @@ Session memory for durable decisions, state, and gotchas. Keep concise, remove o
   `_begin_incident()` now starts one per focused NPC (`has_open_incident()` guard), verbs call
   `_ensure_incident()`, and `ShiftCoordinator._finish_shift()` closes leftovers as `unresolved`
   before building the review.
+- **Editor-ready venues (2026-10-31):** `tools/export_venues.gd` (a SceneTree script) saves the
+  three factory scenarios to `content/venues/<id>.tres` with `ResourceSaver`; the `.tres` files
+  round-trip through `ResourceLoader` (events, profiles, policy, shift phases, door lines,
+  locations). `test_venue_resources.gd` also fails if the exported files are missing or stale
+  relative to the factory, so re-run the export after changing `ScenarioFactory`.
+- **Vision judge (2026-10-31):** `python3 tools/screen_designs.py judge` sends the capture plus
+  its concept mockup to a vision model (`DEFAULT_JUDGE_MODEL = google/gemini-2.5-flash-lite`,
+  override with `--model`; `openai/gpt-4o-mini` also works). Reads the repo `.env` via
+  `_load_env_file()` (never overrides real env). Verdicts are classed `match` / `review`
+  (mismatch below `--fail-confidence`, default 0.6) / `diff` (confident mismatch → exit 1) /
+  `unknown`. `--dry-run`, `--json`, `--only` supported. The prompt explicitly ignores art style,
+  because the references are stylised mockups; the live run gave 3 match, 3 review, 0 diff.
+  Python tests: `cd tools && python3 -m unittest test_asset_pipeline test_screen_designs`.
 - **String formatting safety (2026-10-31):** `Strings.placeholder_count()` counts `%` specs
   (ignoring `%%`), `fmt()` warns and returns the template when the arg count does not match
   (instead of raising an engine error), and `validate()` lints the table for trailing `%`,

README.md

@@ -31,7 +31,7 @@ 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: v0.2.14** — string-formatting safety, plus public downloads (no sign-in) on the host.
+> **Latest: v0.2.16** — editor-ready `.tres` venues; the planned backlog is complete.
 > 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
@@ -195,6 +195,9 @@ shared art-direction suffix so the frames read as one coherent game. Requests us
 a 3:2 landscape source and crop to the 16:9 capture dimensions.
 
 ```bash
+# Export the built-in scenarios to editor-authorable .tres resources
+godot --headless --path . --script res://tools/export_venues.gd
+
 # Deterministic wireframes (offline, no API key)
 python3 tools/screen_designs.py generate --draft
 
@@ -205,13 +208,26 @@ python3 tools/screen_designs.py generate
 # Compare docs/screenshots/*.png against the designs
 python3 tools/screen_designs.py compare
 python3 tools/screen_designs.py compare --json
+
+# Ask a vision model whether each capture realises its design's screen and layout
+# (requires OPENROUTER_API_KEY; the repo .env is read automatically)
+python3 tools/screen_designs.py judge
+python3 tools/screen_designs.py judge --model openai/gpt-4o-mini --json
+python3 tools/screen_designs.py judge --only 03-   # one capture
+python3 tools/screen_designs.py judge --dry-run    # build requests, no network
 ```
 
 `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
 semantic judge — pixel and perceptual metrics cannot decide whether a frame's
-composition is *right*, so a vision-model pass is the documented follow-up (see
+composition is *right*.
-`TODO.md`). Regenerate the designs after changing screen layout, then re-run
+
+`judge` covers that gap: it sends each capture together with its concept mockup to
+a vision model and asks whether the capture realises the same screen and layout
+intent. Art style, fidelity, fonts, and placeholder text are explicitly ignored.
+Verdicts are classed as `match`, `review` (a mismatch below `--fail-confidence`,
+default 0.6 — expected when a concept mockup is more stylised than the game), or
+`diff` (a confident mismatch, which exits non-zero). Regenerate the designs after changing screen layout, then re-run
 `compare` after regenerating the game screenshots with
 `src/test/capture_screenshots.gd`.
 
@@ -313,7 +329,7 @@ Implemented so far:
 - Godot 4.3 project scaffold, input map, procedural world builder
 - Venue-driven simulation core: `ShiftCoordinator`, `VenueScenario`, `EventScheduler`, `NPCController` + FSM, `AccessVerifier`, `EscalationManager`, `RadioSystem`, `IncidentRecorder`, `ReputationEvaluator`, `CrowdSystem`
 - Three authored scenarios (Hollywood Boulevard building, The Joke Shop, Late Night TV Studio) with access policies, NPC archetypes, and event pools
-- Headless unit tests: **153 passing** (access rules and venue-correct access loadout, escalation, radio cooldown/battery, NPC reaction determinism, door lock, flashlight perception, persistence round-trip, settings round-trip, navmesh, step colliders, skyline alpha, scenario data, full-shift simulation, wand screening, responder dispatch, localization strings, focus cone, action wheel, session shell, PLAN verbs and incident recording, crowd presentation, emergency aftermath, body-camera timeline, NPC theater poses, audio, accessibility, authored scenario content, string formatting)
+- Headless unit tests: **157 passing** (access rules and venue-correct access loadout, escalation, radio cooldown/battery, NPC reaction determinism, door lock, flashlight perception, persistence round-trip, settings round-trip, navmesh, step colliders, skyline alpha, scenario data, full-shift simulation, wand screening, responder dispatch, localization strings, focus cone, action wheel, session shell, PLAN verbs and incident recording, crowd presentation, emergency aftermath, body-camera timeline, NPC theater poses, audio, accessibility, authored scenario content, string formatting, `.tres` venue round-trip)
 - Simulation extras: protester archetype, CALL_SOMEONE reaction, door lock/secure mechanic (visual indicator), flashlight with night perception bonus, LATE shift phase reaching the violent-threat event
 - First-person prototype with interaction HUD, access inspection, wand screening, radio report form (incl. emergency hold-to-confirm), dispatched responder avatars, aim-free targeting, venue cycling between all three scenarios, color-coded escalation feedback, procedural audio cues, navigation-mesh NPC paths, JSON-backed localized strings, persisted shift history, debug overlay, and shift review
 - Control pass: focus cone on NPC heads with a billboarded blue circle in front of the face and name, action wheel (LMB/Space) with de-escalation-first slices, mouse-look freeze while a panel is open, acceleration-based walking, and named input actions (`action_menu`, `confirm`, `cancel`, `inspect`, `wand`)
@@ -330,6 +346,7 @@ Implemented so far:
 - NPC theater: seated guests sit on the steps with bent legs, influencers and tourists raise a camera prop while photographing, performers sway their sign, and filming visitors pan slowly — all once they reach their intent's waypoint
 - Audio: a looping procedural crowd bed (filtered murmur) whose volume follows `CrowdSystem.mood`, plus radio open/close crackle. All generated at runtime, no audio assets, and safe with a dummy audio server
 - Accessibility: the escalation cue shows a shape meter plus the numeric level (`Escalation: Blocking [###--] L3/5`) so it reads in grayscale, and the HUD font scale from settings is applied at boot by resizing fonts (not Control.scale, which broke the right-aligned layout)
+- Editor-ready venues: `tools/export_venues.gd` writes `content/venues/<id>.tres` from `ScenarioFactory`, and the `.tres` files load back with events, profiles, policy, phases, door lines, and locations intact (the factory stays the source of truth)
 - Localization safety: `Strings.fmt` validates the placeholder count before formatting and fails safe (warns, returns the template) instead of raising an engine error, `Strings.placeholder_count` ignores `%%`, and `Strings.validate()` lints the table for trailing `%`, unsupported conversions, and mixed positional/sequential placeholders
 - Authored scenario content: Joke Shop reservation-without-ID, borrowed/mismatched ID, a guest who refuses the wand screen, and a late arrival during a performance; Studio filming-boundary repeats and a celebrity arrival that draws a small crowd; Building events that point the player at the body camera and request-reason verbs
 - Visual polish pass (v0.2.0): phase-based lighting (sun/sky/ambient per shift phase), street lamps with night-mode bulbs and omni lights, glowing marquee signage, crosswalk, planters and low-poly street trees, NPC height/brightness variety, denser routine traffic — day and late-night screenshot sets

TODO.md

@@ -1,22 +1,15 @@
 # TODO
 
-Godot 4.3 prototype. Latest release **v0.2.14**. Headless suite **153/153**, plus the session,
+Godot 4.3 prototype. Latest release **v0.2.16**. Headless suite **157/157** plus 30 Python
-PLAN-verb, crowd, emergency, timeline, audio, scenario-content, and windowed focus/radial smokes.
+tooling tests; the session, PLAN-verb, crowd, emergency, timeline, audio, scenario-content, and
-Anonymous downloads are enabled on the host.
+windowed focus/radial smokes pass. Anonymous downloads are enabled on the host.
 
-## Screen design references (QA tooling)
+All planned backlog sections are complete (see `DONE.md`). Optional future ideas live below.
 
-- [x] `tools/screen_designs.py generate` writes one reference design per screen
+## Future ideas (optional, not scheduled)
-      (from the `docs/` descriptions) to `docs/screens/designs/`, with an offline
-      `--draft` wireframe mode and an OpenRouter `--ai` mockup mode.
-- [x] `tools/screen_designs.py compare` checks `docs/screenshots/*.png` against the
-      designs (aspect ratio, size, blank-frame, and layout/palette/detail drift).
-- [ ] Vision-model judge for semantic screenshot comparison. Pixel and perceptual
-      metrics cannot decide whether a frame's composition is correct; a follow-up
-      should send the capture + reference design to a vision model and ask whether
-      they depict the same screen.
 
-## Tooling (when an editor workflow exists)
+- [ ] Live 3D body-camera replay (the timeline is text-only today).
-
+- [ ] LOD/culling for NPCs if `MAX_LIVE_NPCS` grows past the measured 16-avatar budget.
-- [ ] IDE/editor-based GUT integration. Until then the custom headless runner stays.
+- [ ] Additional venues or seasonal events authored from the new `.tres` files.
-- [ ] Optional later: author venues as `.tres` resources instead of `ScenarioFactory` functions.
+- [ ] Real voice/dialogue audio (the crowd bed and radio crackle are procedural).
+- [ ] Web export build target.

content/venues/hollywood_building.tres

@@ -0,0 +1,794 @@
+[gd_resource type="Resource" script_class="VenueScenario" load_steps=17 format=3]
+
+[ext_resource type="Script" path="res://src/core/access_policy.gd" id="1_2u28i"]
+[ext_resource type="Script" path="res://src/core/npc_profile.gd" id="2_acokf"]
+[ext_resource type="Script" path="res://src/core/venue_scenario.gd" id="3_mqiqi"]
+
+[sub_resource type="Resource" id="Resource_i8fga"]
+script = ExtResource("1_2u28i")
+required_artifacts = {
+1: true
+}
+grant_if_any_required = false
+minimum_age = 0
+require_id = false
+wand_screening_required = false
+policy_summary = "Private property. Entry requires recognition or a valid wristband."
+
+[sub_resource type="Resource" id="Resource_c7lhe"]
+script = ExtResource("2_acokf")
+id = "tourist"
+display_name = "Tourist"
+npc_type = 0
+temperament = 0.1
+base_compliance = 0.9
+return_probability = 0.0
+reactions_by_level = {}
+default_reactions = {
+1: {
+0: 80,
+2: 8,
+3: 12
+},
+2: {
+0: 70,
+1: 10,
+2: 12,
+4: 8
+},
+3: {
+0: 55,
+1: 15,
+2: 20,
+4: 10
+},
+4: {
+1: 65,
+2: 15,
+7: 20
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String](["Oh sure, sorry, just taking a picture.", "Is there a better spot to stand?", "Understood, moving."])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_0t6ar"]
+script = ExtResource("2_acokf")
+id = "confused_visitor"
+display_name = "Confused Visitor"
+npc_type = 3
+temperament = 0.2
+base_compliance = 0.85
+return_probability = 0.0
+reactions_by_level = {}
+default_reactions = {
+1: {
+0: 80,
+2: 8,
+3: 12
+},
+2: {
+0: 70,
+1: 10,
+2: 12,
+4: 8
+},
+3: {
+0: 55,
+1: 15,
+2: 20,
+4: 10
+},
+4: {
+1: 65,
+2: 15,
+7: 20
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String](["Wait, this isn't the entrance?", "Sorry about that, I'm a bit lost."])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_wyv8p"]
+script = ExtResource("2_acokf")
+id = "delivery"
+display_name = "Delivery Worker"
+npc_type = 10
+temperament = 0.25
+base_compliance = 0.8
+return_probability = 0.0
+reactions_by_level = {}
+default_reactions = {
+1: {
+0: 80,
+2: 8,
+3: 12
+},
+2: {
+0: 70,
+1: 10,
+2: 12,
+4: 8
+},
+3: {
+0: 55,
+1: 15,
+2: 20,
+4: 10
+},
+4: {
+1: 65,
+2: 15,
+7: 20
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String](["Where should I leave this?"])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_v2hc4"]
+script = ExtResource("2_acokf")
+id = "street_performer"
+display_name = "Street Performer"
+npc_type = 1
+temperament = 0.45
+base_compliance = 0.55
+return_probability = 0.0
+reactions_by_level = {
+1: {
+0: 55,
+2: 15,
+3: 30
+}
+}
+default_reactions = {
+1: {
+0: 80,
+2: 8,
+3: 12
+},
+2: {
+0: 70,
+1: 10,
+2: 12,
+4: 8
+},
+3: {
+0: 55,
+1: 15,
+2: 20,
+4: 10
+},
+4: {
+1: 65,
+2: 15,
+7: 20
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String]([])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_lg4td"]
+script = ExtResource("2_acokf")
+id = "influencer"
+display_name = "Influencer"
+npc_type = 2
+temperament = 0.5
+base_compliance = 0.5
+return_probability = 0.0
+reactions_by_level = {
+1: {
+0: 40,
+2: 10,
+3: 30,
+4: 20
+},
+2: {
+0: 30,
+2: 20,
+4: 35,
+8: 15
+},
+3: {
+0: 10,
+1: 15,
+2: 20,
+4: 30,
+8: 25
+}
+}
+default_reactions = {
+1: {
+0: 80,
+2: 8,
+3: 12
+},
+2: {
+0: 70,
+1: 10,
+2: 12,
+4: 8
+},
+3: {
+0: 55,
+1: 15,
+2: 20,
+4: 10
+},
+4: {
+1: 65,
+2: 15,
+7: 20
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String](["This is public sidewalk, you can't stop me from filming."])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_ijl2s"]
+script = ExtResource("2_acokf")
+id = "intoxicated"
+display_name = "Intoxicated Pedestrian"
+npc_type = 4
+temperament = 0.6
+base_compliance = 0.4
+return_probability = 0.0
+reactions_by_level = {
+1: {
+0: 30,
+2: 20,
+3: 50
+},
+2: {
+0: 40,
+2: 35,
+3: 15,
+4: 10
+}
+}
+default_reactions = {
+1: {
+0: 80,
+2: 8,
+3: 12
+},
+2: {
+0: 70,
+1: 10,
+2: 12,
+4: 8
+},
+3: {
+0: 55,
+1: 15,
+2: 20,
+4: 10
+},
+4: {
+1: 65,
+2: 15,
+7: 20
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+reaction_delay = 1.8
+dialogue_lines = Array[String]([])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_eycmk"]
+script = ExtResource("2_acokf")
+id = "trespasser"
+display_name = "Trespasser"
+npc_type = 5
+temperament = 0.55
+base_compliance = 0.35
+return_probability = 0.6
+reactions_by_level = {
+1: {
+0: 30,
+2: 25,
+3: 45
+},
+2: {
+0: 40,
+2: 35,
+6: 25
+},
+3: {
+1: 35,
+2: 25,
+6: 15,
+7: 10,
+8: 15
+},
+4: {
+1: 70,
+7: 30
+},
+5: {
+1: 30,
+5: 50,
+7: 20
+}
+}
+default_reactions = {
+1: {
+0: 80,
+2: 8,
+3: 12
+},
+2: {
+0: 70,
+1: 10,
+2: 12,
+4: 8
+},
+3: {
+0: 55,
+1: 15,
+2: 20,
+4: 10
+},
+4: {
+1: 65,
+2: 15,
+7: 20
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String](["I'm just here to see a friend, come on.", "I'll be inside for ten seconds."])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_ggtpw"]
+script = ExtResource("2_acokf")
+id = "mental_crisis"
+display_name = "Person in Crisis"
+npc_type = 7
+temperament = 0.7
+base_compliance = 0.3
+return_probability = 0.4
+reactions_by_level = {
+1: {
+0: 25,
+2: 20,
+3: 55
+},
+2: {
+0: 25,
+2: 35,
+3: 30,
+5: 10
+},
+3: {
+0: 25,
+1: 15,
+2: 30,
+5: 30
+},
+4: {
+1: 40,
+5: 35,
+7: 25
+},
+5: {
+1: 25,
+5: 60,
+7: 15
+}
+}
+default_reactions = {
+1: {
+0: 80,
+2: 8,
+3: 12
+},
+2: {
+0: 70,
+1: 10,
+2: 12,
+4: 8
+},
+3: {
+0: 55,
+1: 15,
+2: 20,
+4: 10
+},
+4: {
+1: 65,
+2: 15,
+7: 20
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+reaction_delay = 2.4
+dialogue_lines = Array[String]([])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_oa64f"]
+script = ExtResource("2_acokf")
+id = "violent_threat"
+display_name = "Violent Threat"
+npc_type = 6
+temperament = 0.95
+base_compliance = 0.05
+return_probability = 0.0
+reactions_by_level = {
+1: {
+2: 25,
+3: 45,
+5: 30
+},
+2: {
+2: 30,
+5: 45,
+7: 25
+},
+3: {
+1: 20,
+5: 45,
+7: 35
+},
+4: {
+1: 15,
+5: 30,
+7: 55
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+default_reactions = {
+1: {
+0: 80,
+2: 8,
+3: 12
+},
+2: {
+0: 70,
+1: 10,
+2: 12,
+4: 8
+},
+3: {
+0: 55,
+1: 15,
+2: 20,
+4: 10
+},
+4: {
+1: 65,
+2: 15,
+7: 20
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String]([])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_7t7dh"]
+script = ExtResource("2_acokf")
+id = "protester"
+display_name = "Protester"
+npc_type = 12
+temperament = 0.5
+base_compliance = 0.4
+return_probability = 0.25
+reactions_by_level = {
+1: {
+0: 25,
+2: 35,
+3: 25,
+4: 15
+},
+2: {
+0: 15,
+2: 40,
+3: 15,
+4: 25,
+8: 5
+},
+3: {
+0: 10,
+1: 25,
+2: 25,
+4: 25,
+8: 15
+},
+4: {
+1: 60,
+2: 20,
+7: 20
+}
+}
+default_reactions = {
+1: {
+0: 80,
+2: 8,
+3: 12
+},
+2: {
+0: 70,
+1: 10,
+2: 12,
+4: 8
+},
+3: {
+0: 55,
+1: 15,
+2: 20,
+4: 10
+},
+4: {
+1: 65,
+2: 15,
+7: 20
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String](["I have every right to be on public sidewalk.", "You can't touch me, this is a lawful protest."])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_8tj1k"]
+script = ExtResource("2_acokf")
+id = "authorized_staff"
+display_name = "Staff Member"
+npc_type = 8
+temperament = 0.15
+base_compliance = 1.0
+return_probability = 0.0
+reactions_by_level = {}
+default_reactions = {
+1: {
+0: 100
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String]([])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_tnpxm"]
+script = ExtResource("2_acokf")
+id = "authorized_guest"
+display_name = "Authorized Guest"
+npc_type = 9
+temperament = 0.2
+base_compliance = 0.95
+return_probability = 0.0
+reactions_by_level = {}
+default_reactions = {
+1: {
+0: 92,
+2: 8
+},
+2: {
+0: 88,
+2: 12
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String]([])
+carried_items = Array[String]([])
+
+[resource]
+script = ExtResource("3_mqiqi")
+id = "hollywood_building"
+display_name = "Hollywood Boulevard Building"
+description = "Steps and entrance of a private building off Hollywood Boulevard."
+access_policy = SubResource("Resource_i8fga")
+equipment = Array[String](["wristband_policy", "flashlight", "radio"])
+locations = {
+"entrance": Vector3(0, 0, 1),
+"guard_post": Vector3(0, 0, -3),
+"queue_area": Vector3(0, 0, 6),
+"sidewalk": Vector3(0, 0, 9),
+"steps_end": Vector3(0, 0, 3)
+}
+npc_profiles = Array[ExtResource("2_acokf")]([SubResource("Resource_c7lhe"), SubResource("Resource_0t6ar"), SubResource("Resource_wyv8p"), SubResource("Resource_v2hc4"), SubResource("Resource_lg4td"), SubResource("Resource_ijl2s"), SubResource("Resource_eycmk"), SubResource("Resource_ggtpw"), SubResource("Resource_oa64f"), SubResource("Resource_7t7dh"), SubResource("Resource_8tj1k"), SubResource("Resource_tnpxm")])
+event_pool = Array[Dictionary]([{
+"base_weight": 1.0,
+"id": "tourist_photo",
+"intent": "photo",
+"kind": "routine",
+"npc_type": 0,
+"phase": 0,
+"probability": 0.42,
+"time_range_s": Vector2(0, 900)
+}, {
+"base_weight": 1.0,
+"id": "protest_gather",
+"intent": "protest",
+"kind": "routine",
+"npc_type": 12,
+"phase": 0,
+"probability": 0.18,
+"time_range_s": Vector2(300, 900)
+}, {
+"base_weight": 1.0,
+"id": "tourist_sit",
+"intent": "sit",
+"kind": "routine",
+"npc_type": 0,
+"phase": 0,
+"probability": 0.26,
+"time_range_s": Vector2(0, 900)
+}, {
+"base_weight": 1.0,
+"id": "confused_enter",
+"intent": "enter",
+"kind": "routine",
+"npc_type": 3,
+"phase": 0,
+"probability": 0.25,
+"time_range_s": Vector2(0, 900)
+}, {
+"base_weight": 1.0,
+"id": "delivery_drop",
+"intent": "deliver",
+"kind": "routine",
+"npc_type": 10,
+"phase": 0,
+"probability": 0.3,
+"time_range_s": Vector2(0, 600)
+}, {
+"base_weight": 1.0,
+"id": "staff_entry",
+"intent": "enter",
+"kind": "routine",
+"npc_type": 8,
+"phase": 0,
+"probability": 0.35,
+"time_range_s": Vector2(0, 600)
+}, {
+"base_weight": 1.0,
+"id": "guest_entry",
+"intent": "enter",
+"kind": "routine",
+"npc_type": 9,
+"phase": 0,
+"probability": 0.25,
+"time_range_s": Vector2(0, 900)
+}, {
+"base_weight": 1.0,
+"id": "performer_show",
+"intent": "perform",
+"kind": "routine",
+"npc_type": 1,
+"phase": 0,
+"probability": 0.24,
+"time_range_s": Vector2(300, 800)
+}, {
+"base_weight": 1.0,
+"hint": "hint.body_camera_reason",
+"id": "building_filming_boundary",
+"intent": "film",
+"kind": "scripted",
+"npc_type": 2,
+"phase": 1,
+"probability": 0.4,
+"time_range_s": Vector2(300, 600)
+}, {
+"base_weight": 1.0,
+"hint": "hint.ask_reason",
+"id": "building_unclear_intent",
+"intent": "enter",
+"kind": "scripted",
+"npc_type": 3,
+"phase": 2,
+"probability": 0.4,
+"time_range_s": Vector2(600, 780)
+}, {
+"base_weight": 1.0,
+"id": "influencer_film",
+"intent": "film",
+"kind": "routine",
+"npc_type": 2,
+"phase": 0,
+"probability": 0.26,
+"time_range_s": Vector2(300, 900)
+}, {
+"base_weight": 1.0,
+"id": "intoxicated_wander",
+"intent": "wander",
+"kind": "routine",
+"npc_type": 4,
+"phase": 1,
+"probability": 0.15,
+"time_range_s": Vector2(600, 900)
+}, {
+"base_weight": 1.0,
+"id": "trespass_test",
+"intent": "trespass",
+"kind": "routine",
+"npc_type": 5,
+"phase": 0,
+"probability": 0.16,
+"time_range_s": Vector2(300, 900)
+}, {
+"base_weight": 1.0,
+"id": "crisis_event",
+"intent": "crisis",
+"kind": "scripted",
+"npc_type": 7,
+"phase": 2,
+"probability": 0.5,
+"time_range_s": Vector2(640, 740)
+}, {
+"base_weight": 1.0,
+"id": "violent_emergency_event",
+"intent": "threat",
+"kind": "scripted",
+"npc_type": 6,
+"phase": 3,
+"probability": 0.28,
+"requires_emergency": true,
+"time_range_s": Vector2(760, 880)
+}])
+shift_phases = {
+0: {
+"start_s": 0.0
+},
+1: {
+"start_s": 300.0
+},
+2: {
+"start_s": 600.0
+},
+3: {
+"start_s": 700.0
+}
+}
+shift_duration_s = 900.0
+policy_summary = ""
+door_staff_lines = {}

content/venues/joke_shop.tres

@@ -0,0 +1,590 @@
+[gd_resource type="Resource" script_class="VenueScenario" load_steps=13 format=3]
+
+[ext_resource type="Script" path="res://src/core/access_policy.gd" id="1_lxsgk"]
+[ext_resource type="Script" path="res://src/core/npc_profile.gd" id="2_wfc6m"]
+[ext_resource type="Script" path="res://src/core/venue_scenario.gd" id="3_8xm7a"]
+
+[sub_resource type="Resource" id="Resource_xha77"]
+script = ExtResource("1_lxsgk")
+required_artifacts = {
+2: true,
+3: true
+}
+grant_if_any_required = false
+minimum_age = 21
+require_id = true
+wand_screening_required = true
+policy_summary = "Government ID and a valid ticket or reservation required. Carry items are screened."
+
+[sub_resource type="Resource" id="Resource_8ksyk"]
+script = ExtResource("2_wfc6m")
+id = "tourist"
+display_name = "Tourist"
+npc_type = 0
+temperament = 0.1
+base_compliance = 0.9
+return_probability = 0.0
+reactions_by_level = {}
+default_reactions = {
+1: {
+0: 80,
+2: 8,
+3: 12
+},
+2: {
+0: 70,
+1: 10,
+2: 12,
+4: 8
+},
+3: {
+0: 55,
+1: 15,
+2: 20,
+4: 10
+},
+4: {
+1: 65,
+2: 15,
+7: 20
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String](["Oh sure, sorry, just taking a picture.", "Is there a better spot to stand?", "Understood, moving."])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_wt1op"]
+script = ExtResource("2_wfc6m")
+id = "confused_visitor"
+display_name = "Confused Visitor"
+npc_type = 3
+temperament = 0.2
+base_compliance = 0.85
+return_probability = 0.0
+reactions_by_level = {}
+default_reactions = {
+1: {
+0: 80,
+2: 8,
+3: 12
+},
+2: {
+0: 70,
+1: 10,
+2: 12,
+4: 8
+},
+3: {
+0: 55,
+1: 15,
+2: 20,
+4: 10
+},
+4: {
+1: 65,
+2: 15,
+7: 20
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String](["Wait, this isn't the entrance?", "Sorry about that, I'm a bit lost."])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_g1jr2"]
+script = ExtResource("2_wfc6m")
+id = "influencer"
+display_name = "Influencer"
+npc_type = 2
+temperament = 0.5
+base_compliance = 0.5
+return_probability = 0.0
+reactions_by_level = {
+1: {
+0: 40,
+2: 10,
+3: 30,
+4: 20
+},
+2: {
+0: 30,
+2: 20,
+4: 35,
+8: 15
+},
+3: {
+0: 10,
+1: 15,
+2: 20,
+4: 30,
+8: 25
+}
+}
+default_reactions = {
+1: {
+0: 80,
+2: 8,
+3: 12
+},
+2: {
+0: 70,
+1: 10,
+2: 12,
+4: 8
+},
+3: {
+0: 55,
+1: 15,
+2: 20,
+4: 10
+},
+4: {
+1: 65,
+2: 15,
+7: 20
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String](["This is public sidewalk, you can't stop me from filming."])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_ys0b0"]
+script = ExtResource("2_wfc6m")
+id = "intoxicated"
+display_name = "Intoxicated Pedestrian"
+npc_type = 4
+temperament = 0.6
+base_compliance = 0.4
+return_probability = 0.0
+reactions_by_level = {
+1: {
+0: 30,
+2: 20,
+3: 50
+},
+2: {
+0: 40,
+2: 35,
+3: 15,
+4: 10
+}
+}
+default_reactions = {
+1: {
+0: 80,
+2: 8,
+3: 12
+},
+2: {
+0: 70,
+1: 10,
+2: 12,
+4: 8
+},
+3: {
+0: 55,
+1: 15,
+2: 20,
+4: 10
+},
+4: {
+1: 65,
+2: 15,
+7: 20
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+reaction_delay = 1.8
+dialogue_lines = Array[String]([])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_bv0jw"]
+script = ExtResource("2_wfc6m")
+id = "trespasser"
+display_name = "Trespasser"
+npc_type = 5
+temperament = 0.55
+base_compliance = 0.35
+return_probability = 0.6
+reactions_by_level = {
+1: {
+0: 30,
+2: 25,
+3: 45
+},
+2: {
+0: 40,
+2: 35,
+6: 25
+},
+3: {
+1: 35,
+2: 25,
+6: 15,
+7: 10,
+8: 15
+},
+4: {
+1: 70,
+7: 30
+},
+5: {
+1: 30,
+5: 50,
+7: 20
+}
+}
+default_reactions = {
+1: {
+0: 80,
+2: 8,
+3: 12
+},
+2: {
+0: 70,
+1: 10,
+2: 12,
+4: 8
+},
+3: {
+0: 55,
+1: 15,
+2: 20,
+4: 10
+},
+4: {
+1: 65,
+2: 15,
+7: 20
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String](["I'm just here to see a friend, come on.", "I'll be inside for ten seconds."])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_7vgx3"]
+script = ExtResource("2_wfc6m")
+id = "violent_threat"
+display_name = "Violent Threat"
+npc_type = 6
+temperament = 0.95
+base_compliance = 0.05
+return_probability = 0.0
+reactions_by_level = {
+1: {
+2: 25,
+3: 45,
+5: 30
+},
+2: {
+2: 30,
+5: 45,
+7: 25
+},
+3: {
+1: 20,
+5: 45,
+7: 35
+},
+4: {
+1: 15,
+5: 30,
+7: 55
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+default_reactions = {
+1: {
+0: 80,
+2: 8,
+3: 12
+},
+2: {
+0: 70,
+1: 10,
+2: 12,
+4: 8
+},
+3: {
+0: 55,
+1: 15,
+2: 20,
+4: 10
+},
+4: {
+1: 65,
+2: 15,
+7: 20
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String]([])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_x43ed"]
+script = ExtResource("2_wfc6m")
+id = "authorized_staff"
+display_name = "Staff Member"
+npc_type = 8
+temperament = 0.15
+base_compliance = 1.0
+return_probability = 0.0
+reactions_by_level = {}
+default_reactions = {
+1: {
+0: 100
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String]([])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_07lsg"]
+script = ExtResource("2_wfc6m")
+id = "authorized_guest"
+display_name = "Authorized Guest"
+npc_type = 9
+temperament = 0.2
+base_compliance = 0.95
+return_probability = 0.0
+reactions_by_level = {}
+default_reactions = {
+1: {
+0: 92,
+2: 8
+},
+2: {
+0: 88,
+2: 12
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String]([])
+carried_items = Array[String]([])
+
+[resource]
+script = ExtResource("3_8xm7a")
+id = "joke_shop"
+display_name = "The Joke Shop"
+description = "Comedy club door: IDs, reservations, and wand screening."
+access_policy = SubResource("Resource_xha77")
+equipment = Array[String](["id_check", "guest_list", "wand", "radio"])
+locations = {
+"door_area": Vector3(0, 0, 3),
+"entrance": Vector3(0, 0, 1),
+"guard_post": Vector3(0, 0, -3),
+"queue_area": Vector3(0, 0, 9),
+"sidewalk": Vector3(0, 0, 9),
+"steps_end": Vector3(0, 0, 3)
+}
+npc_profiles = Array[ExtResource("2_wfc6m")]([SubResource("Resource_8ksyk"), SubResource("Resource_wt1op"), SubResource("Resource_g1jr2"), SubResource("Resource_ys0b0"), SubResource("Resource_bv0jw"), SubResource("Resource_7vgx3"), SubResource("Resource_x43ed"), SubResource("Resource_07lsg")])
+event_pool = Array[Dictionary]([{
+"base_weight": 1.0,
+"id": "guest_valid",
+"intent": "enter",
+"kind": "routine",
+"npc_type": 9,
+"override_access": {
+"has_id": true,
+"has_ticket": true
+},
+"phase": 0,
+"probability": 0.3,
+"time_range_s": Vector2(0, 900)
+}, {
+"base_weight": 1.0,
+"id": "guest_no_ticket",
+"intent": "enter",
+"kind": "routine",
+"npc_type": 9,
+"override_access": {
+"has_id": true,
+"has_ticket": false
+},
+"phase": 0,
+"probability": 0.18,
+"time_range_s": Vector2(0, 900)
+}, {
+"base_weight": 1.0,
+"id": "guest_expired_id",
+"intent": "enter",
+"kind": "routine",
+"npc_type": 9,
+"override_access": {
+"has_id": true,
+"has_ticket": true,
+"id_status": 1
+},
+"phase": 0,
+"probability": 0.12,
+"time_range_s": Vector2(0, 900)
+}, {
+"base_weight": 1.0,
+"id": "guest_no_id",
+"intent": "enter",
+"kind": "routine",
+"npc_type": 9,
+"override_access": {
+"has_id": false,
+"has_ticket": true
+},
+"phase": 0,
+"probability": 0.12,
+"time_range_s": Vector2(0, 900)
+}, {
+"base_weight": 1.0,
+"hint": "hint.reservation_no_id",
+"id": "joke_guest_reservation_no_id",
+"intent": "enter",
+"kind": "scripted",
+"npc_type": 9,
+"override_access": {
+"guest_list_status": 0,
+"has_guest_list": true,
+"has_id": false,
+"has_ticket": false
+},
+"phase": 2,
+"probability": 0.45,
+"time_range_s": Vector2(620, 860)
+}, {
+"base_weight": 1.0,
+"hint": "hint.borrowed_id",
+"id": "joke_borrowed_id",
+"intent": "enter",
+"kind": "scripted",
+"npc_type": 9,
+"override_access": {
+"has_id": true,
+"has_ticket": true,
+"id_status": 3,
+"ticket_status": 0
+},
+"phase": 1,
+"probability": 0.4,
+"time_range_s": Vector2(320, 700)
+}, {
+"base_weight": 1.0,
+"hint": "hint.refuses_wand",
+"id": "joke_refuses_wand",
+"intent": "enter",
+"kind": "scripted",
+"npc_type": 9,
+"override_access": {
+"has_id": true,
+"has_ticket": true,
+"id_status": 0,
+"ticket_status": 0
+},
+"phase": 2,
+"probability": 0.4,
+"refuses_screening": true,
+"time_range_s": Vector2(650, 880)
+}, {
+"base_weight": 1.0,
+"hint": "hint.late_arrival",
+"id": "joke_late_arrival",
+"intent": "arrive",
+"kind": "scripted",
+"npc_type": 9,
+"override_access": {
+"has_id": true,
+"has_ticket": true,
+"id_status": 0,
+"ticket_status": 0
+},
+"phase": 2,
+"probability": 0.35,
+"time_range_s": Vector2(700, 860)
+}, {
+"base_weight": 1.0,
+"id": "joke_staff",
+"intent": "enter",
+"kind": "routine",
+"npc_type": 8,
+"phase": 0,
+"probability": 0.25,
+"time_range_s": Vector2(0, 900)
+}, {
+"base_weight": 1.0,
+"id": "performer_show",
+"intent": "perform",
+"kind": "routine",
+"npc_type": 1,
+"phase": 0,
+"probability": 0.15,
+"time_range_s": Vector2(300, 800)
+}, {
+"base_weight": 1.0,
+"id": "influencer_film",
+"intent": "film",
+"kind": "routine",
+"npc_type": 2,
+"phase": 0,
+"probability": 0.15,
+"time_range_s": Vector2(300, 900)
+}, {
+"base_weight": 1.0,
+"id": "joke_disruptive",
+"intent": "force_entry",
+"kind": "scripted",
+"npc_type": 4,
+"phase": 2,
+"probability": 0.5,
+"time_range_s": Vector2(650, 830)
+}])
+shift_phases = {
+0: {
+"start_s": 0.0
+},
+1: {
+"start_s": 300.0
+},
+2: {
+"start_s": 600.0
+},
+3: {
+"start_s": 700.0
+}
+}
+shift_duration_s = 900.0
+policy_summary = ""
+door_staff_lines = {
+"id_check": ["May I see your ID, please?", "Could you show me some identification?"],
+"prohibited_item": ["I can't allow that item inside. Please leave it outside.", "That item isn't permitted in the venue."],
+"refusal": ["I'm sorry, I can't let you in without that.", "Without a valid ID, I can't admit you tonight."],
+"ticket_check": ["Your ticket or reservation, please.", "Do you have a ticket for tonight's show?"],
+"wand_check": ["Please step forward for the wand check.", "Arms out, please — just a quick screening."]
+}

content/venues/tv_studio.tres

@@ -0,0 +1,810 @@
+[gd_resource type="Resource" script_class="VenueScenario" load_steps=17 format=3]
+
+[ext_resource type="Script" path="res://src/core/access_policy.gd" id="1_xxhx3"]
+[ext_resource type="Script" path="res://src/core/npc_profile.gd" id="2_fiebn"]
+[ext_resource type="Script" path="res://src/core/venue_scenario.gd" id="3_2dvuq"]
+
+[sub_resource type="Resource" id="Resource_blmt0"]
+script = ExtResource("1_xxhx3")
+required_artifacts = {
+1: true,
+3: true,
+4: true,
+5: true
+}
+grant_if_any_required = true
+minimum_age = 0
+require_id = false
+wand_screening_required = false
+policy_summary = "Entry requires a wristband, credential, ticket, or guest-list confirmation."
+
+[sub_resource type="Resource" id="Resource_oddac"]
+script = ExtResource("2_fiebn")
+id = "tourist"
+display_name = "Tourist"
+npc_type = 0
+temperament = 0.1
+base_compliance = 0.9
+return_probability = 0.0
+reactions_by_level = {}
+default_reactions = {
+1: {
+0: 80,
+2: 8,
+3: 12
+},
+2: {
+0: 70,
+1: 10,
+2: 12,
+4: 8
+},
+3: {
+0: 55,
+1: 15,
+2: 20,
+4: 10
+},
+4: {
+1: 65,
+2: 15,
+7: 20
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String](["Oh sure, sorry, just taking a picture.", "Is there a better spot to stand?", "Understood, moving."])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_byir2"]
+script = ExtResource("2_fiebn")
+id = "confused_visitor"
+display_name = "Confused Visitor"
+npc_type = 3
+temperament = 0.2
+base_compliance = 0.85
+return_probability = 0.0
+reactions_by_level = {}
+default_reactions = {
+1: {
+0: 80,
+2: 8,
+3: 12
+},
+2: {
+0: 70,
+1: 10,
+2: 12,
+4: 8
+},
+3: {
+0: 55,
+1: 15,
+2: 20,
+4: 10
+},
+4: {
+1: 65,
+2: 15,
+7: 20
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String](["Wait, this isn't the entrance?", "Sorry about that, I'm a bit lost."])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_3tt0b"]
+script = ExtResource("2_fiebn")
+id = "delivery"
+display_name = "Delivery Worker"
+npc_type = 10
+temperament = 0.25
+base_compliance = 0.8
+return_probability = 0.0
+reactions_by_level = {}
+default_reactions = {
+1: {
+0: 80,
+2: 8,
+3: 12
+},
+2: {
+0: 70,
+1: 10,
+2: 12,
+4: 8
+},
+3: {
+0: 55,
+1: 15,
+2: 20,
+4: 10
+},
+4: {
+1: 65,
+2: 15,
+7: 20
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String](["Where should I leave this?"])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_ihxib"]
+script = ExtResource("2_fiebn")
+id = "street_performer"
+display_name = "Street Performer"
+npc_type = 1
+temperament = 0.45
+base_compliance = 0.55
+return_probability = 0.0
+reactions_by_level = {
+1: {
+0: 55,
+2: 15,
+3: 30
+}
+}
+default_reactions = {
+1: {
+0: 80,
+2: 8,
+3: 12
+},
+2: {
+0: 70,
+1: 10,
+2: 12,
+4: 8
+},
+3: {
+0: 55,
+1: 15,
+2: 20,
+4: 10
+},
+4: {
+1: 65,
+2: 15,
+7: 20
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String]([])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_c57iy"]
+script = ExtResource("2_fiebn")
+id = "influencer"
+display_name = "Influencer"
+npc_type = 2
+temperament = 0.5
+base_compliance = 0.5
+return_probability = 0.0
+reactions_by_level = {
+1: {
+0: 40,
+2: 10,
+3: 30,
+4: 20
+},
+2: {
+0: 30,
+2: 20,
+4: 35,
+8: 15
+},
+3: {
+0: 10,
+1: 15,
+2: 20,
+4: 30,
+8: 25
+}
+}
+default_reactions = {
+1: {
+0: 80,
+2: 8,
+3: 12
+},
+2: {
+0: 70,
+1: 10,
+2: 12,
+4: 8
+},
+3: {
+0: 55,
+1: 15,
+2: 20,
+4: 10
+},
+4: {
+1: 65,
+2: 15,
+7: 20
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String](["This is public sidewalk, you can't stop me from filming."])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_bk410"]
+script = ExtResource("2_fiebn")
+id = "intoxicated"
+display_name = "Intoxicated Pedestrian"
+npc_type = 4
+temperament = 0.6
+base_compliance = 0.4
+return_probability = 0.0
+reactions_by_level = {
+1: {
+0: 30,
+2: 20,
+3: 50
+},
+2: {
+0: 40,
+2: 35,
+3: 15,
+4: 10
+}
+}
+default_reactions = {
+1: {
+0: 80,
+2: 8,
+3: 12
+},
+2: {
+0: 70,
+1: 10,
+2: 12,
+4: 8
+},
+3: {
+0: 55,
+1: 15,
+2: 20,
+4: 10
+},
+4: {
+1: 65,
+2: 15,
+7: 20
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+reaction_delay = 1.8
+dialogue_lines = Array[String]([])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_jp52w"]
+script = ExtResource("2_fiebn")
+id = "trespasser"
+display_name = "Trespasser"
+npc_type = 5
+temperament = 0.55
+base_compliance = 0.35
+return_probability = 0.6
+reactions_by_level = {
+1: {
+0: 30,
+2: 25,
+3: 45
+},
+2: {
+0: 40,
+2: 35,
+6: 25
+},
+3: {
+1: 35,
+2: 25,
+6: 15,
+7: 10,
+8: 15
+},
+4: {
+1: 70,
+7: 30
+},
+5: {
+1: 30,
+5: 50,
+7: 20
+}
+}
+default_reactions = {
+1: {
+0: 80,
+2: 8,
+3: 12
+},
+2: {
+0: 70,
+1: 10,
+2: 12,
+4: 8
+},
+3: {
+0: 55,
+1: 15,
+2: 20,
+4: 10
+},
+4: {
+1: 65,
+2: 15,
+7: 20
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String](["I'm just here to see a friend, come on.", "I'll be inside for ten seconds."])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_5kplf"]
+script = ExtResource("2_fiebn")
+id = "mental_crisis"
+display_name = "Person in Crisis"
+npc_type = 7
+temperament = 0.7
+base_compliance = 0.3
+return_probability = 0.4
+reactions_by_level = {
+1: {
+0: 25,
+2: 20,
+3: 55
+},
+2: {
+0: 25,
+2: 35,
+3: 30,
+5: 10
+},
+3: {
+0: 25,
+1: 15,
+2: 30,
+5: 30
+},
+4: {
+1: 40,
+5: 35,
+7: 25
+},
+5: {
+1: 25,
+5: 60,
+7: 15
+}
+}
+default_reactions = {
+1: {
+0: 80,
+2: 8,
+3: 12
+},
+2: {
+0: 70,
+1: 10,
+2: 12,
+4: 8
+},
+3: {
+0: 55,
+1: 15,
+2: 20,
+4: 10
+},
+4: {
+1: 65,
+2: 15,
+7: 20
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+reaction_delay = 2.4
+dialogue_lines = Array[String]([])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_6bscs"]
+script = ExtResource("2_fiebn")
+id = "violent_threat"
+display_name = "Violent Threat"
+npc_type = 6
+temperament = 0.95
+base_compliance = 0.05
+return_probability = 0.0
+reactions_by_level = {
+1: {
+2: 25,
+3: 45,
+5: 30
+},
+2: {
+2: 30,
+5: 45,
+7: 25
+},
+3: {
+1: 20,
+5: 45,
+7: 35
+},
+4: {
+1: 15,
+5: 30,
+7: 55
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+default_reactions = {
+1: {
+0: 80,
+2: 8,
+3: 12
+},
+2: {
+0: 70,
+1: 10,
+2: 12,
+4: 8
+},
+3: {
+0: 55,
+1: 15,
+2: 20,
+4: 10
+},
+4: {
+1: 65,
+2: 15,
+7: 20
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String]([])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_n4lxh"]
+script = ExtResource("2_fiebn")
+id = "protester"
+display_name = "Protester"
+npc_type = 12
+temperament = 0.5
+base_compliance = 0.4
+return_probability = 0.25
+reactions_by_level = {
+1: {
+0: 25,
+2: 35,
+3: 25,
+4: 15
+},
+2: {
+0: 15,
+2: 40,
+3: 15,
+4: 25,
+8: 5
+},
+3: {
+0: 10,
+1: 25,
+2: 25,
+4: 25,
+8: 15
+},
+4: {
+1: 60,
+2: 20,
+7: 20
+}
+}
+default_reactions = {
+1: {
+0: 80,
+2: 8,
+3: 12
+},
+2: {
+0: 70,
+1: 10,
+2: 12,
+4: 8
+},
+3: {
+0: 55,
+1: 15,
+2: 20,
+4: 10
+},
+4: {
+1: 65,
+2: 15,
+7: 20
+},
+5: {
+1: 30,
+5: 40,
+7: 30
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String](["I have every right to be on public sidewalk.", "You can't touch me, this is a lawful protest."])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_6st6l"]
+script = ExtResource("2_fiebn")
+id = "authorized_staff"
+display_name = "Staff Member"
+npc_type = 8
+temperament = 0.15
+base_compliance = 1.0
+return_probability = 0.0
+reactions_by_level = {}
+default_reactions = {
+1: {
+0: 100
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String]([])
+carried_items = Array[String]([])
+
+[sub_resource type="Resource" id="Resource_nf2oq"]
+script = ExtResource("2_fiebn")
+id = "authorized_guest"
+display_name = "Authorized Guest"
+npc_type = 9
+temperament = 0.2
+base_compliance = 0.95
+return_probability = 0.0
+reactions_by_level = {}
+default_reactions = {
+1: {
+0: 92,
+2: 8
+},
+2: {
+0: 88,
+2: 12
+}
+}
+reaction_delay = 0.6
+dialogue_lines = Array[String]([])
+carried_items = Array[String]([])
+
+[resource]
+script = ExtResource("3_2dvuq")
+id = "tv_studio"
+display_name = "Hollywood Blvd Late Night TV Studio"
+description = "Crowd, celebrities, and staff around a late-night studio."
+access_policy = SubResource("Resource_blmt0")
+equipment = Array[String](["wristband_policy", "guest_list", "radio", "flashlight"])
+locations = {
+"entrance": Vector3(0, 0, 1),
+"guard_post": Vector3(0, 0, -3),
+"queue_area": Vector3(0, 0, 9),
+"sidewalk": Vector3(0, 0, 9),
+"stage_door": Vector3(6, 0, -2),
+"steps_end": Vector3(0, 0, 3)
+}
+npc_profiles = Array[ExtResource("2_fiebn")]([SubResource("Resource_oddac"), SubResource("Resource_byir2"), SubResource("Resource_3tt0b"), SubResource("Resource_ihxib"), SubResource("Resource_c57iy"), SubResource("Resource_bk410"), SubResource("Resource_jp52w"), SubResource("Resource_5kplf"), SubResource("Resource_6bscs"), SubResource("Resource_n4lxh"), SubResource("Resource_6st6l"), SubResource("Resource_nf2oq")])
+event_pool = Array[Dictionary]([{
+"base_weight": 1.0,
+"id": "audience_ticket",
+"intent": "enter",
+"kind": "routine",
+"npc_type": 9,
+"override_access": {
+"has_ticket": true
+},
+"phase": 0,
+"probability": 0.35,
+"time_range_s": Vector2(0, 900)
+}, {
+"base_weight": 1.0,
+"id": "protest_outside",
+"intent": "protest",
+"kind": "routine",
+"npc_type": 12,
+"phase": 0,
+"probability": 0.18,
+"time_range_s": Vector2(300, 900)
+}, {
+"base_weight": 1.0,
+"id": "celebrity_arrival",
+"intent": "arrive",
+"kind": "routine",
+"npc_type": 9,
+"override_access": {
+"has_guest_list": true
+},
+"phase": 0,
+"probability": 0.2,
+"time_range_s": Vector2(300, 700)
+}, {
+"base_weight": 1.0,
+"id": "crew_shift",
+"intent": "enter",
+"kind": "routine",
+"npc_type": 8,
+"phase": 0,
+"probability": 0.3,
+"time_range_s": Vector2(0, 700)
+}, {
+"base_weight": 1.0,
+"id": "tourist_photo",
+"intent": "photo",
+"kind": "routine",
+"npc_type": 0,
+"phase": 0,
+"probability": 0.35,
+"time_range_s": Vector2(0, 900)
+}, {
+"base_weight": 1.0,
+"id": "confused_enter",
+"intent": "enter",
+"kind": "routine",
+"npc_type": 3,
+"phase": 0,
+"probability": 0.25,
+"time_range_s": Vector2(0, 900)
+}, {
+"base_weight": 1.0,
+"id": "influencer_film",
+"intent": "film",
+"kind": "routine",
+"npc_type": 2,
+"phase": 0,
+"probability": 0.28,
+"time_range_s": Vector2(0, 900)
+}, {
+"base_weight": 1.0,
+"id": "trespass_blend",
+"intent": "blend_in",
+"kind": "routine",
+"npc_type": 5,
+"phase": 0,
+"probability": 0.15,
+"time_range_s": Vector2(300, 900)
+}, {
+"base_weight": 1.0,
+"id": "studio_counterfeit",
+"intent": "counterfeit_credential",
+"kind": "scripted",
+"npc_type": 5,
+"override_access": {
+"credential_status": 2,
+"wristband_status": 2
+},
+"phase": 2,
+"probability": 0.55,
+"time_range_s": Vector2(620, 780)
+}, {
+"base_weight": 1.0,
+"hint": "hint.film_boundary",
+"id": "studio_film_boundary",
+"intent": "film_boundary",
+"kind": "scripted",
+"npc_type": 2,
+"phase": 1,
+"probability": 0.5,
+"time_range_s": Vector2(330, 560)
+}, {
+"base_weight": 1.0,
+"hint": "hint.film_boundary_repeat",
+"id": "studio_film_boundary_repeat",
+"intent": "film_boundary",
+"kind": "scripted",
+"npc_type": 2,
+"phase": 2,
+"probability": 0.45,
+"time_range_s": Vector2(640, 830)
+}, {
+"base_weight": 1.0,
+"extra_spawns": [{
+"intent": "photo",
+"npc_type": 0
+}, {
+"intent": "photo",
+"npc_type": 0
+}, {
+"intent": "film",
+"npc_type": 2
+}],
+"hint": "hint.celebrity_arrival",
+"id": "studio_celebrity_arrival",
+"intent": "arrive",
+"kind": "scripted",
+"npc_type": 9,
+"override_access": {
+"guest_list_status": 0,
+"has_guest_list": true
+},
+"phase": 2,
+"probability": 0.5,
+"time_range_s": Vector2(620, 760)
+}, {
+"base_weight": 1.0,
+"id": "studio_follow_through",
+"intent": "follow_authorized",
+"kind": "scripted",
+"npc_type": 5,
+"override_access": {
+"has_credential": false,
+"has_guest_list": false,
+"has_ticket": false,
+"has_wristband": false
+},
+"phase": 2,
+"probability": 0.45,
+"time_range_s": Vector2(700, 860)
+}])
+shift_phases = {
+0: {
+"start_s": 0.0
+},
+1: {
+"start_s": 300.0
+},
+2: {
+"start_s": 600.0
+},
+3: {
+"start_s": 700.0
+}
+}
+shift_duration_s = 900.0
+policy_summary = ""
+door_staff_lines = {}

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="0.2.14"
+config/version="0.2.16"
 run/main_scene="res://scenes/main.tscn"
 config/features=PackedStringArray("4.3", "GL Compatibility")
 

src/test/tests/test_venue_resources.gd

@@ -0,0 +1,62 @@
+extends RefCounted
+## Venues can be authored as `.tres` resources: the built-in factories export and
+## round-trip without losing their data (optional editor workflow, TODO tooling).
+
+const Factory := preload("res://src/content/scenario_factory.gd")
+const Rules := preload("res://src/core/rules.gd")
+const VenueScenario := preload("res://src/core/venue_scenario.gd")
+
+func test_venues_round_trip_through_tres() -> bool:
+	var scenarios := [Factory.hollywood_building(), Factory.joke_shop(), Factory.tv_studio()]
+	for scenario in scenarios:
+		var path := "user://%s_roundtrip.tres" % scenario.id
+		var err: int = ResourceSaver.save(scenario, path)
+		if err != OK:
+			return TestUtils.fail("could not save %s (error %d)" % [scenario.id, err])
+		var loaded = ResourceLoader.load(path)
+		if not (loaded is VenueScenario):
+			return TestUtils.fail("%s did not load back as VenueScenario" % scenario.id)
+		var a := TestUtils.check_eq(loaded.id, scenario.id, "%s id survives" % scenario.id)
+		var b := TestUtils.check_eq(loaded.display_name, scenario.display_name, "%s name survives" % scenario.id)
+		var c := TestUtils.check_eq(loaded.event_pool.size(), scenario.event_pool.size(), "%s event pool survives" % scenario.id)
+		var d := TestUtils.check_eq(loaded.npc_profiles.size(), scenario.npc_profiles.size(), "%s profiles survive" % scenario.id)
+		var e := TestUtils.check_eq(loaded.waypoint_for_intent("sit"), scenario.waypoint_for_intent("sit"), "%s locations survive" % scenario.id)
+		if not (a and b and c and d and e):
+			return false
+	return true
+
+func test_exported_tres_files_match_the_factory() -> bool:
+	## content/venues/*.tres is generated by tools/export_venues.gd; make sure it is
+	## present and not stale relative to the factory.
+	for scenario in [Factory.hollywood_building(), Factory.joke_shop(), Factory.tv_studio()]:
+		var path := "res://content/venues/%s.tres" % scenario.id
+		if not FileAccess.file_exists(path):
+			return TestUtils.fail("missing exported venue %s — run tools/export_venues.gd" % path)
+		var loaded = ResourceLoader.load(path)
+		if not (loaded is VenueScenario):
+			return TestUtils.fail("%s is not a VenueScenario" % path)
+		if loaded.event_pool.size() != scenario.event_pool.size():
+			return TestUtils.fail("%s is stale (events %d vs %d) — re-run tools/export_venues.gd" % [
+				path, loaded.event_pool.size(), scenario.event_pool.size()])
+		if not TestUtils.check_eq(loaded.shift_duration_s, scenario.shift_duration_s, "%s duration matches" % scenario.id):
+			return false
+	return true
+
+func test_exported_policy_and_events_intact() -> bool:
+	var loaded = ResourceLoader.load("res://content/venues/joke_shop.tres")
+	var a := TestUtils.check(loaded != null and loaded.access_policy != null, "access policy survives export")
+	var b := TestUtils.check_eq(loaded.access_policy.require_id, true, "joke shop still requires ID")
+	var c := TestUtils.check_eq(loaded.access_policy.wand_screening_required, true, "wand screening still required")
+	var d := TestUtils.check_eq(loaded.equipment.has("wand"), true, "equipment survives export")
+	var ids: Array = []
+	for event in loaded.event_pool:
+		ids.append(str((event as Dictionary).get("id", "")))
+	var e := TestUtils.check(ids.has("joke_refuses_wand"), "authored events survive export")
+	var f := TestUtils.check(loaded.door_staff_lines.has("refusal"), "door-staff lines survive export")
+	return a and b and c and d and e and f
+
+func test_exported_phases_survive() -> bool:
+	var loaded = ResourceLoader.load("res://content/venues/hollywood_building.tres")
+	var a := TestUtils.check(loaded.shift_phases.has(Rules.Phase.LATE), "late phase survives export")
+	var b := TestUtils.check_eq(int(loaded.shift_phases[Rules.Phase.LATE].get("start_s", -1)), 700, "late start preserved")
+	return a and b

tools/export_venues.gd

@@ -0,0 +1,26 @@
+extends SceneTree
+## Export the built-in scenarios to `.tres` resources for editor authoring.
+##
+## Usage:
+##   godot --headless --path . --script res://tools/export_venues.gd
+##
+## Writes content/venues/<id>.tres. These mirror ScenarioFactory exactly; the
+## factory stays the source of truth for the prototype, and the exported files are
+## what an editor-based workflow would edit and ship.
+
+const Factory := preload("res://src/content/scenario_factory.gd")
+
+func _initialize() -> void:
+	var out_dir := "res://content/venues"
+	DirAccess.make_dir_recursive_absolute(out_dir)
+	var scenarios := [Factory.hollywood_building(), Factory.joke_shop(), Factory.tv_studio()]
+	var failures := 0
+	for scenario in scenarios:
+		var path := "%s/%s.tres" % [out_dir, scenario.id]
+		var err: int = ResourceSaver.save(scenario, path)
+		if err == OK:
+			print("wrote %s" % path)
+		else:
+			printerr("failed to write %s (error %d)" % [path, err])
+			failures += 1
+	quit(0 if failures == 0 else 1)

tools/screen_designs.py

@@ -17,6 +17,12 @@ Two commands:
                --draft  deterministic wireframe sketches drawn with Pillow
                         (no network or API key; good for CI and layout checks).
 
+  judge      send each capture together with its reference design to a vision
+             model and ask whether they depict the same screen. Pixel and
+             perceptual metrics cannot judge composition; this closes that gap.
+             Requires OPENROUTER_API_KEY (falls back to the repo .env).
+               --dry-run  build and print the requests without calling the API.
+
   compare    compare docs/screenshots/*.png against the reference designs and
              flag gross drift. Semantic composition is judged with coarse,
              Pillow-only signals (aspect ratio, frame size, blank-frame
@@ -33,6 +39,7 @@ Run from the repo root:
 """
 
 import argparse
+import json
 import os
 import sys
 from pathlib import Path
@@ -54,6 +61,10 @@ ASPECT = 16 / 9
 # the model asset_pipeline.py already trusts for non-alpha roles).
 DEFAULT_MODEL = "openai/gpt-5-image-mini"
 
+# Vision model used by `judge`. Cheap, multimodal, and good at "same screen?".
+DEFAULT_JUDGE_MODEL = "google/gemini-2.5-flash-lite"
+OPENROUTER_CHAT_URL = "https://openrouter.ai/api/v1/chat/completions"
+
 # Shared art direction, appended to every prompt so the generated frames read
 # as one coherent game. "scene" entries are first-person 3D world views;
 # "ui" entries are in-game panels overlaid on a softened scene.
@@ -582,6 +593,193 @@ def compare(args):
 
 # ---------------------------------------------------------------------------
 
+# ---------------------------------------------------------------------------
+# Vision judge — semantic "same screen?" check against the reference designs.
+# ---------------------------------------------------------------------------
+
+JUDGE_INSTRUCTIONS = (
+    "You are reviewing screenshots of a low-poly 3D security-guard game. "
+    "IMAGE 1 is a CONCEPT MOCKUP of the intended screen (it may be painted in a "
+    "different art style and show different actors); IMAGE 2 is the ACTUAL "
+    "capture from the game. Different art style, fidelity, fonts, and character "
+    "models are EXPECTED and must be ignored.\n\n"
+    "Judge only whether IMAGE 2 realises the same SCREEN and LAYOUT INTENT as "
+    "IMAGE 1: is it the same kind of screen (world view, HUD overlay, modal "
+    "panel), are the main interface regions present in roughly the same places "
+    "(target line, inspection card, report form, on-screen buttons), and is the "
+    "subject of the shot comparable (entrance, street, person)?\n\n"
+    "Answer with JSON only: {\"match\": true|false, \"confidence\": 0..1, "
+    "\"differences\": [\"short point\", ...]}. Set match=true when the capture "
+    "realises the mockup's screen even if it looks much simpler."
+)
+
+
+def _load_env_file(path=None):
+    """Populate os.environ from a .env file without overriding real variables."""
+    path = Path(path) if path else ROOT / ".env"
+    if not path.is_file():
+        return
+    for raw in path.read_text(encoding="utf-8").splitlines():
+        line = raw.strip()
+        if not line or line.startswith("#") or "=" not in line:
+            continue
+        key, value = line.split("=", 1)
+        os.environ.setdefault(key.strip(), value.strip().strip("\"'"))
+
+
+def _data_url(path):
+    import base64
+    payload = Path(path).read_bytes()
+    return "data:image/png;base64," + base64.b64encode(payload).decode("ascii")
+
+
+def build_judge_request(model, screen, capture_path, design_path):
+    """Build the OpenRouter chat payload for one capture/design pair."""
+    prompt = (f"{JUDGE_INSTRUCTIONS}\n\nScreen: {screen['title']} "
+              f"({screen['source']}). Design notes: {screen['description']}")
+    return {
+        "model": model,
+        "messages": [{
+            "role": "user",
+            "content": [
+                {"type": "text", "text": prompt},
+                {"type": "image_url", "image_url": {"url": _data_url(design_path)}},
+                {"type": "image_url", "image_url": {"url": _data_url(capture_path)}},
+            ],
+        }],
+        "temperature": 0,
+        "response_format": {"type": "json_object"},
+    }
+
+
+def parse_judge_response(payload):
+    """Extract a verdict dict from an OpenRouter chat response."""
+    try:
+        text = payload["choices"][0]["message"]["content"]
+    except (KeyError, IndexError, TypeError):
+        return {"match": None, "confidence": 0.0,
+                "differences": ["unreadable model response"]}
+    if isinstance(text, list):  # some providers return content parts
+        text = "".join(part.get("text", "") for part in text
+                       if isinstance(part, dict))
+    text = str(text).strip()
+    start, end = text.find("{"), text.rfind("}")
+    if start >= 0 and end > start:
+        text = text[start:end + 1]
+    import json
+    try:
+        data = json.loads(text)
+    except ValueError:
+        return {"match": None, "confidence": 0.0,
+                "differences": [f"non-JSON response: {text[:120]}"]}
+    differences = data.get("differences") or []
+    if not isinstance(differences, list):
+        differences = [str(differences)]
+    return {
+        "match": data.get("match") if isinstance(data.get("match"), bool) else None,
+        "confidence": float(data.get("confidence", 0.0) or 0.0),
+        "differences": [str(item) for item in differences],
+    }
+
+
+def classify(verdict, threshold=0.6):
+    """Turn a model verdict into a QA class.
+
+    The reference images are concept mockups, so a low-confidence disagreement is
+    a review note, not a failure. Only a confident mismatch fails the check.
+    """
+    if verdict.get("match") is True:
+        return "match"
+    if verdict.get("match") is False:
+        return "bad" if float(verdict.get("confidence", 0.0)) >= threshold else "review"
+    return "unknown"
+
+
+def _call_openrouter(body, timeout=180):
+    import urllib.error
+    import urllib.request
+    key = os.environ.get("OPENROUTER_API_KEY", "").strip()
+    if not key:
+        raise ValueError("OPENROUTER_API_KEY is not set (repo .env is read "
+                         "automatically); use --dry-run to inspect requests")
+    req = urllib.request.Request(
+        OPENROUTER_CHAT_URL,
+        data=json.dumps(body).encode("utf-8"),
+        headers={
+            "Authorization": f"Bearer {key}",
+            "Content-Type": "application/json",
+            "HTTP-Referer": "https://git.allucanget.biz/zwitschi/security-game",
+            "X-Title": "Step Line",
+        },
+        method="POST",
+    )
+    try:
+        with urllib.request.urlopen(req, timeout=timeout) as resp:
+            return json.loads(resp.read().decode("utf-8"))
+    except urllib.error.HTTPError as exc:
+        detail = exc.read().decode("utf-8", "replace")
+        raise ValueError(f"OpenRouter HTTP {exc.code}: {detail[:300]}")
+
+
+def judge(args):
+    _load_env_file()
+    if not SCREENSHOTS_DIR.is_dir():
+        sys.exit(f"error: no screenshots directory at {SCREENSHOTS_DIR}")
+    refs = {screen["name"]: screen["ref"] for screen in SCREENS if screen["ref"]}
+    by_name = {screen["name"]: screen for screen in SCREENS}
+    results = []
+    for capture in sorted(SCREENSHOTS_DIR.glob("*.png")):
+        if args.only and args.only not in capture.name:
+            continue
+        design_name = next((n for n, ref in refs.items()
+                            if ref == capture.name), None)
+        if design_name is None:
+            results.append({"capture": capture.name, "screen": None,
+                            "match": None, "confidence": 0.0,
+                            "differences": ["no design reference for this capture"]})
+            continue
+        reference = _design_path(design_name)
+        if not reference.is_file():
+            results.append({"capture": capture.name, "screen": design_name,
+                            "match": None, "confidence": 0.0,
+                            "differences": ["missing reference design; run generate"]})
+            continue
+        body = build_judge_request(args.model, by_name[design_name],
+                                   capture, reference)
+        if args.dry_run:
+            results.append({
+                "capture": capture.name, "screen": design_name, "match": None,
+                "confidence": 0.0, "model": body["model"],
+                "differences": [f"dry run: {len(body['messages'][0]['content'])} parts"],
+            })
+            continue
+        verdict = parse_judge_response(_call_openrouter(body))
+        verdict.update({"capture": capture.name, "screen": design_name,
+                        "class": classify(verdict, args.fail_confidence)})
+        results.append(verdict)
+
+    if args.json:
+        print(json.dumps(results, indent=2))
+    else:
+        labels = {"match": "MATCH", "review": "REVIEW", "bad": "DIFF",
+                  "unknown": "UNKNOWN"}
+        for result in results:
+            print(f"{labels[result['class']]:7} {result['capture']} "
+                  f"(design: {result['screen']}) "
+                  f"confidence={result['confidence']:.2f}")
+            for difference in result["differences"]:
+                print(f"      - {difference}")
+        counts = {key: sum(1 for r in results if r["class"] == key)
+                  for key in labels}
+        print(f"Summary: {counts['match']}/{len(results)} match, "
+              f"{counts['review']} review, {counts['bad']} diff "
+              f"(fail threshold confidence >= {args.fail_confidence:.2f})")
+
+    if args.dry_run:
+        return 0
+    return 1 if any(r["class"] == "bad" for r in results) else 0
+
+
 def build_parser():
     parser = argparse.ArgumentParser(
         description="Generate and compare Step Line screen-design references.")
@@ -599,6 +797,18 @@ def build_parser():
                      default=generate_textures.GEN_SIZE)
     gen.set_defaults(handler=generate, draft=False)
 
+    judge_cmd = commands.add_parser(
+        "judge", help="ask a vision model whether captures match the designs")
+    judge_cmd.add_argument("--model", default=DEFAULT_JUDGE_MODEL)
+    judge_cmd.add_argument("--json", action="store_true")
+    judge_cmd.add_argument("--dry-run", action="store_true",
+                           help="print requests instead of calling the API")
+    judge_cmd.add_argument("--only", default="",
+                           help="only judge captures whose name contains this text")
+    judge_cmd.add_argument("--fail-confidence", type=float, default=0.6,
+                           help="a mismatch at or above this confidence fails")
+    judge_cmd.set_defaults(handler=judge)
+
     cmp = commands.add_parser(
         "compare", help="compare docs/screenshots/*.png against the designs")
     cmp.add_argument("--json", action="store_true")

tools/test_screen_designs.py

@@ -86,5 +86,97 @@ class ScreenDesignsTests(unittest.TestCase):
         self.assertTrue(any("aspect" in e for e in report["errors"]))
 
 
+class VisionJudgeTests(unittest.TestCase):
+    def setUp(self):
+        self.temp_dir = tempfile.TemporaryDirectory()
+        self.root = Path(self.temp_dir.name)
+        self.capture = self.root / "capture.png"
+        self.design = self.root / "design.png"
+        Image.new("RGB", (64, 36), (20, 30, 40)).save(self.capture)
+        Image.new("RGB", (64, 36), (200, 190, 180)).save(self.design)
+        self.screen = screen_designs.SCREENS[0]
+
+    def tearDown(self):
+        self.temp_dir.cleanup()
+
+    def test_judge_request_embeds_both_images(self):
+        body = screen_designs.build_judge_request(
+            "model-x", self.screen, self.capture, self.design)
+        self.assertEqual(body["model"], "model-x")
+        self.assertEqual(body["temperature"], 0)
+        self.assertEqual(body["response_format"], {"type": "json_object"})
+        parts = body["messages"][0]["content"]
+        self.assertEqual(parts[0]["type"], "text")
+        images = [p for p in parts if p["type"] == "image_url"]
+        self.assertEqual(len(images), 2, "design and capture are both attached")
+        for image in images:
+            self.assertTrue(image["image_url"]["url"].startswith(
+                "data:image/png;base64,"))
+        self.assertIn(self.screen["title"], parts[0]["text"])
+        self.assertIn("mockup", parts[0]["text"].lower())
+
+    def test_parse_plain_json_verdict(self):
+        payload = {"choices": [{"message": {"content":
+            '{"match": true, "confidence": 0.9, "differences": ["style"]}'}}]}
+        verdict = screen_designs.parse_judge_response(payload)
+        self.assertTrue(verdict["match"])
+        self.assertAlmostEqual(verdict["confidence"], 0.9)
+        self.assertEqual(verdict["differences"], ["style"])
+
+    def test_parse_fenced_json_verdict(self):
+        payload = {"choices": [{"message": {"content":
+            'Sure:\n```json\n{"match": false, "confidence": 0.7}\n```'}}]}
+        verdict = screen_designs.parse_judge_response(payload)
+        self.assertFalse(verdict["match"])
+        self.assertAlmostEqual(verdict["confidence"], 0.7)
+
+    def test_parse_content_parts(self):
+        payload = {"choices": [{"message": {"content": [
+            {"type": "text", "text": '{"match": true, "confidence": 0.5}'}]}}]}
+        verdict = screen_designs.parse_judge_response(payload)
+        self.assertTrue(verdict["match"])
+
+    def test_parse_non_json_is_unknown(self):
+        payload = {"choices": [{"message": {"content": "no idea"}}]}
+        verdict = screen_designs.parse_judge_response(payload)
+        self.assertIsNone(verdict["match"])
+        self.assertTrue(verdict["differences"])
+
+    def test_parse_missing_choices_is_unknown(self):
+        verdict = screen_designs.parse_judge_response({})
+        self.assertIsNone(verdict["match"])
+
+    def test_classify_thresholds(self):
+        self.assertEqual(screen_designs.classify(
+            {"match": True, "confidence": 0.1}), "match")
+        self.assertEqual(screen_designs.classify(
+            {"match": False, "confidence": 0.9}), "bad")
+        self.assertEqual(screen_designs.classify(
+            {"match": False, "confidence": 0.3}), "review")
+        self.assertEqual(screen_designs.classify(
+            {"match": None, "confidence": 0.0}), "unknown")
+        self.assertEqual(screen_designs.classify(
+            {"match": False, "confidence": 0.55}, threshold=0.5), "bad")
+
+    def test_env_file_does_not_override_existing(self):
+        env_path = self.root / ".env"
+        env_path.write_text('OPENROUTER_API_KEY=from-file\nOTHER=1\n',
+                            encoding="utf-8")
+        import os
+        old = os.environ.get("OPENROUTER_API_KEY")
+        os.environ["OPENROUTER_API_KEY"] = "from-env"
+        os.environ.pop("OTHER", None)
+        try:
+            screen_designs._load_env_file(env_path)
+            self.assertEqual(os.environ["OPENROUTER_API_KEY"], "from-env")
+            self.assertEqual(os.environ.get("OTHER"), "1")
+        finally:
+            if old is None:
+                os.environ.pop("OPENROUTER_API_KEY", None)
+            else:
+                os.environ["OPENROUTER_API_KEY"] = old
+            os.environ.pop("OTHER", None)
+
+
 if __name__ == "__main__":
     unittest.main()