jpmschweitzerandClaude Fable 5
c765efd54e
Infra: offset-shell gains --per-body mode (each body's own segments, cut/mask thresholds derived from that body's bone landmarks — reproduces the hand-calibrated reference constants exactly on average_m); compositor prefers <body>_mask.png with reference_mask.png fallback; tshirt re-authored per-body on all 11 (the Q-060 torso poke-through class is GONE — residual flags are a sleeve-hem epsilon artifact on thick arms, offset-insensitive, documented). Garments (all per-body x 11, chromakey-gated <=150px worst, previewed): hoodie (hood-down roll, kangaroo pocket, logo), button-down (collar/placket), shorts, jeans (analytic denim field driving albedo+mask together; boundary weld + open-rim flattening — real segment-splitter findings), formal pants, jacket (over-shirt standoff, zip), suit_jacket_black (lapel region, tintable shirt triangle — the hand-author proof), uniform_utility (11-segment coverall, gap-free waist join by construction, 4-zone showcase, logo patch). Try-on UI: creation screen shows per-region tint pickers (multi_region garments) + logo picker (logo_capable + logos/*.png scan), data-driven off manifest+coverage. Manifest merged by the lead: 12 clothing entries. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
garment-qa — chromakey garment-clipping QA (T-1089)
Automatically detects clothing clip-through with a two-pass depth-proximity
chromakey. Per view (clips × sampled frames × 4 camera yaws), the capture scene renders
the SAME frozen animation frame twice: pass A paints the body segments a garment
claims to cover (coverage.json hides) flat unshaded magenta, garment + head/hands
normal; pass B is identical except the garment is flat cyan and every garment
vertex is nudged clip_epsilon_m (default 3 cm) toward the camera. A body-key pixel
that is magenta in A but cyan in B means the ε-shifted cloth now covers it — the body sat
within ε in front of the cloth = poking through. This separates a true clip from a limb
merely crossing in front of the torso, an open collar, or a bare arm over background
(all of which stay magenta because the cloth behind them is > ε away).
Run: tooling/garment-qa/run-garment-qa [config.json] (defaults to
configs/peasant.json). It launches Godot (~/bin/godot4, opengl3, xvfb-run when
headless) on the capture scene, then runs the analyzer.
Config (path passed to the scene via GARMENT_QA_CONFIG): garments
({item_id,slot} catalogue items, or {glb,covers[]} for a raw WIP garment),
body_types, clips, frames_per_clip, yaws, head_id/hair_id/eyebrow_id/skin_tone,
out_dir.
Read the report: <out_dir>/report.json — the same summary prints to stdout. Two
metrics per capture:
clip_through_pixels/largest_clip_component— key pixels the ε-shifted cloth covers (skin ≤ ε in front of cloth). This is the real defect and it gates: a capturefails when its largest connected clip blob ≥--min-pixels(default 8, tolerating AA edges).clip_through_failures+ theby_groupclipfail/worstClipcolumns roll it up.exposed_skin_pixels— key pixels the shift did NOT cover (skin well in front of any cloth: collar/sleeve/ankle gaps, a limb crossing the torso). Informational; does not gate.
Tune sensitivity with clip_epsilon_m in the config (smaller = only tighter pokes count)
and --min-pixels on the analyzer. Failing/flagged frames are copied to
<out_dir>/failures/*_HL.png with exposed_skin lime, clip_through filled red, and
each clip blob boxed.
Note: the Godot scene lives at client/tools/garment_qa/chromakey_scene.gd (not here)
because Godot res:// paths cannot leave the client project root.