A room of devices now plays one game: host simulates, clients send input
and render replicated truth.
- libs/game/sim/player.rs: Players roster on GameWorld, slot 0 is always
this device. Player 0's input stays in the world's original held/pressed/
pad/cam_yaw fields and is mirrored into the roster, which is what keeps
single-player numerics bit-identical (tape gate confirms). Ids are never
reused, so a stale reference resolves to None, never to somebody else
- The camera-movement knot resolved: world.player_move(p) rotates that
player's axes by THEIR cam_yaw, carried in their input packet. Player 0's
branch is the original expression character-for-character (the f32 cos
widened to f64 kept deliberately — tidying it would move the numbers)
- libs/game/session/replication.rs: Shared = pos/vel/size/kind/tag;
Derived = facing/anim/scale/glow/blob shadows, recomputed client-side and
costing zero wire bytes; Local = camera/audio/effects. Statics never enter
the per-tick stream
- Protocol (additive, version unchanged): EntityDesc + Descriptors message
splits rare reliable construction data from volatile unreliable state —
without it a joiner sees poses for entities it cannot build. EntityDesc
carries pos because statics never appear in the state stream (the
late-joiner test caught ground arriving at the origin)
- Script: game.players/player_name/player_entity/player_input/bot/on_join/
on_leave; blocks gained owner: PlayerId so a car reads its own driver
- Arcade: ARCADE_HOST=1 / ARCADE_JOIN=<addr>; clients skip world
construction and don't simulate
- Racing wire volume, 6 players x 60Hz x 200 entities: 2400 pps,
20.9 Mbit/s up (audit projected 74 Mbit for the XR stack). Asserted in
racing_scenario_wire_volume_fits_a_living_room
Two more not-a-playable-default bugs, same class as M1b's rng-at-zero:
Entity::default() leaves gravity_scale 0 (weightless wheels) and ground
without friction gives no traction — only the DSL path filled these in.
255 tests green; tape probe BYTE_IDENTICAL; xr/arcade/gamemaker build.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The thesis proof: examples/gamemaker/resources/fixtures/racing.splash is a
complete playable racing game in 72 lines (12-corner oval from a waypoint
loop, 4 cars, gates, standings, restart) with no physics, no AI and no lap
bookkeeping in script. Blocks run engine-side at 60Hz: Blocks::pre_step
(intent -> motion) before step_world, post_step after; Blocks is Clone and
snapshots beside GameWorld so a failed eval rolls both back together.
- game.car (4 suspension raycasts on a box3d rigid chassis), game.character
(drives the existing mover sweep + owns idle/walk/run blending),
game.plane; game.drive/autodrive/speed
- Brains: game.wander/chase/patrol/caught — the fixture's hand-rolled AI,
absorbed engine-side
- Race kit: spawnpoint, checkpoint, place, race, standings, lap/rank/
finished, score/score_of (Shared-tier data, ready for replication)
raycast_vehicle audit (defects documented in car.rs, still live in xr):
libm sin/cos in steering (unreplicable), a wrong side-impulse denominator
(iaj.dot(iaj) where it should be (I^-1 aJ).aJ), and an unguarded division.
Kept the structure, replaced Bullet's friction solver with an arcade force
model: suspension acts at the contact point, grip and drive through the
centre of mass, steering as yaw torque — no lateral force can generate
roll, so it is stable by construction rather than by roll_influence fudge.
Engine bug fixed at the source: GameWorld::new() left rng at 0 and
xorshift64* is a fixed point at zero, so rand() returned 0 forever for any
world built through the sim API. reset_content seeds on every eval, which
hid it from gamemaker entirely; found by a wander brain that never left home.
Tape probe byte-identical; racing fixture evals clean and drives (AI follow
the line, gates bank in order).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Harvest-and-rebuild from xr/src/net after the adversarial audit (verdict:
transport promote-with-fixes, authority model rewrite).
- Authority: explicit Host/Client roles. Client->host Join/Input/Intent/
Leave/Ping; host->client Welcome/StateBatch/Event/Bye/Pong. No per-object
authority field and no takeover messages — authority theft (audit H-11)
is unrepresentable, not merely blocked
- Auth: self-contained SHA-256/HMAC; every datagram and frame is
magic|version|sender|payload|mac, verified BEFORE any peer state is read
or written. Closes seq-window poisoning, spoofed kick, address hijack
- Endpoints are pumped, not threaded: nothing blocks, so the connect-flood
stall (H-5) cannot occur and a full session runs deterministically in one
test process. The host only ever accepts, never initiates
- Harvested: LZ4 frame codec (check-before-allocate), partial-tail drain,
budgeted read/write loops, MTU batching, peer/config shapes. Frame cap
4MiB -> 256KiB now that XR alignment payloads are gone
- Per-entity sequencing (a stale datagram drops only its stale members),
rejoin seq reset, player cap, peer timeout, snapshot-based mid-join
- Measured 6 clients x 60Hz x 200 entities: 2880 pps, 3.13 MB/s (~25 Mbit
up) — Quest WiFi viable without delta encoding yet
- Hostile suite: one test per audit attack + 3000-mutation fuzz that must
never panic or wedge the host. 24/24 green
- micro_serde: String::de_bin no longer panics on invalid UTF-8, checked
offset arithmetic, Vec::de_bin rejects counts the buffer cannot back and
never sizes allocation from the wire (11/11)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- libs/game/sim/dynamics.rs: box3d world inside GameWorld, body mirror
RECONCILED against the sorted entity list per tick (merge-walk), so
retain/rollback/reset are correct by construction. Statics + kinematics
mirrored (kinematics via target transforms so resting rigids inherit
platform velocity); smooth terrain as a box3d heightfield
- New BodyKind::Rigid + body:"rigid" with density/friction/restitution;
game.push = mass-scaled impulse; set_pos/set_vel detected via bit-exact
pose caches (no new dispatch arms). Sphere rigids roll on real spheres
- Entity.orient quat read back per tick; renderer builds quat instance
transforms for rigids (no shader change). Step order: mover sweep
verbatim -> reconcile -> world_step(dt, 4) -> readback; rigid-free
worlds skip the solver
- GameWorld stays Clone via box3d snapshot round-trip (bit-identical
continuation proven by test)
- Determinism: double-run equality + golden hash 0xa8a2baf71e4a564f
(aarch64, debug and release). Perf: 0.038 ms/tick for 100 movers +
50 rigids + 65x65 terrain (budget 2 ms)
- Tape probe BYTE_IDENTICAL; box3d crate untouched; arcade demo gains a
kicked crate stack (captures verified: settles upright, then topples
with rotated resting poses)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- libs/game/render/skin.rs: GLB container + owned-JSON parser, dense
accessors, multi-primitive skinned meshes, skin + inverse binds, full
node-hierarchy palette, T/R/S clips (linear/step), nlerp blending.
Hermetic tests via an in-code 2-joint GLB; real-asset test skips with a
hint when the download hasn't run
- DrawGameSkinned shader (PbrVertex + albedo texture, terrain-style
lighting); skinned batch draws between opaque and alpha passes.
CPU skinning for now (sub-ms at 3716 verts): the uniform_buffer GPU path
has zero in-tree runtime consumers — SkinnedModel::palette is the seam
for the GPU swap
- apps/arcade: download_assets.sh (KayKit pinned commit + sha256,
idempotent, dir gitignored, CC0 license note in-repo); Knight patrols
the demo world with idle/walk blending, yaw follows path; captures
verified (pose advances, depth-occludes correctly)
- renderer binary_search sites use the shared sorted-id helper from M0r
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- Entity lookup O(log n): shared entity_index_sorted helper, single
push_entity spawn path with ascending-id assert + per-tick sorted
debug_assert — the sorted-Vec invariant is now enforced, not hoped
- WorldSnapshot captures next_id: failed-eval rollback can no longer mint
colliding ids under surviving entities (review defect fixed)
- game.log buffered (1s/16KiB/eval-boundary flush), agent RPC poll gated
on one .agent dir-mtime stat — no per-tick file I/O left
- Camera rig authoritative on GameWorld (orbit/chase state); widget keeps
only device-input accumulation; mailbox drain order unchanged
- Per-tick cumulative script budget: with_instruction_limit reports
consumption (incl. trap-wipe subtlety), gamemaker tick holds ONE 500k
pool across on_tick + timers + touch events
- Tape probe verified BYTE-IDENTICAL vs pre-cleanup reference
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- libs/game/math: cross-arch bit-deterministic f32 kernel (f64-internal
fdlibm-style polynomial kernels, exactly-rounded IEEE ops only, zero
platform-libm transcendentals). Parity golden hashes recorded on aarch64;
equal hashes on every other target IS the determinism test
- libs/game/sim: the gamemaker world moved verbatim (entity/terrain/world/
queries/step — float expression order preserved so tapes replay
bit-identically). No Cx, no draw types, no ScriptObjectRef: script
callbacks are CallbackSlots resolved through a generation-tagged
host-side CallbackTable in game_view.rs; sim reset no longer touches audio
- examples/gamemaker: game_view.rs 5545 -> 4640 lines (script boundary,
rendering, input devices, host I/O remain); per-tick args/input objects
built via unchecked pushes + release_transient (flat-heap tick path)
- apps/arcade: Makepad Arcade app shell + workspace membership
- Verified: headless sandbox3d fixture (90 entities) boots end-to-end;
gamemaker/sim/math/script-test suites green
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
libs/mbtile_reader gains the .mkmap consumer: root.mkidx parse (Hilbert
tile ids, root ranges -> brotli leaf directories -> shard/offset/len),
positioned shard reads, same get_metadata/get_tile_decoded surface as
MbtilesReader; TileArchiveReader sniffs the path so mbtiles_path can
point at either. Index format v2 drops JSON: the metadata section is now
varint KV like the leaves (writer + reader; no serde in the container).
Loader, zoom-range probe and the headless harness go through the enum;
bridge-dz/overlay sidecars stay mbtiles. Harness parity via shards:
worst AMS rz16 164.7ms, z12 native 51.3ms — identical to mbtiles. App
repointed to local/maps/europe-base-br.mkmap (111 shards + root.mkidx,
the exact bytes a CDN would serve).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Overnight run 2026-08-01: 9,380,390 tiles z2-14 in 3.2h, faces bake 1h
(+8GB, worker-side brotli q10), transmux to 99 shards all <510MB.
App repointed to europe-base-br-faces.mbtiles. nl-bridge-dz verified
byte-identical against the new base (deterministic feature indices).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- Sign probe was 57-76% of z9/z13 fill cost (point_in_fill_rule scans all
contours per probe): exact bbox prefilter (always on, bit-identical) +
trusted-winding map-only mode (holes take the exterior's sign; bowties
and orphan slivers keep the probe). Sweep rework: persistent zero-alloc
tessellator, events sorted once + cursor (BinaryHeap::pop was 40% of
fill CPU), ~V events instead of 2V, direct index output. 4.4-7x per
tile, worst per-fill 42.9ms -> 4.5ms, 6798/6798 fixture fills
bit-identical in both modes. MAKEPAD_TESS_DUMP fixture capture +
fixture_bench with per-stage split.
- Baked-fill fast path (v2-fills-1, flat mode): field-100 strip decode,
per-triangle Sutherland-Hodgman clip to the fill overlap rect, edge AA
via new Tessellator::fill_fringe_into over the deduped rings; 5% area
guard falls back to runtime tess — and caught a real emitter bug
(inverted ring winding on z13 water would have erased a water body).
MAKEPAD_NO_BAKED_FILLS=1 kill switch; baked_fill_audit headless test.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Speech-to-text anglicizes Dutch names ("Harlem" for Haarlem). When the
literal token intersection surfaces no settlement, the query re-runs with
near-miss tokens (banded edit distance 1, 2 for long tokens; first letter
pinned, sorted-table range scan, capped) unioned per token — the tiered
scorer then ranks the town of Haarlem above an exactly-named minor POI
naturally (settlement tier + rank dwarf the exact-name bonus). NL
in-memory index only; the europe searchdb keeps literal matching.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* TextFlow: fix inline `<code>` spans sagging below the baseline
finish_row_center centered every walk by its own height, so a code run's
shorter walk got a larger downward shift than the surrounding prose under
`RowAlign.Center`. That undid TextFlow's baseline_shift: inline `<code>`
spans sat a few px below the line's baseline, and their descenders poked
out of the bottom of the code box.
* FinishedWalk now carries an optional `align_height` that text runs set
to their line style's height, so every text run on a row receives the
same centering shift and stays on the baseline. Also fixes sub- and
superscripts drifting under `RowAlign.Center`.
* The per-style metrics probe now caches descenders too, since we need
the full line height (ascender + descender) to compute `align_height`.
* Html/Markdown: make the fixed/code font size scale configurable
Replaces the hardcoded 0.85 `FIXED_FONT_SIZE_SCALE` consts with a
`fixed_font_size_scale` live property on TextFlow (default 0.85), so
apps can tune how much smaller `<code>` text renders than the prose.
* cargo_makepad: don't include `resources/android`/`ios` on every platform
Runtime asset bundling copied each crate's entire `resources/` tree into
every package, so `resources/android/` (manifest template, launcher icon
mipmaps) shipped as dead weight inside APK assets and Apple bundles, and
any `resources/ios/` content would ship on Android too. Those dirs are
platform-specific, so only their own platform should bundle them.
* Add `cp_all_skip_top()` to `makepad-shell`: like `cp_all()`, but skips
top-level entries by exact name.
* Android (APK and AAB staging): bundle `resources/android/` minus the
packaging inputs `AndroidManifest.xml.template` and `res/`, which
already reach the package via the generated manifest and the aapt
`res/` pipeline; skip `resources/ios/` entirely.
* Apple bundles: skip `resources/android/`, keep `resources/ios/`.
- ggml: read-only mmap module (unix-gated) + two-region Context (mapped
weights / dirty caches) + segmented Metal buffer binding; llama loads
GGUF weights as file-backed clean pages (jetsam-exempt) with owned-arena
fallback (MAKEPAD_LLAMA_NO_MMAP=1). Route app dirty footprint 12GB -> 4-7GB;
model load becomes lazy page-in; A/B byte-identical on 4B + 9B.
- llama: fix graph-cache keying corruption — a graph keyed wider than the
KV cache corrupted attention for any prefill batch >= 2 (flash op reads
permute-node dims baked at build; view reconfigure never reached the
kernel; masks were written cache-narrow). Masks now always fill the full
graph key width and graphs key by 1024-buckets; reconfigure path removed.
Verified byte-exact vs per-length reference across batch 1/2/8/64/512,
short+long prompts, mmap on/off, plus a two-session concurrency probe.
- voice: passive VoiceWaves no longer register the global audio-input
callback (the invisible caption-bar wave stole mic audio — last
registrant wins — and spawned duplicate whisper workers); whisper back
to F16 default (voice Metal library has no quantized kernels; q5_0
failed every GPU matmul); raw transcripts render immediately.
- route: kokoro TTS voice output (speaker toggle; streams reply sentences,
announces nav maneuvers + arrival) with barge-in — voice activity on the
mic stops playback instantly; dispatcher context 8k -> 32k (hybrid KV is
12/48 layers, ~48KB/token); window caption bar suppressed under studio.
- llama-generate: --max-context/--prefill-batch-size + state fingerprints;
new llama_concurrent_probe bin.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Shadows are polygons, not passes: each building's roof ring is projected
along the sun's ground direction by height * shadow_len, and footprint +
projection + silhouette quads dissolve into ONE per-tile union (i_overlay
chunked, the road-union lesson) so overlaps never double-darken. Emitted
as material-6 ground fills in the ICON pass — in a city almost all
ground is road surface, and anything earlier gets painted over by the
street passes — with micro-depth 0.40, above the whole grounded road
ladder but below lifted deck bumps. The decal bakes full-dark and the
shader scales it by the live shadow_alpha uniform, so time-of-day fades
don't need a rebake. LOD gates: 3D mode, z>=14, and skip shadows under
2 px at bake magnification. Trees get soft contact-shadow discs.
Terrain: horizon-march cast shadows in the hillshade worker (17-step
exponential stride, ~15 ms per 512px region), skipped automatically
when regional relief is under 150 m. Hillshade + march light from the
one SceneSun via a new per-request sun/flag channel to the worker.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
One global light (draw/src/scene_sun.rs): SceneSun POD shared by the
tile bake, ball lighting and terrain hillshade, replacing three
hardcoded sun rigs. ShinyConfig carries every shiny.md toggle; it rides
CompiledMapTheme so bake-flag flips reuse the style-epoch restyle and
stale tiles stay drawable (MapView::update_shiny).
T1: shape-0 geometry now carries its surface normal in param1/2 and a
material id in param3 (walls/roofs/water/canopy/green) — channels were
free, no vertex-format growth. DrawMapVector dispatches per-material
pixel effects behind uniform gates that default off (legacy frame when
off): T4 water noise sheen + sun glint, T4b building specular sheen
with heading-rotation highlight sweep, T5 canopy clump noise + rim and
green-area patchiness.
T2 (first slice): wall vertical AO gradient (ground-contact darkening)
and roof-edge parapet AO strips, baked at zero GPU cost behind bake_ao.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Inhouse i_overlay 7.0.3 and its i_float/i_shape/i_key_sort/i_tree deps
(used by the map road union mesh under the widgets 'maps' feature) as
workspace-excluded path crates, stripped of tests/locks/registry crud.
i_float's no_std libm dependency is removed by switching it to std
float math, so the maps feature no longer pulls any external crates.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Bridge elevation (bridge.md M1+M2): tools/map_tiles bridge-bake solves
per-vertex road/rail dz over the OSM graph (crossing clearance, grade
ramps, deck holds, junction consensus) with AHN DSM-DTM measured deck
profiles (BigTIFF reader in geodata, WGS84->RD), baked as bridge_dz +
per-base-tile base_dz (L/F/P join to exact renderer geometry). Renderer
joins dz through parse into TileWay.dz; strokes/arrows/fills lift off
their own profiles; tunnels never deck.
Road overlay unifier: painter's algorithm as geometry — per-way segment
rects + vertex discs, i_overlay top-down subtraction cascade into
DISJOINT faces (overlay_paint_groups), triangulated once; flat render is
pixel-equal to paint order (proven 0-diff on the abstract unit case) and
tilt cannot reorder it. Legacy strokes interleave by rank; plazas join
the cascade at true alpha. @roads 0/1 A/B toggle, @abtest headless
CPU-raster diff harness (1.50% vs 2D reference on the Raampoort tile),
@cam debug camera, bridge_eval.sh aerial-vs-render loop.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Terrain gets real z in tilt mode: a displaced 288x216 surface mesh plus
per-vertex ground lift for all tile geometry (roads/fills/buildings/icons)
via vertex-stage sample_lod of a terrarium-packed elevation texture, with
labels riding the same ground through a lift-aware camera delta. Depth
domains rescale per frame to stay inside the -24 budget; road passes get
a relief-scaled clearance over the surface so cities keep correct
street-vs-building order. Regional zooms (<z14) drape landcover colors
into the hillshade (full-res MVT rasterization, treeline fade) instead of
lifting km-scale polygons that cannot follow relief.
Terrain build now covers EV-trip Europe (lat 43..58, lon -5..17, 8.8 GB
GLO-30 z6-12) with sign-safe Copernicus stems, transparent no-data, and
an Alpine rock/snow ramp. Terrain requests render 4096x3072 over ~3
viewports and only re-render on real movement.
Also: NOMADS GFS wind particle layer synced to the weather clock with 3D
altitude, rain cloud deck lift, stuck-tile fixes (expiring missing set,
decode-failure backoff, restyle placeholder purge), 78-degree tilt
ceiling, and park fill z-fight fix via widened micro-depth ranks.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- rain radar layer: pure-Rust KNMI HDF5 reader (superblock v0 walk,
single-chunk deflate datasets, byte-exact vs h5py), ellipsoidal polar
stereographic reprojection (20 m vs product corners), bilinear value
sampling -> smooth banded isolines, textured quad overlay through the
overlay camera, 25-frame nowcast animation; RadarSync polls at most
once per 4 min through a disk-persisted gate and caches frames on disk
- makepad-geodata + makepad-tesla crates join the workspace (overlay
builders, radar sync, NL open-data layers; transit routes now z7-14)
- Europe major-roads routing graph: nav-build --major-roads does a
ways-first scan (5.7M ways / 46M nodes / 194 s / 971 MB) and the app
falls back to it when a route leaves the regional graph — Amsterdam to
Paris routes offline (501.8 km)
- 3D flying markers: chargers/POIs/stops ride thin stalks with DYNAMIC
height (each pin clears its own building +8 m); labels, kW text,
brand and tap zones all consume the baked per-marker lift; stalks and
buildings grow together on the 2D->3D transition (per-tile flat->3D
fade heights, no replay on zoom regens)
- markers depth-honest (small bias, buildings occlude them); phong-lit
canopy/light spheres matching the buildings' NW sun; buildings tint by
BAG age in 3D; district area tints (rank 60, alpha .32); transit line
labels + stop names; follow-mode is an explicit attach/detach toggle;
rotation release schedules the label re-place (no stuck upside-down
labels after a fast spin)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- Tesla-style droplet pins anchored at the tail tip (rotate around the
exact site point in tilted views); red exclusively Tesla, amber DC,
blue AC; Tesla pins show stall count, others peak kW
- in-pin text through the normal text renderer: billboard-anchored
glyphs (anchor scales with the map, glyph size constant), exempt from
label collision/repeat culling, no halo
- upright camera-delta labels: straightened labels (place names, POIs,
brands, pin text) translate with the rotation gesture but stay
horizontal — no more rotate-then-snap on regen
- per-icon zoom floors baked in vertex param4 + live icon_zoom uniform:
stale deeper-bucket tiles never flash markers on zoom-out (param4 is
lift-height only for non-icon shapes — icons stay on the ground)
- motorway exit labels (street_labels_points): carto-red name + ref
- 2D/3D mode: tilt gesture syncs app state (TiltChanged action), tilt
release near-flat settles to exact 0, mode flip re-bakes tiles
(extrusions appear/disappear without a zoom nudge)
- Simple 3D Buildings: building:part volumes with min_height bases;
outlines containing parts flatten to footprints; famous buildings
with tourism=attraction extrude instead of dying as attraction fills
- little 3D trees in tilt mode: crossed trunk quads + sphere-slice
ball canopy (architecture-model proportions)
- searchdb/mbtiles support work: reach-based distance ranking, direct
tile lookup + writer ordering
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
LlamaSession gains append_image_embeddings: precomputed vision embeddings
prefill through a second Embeddings-input graph spec sharing the same
cache tensors (SessionGraphParams grows an embeddings_input discriminant).
HybridDecodeBatchLayout gains an optional pre-expanded rope_positions
override, threaded to encode_rope_positions — cache indices and attention
masks stay linear while image tokens get qwen-vl 2D positions
[pos0, pos0+y, pos0+x, 0] and the span advances rope position by
max(w, h). Text after an image continues from the shifted position; pure
text paths are byte-identical to before (verified via llama-generate).
vlm-probe runs the whole thing: ppm -> vision tower -> chatml with
vision_start/end -> greedy. Output is token-for-token identical to
llama-mtmd-cli --temp 0 on both test images (radar scene description and
'A red circle.'). 229-token mixed prefill 0.98s, generation 27.9 tok/s
on the 9B UD-Q4_K_XL.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
New vision module: mmproj GGUF load (reuses the arch-agnostic loader),
exact-port preprocessing (calc_size_preserved_ratio, f64 bilinear resize to
match the reference binary's double promotion, block-major patch unfold),
and the 27-block ViT graph: patchify as two matmuls vs the flattened conv
weights, interpolated learned pos-embd (gpu bilinear+antialias, gathered to
block order), 2D vision rope, full bidirectional flash attention (f16 k/v,
f32 prec), layernorm composed as norm-mul-add, and the qwen3vl_merger
2-layer MLP into the LLM's 4096-dim space.
vlm-vision-probe validates against clip.cpp dumps: preproc bit-exact on
aligned images (1e-7), embeddings rms 3e-4..9e-4 / cosine 0.99999+ on all
three test images — inside the oracle's own flash-vs-composed spread
(rms 8.9e-4). 64-token encode 38ms, 192-token 103ms after graph compile.
Also fixes a stale DeltaNetRecurrentBlockSpec test initializer that broke
cargo test compilation.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
New makepad-converse crate: SpeechOutput/Playback moved out of gamemaker
(mix_into for custom audio callbacks, install_audio_output convenience);
TranscriptFilter trait + PassthroughFilter + FilterWorker thread (filters
built on the worker via factory since LlamaSession is not Send);
ConversePipeline wiring filter -> makepad_ai agent backend -> speech with a
ConverseAction stream, llm leg pluggable (claude-code / acp /
openai-compatible base_url for local servers). QwenFilter behind the
local-llm feature: chatml prompt, non-thinking prefill, greedy, SEND:/SKIP:
line protocol, fail-open parse; filter-repl bin for interactive testing.
Gamemaker's speech leg now uses the crate; its agent plumbing stays local.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Ports the silero v5 16k branch to pure rust (minimal onnx-protobuf weight
extraction, hardcoded graph: stft-conv, 4x conv+relu, lstm cell, sigmoid
head), 512-sample chunks with 64-sample carried context. Validated against
onnxruntime to 2.3e-6 max diff (fixtures committed), ~425us/chunk release.
Model loads from repo-root silero_vad.onnx or MAKEPAD_VAD_MODEL. vad-test
bin for wav files. window_voice_input now gates packets on vad probability
(0.5 enter / 0.35 exit) and falls back to the rms gate when the model file
is missing — the log line says which gate is active.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Grid width for the non-flat unary path was ne01 while the kernel decomposes
tgpig.x into (ne0-chunk, row) — rows past ntg were silently dropped, masked
below the 32768-element flat-path threshold; silu on [8192, n] crossed it at
prefill batch 4 and corrupted qwen35 batched prefill. Grid is now
ne01 * ceil(ne0/nth). Adds metal unary/gated-delta-net/ssm_conv regression
tests, the llama-batch-probe bisect harness, prefill batch default 32, and
keeps the graph cache until a reserve-retry actually needs eviction.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
score_search_hit: settlements are near-immune to distance ("brussels"
from Amsterdam means Bruxelles, not the closest Brusselsestraat),
POIs/streets keep strong local bias, and a number token signals
address intent. nav-build --places-only scans a pbf for settlement
nodes into a compact index (Europe: 1.31M places, 67MB, 60s); the app
merges it with the regional full index, deduping same-name near hits.
Route overlay decimation now measures against the last drawn point,
bounding the error at ~1.5px — pairwise skipping compounded and
visibly reshaped the route when zoomed out.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Stroke geometry now bakes the centerline anchor per vertex (svg
tessellator emits anchors; offsets ride in param1/2, width-growth
class in param3, shape_id+100 marks expand mode — the shared vertex
format is unchanged). The map vertex shader re-expands each stroke
with a per-class width correction (regular roads, thin paths/rails,
waterways, constant-px building outlines) computed from the tile's
styled bucket vs the live fractional view zoom.
Tiles rendered at a stale zoom bucket keep the exact widths a fresh
restyle would produce, through the whole gesture: no fat roads while
zooming in, no width snap when the rebuild lands, dash dots and
building outlines stay crisp. Fading outgoing generations carry their
own bucket so they correct too.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Conversion tooling (tools/map_tiles): curated Shortbread base pyramid
from a VersaTiles planet archive (bbox extract, brotli->gzip transcode
parallelized per 256x256 block), all-tag native OSM pbf detail
converter, pbf audit, and nav-build/nav-probe producing the routing
graph + search index artifacts. download_map.sh orchestrates pinned
downloads and conversions. mbtile_reader writer now skips SQLite's
lock-byte page at byte offset 1 GiB — allocating through it corrupted
every database over 1 GiB ("2nd reference to page 16385"); the 31 GB
Europe conversion passes integrity checks.
Navigation (libs/map_nav, new): region.search place/POI/street/address
index (prefix autocomplete, NL/EN category synonyms, proximity
ranking) and region.graph routing graph (CSR directed edges,
car/bike/foot speeds, oneway, turn restrictions, snap grid, A*),
maneuver generation and the NavSession map-matching state machine;
26 unit tests.
MapView interaction layer: MapViewAction, camera API + animated
fly_to, overlay.rs (route polyline with traveled dimming, markers,
position puck), per-widget mbtiles_path override, archive
minzoom/maxzoom honored for tile requests, zoom-level cross-fade over
the previous level's imagery, floating panels win hit-testing.
examples/map is the navigator app: worker-thread search, Drive/Bike/
Walk routing, simulated turn-by-turn with banner, follow camera.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Direct (zoom, column, row) tile queries so the map no longer scans an
entire zoom level per batch, plus a writer for producing mbtiles
archives.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- per-end line caps (Tessellator::stroke_ends): butt at tile-clip cuts,
round at true ends — road cap discs no longer stamp over neighbor
tiles' tram tracks and roads at seams
- fill polygons clipped to their own tile square (Sutherland-Hodgman);
a tile's MVT buffer fragments no longer overpaint the neighbor;
building outlines skip segments running along the tile cut
- stroke clip padding 3px (under the generator buffer) so boundary
cuts are detectable
- white label halos (8-offset underdraw, theme label_halo color)
- carto POI label colors (orange food, purple shops, brown culture,
muted house numbers) from shortbread poi attributes
- label placement hysteresis across frames (no flicker while panning)
- street_polygons fill ranked below sites/parks (Bellamyplein-class
plazas no longer cover the park inside them)
- max zoom 19 with width stops for z18/19
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* Fix rendering, gradient, sampling, etc issues on older GPUs
* Fix bug in `box_y` sdf function, which caused gradients to be split
into two bands incorrectly. Mostly a problem on lower-res screens.
* Use per-texture filtering instead of GL sampler objects on Linux,
especially for Mesa drivers that ignore min filter samplers.
This should help prevent blocky/pixellated things like emoji/avatars
* Improve rendering sharpness on low-DPI screens (icons, emoji, images)
On 1.0-DPI screens, emoji/SVG-icons/avatars were minified without
adequate sampling and SVG AA was sub-pixel, producing blocky/aliased
output. This reworks each path and adds optional full-window SSAA.
SVG icons (device-aware AA + round caps):
- draw_svg.rs/draw_vector.rs/render.rs: size the fill & stroke AA
fringe and the curve-flatten tolerance in DEVICE pixels (≈constant
regardless of icon size), so edges resolve via the analytic
d/fwidth coverage and curves stay smooth at any scale; re-tessellate
on scale change.
- triangulate.rs: thread the flatten tolerance through path fill/stroke.
- tessellate.rs: emit round caps as a solid disc (u=0.5) instead of a
radial fade that collapsed to a square at small sizes.
- widgets/icon.rs: don't clip the Icon to its Fit bounds, so round
caps that extend past the box render fully instead of being sheared.
Emoji:
- glyph_raster_image.rs/rasterizer.rs: rasterize color emoji near the
on-screen size with an alpha-weighted box downscale (geometric-mean
scale factor) instead of the font's native PNG strike.
Images / avatars (mipmaps):
- image_cache.rs/texture.rs/draw_list.rs/lib.rs: optionally emit a CPU
mipmap chain (VecMipBGRAu8_32) for non-animated images so minified
avatars/thumbnails sample cleanly. Env-gated MAKEPAD_IMAGE_MIPMAPS;
default on for GL on Linux.
- metal.rs: real per-level mip upload. d3d11.rs/vulkan.rs/web_gl.rs:
safe single-level fallback (no crash; real mips TODO).
Full-window supersampling (optional):
- window.rs: render the whole UI into an offscreen target at
MAKEPAD_SUPERSAMPLE× device resolution and downscale-resolve into the
window. Default 2×, env-tunable, 1× disables. Modeled on the existing
GaussStack render-to-texture path.
* don't unconditionally enable supersampling SSAA of 2x by default
it's too expensive and too slow for most older devices
* cleanup, reduce comment verbosity
* improve SVG anti aliasing
* Windows: fix laggy/juddery scroll performance
- Pace the render loop to the display refresh using a DXGI frame-latency
waitable object and present with vsync, replacing the free-spinning,
uncapped Poll loop that caused uneven scroll cadence.
- Coalesce consecutive WM_MOUSEMOVE messages and paint once per loop pass
to stop the judder when moving the mouse during fling deceleration.
- Cache get_dpi_factor() and the WM_NCHITTEST WindowDragQuery result to
avoid per-mouse-move GetDeviceCaps syscalls and widget-tree hit-tests.
- Throttle XInput/DirectInput polling of empty/disconnected controller
slots, which was stalling the UI thread.
- Rework the momentum fling to a native exponential model with a
frame-interval EMA, and stop the tail auto-scroll from fighting an
active fling/drag.
- D3D11: update the glyph atlas and image textures in place via
UpdateSubresource instead of recreating them on every change, and
spread D3D11 shader-object creation across frames.
- Slug atlas: only force a full re-layout on a width change; append rows
on height growth.
* Windows: correctness fixes from review (off the scroll hot path)
- d3d11: close the DXGI frame-latency waitable HANDLE in Drop (it was
leaked once per main-window lifecycle and the field comment was wrong);
keep popup swap chains at frame-latency 1; track the waitable-swapchain
flag for ResizeBuffers instead of inferring it from the handle; present
without the vsync interval during a live resize.
- windows.rs: poll game input on the idle signal tick so a gamepad button
can be serviced while the app is otherwise idle.
- win32_window / window: invalidate the WM_NCHITTEST / WindowDragQuery
caches on window move and on a caption relayout, with a generation
counter guarding against a reentrant invalidation being clobbered.
- windows_game_input: detect a controller already plugged in at launch via
a one-shot full scan on the first poll, probe slot 0 (Player 1) first,
and offset the DirectInput enumeration so it never stacks with the
XInput probe.
- comment/doc corrections.
* Image cache: accept any Arc<D: AsRef<[u8]> + ?Sized> for async image data
The load_image_from_data_async family required Arc<Vec<u8>>, forcing callers
that already hold the bytes as Arc<[u8]> (e.g. a content-addressed media cache)
to copy the whole buffer via .to_vec() just to satisfy the type. Generalize the
data parameter to Arc<D> where D: AsRef<[u8]> + ?Sized, so those callers can pass
their existing Arc by refcount-clone with no byte copy. The decode path only ever
borrowed the bytes (&[u8]), so this is purely a signature relaxation; existing
Arc<Vec<u8>> callers are unaffected (D = Vec<u8>).
* Linux: GL glyph-atlas in-place texture update + X11/Wayland mouse-move coalescing
* Scroll: unified fling model + native trackpad momentum deceleration
Share one kinetic-scroll model between PortalList and ScrollBar (and thus
ScrollXView/ScrollYView/ScrollXYView) via a new widgets/src/scroll_motion.rs:
- Touch-drag flicks use an iOS-style exponential self-decay, frame-rate
independent via a per-frame integrator with dt smoothing.
- Trackpad scrolling applies the OS momentum directly while fast (responsive,
full native speed), then hands off to a gentler self-decaying tail once it
slows past a threshold, so the deceleration is longer and smoother than the
OS's short, choppy tail. Handoff is seeded at the current speed for a
continuous transition; the seed is clamped against degenerate event timing.
- Add ScrollPhase to scroll events, mapped from NSEventPhase/momentumPhase on
macOS and wl_pointer AxisStop on Wayland; None elsewhere (wheels/X11/Windows
behave as before). MAKEPAD_RAW_TRACKPAD_MOMENTUM=1 bypasses the smoothed tail.
- A press catches an in-progress fling (stops the scroll, consumes the press so
it doesn't also activate a child), matching iOS/Android/macOS.
* Shader codegen: prefix Metal/WGSL locals to avoid reserved-word collisions
The Metal/WGSL backends emitted user-declared shader locals verbatim, so a
local named after a reserved type keyword (e.g. `half`) produced invalid
shader source and failed to compile at runtime. Prefix them with `l_` like the
HLSL/GLSL backends already do.
* TextFlow: don't panic on unbalanced HTML close tags
end_code/end_quote unwrapped the area stack, so a stray `</pre>` or
`</blockquote>` in untrusted content (e.g. a chat message) panicked. Return
early instead, and drop a vestigial per-list-item area-stack push that leaked
an entry and could hand a stray close tag the wrong block's area.
* Scroll: expose fling decel, handoff threshold, & tail-decel as `#[live]` fields
This allows app devs to override the scroll feel per-widget in the DSL,
or globally by overriding the base widget's defaults — verified that a DSL
override takes effect.
* Windows: fix frame pacing, paste crash, and wheel input backlog
- Wait on the frame-latency waitable right before each window's vsync
present instead of on every Paint, so input no longer stalls behind
waits that have no matching present. Drain leftover credits after a
live resize.
- Pasting when the clipboard has no text no longer panics.
- The poll loop now handles up to 32 messages (2 ms) per frame and
merges consecutive mouse-wheel messages, so fast wheels can't build a
backlog that keeps scrolling after the gesture ends. Sleep 1 ms when a
frame presents nothing so animation polling doesn't spin a core.
* Image: don't build unused mip chains; fix stale images in recycled widgets
- Only build the CPU mip chain when a backend actually uploads it
(Metal, behind its env var), and build it on the decode thread instead
of the UI thread. Linux GL still gets its mipmaps via glGenerateMipmap
and now retains less CPU memory per image.
- Recycled Image widgets no longer show the previous item's image or
apply an old decode result. Placeholder textures set via set_texture
(like blurhashes) stay visible while the real image decodes, and a
failed load clears the widget instead of leaving old content up.
* Widgets: avoid needless caption redraws; cheaper PortalList height tracking
- Label::set_text does nothing when the text hasn't changed, and the
window caption title is only synced when it actually changes, so mouse
moves and animation ticks no longer redraw the whole window every
event. The caption centering padding requests its own redraw now.
- PortalList records item heights only when new or changed, and only
re-applies the default height after it drifts by half a pixel, so big
lists don't walk every unmeasured item on every scroll frame.
* Text: cache layouts of long texts; stop cloning glyph outlines every frame
- The layout cache now accepts texts of any length (long messages and
code blocks used to re-layout on every scroll frame). It is a real LRU
with a byte budget on top of the entry cap, and texts drawn in the
current frame are never evicted, so one heavy frame can't thrash the
cache into a permanent miss cycle. The shaper cache is LRU now too.
- Glyph outlines are shared via Rc, so drawing a cached glyph no longer
copies its command list, and outline complexity is computed once when
the outline is built instead of every frame.
* Html: fix stale links/spans in recycled widgets and <details> renumbering
- set_text only rebuilds when the content actually changed, so a
recycled link can't open the previous message's URL, and re-setting
identical content keeps the user's <details> open/closed state.
- Custom widgets and <details> are keyed by their node index instead of
a visit-order counter, so toggling a collapsed <details> can't
renumber the widgets after it and rebind them to the wrong nodes.
item_with_scope also recreates its widget when the template changes.
* Linux: fixed-distance wheel scrolling; Wayland frame-callback pacing
- Wheel scrolling moves a fixed 60 px per detent on X11 and Wayland
instead of a timing-based guess that flipped between 12 px and 240 px
depending on how events batched. Wayland reads real detent counts via
AxisValue120 (wl_seat v9, with AxisDiscrete as the older fallback) and
maps keymaps MAP_PRIVATE as v7+ requires. Touchpads are unchanged.
- Wayland frames are paced with wl_surface frame callbacks and swap
interval 0, so redrawing a hidden or minimized window can no longer
hang the whole app inside eglSwapBuffers (compositors withhold frame
callbacks for hidden windows). Windows with a callback in flight skip
presenting and stay dirty; X11 keeps vsync exactly as before.
* Text: bigger layout cache budget, reclaimed at the end of each frame
A maximal ~60 KB message lays out to roughly 4 MB of glyphs, so the 4 MB
budget couldn't hold even one alongside a normal screen. Raise it to
16 MB, and run eviction at the end of every frame so memory over the
budget is freed one frame after its content leaves the screen, instead
of lingering until some later layout happens to insert a new entry.
* Fix oversized uniform slices: the array lengths were in bytes, not f32 elements
* Wayland: flush buffered mouse motion before scroll events, and drop motion for closed windows
* GL: fall back to non-mipmapped filtering when glGenerateMipmap fails on strict GLES3 drivers
* Text: bucket emoji raster scales so zooming reuses atlas slots instead of re-decoding every step
* Image: add has_content() and record texture provenance on cache-hit loads too
* Scroll: native trackpad momentum, Chrome-model bounce; presses catch motion, never click children
* Dock: redraw the newly selected tab immediately when the active tab is closed
* Html: standard link colors with pressed precedence; skip re-parsing unchanged text; color setters
* Image: don't redraw on cache-hit loads of the already-bound image (per-draw reloaders looped forever)
* Scroll: log macOS momentum-end phase bits to check Cancelled (touch-cut) vs Ended (natural fade)
* Scroll: momentum state machine; flicks survive pagination; edge sentinels & once-per-frame actions
* Scroll: remove the MAKEPAD_SCROLL_DEBUG diagnostics
* Scroll: time-based fling velocity window; pointer fan-out guard; parked flings survive pagination
* PortalList: optional reached-start/end margins (Some(0) default); repositioning re-announces the edges
* Linux/Wayland: honor UI zoom across window resizes; scale caption bar with zoom
Keep the wayland-side window geom in native units so the zoomed dpi isn't
read back as "native" on the next Configure — UI zoom no longer resets or
flickers on maximize/tile. Also let the caption bar height scale with the
zoom (pin to native only on macOS, where the buttons are OS traffic lights).
* Windows: D3D11 fixes for drawlist mgmt
trying to help with the `new_batch` bugs
* draw_list.rs — `set_zbias` now returns whether it changed
* d3d11.rs — uploads draw_call_uniforms on the given condition:
`uniforms_dirty || zbias_changed || buffer.is_none()`
and the zbias advance is hoisted above the early-continues
* Scroll: hard flicks carry farther and boost on re-flick; iOS-style touch rubber band with per-edge bounce gating; Android fling spline behind a flag
* Splitter: redraw both pane subtrees on drag; cached views keep fresh fixed sizes in the dirty check
* iOS: re-deliver window-geometry changes dropped by re-entrant UIKit callbacks; Init only ever from the first draw
* final cleanup fixes. Ensure all examples, experiments, `studio` all work
* Image: skip re-parsing an SVG that is already shown, keyed on the caller's shared bytes
* CachedView: fix upside-down offscreen texture on GL/GL-ES
GL/GL-ES store offscreen FBOs bottom-up, unlike Metal/D3D/WGSL.
The DSL->script-shader migration switched the CachedView composite to plain
.sample() (non-flipping sample2d on GL), so cached views rendered
vertically mirrored on GL/GL-ES; Metal was fine on macOS.
Add a `sample_rt` script sampler (emits the V-flipping sample2d_rt on
GLSL, plain no-flip sample elsewhere) and use it in the CachedView and
CachedRoundedView composites.
* Fix `AdaptiveView::redraw()` to actually do something
libs/tts was never tracked despite being a build dependency of the gamemaker
example. tools/download_tts.sh fetches the public upstream weights (HuggingFace
Kokoro-82M + whisper.cpp) and converts them locally with the in-repo stdlib-only
converter; model artifacts are gitignored.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The parallel batch machinery from 369de6929 only ever existed to chase a
default-on multi-threaded win that never came (washer w8 still +54% with
the hybrid on). At w1 — the only configuration this opt-in flag is for —
parallel_for runs inline, so the serial path gives the identical result
for ~340 fewer lines. Wire up the previously-dead
dynamic_tree_self_pairs/cross_pairs into a serial collect_batch_candidates
(three BVTT self/cross traversals -> canonical (a,b,child) sort -> serial
filter into move_results[0]) and delete BatchWork, BatchCtx, batch_drain_*,
BatchFilterCtx, batch_filter_*, bvtt_step, dynamic_tree_bvtt_drain/expand,
and the batch_frontier/worker_* scratch fields.
Determinism preserved exactly: OFF 0x61E35C31/step314 bit-identical, ON
0xBE99C5F7/step313 identical across workers 1/2/4. The debug SET-equality
oracle and the determinism_broad_phase_hybrid_across_worker_counts test
are unchanged and still pass; zero warnings.
PGO: pgo.sh never trained -bp=1, so an off-path-only profile laid the
hybrid branch out cold and collapsed the win to ~-5%. Add one -b=8 -bp=1
training run (neutral for the default path — counts merge, the OFF branch
stays hot) and retrain.
Corrected README numbers to measured values (hybrid-trained profile,
paired -bp toggle, washer w1): pair-finding stage 7.6k -> 3.6k ms/1000
(-52%); total ~-17% (~19.0k vs ~22.6k), which beats C (20661) and narrows
Rapier's lead from ~23% to ~12% — not the "17.7k / within 5% / -19%"
369de6929 claimed. Still default-off (w8 regresses ~+54%), opt-in
single-threaded accelerator for churn-heavy scenes.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Broad-phase-hybrid subsection (why washer loses, the batch design, the
determinism proof, the single-thread win / multi-thread floor tradeoff,
and the default-off rationale). Washer row in the single-thread rapier
table annotated with the opt-in number (~17.7s, beats C, ~5% behind
rapier → box3d ahead-or-even on all nine single-threaded).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
WorldDef.enable_broad_phase_hybrid (default false; -bp=0/1 bench toggle):
an adaptive batch broad phase for high-churn scenes. When
move_count*4 > proxy_count, replaces the per-moved-proxy tree queries
(8k proxies x 3 root-descents on washer) with three BVTT self/cross
traversals (dynamic self + dynamic x static + dynamic x kinematic) that
share the upper-tree descent, plus an O(n) bottom-up refit instead of
the median rebuild. Both traversal and candidate-filter are parallelized
across the task system (per-worker buffers → merge → canonical sort by
(shape_a,shape_b,child) → deterministic contact creation).
Correctness: a #[cfg(debug_assertions)] SET-equality assertion (batch
candidate set == per-mover set) runs in every test and never fires — the
proof the BVTT finds identical contacts (the hash can't prove it since
creation order legitimately re-baselines). New test
determinism_broad_phase_hybrid_across_worker_counts. OFF hash 0x61E35C31
bit-identical; ON hash 0xBE99C5F7 identical across workers 1/2/4 +
external tasks. 180/186/180/180 tests, zero warnings, profile retrained.
Single-threaded washer -18.7% (17715 vs 21780, broad phase -51%) — beats
C (20661), within ~6% of Rapier (16844). DEFAULT OFF because it regresses
multi-threaded (washer w8 +52%): the batch materializes ~40-50k
candidates/step and serially merges+sorts them (a fundamental floor the
inline per-mover path avoids by filtering in the query callback), so at
w8 the parallel per-mover queries win. Cannot be worker-gated (would
break cross-worker determinism). Correct, deterministic, zero-cost when
off — an opt-in single-threaded accelerator for churn-heavy scenes.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds the C Box3D column to the nine-scene rapier table, all from one
same-window interleaved single-thread run (2026-07-06). Percentages vs
the box3d Rust column. box3d Rust beats Rapier on 8/9 (junkyard flipped
to a +5% win post-tier-2; only washer lost, Rapier's incremental-BVH
broad phase). vs C: within ~7% geomean, ahead on both pyramid scenes,
worst is junkyard +18%. Replaces the derived † junkyard cell with a
direct measurement. Headline updated 7/9→8/9.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
query_tree_for_pairs was materializing every tree-query hit into a Vec
then re-iterating; C runs try_add_pair inline in the query callback
(b3PairQueryCallback). Rewrote to filter inline like C (both world
borrows are shared, so it compiles); only the rare compound inner-query
still uses a child_hits scratch (no compounds in washer/junkyard/
pyramids/trees, so pair-discovery order is unchanged). Removed the
now-dead PairScratch.hits field.
query_tree_for_pairs is washer's single hottest symbol (8k dynamic cubes
churned by a rotating drum re-query the whole tree every step). washer
broad phase -3% (paired plain + retrained-PGO), junkyard -1.4%,
pyramids/trees neutral. Hash bit-identical (0x61E35C31) — pure
structural, same discovery order. 179/185/179/179 tests, zero warnings.
Profile retrained dual-mode.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Instrumentation used to decompose the washer scene (which phase holds
rapier's ~24% advantage over box3d). Timer.rs drops the profiler-feature
gate so PhysicsPipeline's per-stage counters always measure (std Instant
instead of web_time); bench gains --stages (per-phase ms split) and
--probe (per-step contact/pair/sleep counts). Diagnostic tooling only;
no effect on simulation. Findings: washer's rapier advantage is entirely
broad phase (box3d ~8.5s vs rapier 1.7s), box3d's narrow phase is
actually faster than rapier's.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Derived cells marked with a dagger and the derivation stated: cold-window
baseline x the same-binary paired improvement (thermal-drift-immune);
direct cold-window rerun will replace them. vs C: junkyard +17%->+7% w1,
+22%->+12% w8, geomeans +6%/+8%. vs rapier: junkyard -8% -> ~parity,
geomean +34%, washer now rapier's only win.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
New middle tier between full manifold recycling and the full SAT, behind
WorldDef.enable_feature_recycling (default true; OFF path bit-identical,
hash 0x61E35C31 verified):
- Case A, separated-witness early-out: a previously-non-touching contact
revalidates only the cached winning axis; still separating beyond the
speculative distance means done in one test. Sound structurally: any
cached axis is a valid separation witness (understates only, which
falls through to the full SAT). Carried junkyard: 24k skips/step,
full SATs 25.4k -> 4.5k per step.
- Case B, touching feature rebuild: re-clips the cached winning feature
under explicit staleness bounds (SATCache::sat_pose at last full SAT,
translation < 4x recycle distance, rotation < ~4.6 deg, forced refresh
every 8 steps); degenerate rebuilds and touching<->separated
transitions fall through same-step.
Probe-driven (junkyard: 89k full SATs/step on 105k pairs, 13k touching;
rapier maintains 3.4x fewer pairs): paired same-binary -fr=0/1 A/Bs show
junkyard -8% in every pairing (collide phase -15%), washer neutral to
-5%, pyramid/rain guards neutral, OFF costs nothing. Same-session
cross-engine junkyard: rapier's -8% lead closes to ~-3%.
pgo.sh now trains BOTH modes (single-mode training starved the remaining
full-SAT path); checked-in profile retrained dual-mode. SATCache pose
serialized in snapshots. feature_recycled_contact_count in Counters.
README: port-extension subsection, soundness argument, updated notes.
Also: rapier bench --probe mode from the workload-probe session.
179/185/179/179 tests green with the tier ON, zero warnings,
determinism suite passes across runs/workers/task systems.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- libs/rapier/crates/bench now mirrors every box3d benchmark scene
(trees100/50/25, junkyard, rain, washer added to large_pyramid/
many_pyramids/joint_grid), same -b indices as the box3d benchmark.
Geometry, densities, filters, spawn cadence and joint counts match;
body/collider/joint counts verified equal on all nine scenes.
- Fix an index-out-of-bounds panic in the vendored rapier simd-stable
constraint grouping (interaction_groups.rs): bodies in a different
island than the interaction (kinematic drivers, dynamics mid
island-merge) indexed the wrong island's conflict masks. Out-of-island
bodies are now exempt from conflict tracking, matching the solver's
existing boundary treatment (bounds-checked gathers, dropped scatters).
Original three scenes reproduce their previous timings after the fix.
- README: full nine-scene single-threaded matrix vs rapier (box3d wins
7/9, +33% geomean; rapier wins the hull-churn scenes junkyard/washer)
with comparability caveats for the extended scenes.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Geomeans over the nine real scenes: +7% w=1 / +9% w=8. The scene stays
in the benchmark binaries (upstream suite parity); its fixed-overhead
story is kept in the known-remainder notes.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
