Mythic Masters: open-world frame budget (95th under 16.7 ms, no hitch, a party of six), hill climb to 8/10, rounds 5+ (from #3705) #3709

Score: 3.3/10 (target 8, on the owner's scale: agent judges halve their number, per the 2026-11-05 reset)

The owner's brief (2026-11-05): Mythic Masters' open world must be performant, especially once friends walk it together (#3663). The world is a heightfield continent with three ground patches rebuilt as you walk, instanced plants, a sky dome and weather, flocks and wild food (src/world/, docs/WORLD-EXPANSION.md).

From #3664, #3686, #3701 and #3705 (rounds 1 to 4, PR #3685): the recipe is cd apps/mythic-masters && bun scripts/walk-budget.ts (walkBudget() for a script), and test/budget.test.ts holds it with MM_BUDGET=1. The walk holds fights off (world.peace; round 1's first tables measured a fight arena, see #3686), and reads the heap after a forced collection. Patch rebuilds, the far forest and the grass are laid over frames, and a wild one's beast compiles its shaders before it shows. Last table, party of one: p95 16.7 ms at both sizes, no frame over 50 ms (worst 33 ms; main has 15 and 14 frames over 50 ms); draw calls 99-134 desktop, 66-100 phone; 4.31 M triangles; heap after a collection 13.7 -> 18 MB (the same on main); load 1.1 to 1.3 s, 6.4 MB.

Next: the party-of-six walk as a row in the recipe and in budget.test.ts (frame time, and draw calls and heap against the +12 / +60 MB limits). It caps points 1 and 2. Gizmo (office/gizmo-2fa8) plans party and quality options on walkBudget() once #3685 merges; the low quality tier and plant culling are in #3682 and #3689. Multiplayer itself is #3663.

Goalpost: 8/10 from the owner

Scored on numbers, not taste, so each round prints the same table from the same recipe (bun run probe mythic-masters --js with the mythicMasters handle; a fixed walk of 90 seconds across a region border at a fixed hour, with a party of one and of six shown):

1. Frame time. 95th percentile under 16.7 ms on this Mac's headless Chrome through the whole walk, and no single frame over 50 ms (the patch hitch gone: builds split over frames or moved to a worker).
2. Draw calls and memory. Draw calls per frame and JS heap printed and flat across the walk; a party of six adds at most 12 draw calls and 60 MB.
3. Load. Time to first walkable frame under 3 s on a cold cache locally, and the bytes it took, printed.
4. Phones. The same walk at a phone viewport with the quality knob (@rustybuns/util/quality) on low stays under 16.7 ms at the 95th; no feature only works at high.
5. A budget that holds. The numbers live in one test (test/budget.test.ts) that fails when a round regresses them, so the next climb can't spend them.

The loop

Each round is one PR against main that says "Part of #N" with the before/after table in the body. A fresh judge scores the five points, halves it, and the comment starts Score: x/10 (target 8) and ends Next: ...; then open "rounds N+ (from #N)", close this one with "Moved up to #new". Keep effect out of the per-frame code. At the target, a MANUAL RUN: for the owner's own walk on their phone.