Session log for the "freezes on a kill" diagnosis (the cause is the camera, not
CPU: shake is integrated by the follow filter, the hold is frame-counted, and the
hit + kill packages stack on the lethal frame) and for the Track B allocation work
the operator selected.
Gotchas archive gains nine dated entries, incl. two that changed how the work was
ranked: GC.GetTotalMemory quantises to 4 KB and is useless for allocation
attribution (use ProfilerRecorder), and an editor-only IMGUI dev tool self-spawns
into Game.unity and dominated every editor-side measurement.
CLAUDE.md: one new pooling/per-frame-cost line, paid for under the net-zero rule by
dropping the DR-051 build-palette text (that code died with the purge), the two
purge enumerations now carried by their DRs, and a duplicated ACES clause.
40183 bytes, under the 40960 budget.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Two new MCP-workflow rules earned the hard way during the A0 gate. Paid for by
condensing the enemy-slide history and the LANTERN direction bullet into the
gotchas archive, which also records the full A0-gate lessons.
Corrected while there: the direction bullet still said the engine fork was OPEN
and must be surfaced before world code. DR-053 closed that on 2026-08-07 —
PARKED, Unity stays.
39850 bytes, 1110 headroom.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
CLAUDE.md — it is loaded every session, so its errors cost the most:
- M13: it still said "No world code until the world-model spike passes
its design review" while DR-049 has been `accepted` since 07-13 and the
roadmap says PASSED. A hard contradiction between the two authority
docs, with CLAUDE.md winning by being always-loaded — plausibly part of
why Phase 2 never started. Now points at the build spec, warns it needs
re-anchoring, and links the parked engine fork.
- Records the H2 hazard as a rule: a socket whose SparkId is missing from
the baked AbilityDatabase silently reads Damage/Range/Cooldown 0.
- L12: the asmdef table was stale on all four rows; also notes the fifth
compilation unit (Scripts/Editor has no asmdef) and that tests now
reference Authoring.
- M19: per-machine setup — the machine-loss recovery checklist — was
missing Blender + blendermcp (which the committed /art-dev skill
hard-requires) and ctx7, and claimed a ${CLAUDE_PROJECT_DIR} in
.mcp.json that isn't there.
- Structures / harvest / persistence / BefourStudios bullets rewritten:
they described deleted subsystems.
- Net-zero rule honoured: the additions pushed it to 41,057 (over the
40,960 hard limit), so two long art-pipeline bullets moved verbatim to
the gotchas archive under a dated heading. 39,661 now — inside the
file's own 39,936 soft ceiling.
- M14: DR-053 files the Bevy fork as PARKED. The guide was reachable from
NOTHING — one file, zero inbound links, and its gating instruction
lived only in machine-local memory, which CLAUDE.md explicitly forbids
as a sole home. It now has a committed home and inbound links.
- DR-054 records this purge, including the three files that were in the
delete set until their consumers were checked and turned out to be
load-bearing.
- M15: 13 superseded DRs re-statused with `superseded_by`. Only DR-002
carried the field before, though the project's own template prescribes
it.
- M19: Home.md stated three wrong facts (latest DR, latest session, date)
— refreshed. Pillars.md and Systems_Index.md now carry warning banners:
both assert things the purges falsified, and Systems_Index still claims
to be "the accurate map of what exists in code today".
- L11: the 4 genuinely-broken wikilinks fixed (typo'd DR filenames). Zero
broken vault-internal links now.
- Session log written — the last three commits before today had none,
breaking the protocol's own bookend rule.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The 13 vault notes were left dirty by basic-memory back-filling
title/type/permalink frontmatter into files written with Write/Edit
(it also strips the trailing newline — restored here so future diffs
stay clean). Content is unchanged; verified frontmatter-only.
packages-lock.json is the com.coplaydev.unity-mcp #main branch ref
silently re-resolving. Pinning that dependency lands with the package
cleanup batch.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Session log for the 07-24 character work. Adds cookbook 14-E: the per-instance _BaseColor override
gotcha (hit-flash sets URPMaterialPropertyBaseColor=(1,1,1) on player/enemy render children, replacing
the material _BaseColor -> flat null-map materials render cream; color via a solid _BaseColorMap texture).
Corrects the older 'clear the map -> uses _BaseColor' note.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Session 2026-07-15: the 5-Spark systems, content, and enemy-test-gym CODE done
(497 EditMode green); the fresh Gym.unity scene assembly + the L3 feel gate remain.
Roadmap Phase-1 status updated. Reusable gotchas banked (reel via re-aimed
KnockbackState; GymTag bypasses the meta spawn guard; manage_scriptable_object
target-object quirk).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Defer the in-game skinned-enemy animated check to a purpose-built semi-permanent
gym scene (Phase 1's 'no world - a gym') with spawn-a-chosen-enemy tooling, rather
than hacking the shared wave roster. Survives the coming enemy-system rework; the
3 skinned prefabs are ready to drop in.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
animationType=Human (enum 3, not Generic); CharactersAvatar.isHuman=true.
CLAUDE.md correct; the grounding agent misread the enum.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A0: all 3 master shaders now present (Emissive-Gloam authored as HLSL w/
in-shader flicker). A1: skinned recipe proven for a LANTERN creature
(EnemyRigTools.BuildDrowner -> EnemyDrowner.prefab); in-game animated run +
custom-kit reattach + suit/2nd-creature still open. Flags the Generic-vs-
Humanoid rig-type discrepancy vs CLAUDE.md to reconcile.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Phase-0 status + Workstream A0/A1 callouts: the in-engine ArtStaging style-proof
scene is built (prop+creature+suit triad under murk + light-is-territory pool
lighting, passes full/200px/grayscale); statics recipe validated in-engine;
skinned Rukhanka bake + 3 master shaders still open.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
New /art-dev skill (SKILL.md + blender-cookbook + style-and-practices refs)
driving LANTERN Blender art work: Auto (headless) for simple changes, the
hybrid nudge-and-bake loop for precision/aesthetics, game-camera verification,
Blender-beginner coaching. Session log covers the A0 style-proof asset set +
the Bathynaut refinement.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Records the A0 material foundation + Phase 1 Group A implementation (steps 1/1b/2/2.5:
socket data model, per-socket stats, AbilityFireSystem restructure + SpawnId repack, feel-layer
migration), 494 green, the editor-focus correction, and the deferrals (L3 gate, AbilityRef
cleanup, Group B content).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adversarial pre-code review (wf_c7575828-934; 23 agents, 0 failures) over the Phase 1
combat-gym design raised 19 findings (8 CONFIRMED + 11 PARTIAL, 0 refuted) and caught
design-breakers before code:
- SpawnId bit budget exhausted (owner16|fireCount12|fork4) -> repack owner14|socket2|
fireCount12|fork4 so 4 sockets don't collide/desync.
- "KEEP as-is" client feel layer is a real migration (CombatFeedback/PlayerAnimationDrive/
HUD read the reworked AbilityRef/AbilityCooldown) + needs a new replicated class signal.
- predict-spawn is Projectile-only (Aoe/Hitscan/decoy = Cone-precedent server-only spawn);
Blink = velocity-blink in its own system (not a transform teleport); SocketCooldown hot
not cold; EffectiveAbilityStats 4-wide; windup needs a rollback-safe resolve tick;
Harpooner reel + player zone = new server-only code, not salvage.
Verdict: pass-with-changes on all 3 lenses, no redesign. Phase1_Combat_Gym_Build_Spec =
the implementation contract (8-step build order, wire/bake churn, open risks, ledger).
DR-050 records it; pre-review design -> superseded.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The tone bible was authored during the autonomous run but slipped between commit batches;
several already-pushed docs (Phase 7 design, operator questions, session log B) link to it.
Wordless Wicks + lamp-morse; per-voice register bounds (Keeper/Siren/Selkie/Klabautermann/
Anchorite/berths); warmth-against-dread; gates all bark generation.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adversarial design review (wf_aa6fb661-e25; 22 agents, 0 failures) over the world-model
proposal + ground-truth code raised 18 findings (12 CONFIRMED + 6 PARTIAL, 0 refuted) and
caught real design-breakers before any code:
- DP-1/RS-1 (HIGH): the seed model was self-contradictory (RunMapMath regenerates the WHOLE
graph per seed, incompatible with a persistent pinned prefix) -> split: graph topology is
a pure function of WorldSeed ONLY; DescentSalt re-knots content; pinning freezes PinnedSalt.
- NR-2/RS-3 (HIGH): salvaged respawn warps a dead Wick to base -> splits the co-located party
-> in-pocket death; warp gated behind party-wipe; revive is new code, not salvage.
- DP-2 (HIGH): born-correct restore is per-entry lazy replay, not a boot one-shot.
- NR-1 phantom-kill CombatFeedback fix; NR-3 enemy wind-up gated on the light-union;
RS-2 RegionTag->PocketTag is a ~23-site semantic rewrite, not a rename.
World_Model_Build_Spec.md = the review-hardened contract (all 18 folded, findings ledger,
build order, open risks). DR-049 records the decision. Spike -> reviewed; proposal -> superseded.
New forks parked (dark-contact policy, lantern placement, END-1/EB-1 mothball timing).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
kronic