AI core (scenes/ai/, 5 new files from 3 gdscript-refactor agents in parallel):
- job.gd (59 lines, Agent A): Job class, RefCounted, label + toils + cursor +
to_dict/from_dict round-trip
- toil.gd (76 lines, Agent A): Toil class, RefCounted; kinds WALK/WAIT/IDLE;
factories walk_to/wait_ticks/idle; Vector2i stored as to_x/to_y ints
because Godot 4 JSON.stringify doesn't round-trip Vector2i
- work_provider.gd (27 lines, Agent A): abstract base, class_name, @export
category/priority, find_best_for() with push_error subclass guard
- job_runner.gd (186 lines, Agent B): Node-derived runner; setup/start_job/
cancel_job/tick; WALK toil delegates to pawn.walk_along_path on first
encounter (sets data.started=true), listens for walk_completed signal;
WAIT decrements ticks_remaining; IDLE never completes; full to_dict/from_dict
- decision.gd (50 lines, Agent C): static pick_next_job(pawn, providers); 5
layers (incapacitation/forced/status/work/idle); layer 1 probes via
has_method to stay future-proof for Phase 9
- rest_provider.gd (31 lines, Agent C): extends WorkProvider; @export rest_tile;
returns [walk_to(rest_tile), idle()] Job
Integration (Opus):
- pawn.gd: added forced_job slot, job_runner ref, _orchestrate_ai called
before _advance_walk on each sim_tick. Calls Decision when forced_job is
queued OR when idle — was a bug initially (only-on-idle never preempted
the never-completing IDLE toil); fixed and caught via MCP runtime test.
Added to_dict/from_dict for save round-trip; captures tile, _path,
_step_progress, _selected, forced_job, job_runner via their serializers.
- selection.gd: rewrote to build a forced-job [walk_to + idle] and set
pawn.forced_job; Decision preempts current job on next tick.
- world.tscn/gd: instantiates RestProvider as child (rest_tile = (50,50)
just outside the stone ring's south-east, reachable from all 3 spawn
tiles); registers via World.register_work_provider; attaches a JobRunner
child to each spawned pawn and wires setup(pawn, pathfinder).
- world.gd autoload: added work_providers list + register/clear methods.
- save_system.gd: write_save walks World.pawns calling to_dict; apply_save
zips dicts to pawns by index (Phase 16 will add stable IDs).
- main.gd: bootstrap log line bumped Phase 2 → Phase 3.
Acceptance — MCP-verified end-to-end:
- 3 pawns boot, Decision assigns each Rest, JobRunner starts each,
all 3 walk to (50,50) on different paths (40/35/30 steps based on
detour around the stone ring), arrive and idle.
- Force Bram to (10,10) via pawn.forced_job; preempt fires:
[decision] Bram: forced 'Go to (10, 10)'. Bram walks while Cora/Edda
stay parked.
- Mid-walk save round-trip (the critical Phase 3 acceptance):
- Paused Bram at (51,10) walking to (70,70) with 79 path steps remaining
- SaveSystem.write_save() → SaveSystem.apply_save(read_save()) after a
mutate-to-(0,0)-with-no-path round-trip
- Restored Bram exactly: tile=(51,10), _path.size=79, walking=true,
job='Go to (70, 70)' at toil_idx=0 (WALK toil with data.started=true)
- Resumed sim → JobRunner's WALK toil saw started=true and did NOT
re-call walk_along_path; the pawn's restored _path continued the walk
naturally → reached (70,26) with 44 steps remaining, still on the
same job. The architecture.md 'mid-toil suspend safe' contract is
provably honored.
Phase 3 gotchas (logged in implementation.md):
- Class-name registration timing bit again (Phase 2 gotcha). Workflow:
agent writes class_name file → MCP reload_project → headless validate.
- Forced-job preempt requires triggering Decision when forced_job != null,
not just when idle (IDLE toil never completes).
- execute_game_script + await Engine.get_main_loop().process_frame is
flaky — MCP auto-recovers but the script's last lines may be lost.
Workaround: split state-inspection into a fresh execute_game_script.
Delegation report this phase:
- gdscript-refactor (Sonnet) Agent A: Job + Toil + WorkProvider abstract
base. 3 files, 162 lines.
- gdscript-refactor (Sonnet) Agent B: JobRunner with toil-execution match
+ walk_completed signal handling + full save round-trip. 1 file, 186
lines.
- gdscript-refactor (Sonnet) Agent C: Decision pipeline + RestProvider.
2 files, 81 lines.
- Opus: Pawn integration (forced_job slot, orchestration, to_dict/from_dict),
Selection rewrite, world.tscn/gd wiring, World autoload work_providers
list, SaveSystem extension, MCP-driven runtime verification including
the mid-walk save round-trip demo, gotcha logging.
~70% of Phase 3's GDScript was written by subagents.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Pawn (scenes/pawn/{tscn,gd}, ~108 lines, gdscript-refactor agent):
- Node2D root (no physics — grid-snapped lerped motion); name + state labels
- _draw() paints body disc with hue derived from name.hash(), dark outline,
yellow selection ring when selected
- Clock = EventBus.sim_tick: each tick advances _step_progress by 1/10;
at 1.0 snaps tile to next waypoint, pops path. STEP_TICKS = 10 →
1 tile / 0.5 s at 1×, scales with Sim speed for free (pause/Fast/Ultra)
- _process() lerps render position between current and next tile every
render frame for smooth visual between sim ticks
- Public API: setup, walk_along_path, is_walking, set_selected,
signals walk_started/walk_completed/arrived_at_destination
Pathfinder (scenes/world/pathfinder.gd, ~110 lines, gdscript-refactor agent):
- AStarGrid2D wrapper, 80² region, DIAGONAL_MODE_NEVER (Rimworld
4-directional), Manhattan heuristic
- API: setup, set_cell_walkable (emits walkability_changed signal),
is_walkable, find_path (excludes start tile, includes end), benchmark
- find_path returns empty Array[Vector2i] for OOB endpoints, solid
destination, or disconnected areas
Selection (scenes/world/selection.gd, ~85 lines, Opus):
- Lives as a Node child of World; _unhandled_input handles mouse clicks
- Click-vs-drag discrimination: 8 px max drift + 300 ms max duration →
drags belong to the camera, only true clicks select/command
- Click on pawn → select (yellow ring); click on walkable empty tile
with a pawn selected → pathfinder.find_path + pawn.walk_along_path
World autoload (autoload/world.gd):
- Added pawn registry: register_pawn, unregister_pawn, pawn_at_tile, clear_pawns
- Untyped Array (Array[Pawn] hits Godot's class_name-not-yet-registered
timing in autoload init; duck typing fine for current consumers)
World scene (scenes/world/{tscn,gd}):
- Pathfinder + Selection nodes added as children
- _ready() wires: pathfinder.setup(MAP_SIZE_TILES), walls → pathfinder
(28 cells from 8×8 stone ring marked impassable), selection.bind(pathfinder),
spawns 3 pawns (Bram/Cora/Edda) at (20/25/30, 40), runs spike benchmark
- main.gd bootstrap line bumped Phase 1 → Phase 2
i18n: 2 new keys (pawn.state.idle, pawn.state.walking)
Spike result — AStarGrid2D path-query timing at 80²:
- 36 paths (all 4-corner pairs × 3 iterations)
- min 6 μs, avg 9.1 μs, max 18 μs
- ~55× faster than the 'sub-millisecond' target in architecture.md
MCP runtime verification:
- play_scene → 3 pawns visible with distinct hashed-hue body colours
- execute_game_script: pathfinder.find_path((20,40)→(50,40)) returns
38-step path (30 straight + 8 detour around the ring)
- bram.walk_along_path(path) → screenshot caught him mid-walk on south
side of ring with state='walking' + selection ring visible
- arrival snapshot: state='idle'
Phase 2 gotcha (documented in implementation.md): class_name registration
happens at editor scan-time, not headless-load-time. First headless run
after authoring class_name files fails until reload_project rebuilds the
global class cache. Workflow: agent writes → MCP reload_project → headless
validate. Documented for future phases.
Delegation report this phase:
- gdscript-refactor (Sonnet) #1: Pawn class — scene, script, draw logic,
movement loop, i18n keys. ~108 lines pawn.gd + 22 lines pawn.tscn.
Headless-validated by the subagent (note: validated before world.gd's
Pawn reference was added).
- gdscript-refactor (Sonnet) #2: Pathfinder class — AStarGrid2D wrapper,
4-dir Manhattan, benchmark utility. ~110 lines pathfinder.gd. Headless-
validated by the subagent.
- Opus: Selection module + World autoload registry + scene integration
(world.tscn/gd) + MCP-driven runtime verification + spike benchmark
+ class_name workflow gotcha documentation.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Project scaffold:
- project.godot at repo root, GL Compatibility renderer (max mobile reach),
pixel-snap on, texture filter nearest, sensor_landscape orientation
- 7 autoloads: World, Sim, GameState, EventBus, Strings, Audit, SaveSystem
- scenes/main/main.{tscn,gd} smoke-test scene with autoload assertions
- Folder layout matches tavernkeep idiom: autoload/ at root, scripts
co-located with scenes/ (not the scripts/autoloads/ mirror originally
sketched in implementation.md)
- Input map: pause, speed_cycle, speed_normal/fast/ultra, confirm, cancel.
Mobile gestures (pinch/drag/long-press) handled at script level via
Godot's InputEventScreenTouch/Drag/MagnifyGesture.
- SaveSystem skeleton: SAVE_VERSION=1, JSON to user://save_slot.json,
version-mismatch warning. Phase 3 expands to real entity state.
- icon.svg placeholder (cabin silhouette on dark green field)
- README.md points at memory.md / implementation.md / docs/
Headless verification: 'godot --headless --path . --quit' exits 0,
'[main] Phase 0 smoke test online.' prints, no errors. Editor-side
green-dot check still pending — needs human launch of editor.
Asset audit (researcher Haiku, 2026-05-10):
- FG_Houses.png NOT autotile-solvable — pre-built decorative house
compositions, 4 distinct roof palettes, no modular wall family.
~½–1 day per material to author terrain bits on top.
- FG_Fortress.png IS autotile-solvable — ~20–30 modular tan-stone
pieces. Wang-style Godot 4 terrain works with minimal extra art.
Iconic Homestead $19.99 fallback not needed.
- No wolf sprite anywhere in the bundle. EvoMonster packs all
cute/fantasy. Need commission, CC0 source, or Ventilatore check.
- Retro Graveyard 16x16 [Kingdom Explorer] confirmed in Tier 3 with
full graveyard suite — direct use in Phase 14.
New open questions surfaced in memory.md:
- Player-built wall material strategy (3 options laid out)
- Wolf sprite acquisition path (Phase 10 blocker)
Project move:
- Repo physical location moved from ~/claude/projects/rimlike to
/mnt/d/godot/rimlike (D: drive, fast for Windows-side editor).
- Symlink at the original WSL path preserves the home-CLAUDE.md
layout convention. Mirrors tavernkeep's pattern.
- Set core.filemode=false to silence DrvFs's everything-is-0777
false-positive on git diff.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
