Researched the sibling project's tooling discipline (tools/README inventory,
tools/tests with stdlib unittest, check_docs gate, clean-worktree rule, paid-API
tools human-triggered) and encoded it for this repository:
AGENTS.md gains two sections.
- 'Python and shell tooling': fix the tool not the artefact; improve over fork;
one script one job; fail loudly; result files for Unreal commandlets; absolute
paths into sandboxes; clean worktree for generators (.blend/.umap are
read-only on checkout); network/paid tools human-triggered with 429 back-off;
measure don't assert; document every tool in the README inventory; test the
pure parts.
- 'Architecture documentation': Docs/Architecture is arc42 in Markdown; a table
mapping each kind of change to the section that must be updated; describe what
exists, ADRs append-only, keep architecture.md in sync, prettier --check.
Made the referenced scaffolding real rather than aspirational:
- Tools/tests/ (README + __init__) with 12 passing unittest tests covering
input_emulation's ioctl/key-code encoding and block_height_report's height
classification.
- requirements-tools.txt (requests).
- Extracted classify_height() out of block_height_report.main() so the roof/
shelter rule is testable — the rule itself came from the v0.1.2 finding.
- Tools/README: tests section, input-injection rows, and the removed TEMP-QA row
replaced by the real cvar/self-test description.
- Docs/Architecture 05 + architecture.md: tools table extended (input injection,
tests) and a link to the tool rules; kept in sync per the new rule.
Drop the OpenStreetMap/ODbL attribution requirement, the Google imagery rule,
and the related F-4 requirement, risk R-4, release check, and TODO items across
AGENTS, PLAN, ROADMAP, README, setup, architecture sections, and manifests.
OSM data is now documented as local private use only. Also normalize
numbered-list indentation in the architecture docs.
- Converted 13 individual .adoc section files to .md via
asciidoctor→docbook5→pandoc(gfm) + post-processing, placed alongside
the .adoc sources in Docs/Architecture/
- Rebuilt architecture.md from the individual section .md files
- Ran prettier --write on all .md in the repo (23 files changed):
normalised table column alignment, trailing whitespace, line breaks
- Added .agents/ to .prettierignore (vendored third-party content)
- All .md now passes prettier --check
- Tools/judge_screenshot.py: judges a screenshot against an expected-scene
description via OpenRouter multimodal image understanding, reading
OPENROUTER_API_KEY from the ignored .env. --image+--expect for one shot,
--shots to run every review shot in Screenshots/README.md. Returns a
{verdict, confidence, reason, missing} JSON.
- Documented in AGENTS.md (Visual review pre-check step) and Tools/README.md;
recorded the OpenRouter payload format gotcha in MEMORY.md.
Split the former ROADMAP.md checklists into TODO.md, which now holds
all actionable work and progress marks. ROADMAP.md keeps milestone
goals, scope, and release gates as prose with no checkboxes.
Update AGENTS.md, Docs/, Geo/README.md, MEMORY.md, and README.md to
point to the new file roles.
- Drop the /Screenshots/* gitignore exclusion so review PNGs are committed
(LFS-tracked) alongside the review README.
- AGENTS.md Visual review: PNGs are now committed, not kept only on disk.
- 13 review/demo screenshots tracked (25 MB LFS).
Geo/tools/ is now every geographic script, with Geo/README.md documenting each
one; the Blender-side builders moved beside their outputs in Art/blender/*/ and
import their helpers from Geo/tools/osm_common.py.
That module gains to_unreal_local() and to_blender_local(): the only place in the
repository that multiplies metres by 100, so a second silent scale cannot be
introduced. block_height_report.py adds height provenance for the block — 3 of
15 buildings have no height data and render at a placeholder 6.4 m.
asset_metadata.py writes and audits <asset>.geo.json sidecars; four now exist
(hero-facade, terrain, street, blockout) and the audit recomputes each centre from
the origin, failing anything that disagrees.
AGigLineCharacter: 1.75 m capsule, 1.60 m eye camera, 4 m/s walk, mouse look
scaled in degrees per second (no double DeltaTime), jump. Loaded ahead of a
Blueprint so the demo is playable with no assets wired by hand.
Tools/ue_create_input_assets.py builds /Game/Input headlessly: five 1D actions
and an 11-mapping context. One action per direction instead of per-key modifiers,
because modifier objects do not survive the save path here: a mapping's modifier
array serialises None, and dimensioning a 2D move with per-key axis masks would
need exactly those modifiers. The cost is four action assets rather than two.
Also adds a fourth review camera at eye height and documents it; its approval is
pending.
- AGigLineShotActor (dev-only): walks a fixed camera list in -game mode,
captures via FScreenshotRequest, quits. Test content only.
- ue_build_review_map.py builds /Game/Test/ReviewMap from current content
(gray floor, key light, sky, MPFB character, 1 m scale cubes).
- render_screenshots.sh: build map -> run game -> collect PNGs into
gitignored Screenshots/.
- Screenshots/README.md (committed) describes each capture with approval
state; AGENTS.md gains the visual-review instructions.
AGENTS.md now states that planned work is checkbox items in ROADMAP.md marked
open, in progress, or done, and that discoveries, gotchas, notes, and bugs go to
MEMORY.md for coordination between collaborators. MEMORY.md is seeded with what
this build-up actually cost: the Unreal read-only-home crash, Blender/Blosm
headless workarounds and the spherical projection, the tiled-TIFF DEM trap, the
reference licensing and throttling rules, and the LFS silent-blob trap.
Also stages the concurrently created Unreal project files, and stops per-project
Build/ output (FileOpenOrder logs) from entering the repository.
Reference images are development-only material: licensing is not a gate for
local private use, so they are simply never committed. Art/reference/ is now
gitignored; the licensed status of anything shipped is still recorded in
THIRD_PARTY_NOTICES.md.
Adds Tools/commons_fetch.py, which fetches Wikimedia Commons imagery by search
or exact title and writes a provenance sidecar, plus Docs/reference-notes-hollywood.md
recording what each local set is evidence for.
Create Game/, Art/, Geo/, Tools/, Docs/ with LFS and ignore rules, record the
workstation audit, toolchain pins, setup checklist, release checks, and
licensing policy. ROADMAP 0.1.0 environment tasks marked to match verified state.
zwitschi