AGENTS.md only described the Blender packs. Add the two skill sets that shipped
with the project since:
- 31 Unreal Engine packs (MIT, quodsoler/unreal-engine-skills f3742d7) at
.agents/skills/ue-*/, targeting UE 5.8 C++, with ue-project-context as the entry
point and a discipline mapping to this project's work.
- The cpp router (MIT, DiamonDinoia/skill-cpp f2617fb) at .agents/skills/cpp/, for
general C++11-23 against the Core Guidelines; the project is C++20.
One directory with sixty scripts stopped being navigable, and the grouping is also the sandbox boundary:
Tools/unreal/ commandlets and the two map builders, with ue_common.py and ue_placement.py as the
shared imports (they need the engine)
Tools/blender/ builders, exporters, the FBX preset, the MPFB character pipeline, blender_screenshots
(they need the Blender Flatpak)
Tools/review/ the visual loop: render_screenshots.sh, judge_screenshot.py, hero_compare.py,
build_comparison_md.py, e2e_asset_check.py, hero_iterate.sh, visual_loop.py,
visual_targets.json
Tools/gen/ image and texture generation: the ComfyUI driver, deterministic texture writers,
reference fetching
Tools/input/ OS-level input injection
root _common.py, check-lfs.sh, addon_compat_probe.py, sibling_asset_audit.py, tests/
Every moved script now resolves the repository root as ../.. and puts the tools root plus its siblings on
sys.path, so 'import ue_common' still works from unreal/. The test suite bootstrap does the same for the five
folders. render_screenshots.sh takes the folder as a third argument to run_cmdlet, and the e2e driver,
hero_iterate.sh and the comparison generator were repointed.
51 README rows now link to their new location, the README gains a Layout section naming each folder's
sandbox, and the architecture notes and Blender README follow the moves.
Verified: 108 tests pass, prettier is clean, judge_screenshot.py and hero_compare.py run from their new
homes, and the e2e run was aborted mid-way (it had been rebuilding an empty DemoMap for 15 minutes) and is
being rerun against the new layout.
The 94 symlinks in ~/.agents/skills and the full second copy in
~/.pi/agent/skills/blender-skills were the same packs under two roots, so Pi
reported a collision for every one of them on every start and silently dropped
the loser.
- The 93 upstream packs, the shared references/ notes and the LICENSE now live
once, flat and one level down, in the common agent folder ~/.pi/agent/skills/.
- The repository keeps only the project-specific pack:
.agents/skills/blender-skills/blender-director/. Its ../references/ links now
point at ~/.pi/agent/skills/references/ because it no longer sits beside them.
Its SKILL.md declared metadata.role twice (specialist, orchestrator), which is
fatal YAML - the pack had never actually loaded.
- AGENTS.md and Docs/toolchain.md describe the split and warn against copying the
common packs back into the repository.
Verified by walking all three discovery roots and parsing every frontmatter:
97 skills loaded, 0 malformed, 0 collisions.
Screenshots/README.md on this branch still used the path-only table, so a reviewer
had to open six PNGs to judge a pass. Every shot now has its own section with the
image embedded, its view, expected content and both verdicts, plus a status table
at the top that links to them.
The known-issues list becomes a table of issue -> version and item that owns it:
pale hero stone, hero entrance doors, the bind-pose animation defect, unproven
camera collision and the terrain-as-pavement strip all point at their TODO owner.
Two stale entries removed: the theatre marquee exists (six trim actors staged) and
'materials not yet created' contradicted the scene conventions.
AGENTS.md now says the README is updated with every visual change, that the image
is embedded inline, and that approval ticks both the section and the table row.
Also removed an orphan: review-demo-retail-frontage.png had been re-copied into
this branch by the capture step although its geometry only exists on
facade-retail-0.1.6.
Owner decision: prioritise realism, keep the performance target but put it last.
Re-applied on a branch after the first attempt landed directly on main (reverted
there; see b8209ce).
- Quality goals (01 + combined architecture.md): 1 visual realism, 2 geographic
fidelity, 3 walkability/usability, 4 reproducibility/portability, 5 provenance,
6 performance efficiency.
- Quality requirements (10 + combined) reordered to match, with two realism
requirements added (a façade reads like the photographs; placement within ~1 m)
and the scenarios renumbered so QS-1 is the reference comparison, QS-9 the frame
rate.
- Guard on both documents so the order cannot become an excuse: performance is a
floor, not a preference - 60 FPS at 1440p without frame generation must be met at
every release; if realism cannot fit, cut the realism scope deliberately and
record it, never the frame rate. Walkability outranks realism in one direction: a
block you fall through is not a demo.
- Solution strategy and 'quality achievement' lead with realism and describe
performance as a budget, not a driver.
- Docs/release-checks.md: the performance check is the last section and the per-
version check list now opens with realism and closes with performance.
- ROADMAP gains a 'Quality priority' section; AGENTS.md gains the tie-break rule
beside the existing scope-cutting rule.
Owner decision: prioritise realism, keep the performance target but put it last.
- Quality goals reordered (01 + combined architecture.md): 1 visual realism,
2 geographic fidelity, 3 walkability/usability, 4 reproducibility/portability,
5 provenance, 6 performance efficiency.
- Quality requirements (10 + combined) reordered to match, with two new realism
requirements (façade reads like the photographs; placement within ~1 m) and the
quality scenarios renumbered so QS-1 is the reference comparison and QS-9 the
frame rate.
- Both documents carry the same guard so the order cannot become an excuse:
performance is a floor, not a preference - 60 FPS at 1440p without frame
generation must be met at every release; if realism cannot fit, the realism scope
is cut deliberately and recorded, never the frame rate. Walkability outranks
realism in one direction: a block you fall through is not a demo.
- Solution strategy and 'quality achievement' now lead with realism and describe
performance as a budget rather than a driver.
- Docs/release-checks.md: the performance check is the last check, with that reason
stated; ROADMAP gains a 'Quality priority' section; AGENTS.md gains the tie-break
rule beside the existing scope-cutting 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