A 3D model pipeline, pushed by Gemini 4 Argon
- agent
- Antigravity CLI
- model
- gemini-4-argon-high
- harness
- Antigravity
- started
- 2026-11-15 01:52 UTC
- took
- 79 min · 492 turns
user
+0:00Your brief is in ~/context/brief-lowmarch-full.md. Read it in full and carry it out.
agent
+0:00read_file{"Path":"~/context/brief-lowmarch-full.md"}
input
{ "Path": "~/context/brief-lowmarch-full.md" }result, 32 lines
Showing lines 1-31 of 31 1: You are running as Gemini 4 Argon (gemini-4-argon) at effort high, in a session of your own. The owner, severian (they/them), asked to see what Gemini 4 Argon would do with one of their lines of work, lowmarch, and to see one visual artifact you can make with what the project already has. The project's own session runs on a different model and is not to be touched; you are a separate, parallel look. 2: 3: ## What lowmarch is 4: A code-built anime character pipeline for a tactics game: VRoid bases reshaped in code, costumes, armour and hair generated in code, drawn by the project's own renderers (a painted three.js renderer is the target; the pixel renderer is abandoned). On 11-08 the owner decided to restart with one character from scratch, to find a faster, better way of working together; they haven't started yet. 5: 6: Read, in this order: 7: 1. `docs/handbook.md` in your worktree (entry point: each rule marked earned or guessed; guessed rules don't bind the restart) 8: 2. `~/context/reflect/lowmarch.html` (the 11-08 reflection; the box at the top is the restart plan) 9: 3. `~/context/lowmarch.md` (state, how to run things; numpy is in the user site, so run python3 without -I) 10: 4. `docs/portrait-guide.md`, `docs/vroid.md`, and whatever else in the repo you judge useful. 11: 12: ## Your workspace 13: - Your current folder is the git worktree `~/work/lowmarch` (branch `argon`, made for you from master a97f25f). Work only here; you may commit here. Never touch any other repo. 14: - Data lives in `~/.local/share/lowmarch/`: read it, don't modify it. 15: - Output folder: `~/out/` (copied to the owner's review route afterwards). 16: - Licences: the Yin/Yang rigs are personal-use study material (keep them out of the visual); FE8 references are study only, never traced or shown; VRoid CC0 bodies and the AvatarSample faces are fine for renders. 17: 18: ## Rules 19: - Headless only: no windows on the owner's desktop. Never run anything that drives Windows programs (no tools/winvroid, no powershell.exe, cmd.exe or anything under /mnt/c). Browser rendering via headless Chromium only (Playwright is at `~/context/sortie-node_modules/playwright`; page-side code compiled by tsx can throw "__name is not defined", so keep page-side code as plain .js evaluated as text). Blender only with `-b`. 20: - Don't install packages. Don't run the full test suite (a test run once ate 36 GB); targeted checks only. 21: - Nothing runs on the C1 machine; no ssh. No network uploads, no publishing anywhere. Never push. 22: - Edit files only in your worktree and your output folder. Never push. 23: 24: ## Deliverable 25: One self-contained HTML page, `index.html` in your output folder, with its images (or a short clip) beside it. The owner finds wordy interfaces tiring: organise, don't narrate; short labelled sections, plain words, no em dashes. At the top: "Gemini 4 Argon (gemini-4-argon), effort high" and the date. 26: 1. **Your read of this line of work:** what's working, what isn't, what you'd keep and drop, and what you would do differently in the restart. Give opinions plainly; disagree with the reflection page where you do. 27: 2. **What you'd do next** if you ran the restart's first session: a short, concrete sequence. 28: 3. **The one visual:** a single visual artifact made with what the project already has (its tools, kits, renderers, models, data). Your choice of what it is; pick the thing that best shows what you'd do with this work. Show it large, then say in a few lines how it was made (the commands, wall time) and what you'd change next. 29: Keep it to one visual; don't build a gallery. Aim to be done in roughly 90 minutes of work. 30: 31: When done, end your turn with: the page path, a 5-line summary, and any commits on your branch. If something only the owner can decide blocks you, say so and stop rather than guessing.
agent
+0:13reasoning
Reading the provided documents sequentially to understand the project's structure and relevant information. This includes the handbook, HTML context, and markdown files. The goal is to establish a solid grasp of the project's goals, methods, and structure.
read_file{"Path":"~/work/lowmarch/docs/handbook.md"}
input
{ "Path": "~/work/lowmarch/docs/handbook.md" }result, 227 lines
Showing lines 1-226 of 226 1: # Lowmarch handbook 2: 3: For whoever picks this up cold. Read this first; everything else is detail it links to. 4: Written 2026-11-08 by the lowmarch session, at the owner's request, with no owner review yet. 5: 6: ## Where things stand 7: 8: - **What it is:** anime characters built in code for a tactics game. The owner named Unicorn Overlord as the style on 9: 10-08; lately they compare against the Yin and Yang rigs. They can't model or draw, and review pictures. 10: - **The owner is restarting** with one character, from scratch, to work out a faster, better process. They start it. 11: Don't build character work before then. The plan is the box at the top of 12: `~/citadel-render/workers/handoff/reflect/lowmarch.html`; the retro below that box is background. 13: - **What exists:** 14 bare T-posed bodies with VRoid faces and hair, 14 expressions each, a painted renderer 14: (`review/vroid-02/index.html`). No dressed character on these bodies, no game frame, no game code. 15: - **Review pages:** cast expressions [redacted: a link to a private page], hair research 16: [redacted: a link to a private page]. Artifacts belong to the account that made them; if you can't 17: update one, ask the lead (personal/citadel-lead-2). 18: - **More detail:** `docs/map.md` (what's current or stale, where big files sit), `docs/todos-2026-11-08.md` (open 19: todos sorted), `~/citadel-render/workers/handoff/lowmarch.md` (history). 20: 21: ## Earned and guessed 22: 23: Every rule below carries a mark, so old rules can't quietly bind the restart. 24: 25: - **Earned:** the owner saw it and said so, or a failure was measured and the fix held. 26: - **Guessed:** I reasoned it, took it from study, or only my own checks passed it. It binds nobody. 27: 28: An earned rule can still be overturned, as long as someone says so out loud. "On old bases" means earned on work now retired. 29: 30: ## Reading the owner's feedback 31: 32: - **Cohesion is about the whole, not a part.** "There has to be cohesion in it" (10-31) arrived about lashes, and I made 33: it a lash rule. The same complaint runs all month: "how the features sit on the face" (10-07), "pieces look floating" 34: (10-08), "head surgery" (10-10), "doesn't fit her body" (10-12). Read it as: this doesn't belong to this person. 35: - **"Hard to explain" means stop naming causes.** "I can't explain it" (10-30) got "I think I can name the something off" 36: from me, then a build. Make options that vary what might be wrong, and let them point. 37: - **They see more than they can say, and they're usually right.** Asked to check thin arms and thighs, the survey data 38: agreed (lesson 27). Take a marked-up screenshot literally: the orange nape line was correct (lesson 14). 39: - **Images are data.** "Cursed", "scar", "surgery" say what it feels like, not what the mesh did. 40: - **Sort praise by size.** Whole-thing verdicts: Saber (10-08), the bodies "look perfect" (10-12). "I like the shadows 41: now" is a part. "I guess that works for now" (10-12) isn't approval. "Go for your list" is delegation, not agreement. 42: - **"Where next?" and "I wonder how else" are requests for a map** and for how far this goes. Answer plainly, including 43: "I don't know if this route gets there". I didn't, and I said "the shading layers are what close the gap" (10-30). Don't. 44: - **Pivots are usually theirs.** If they're doubting the base, something's been wrong for a while. Say it first next time. 45: - **"I'm lost" (10-30) and "I just need the sheets" (10-31)** mean fewer words. Skip ledger numbers during review. 46: - **Money:** they've offered to buy tools (10-30), and declined a cost they hadn't noticed (11-02). Free path first, money 47: in line one, nothing spent without a fresh go. 48: 49: ## Showing options fast 50: 51: The ladder, cheapest first. Stay as low as you can, and only build the owner's pick properly. 52: 53: | Change | Tool | Cost | 54: |---|---|---| 55: | Camera, colours, rough blocks on a stand-in | `tools/session/frame.py` | 3 options in 5 s (measured 11-08; 6 s cold, 3 s warm on 11-09) | 56: | Painted renderer's page only | `tools/shots/arm_shoot.py`, on a copy of the site | 8 s a body (measured 11-08) | 57: | A face or expression | `tools/shots/variant_build.py`, then shoot | roughly 1 min a body (older note, not re-measured) | 58: | Any file in cage's cache key (below) | `python3 -I tools/cage.py` | about 10 min for all 14 (10-31) | 59: 60: **First session:** 61: 62: ```bash 63: S=$(python3 tools/session/rows.py new first --ref PICTURE) # the session folder 64: python3 tools/session/frame.py --info arm_f_slender # height and landmarks, for placing blocks 65: cp tools/session/smoke_spec.json $S/frame.json # then edit camera and options to match the picture 66: python3 tools/session/frame.py $S/frame.json $S/r1 # one PNG per option 67: python3 tools/session/rows.py add "Big shapes" $S/r1/*.png --note "under 100 words" 68: cw view $S/latest.png # the row, beside their picture 69: python3 tools/session/rows.py answer "B, shorter hair" # timed; rows.py log prints the rounds 70: ``` 71: 72: Publish with the Artifact tool from the same path each time, so the link stays put. Use `$S/index_noref.html` unless the 73: owner has said a private page may hold their picture (see "Things that don't bend"). `--blind` shuffles a row's labels. 74: 75: **The spec** (`tools/session/smoke_spec.json` is a working example, and a test, not a design): 76: 77: - `figure`: a built armory body. It's a stand-in; `look.hide: ["hair"]` drops its hair. 78: - `frame`: `w`, `h`, `ground_y` (where the feet stand), `horizon`, `background`, `ground`, and `camera`: `kind` (`ortho` or 79: `persp`), `fov`, `yaw`, `pitch`, `figure_h` (share of the frame's height), `figure_x`. 80: - `look`, overridden per option: `skin`, `shade`, `hair`, `hair_shade`, `cloth`, `cloth_shade`, `ink`, `outline` (metres), 81: `threshold`, `light`, `features` (flat eyes and lines), `hide`. 82: - `options[].blocks`: `ball`, `tube` (points, radii, `flat`) and `loft` (rings), in metres from a landmark in `at`. 83: +x is the model's left, +y up, +z front. 84: 85: `tools/session/smoke.sh` tests the kit end to end in about 7 s (9 s cold after a restart, 11-09). It needs the built armory site and network for three.js. 86: The frame page is flat two-tone on purpose. It isn't the game's look, so don't judge finish on it. 87: 88: ## How to run 89: 90: "Ran" means run on 11-08 at master `c4f1015`. numpy is in user site-packages, so `-I` works for `cage.py` but breaks 91: `lash_check.py`. 92: 93: | Command | What it does | Status | 94: |---|---|---| 95: | `python3 -I tools/cage.py [NAME...]` | builds armory bodies, cached | ran, one body, cached | 96: | `LOWMARCH_SITE=armory python3 review/vroid-02/build.py` | builds the armory into `review/out/armory/site/` | not re-run; built 10-31 | 97: | `python3 tools/lash_check.py [NAME...]` | open lash against closed lids, on meshes | ran, one body, 8 s | 98: | `ROWS=0 python3 tools/shots/arm_shoot.py SITE OUT NAME...` | shoots a site copy, headless | ran, one body, 8 s | 99: | `tools/shots/all14.sh OUT` | 6 expressions on all 14 bodies | copied, not re-run; wipes OUT first | 100: | `python3 tools/regress.py NAME [TAG]` | geometry diff against a published version | not re-run | 101: | `python3 tools/winvroid/winvroid.py bases\|samples` | drives VRoid Studio on Windows | blocked until the owner allows V.dll (#1105); takes over the PC, needs their go | 102: 103: - **Cage's cache key** hashes `cage.py, fit.py, proportions.py, makehuman.py, anthro.py, heads.py, vroid_portrait.py, 104: collide.py`. Touching any of them rebuilds every body. `export_glb.py` isn't in the key, but its changes need the GLBs rebuilt. 105: - **Browsers:** headless only. Headed windows pop up on the owner's desktop. 106: - **Data** lives outside the repo, in `~/.local/share/lowmarch/`. Paths are in `docs/map.md`. 107: - **The skeleton trap:** the bind pose holds the arms down while the mesh is T-posed (lesson 26). Arm bones' world 108: positions don't mark the visible arm. `frame.py --info` reports arms from the skin instead. 109: 110: ## The rules 111: 112: Each links to its lesson in `docs/portrait-guide.md` (L12 is lesson 12). 113: 114: ### Working with the owner 115: 116: | Rule | Mark | Basis | 117: |---|---|---| 118: | Ask "is this good?" of a whole character, not a part | Earned | Saber 10-08, bodies 10-12; parts get only local praise | 119: | Put a reference beside ours | Earned | "there's no muscle bulge" 10-09, L19 | 120: | Blind rows for close calls | Earned | Sharpest verdict of the month, 10-30 | 121: | Check the view the owner will see | Earned | L12; wrong renderer on 10-30 | 122: | A fix that moves another part is a regression until compared | Earned | L13, L28 | 123: | Study first, on anything new | Earned | Chin shadow took 3 builds before research (L33 to L35); sleeves and Saber jumped with study first | 124: | Tuned on one face means tuned on one face: check the rest before calling a range done | Earned | Mouths broke on the other 12 (L40) | 125: | Judge only in the game frame | Guessed | Retro; never tried | 126: | Rough blocks before detail | Guessed | Retro; never tried | 127: | One change a row, 3 or 4 options, under 100 words | Guessed | Retro; never tried | 128: | Two rounds with no visible change: stop and say so | Guessed | Retro; never tried | 129: 130: ### Bases and bodies 131: 132: | Rule | Mark | Basis | 133: |---|---|---| 134: | VRoid whole, shaped by a MakeHuman cage, own head kept | Earned | "it looks perfect" 10-12, L25 | 135: | Head grafts don't pass | Earned | "surgery" 10-10, L17, L25 | 136: | Read flesh against survey percentiles at the body's height and waist | Earned | Matched the owner's eye, L27 | 137: | Ranges measured on armoured figures don't fit bare bodies | Earned | L24, L27 | 138: | Tie a hand to body height | Earned | L28 | 139: | Don't force ratios from 2D art onto a 3D face | Earned | "too sharp" 10-12, L30 | 140: | A VRoid face as built is good enough | Guessed | The verdict was only "I guess that works for now" | 141: | No better shippable base than VRoid exists | Guessed | Research 11-08; candidates not all tried | 142: 143: ### Faces 144: 145: | Rule | Mark | Basis | 146: |---|---|---| 147: | Shadow made by bending mesh normals reads as a scar | Earned | 10-30, L33, L34 | 148: | Chin shadow cast from the jaw in screen space | Earned | "I like the shadows now" 10-30, L35 | 149: | Proxy face normals for a clean edge | Earned | Kept 10-30, L32 | 150: | One lash size per character, open and closed | Earned | Owner's rule 10-31, L38. A sample of cohesion, not the whole of it | 151: | A shut lid is one solid stroke | Earned | "the eyes look good now" 10-31, L38 | 152: | Mouth inside from VRoid's texture, anime palette | Earned | Blind pick 10-30, L39 | 153: | One-sided shapes for a smug look | Earned | Blind pick 10-30, L39 | 154: | Age takes more than lines | Earned | "hardly reflect old men" 10-08; never solved, #768 | 155: | 15% lash limit, split-line check | Guessed | My number, L38 | 156: | Shading line at the head's middle, front stays lit | Guessed | My choice, L32. At 35° the far side reads flat. Test this first | 157: | Force shadow on the far side of the face | Guessed | L03 on a retired mannequin; research agrees, never tried here | 158: | Brows drawn through the bangs | Guessed | The owner doubted it: "not sure if eyebrows are supposed to show up on top of hair" (10-30) | 159: | Hold the mouth 2 mm off the chin; teeth only above 8 to 11 mm | Guessed | L40, no verdict | 160: | One expression list for every face | Guessed | Research says per character; the open mouths look alike | 161: | Flat eye plane, per-angle tables | Guessed | L03. Arc System Works calls a tilted flat eye a mistake | 162: | FE8 house style: purple ink, tone rules | Guessed | From the pixel era, now abandoned | 163: 164: ### Hair 165: 166: | Rule | Mark | Basis | 167: |---|---|---| 168: | Few clumps of different widths, not even points | Earned | "seven pointed bangs" 10-08, L14 | 169: | Nape level with the bottom of the earlobe | Earned | Owner's orange line, L14 | 170: | Sample-style hair beat the kit's locks | Earned | 10-08, #735 | 171: | Hair must not sink into the body | Earned | 10-13. The fix (L31) passed only my replay, not the owner's eye | 172: | Dark layer under the locks closes gaps | Guessed | Proposed 10-31, not built | 173: | Hair keeps its own normals | Guessed | My eye, L32. Studios copy from simple shapes, so retest | 174: | Back, then sides, then front | Guessed | My 10-31 report; no source confirms it | 175: 176: ### Clothes and armour 177: 178: | Rule | Mark | Basis | 179: |---|---|---| 180: | Fit by rays to what's underneath; nothing floats | Earned, old bases | "floating" 10-08, then Aldric, L07 | 181: | An under-layer next to skin isn't skin-toned | Earned, old bases | 10-08, L10 | 182: | Loose sleeves; no muscle through cloth | Earned, old bases | 10-09, L19 | 183: | Check with arms out; cast waist rings on the torso only | Earned, old bases | L12, L13 | 184: | Layered skirts share weights | Earned, old bases | Owner spotted the underskirt, L13 | 185: | Long skirts posed, not simulated | Earned, old bases | Every free-cloth variant broke, L11; the owner never judged it in motion | 186: | Garment offsets in millimetres | Guessed | L07, tuned on old bases | 187: | Folds as ripples built into the garment | Guessed | L19. Studios place folds by hand for a pose | 188: 189: ### Rendering 190: 191: | Rule | Mark | Basis | 192: |---|---|---| 193: | The painted renderer is the target; pixels are abandoned | Earned | Owner 10-30 | 194: | Flattice waits until scenes have a camera | Earned | Owner 10-30 | 195: | A colour ramp per skin tone | Earned | Owner asked for the range; L36 | 196: | Orthographic cameras everywhere | Guessed | My default; the owner never chose it. Their picture decides | 197: | Headlight from the upper left, near-white default skin | Guessed | Never chosen | 198: | Paint numbers measured off Unicorn Overlord (L10) | Guessed | Taken from paintings; the reference has since moved | 199: 200: ## Things that don't bend 201: 202: These are facts or standing instructions, not lessons. 203: 204: - **Yin and Yang rigs:** personal-use licence. Study only, never ship. 205: - **References:** never traced, shipped or committed (`docs/study.md`). The same doc also keeps them off published pages. 206: I wrote that clause and it's guessed; the owner hasn't ruled on a private page. The retro's box says "your picture on 207: the left", so ask them. Until then, the published sheet leaves it out. 208: - **VRoid licence:** read by hand on 11-09, in `docs/vroid.md` ("Licence, read 2026-11-09", #1443). Baked characters in a 209: sold game, public pages and renders are allowed, no credit needed. A player-facing creator needs pixiv's licence. Our 210: exports' `Redistribution_Prohibited` fields were set at our export and don't bind us. Open: unedited A to Z textures in 211: a paid game. The owner decides what ships. 212: - **Blender:** nothing gets installed into it without the owner's go. A trial plan is enough. 213: - **The repo has no remote.** The owner hasn't decided, so don't add one. Commit locally. 214: - **Writing:** docs terse, no em dashes. Pages the owner may share carry no employer names. Public write-ups call this 215: "a 3D model pipeline". 216: - **Contact** for anything outside lowmarch: personal/citadel-lead-2. 217: 218: ## What I'd watch for 219: 220: These are my own weak spots, from the retro. 221: 222: - I judge my own pictures badly. Treat my checks as a floor, not a verdict. 223: - I reach for a cause and a build when the honest answer is "show me which". 224: - I write a checker after the owner catches a fault, and it tends to measure the part, not the whole. 225: - Lessons I've written don't stop me repeating a mistake. L03 said to force shade on the far side of the face, and L32 226: undid it without noticing. Read the marks above before relying on a lesson.
read_file{"Path":"~/context/reflect/lowmarch.html"}
input
{ "Path": "~/context/reflect/lowmarch.html" }result, 141 lines
Partial read (lines 1-442 of 442). Showing bytes 0-46080 of 348836 in this line range, truncated at the 46080-byte limit. To read the rest of this line range, call this tool again with the same StartLine and EndLine and ByteOffset=46080. 1: <!doctype html> 2: <html lang="en"> 3: <head> 4: <meta charset="utf-8"> 5: <meta name="viewport" content="width=device-width, initial-scale=1, viewport-fit=cover"> 6: <meta name="claude:viewport-fit-sides" content="cover"> 7: <title>Lowmarch, Looking Back</title> 8: <style> 9: /* Layout: one reading column, tables in their own scroll boxes. A cel ramp (lit, shade, deep, ink) from the portrait guide is the only flourish; ink is purple, never black, as the house style says. */ 10: :root { 11: --bg: #f5f3f7; --panel: #fbeee7; --panel2: #ebe7f0; --fg: #2b2336; --muted: #675f73; --rule: #d8d2e0; 12: --ink: #3c2a55; --accent: #6a3f8f; --guess: #8a4b1d; --good: #2c6a4c; --hold: #8a4b1d; --no: #8f2f3c; 13: --lit: #f8e1d5; --shade: #c6a89b; --deep: #73524f; 14: --head: "Avenir Next", "Segoe UI Variable Display", "Segoe UI", system-ui, sans-serif; 15: --body: "Segoe UI Variable Text", "Segoe UI", system-ui, -apple-system, sans-serif; 16: --mono: "Cascadia Mono", ui-monospace, "SFMono-Regular", Menlo, monospace; 17: } 18: @media (prefers-color-scheme: dark) { :root:not([data-theme="light"]) { 19: --bg: #17141c; --panel: #2a211f; --panel2: #231f2b; --fg: #ece7f1; --muted: #a79fb3; --rule: #383243; 20: --ink: #d8c8ec; --accent: #c4a2e6; --guess: #e6ae7a; --good: #86cfa8; --hold: #e6ae7a; --no: #ee9aa6; color-scheme: dark } } 21: :root[data-theme="dark"] { 22: --bg: #17141c; --panel: #2a211f; --panel2: #231f2b; --fg: #ece7f1; --muted: #a79fb3; --rule: #383243; 23: --ink: #d8c8ec; --accent: #c4a2e6; --guess: #e6ae7a; --good: #86cfa8; --hold: #e6ae7a; --no: #ee9aa6; color-scheme: dark } 24: html { -webkit-text-size-adjust: 100%; } 25: body { margin: 0; background: var(--bg); color: var(--fg); font: 400 16px/1.55 var(--body); } 26: .wrap { max-width: 880px; margin: 0 auto; padding-block: 26px 70px; 27: padding-left: max(16px, env(safe-area-inset-left, 0px)); padding-right: max(16px, env(safe-area-inset-right, 0px)); } 28: .ramp { display: grid; grid-template-columns: 5fr 3fr 2fr 1fr; height: 8px; border-radius: 4px; overflow: hidden; margin-bottom: 20px; } 29: .ramp i { display: block; } 30: h1, h2, h3 { font-family: var(--head); color: var(--ink); text-wrap: balance; line-height: 1.15; margin: 0; } 31: h1 { font-size: 2.2rem; font-weight: 700; letter-spacing: -0.01em; } 32: h2 { font-size: 1.5rem; font-weight: 700; margin-top: 52px; padding-top: 16px; border-top: 2px solid var(--ink); } 33: h3 { font-size: 1.08rem; font-weight: 700; margin-top: 28px; } 34: p { margin: 10px 0 0; max-width: 72ch; } 35: ul, ol { margin: 10px 0 0; padding-left: 1.2em; display: grid; gap: 6px; } 36: li { max-width: 72ch; } 37: a { color: var(--accent); text-underline-offset: 2px; } 38: a:focus-visible, summary:focus-visible { outline: 2px solid var(--accent); outline-offset: 2px; border-radius: 2px; } 39: q { quotes: "\201C" "\201D"; } 40: .meta { color: var(--muted); font-size: 0.92rem; margin-top: 8px; } 41: .jump { display: flex; flex-wrap: wrap; gap: 6px 16px; margin-top: 12px; font-size: 0.95rem; } 42: .box { margin-top: 20px; background: var(--panel); border-radius: 10px; padding: 16px 18px; } 43: .box h2, .box h3 { margin: 0; padding: 0; border: 0; font-size: 1.1rem; } 44: .box.alt { background: var(--panel2); } 45: .box ol, .box ul { gap: 8px; } 46: .tally { display: grid; grid-template-columns: repeat(auto-fit, minmax(118px, 1fr)); gap: 10px 16px; margin-top: 14px; } 47: .tally div { min-width: 0; border-top: 1px solid var(--rule); padding-top: 6px; } 48: .tally b { display: block; font: 700 1.3rem/1.2 var(--mono); color: var(--ink); font-variant-numeric: tabular-nums; } 49: .tally span { font-size: 0.82rem; color: var(--muted); line-height: 1.3; display: block; } 50: figure { margin: 18px 0 0; } 51: figure img { display: block; width: 100%; height: auto; border-radius: 6px; } 52: figcaption { color: var(--muted); font-size: 0.88rem; margin-top: 7px; max-width: 76ch; } 53: .tbl { overflow-x: auto; margin-top: 12px; } 54: table { border-collapse: collapse; width: 100%; font-size: 0.92rem; } 55: .tbl.w table { min-width: 680px; } 56: th, td { text-align: left; vertical-align: top; padding: 8px 10px 8px 0; border-bottom: 1px solid var(--rule); } 57: th { font-weight: 600; font-size: 0.74rem; letter-spacing: 0.05em; text-transform: uppercase; color: var(--muted); } 58: td:first-child { font-weight: 600; color: var(--ink); } 59: .two { display: grid; grid-template-columns: 3fr 2fr; gap: 6px 26px; } 60: .two > div { min-width: 0; } 61: .two h4 { margin: 12px 0 0; font: 600 0.74rem/1.3 var(--body); letter-spacing: 0.05em; text-transform: uppercase; color: var(--muted); } 62: .two ul { font-size: 0.95rem; } 63: @media (max-width: 640px) { .two { grid-template-columns: 1fr; } h1 { font-size: 1.85rem; } } 64: .g { font: 500 0.68rem/1 var(--mono); color: var(--guess); border: 1px solid currentColor; border-radius: 99px; padding: 1px 6px; white-space: nowrap; vertical-align: 1px; } 65: sup a { text-decoration: none; font-size: 0.72rem; padding: 0 1px; } 66: .tag { display: inline-block; font: 500 0.72rem/1.4 var(--mono); padding: 0 7px; border-radius: 99px; border: 1px solid currentColor; white-space: nowrap; } 67: .tag.yes { color: var(--good); } .tag.later { color: var(--hold); } .tag.no { color: var(--no); } 68: .note { color: var(--muted); font-size: 0.9rem; } 69: .chain { display: grid; grid-template-columns: 4.2em 1fr; gap: 2px 10px; font-size: 0.92rem; margin-top: 10px; max-width: 72ch; } 70: .chain b { font: 500 0.82rem/1.55 var(--mono); color: var(--muted); } 71: .src { font-size: 0.85rem; color: var(--muted); list-style: decimal; padding-left: 1.9em; gap: 3px; } 72: .src li { max-width: none; overflow-wrap: anywhere; scroll-margin-top: 12px; } 73: .src li:target { color: var(--fg); background: var(--panel2); } 74: .start { border: 2px solid var(--ink); background: var(--bg); } 75: .start h2 { font-size: 1.35rem; } 76: .start h3 { margin-top: 16px; font-size: 1rem; } 77: .bg-label { margin: 34px 0 0; font: 600 0.74rem/1.3 var(--body); letter-spacing: 0.05em; text-transform: uppercase; color: var(--muted); } 78: </style> 79: </head> 80: <body> 81: <div class="wrap"> 82: <div class="ramp" aria-hidden="true"><i style="background:var(--lit)"></i><i style="background:var(--shade)"></i><i style="background:var(--deep)"></i><i style="background:#3c2a55"></i></div> 83: <h1>Lowmarch, Looking Back</h1> 84: <p class="meta">From the lowmarch session, 2026-11-08. Reflection and research only: nothing was built, rendered or changed. Dates are your local dates.</p> 85: <nav class="jump" aria-label="On this page"><a href="#start">First session</a><a href="#reflect">1. What happened</a><a href="#pros">2. How professionals do it</a><a href="#tools">3. Tools</a><a href="#forward">4. How to move forward</a><a href="#sources">Sources</a></nav> 86: 87: <section class="box start" id="start"> 88: <h2>Start here: the first session</h2> 89: <p>You want to start over with one character, from scratch, so we can work out together how I should work. Nothing is built yet, and I'll wait for you to start it. Everything below this box is background: you don't need to read it or comment on it first.</p> 90: 91: <h3>The one thing I'd ask first</h3> 92: <p><strong>Show me one picture you wish was a screenshot of our game.</strong> It can come from anything. It gives me the look, the camera, how big the character is on screen and what they're doing, without you having to put any of that into words. We'd study it only, never trace or ship it.</p> 93: 94: <h3>The session, about an hour</h3> 95: <ol> 96: <li>I say back what I see in your picture, in a few lines. You correct me.</li> 97: <li>I set up that frame: same camera, same size, a plain grey figure standing in. We judge only there from now on, not on T-poses on black.</li> 98: <li><strong>Row 1, big shapes:</strong> hair and outfit as rough flat-coloured blocks, 3 or 4 options. You pick one or mark it up.</li> 99: <li><strong>Row 2, light and dark:</strong> skin tone and the pattern of shadow on your pick, 3 options.</li> 100: <li>I write down what you picked and why, in your words. Then we spend five minutes on what was slow or annoying. That's what this session is really testing.</li> 101: </ol> 102: <p>Later sessions stay in the same frame: the face, then clothes, then one motion. That gets us one whole character, and a record of what each step cost.</p> 103: 104: <h3>How I'd show options quickly</h3> 105: <ul> 106: <li><strong>One link, updated in place,</strong> so you never have to hunt for a file.</li> 107: <li><strong>Your picture on the left, options beside it,</strong> labelled A, B, C. Answer "B", or draw on it.</li> 108: <li><strong>Each row changes one thing,</strong> with under 100 words beneath it.</li> 109: <li><strong>Rough first.</strong> Blocks and colour changes should take minutes, and only your pick gets built properly. If a row will take more than 10 minutes, I'll say so before starting.</li> 110: <li><strong>I time every round,</strong> from your answer to the next row. I haven't timed this way of working yet, so those first times are the number we try to beat.</li> 111: </ul> 112: <p class="note">I'm taking "from scratch" to mean a new character and a new way of working. The current bodies, VRoid base and renderer stay on the shelf, used only if they help. If you meant those too, tell me, because it changes the first hour.</p> 113: </section> 114: 115: <p class="bg-label">Background: the retro</p> 116: 117: <section class="box"> 118: <h2>Short version</h2> 119: <ol> 120: <li><strong>The bodies worked. Nothing since has had that feeling.</strong> Your last words for a whole thing were <q>it looks perfect</q> (10-12). Since then praise has been for parts.</li> 121: <li><strong>The real complaint all month is parts that don't belong together.</strong> You said it best: <q>there has to be cohesion in it</q> (10-31). I turned that into a lash rule. The word was bigger than the lash.</li> 122: <li><strong>I never told you the big limit.</strong> I don't know if this route reaches what you compare it to, and I said things that sounded like I did. Studios get that look from a person's eye making many hand decisions, per angle.</li> 123: <li><strong>We've never seen the current bodies dressed, moving, or in a game frame.</strong> They're 14 bare T-poses, judged on black tiles.</li> 124: <li><strong>What I'd do:</strong> restart on one whole character in one game frame, and have you choose between rows early. Free. One week answers the ceiling question better than more fixes.</li> 125: </ol> 126: </section> 127: 128: <h2 id="reflect">1. What happened</h2> 129: <div class="tally"> 130: <div><b>9</b><span>active days: 10-07 to 10-13, 10-30, 10-31</span></div> 131: <div><b>13,979</b><span>lines of tool code</span></div> 132: <div><b>40</b><span>lessons written, 1,440 lines</span></div> 133: <div><b>32</b><span>open todos, 19 of them from the first week</span></div> 134: <div><b>0</b><span>dressed characters on the current bodies</span></div> 135: <div><b>0</b><span>game frames composed, 0 lines of game</span></div> 136: </div> 137: 138: <h3>Where it stands</h3> 139: <figure> 140: <img src="[redacted: data-URI prefix][redacted: base64 data]