Files
hyperframes/packages/cli/src/capture/agentPromptGenerator.ts
WaterrrForever b9be0b2625 feat(skills,studio,media-use): the intent layer, review loop, and user memory — BRIEF.md, companion mode, recipes; /website-to-video folds into /product-launch-video (#2133)
* feat(studio,cli): per-frame board comments, self-refreshing storyboard, status-aware preview landing

Per-frame comment boxes on the storyboard board batch into
.hyperframes/frame-comments.json (a resubmit wins per frame; unconsumed
comments on other frames are kept). Submitted-but-unconsumed comments
stay visible — a toolbar banner plus a per-tile echo — until the agent
consumes the file; the banner also says what to do next (reply anything
in the agent chat).

The board keeps itself current: GET /projects/:id/signature exposes the
watcher-cached project signature, the storyboard payload carries the
signature it was derived from, and the view polls at 2s (hidden tabs
skipped, re-checked on visibility), refetching in place with no loading
flash. Posters bake the signature into their URL so tiles fill in as
sketches land and a poster that failed mid-write retries on the next
version; the empty state upgrades itself when STORYBOARD.md appears,
and its handoff prompt now points the agent at the review loop and uses
the parser's real status vocabulary (outline, not planned).

preview lands the browser on the storyboard view while the board is the
review surface — any frame built, or pure planning (srcs declared, none
on disk yet) — and on the timeline once the video is assembled.

* feat(skills): the review loop — plan, sketch, build as one shared process

hyperframes-core/references/review-loop.md is the single source for the
three-pass collaborative review: the plan proposed on a live board
(§ 1), wireframe sketches marked built with one layout question (§ 2 —
real words on plain blocks, run no CLI; a confirmed board is itself a
valid deliverable when the user asked for a storyboard, not a video),
the build dressing confirmed layouts (§ 3, worker or inline), and the
final look (§ 4). Autonomous runs skip every gate and keep one question
before render.

The three narrative workflows' Steps 3/4/6 collapse to references plus
their sketch stand-ins (captured-asset blocks for product-launch-video,
plain code panels for pr-to-video); the confirmed-sketch handoff stays
in each frame-worker prompt. general-video plans on a board for
multi-scene narrative pieces in collaborative mode — its sketch pass is
layout-before-animation with the user watching. The router treats
"I want a storyboard" as a process request rather than a route, and
closes exploratory intake by recommending a route plus how the run will
review.

The supporting contracts land next door: the comments channel (silent
submit, one reply picks it up, check the file before the words) in
brief-contract § 1; the sidecar schema and the built status rung in
storyboard-format; the mode question asked first and alone in the three
workflows' Step 0.

* feat(media-use): user memory — remembered preferences and frozen recipes

Two tiers of memory on media-use's existing two-tier storage split.

Preferences (lightweight): confirmed brief answers — destination, aspect,
language, mode, voice, style preset — recorded to the project's
.media/preferences.json (committed, the team inherits it) and promoted
to the personal ~/.media/preferences.json once the same value is
confirmed in two different projects (a sightings ledger accumulates the
cross-project evidence user-side, since project files can't see each
other). prefs.mjs get/record; merge reads project-over-user; a changed
value restarts its provenance.

Recipes (heavyweight): one approved run frozen as a named, versioned
bundle — frame.md, the storyboard skeleton (structure kept: durations,
transitions, srcs, Video direction; statuses reset to outline; content
blanked to per-frame fill-ins naming the beat's role), and the confirmed
brief values. Named folders, not content hashes: re-freezing bumps
version and archives <name>@v<N>; a freeze is already confirmed, so it
promotes to the user tier immediately. recipe.mjs freeze/list/use, plus
resolve --type recipe --entity <name> delegating like grade/lut.

16 new node --test cases; the media-use lib suite is 168/168.

* feat(skills): wire user memory into the brief and the review loop

brief-contract § 2 gains Remembered defaults: read the merged
preferences before Round 2 and let a remembered value become the
recommended option with a receipt naming its source project. Memory
changes the default, never the question — every ask-marked field still
gets asked, and what the request says this time beats what was picked
last time. Record only what the user actually confirmed (a defaulted
voice nobody chose is not an answer; a "go" that accepts the
recommended defaults is). The first record announces itself once;
after that the receipts carry the reminder. In autonomous mode a
remembered value becomes the decided value, receipt included.

The three narrative workflows read the remembered defaults before
Round 2, record the confirmed answers at the Step 0 gate, record the
chosen preset at the Step 2 gate (pr-to-video excepted — its preset is
fixed), and fall back to the remembered voice when the request names
none. general-video's discovery reads the same defaults.

Recipes wire in at both ends: Step 0 checks for a matching recipe
before the mode question — one question, plural-aware, and adopting
one fills the brief, skips the design step, and drafts the storyboard
from the frozen skeleton while every review gate still runs. The
review loop's final look (§ 4) offers the freeze once after approval,
and the confirmation teaches the recall phrase — the name is something
the system reminds the user of, never something they must remember.
The router recognizes a named recipe or "like last time" as a route.

* docs(skills): the sketch pass names check, not the deprecated validate

* feat(skills): intent-layer references — process, route briefs, capability menu, BRIEF.md format

* feat(media-use): brief skeleton as the recipe's fourth artifact; flow/storyboard preference keys

* feat(skills): the intent layer conducts every brief — workflows execute BRIEF.md

* feat(skills): retire the mode preference key; sync catalog surfaces for intent layer

* refactor(skills): dedupe router vs intent-layer guidance — one owner per rule

* feat(skills): the design ask — own spec, pick by eye from showcases, or defer

* docs(skills): the design ask says the honest line on capture routes

* feat(skills): product-launch-video absorbs website-to-video as the tour angle

* refactor(skills): keep product-launch-video pristine — a tour is brief intent, not a pipeline branch

* feat(skills): production loop + genre lenses; general-video goes freeform (route yours, laws hold)

* refactor(skills): /hyperframes is the front door - route tables and scope lists leave the workflows

* docs(skills): review-loop pass across skill catalog

* fix(cli): pass project dir to openStudioBrowser in background-server path

* feat(skills): add pitch-round reference - verbalized sampling concept gate

* feat(skills): wire pitch round into intent layer - completeness triage + route eligibility

* feat(skills): editorial capability recommendations, handoff disciplines, menu-probe split

* feat(skills): pitches carry their machinery; source-only-formed requests pitch the telling

* feat(skills): companion goes director - ceiling treatment plus blueprint/rule citation discipline

* fix(scripts): sandbox npx-leak guard - private npm global prefix keeps npx on the branch CLI

* chore(skills): resync manifest hash after formatter pass reflowed general-video tables

* fix(skills): recipe freeze reads workflow from BRIEF.md; style_preset records require workflow scope

Two holes found by a live companion-run freeze: the agent-supplied --workflow
contradicted the run's actual workflow (recipe.json said faceless-explainer,
brief-skeleton said general-video), and the style_preset lookup missed because
the preference had been recorded under the bare key.

- freezeRecipe resolves the workflow from BRIEF.md frontmatter; the flag is a
  fallback for briefless projects and a contradicting flag is ignored (noted).
- recordPreference refuses a bare style_preset — the scoped key is the only
  writable shape; freeze tolerates legacy bare records via read fallback.
- review-loop § 4 / media-use SKILL / brief-format wording follow the machinery.
2026-07-15 21:19:14 +08:00

214 lines
8.2 KiB
TypeScript

/**
* Generate AGENTS.md and CLAUDE.md for captured website projects.
*
* Writes the same content to both filenames so any AI agent auto-discovers it:
* - AGENTS.md — universal convention (Cursor, Codex, Gemini CLI, Windsurf, Aider, Jules)
* - CLAUDE.md — Claude Code convention
*
* This file generates a DATA INVENTORY that tells the AI agent what files
* exist and what they contain. The actual workflow lives in the
* product-launch-video skill — this file points agents there.
*/
import { writeFileSync, readdirSync, existsSync } from "node:fs";
import { join } from "node:path";
import type { DesignTokens } from "./types.js";
import type { AnimationCatalog } from "./animationCataloger.js";
import type { CatalogedAsset } from "./assetCataloger.js";
/**
* Infer a human-readable role hint from a hex color based on luminance and saturation.
* Not a substitute for DESIGN.md — just helps orient agents scanning the brand summary.
*/
// fallow-ignore-next-line complexity
function inferColorRole(hex: string): string {
const r = parseInt(hex.slice(1, 3), 16) / 255;
const g = parseInt(hex.slice(3, 5), 16) / 255;
const b = parseInt(hex.slice(5, 7), 16) / 255;
if (isNaN(r) || isNaN(g) || isNaN(b)) return "color";
const max = Math.max(r, g, b);
const min = Math.min(r, g, b);
const luminance = 0.2126 * r + 0.7152 * g + 0.0722 * b;
const saturation = max === 0 ? 0 : (max - min) / max;
if (luminance < 0.04) return "bg-dark";
if (luminance > 0.9) return "bg-light";
if (saturation > 0.4 && luminance > 0.05 && luminance < 0.7) return "accent";
if (luminance < 0.2) return "surface-dark";
if (luminance > 0.7) return "surface-light";
return "neutral";
}
export function generateAgentPrompt(
outputDir: string,
url: string,
tokens: DesignTokens,
_animations: AnimationCatalog | undefined, // reserved for future animation summary
hasScreenshot: boolean,
hasLottie?: boolean,
hasShaders?: boolean,
_catalogedAssets?: CatalogedAsset[], // reserved for future asset inventory
_detectedLibraries?: string[],
): void {
const prompt = buildPrompt(outputDir, url, tokens, hasScreenshot, hasLottie, hasShaders);
writeFileSync(join(outputDir, "AGENTS.md"), prompt, "utf-8");
writeFileSync(join(outputDir, "CLAUDE.md"), prompt, "utf-8");
writeFileSync(join(outputDir, ".cursorrules"), prompt, "utf-8");
}
// fallow-ignore-next-line complexity
function buildPrompt(
outputDir: string,
url: string,
tokens: DesignTokens,
hasScreenshot: boolean,
hasLottie?: boolean,
hasShaders?: boolean,
): string {
const title = tokens.title || new URL(url).hostname.replace(/^www\./, "");
const colorSummary = tokens.colors
.slice(0, 10)
.map((hex) => `${hex} (${inferColorRole(hex)})`)
.join(", ");
const fontSummary =
tokens.fonts
.map(
(f) =>
f.family +
(f.variable && f.weightRange
? ` (${f.weightRange[0]}-${f.weightRange[1]} variable)`
: f.weights.length > 0
? ` (${f.weights.join(",")})`
: ""),
)
.join(", ") || "none detected";
// Build the data inventory table rows
// Helper: find all contact sheet pages for a given base name. Matches the
// exact base file plus paginated variants only (e.g. `contact-sheet.jpg`,
// `contact-sheet-2.jpg`, `contact-sheet-3.jpg`). The "-NNN" suffix is digits
// only, so unrelated files that happen to share the prefix (notably the
// `contact-sheet-svgs.jpg` SVG fallback sheet in assets/) don't get mixed in.
function contactSheetRows(dir: string, baseFile: string, label: string): string[] {
const fullDir = join(outputDir, dir);
if (!existsSync(fullDir)) return [];
const baseName = baseFile.replace(/\.jpg$/, "");
// Escape regex metacharacters in baseName so future callers can pass
// filenames containing `.`, `+`, `(`, etc. without the regex breaking.
const escapedBase = baseName.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
const paginatedRe = new RegExp(`^${escapedBase}(?:-(\\d+))?\\.jpg$`);
// Sort by the numeric page suffix so `contact-sheet-10.jpg` lands after
// `contact-sheet-2.jpg`, not before (default string sort orders them
// lexicographically and breaks at 10+ pages). Unpaginated `contact-sheet.jpg`
// gets page 0 so it sorts first if it co-exists with paginated files.
const all = readdirSync(fullDir)
.filter((f) => paginatedRe.test(f))
.map((f) => ({ name: f, page: parseInt(f.match(paginatedRe)?.[1] ?? "0", 10) }))
.sort((a, b) => a.page - b.page)
.map((entry) => entry.name);
if (all.length === 0) return [];
if (all.length === 1) {
return [`| \`${dir}/${all[0]}\` | ${label} |`];
}
return all.map((f, i) => `| \`${dir}/${f}\` | ${label} — page ${i + 1} of ${all.length} |`);
}
const tableRows: string[] = [];
if (hasScreenshot) {
const screenshotRows = contactSheetRows(
"screenshots",
"contact-sheet.jpg",
"**View this first.** All scroll screenshots in labeled grid — see the entire page at a glance",
);
if (screenshotRows.length > 0) {
tableRows.push(...screenshotRows);
} else {
tableRows.push(
"| `screenshots/contact-sheet.jpg` | **View this first.** All scroll screenshots in one labeled grid. |",
);
}
tableRows.push(
"| `screenshots/scroll-*.png` | Individual viewport screenshots if you need detail on a specific section. |",
);
}
tableRows.push(
`| \`extracted/tokens.json\` | Design tokens: ${tokens.colors.length} colors, ${tokens.fonts.length} fonts, ${tokens.headings?.length ?? 0} headings, ${tokens.ctas?.length ?? 0} CTAs |`,
);
// design-styles.json is written from a try/catch in capture/index.ts and
// gets skipped when the live-DOM style extraction fails. Only list it in the
// agent prompt when it actually exists, so the agent isn't pointed at a 404.
if (existsSync(join(outputDir, "extracted", "design-styles.json"))) {
tableRows.push(
"| `extracted/design-styles.json` | Computed styles from live DOM: typography hierarchy, button/card/nav styles, spacing scale, border-radius, box shadows. Primary data source for DESIGN.md. |",
);
}
tableRows.push(
"| `extracted/asset-descriptions.md` | One-line description of every downloaded asset. Read this for asset selection — only open individual files for safe-zone checking. |",
);
tableRows.push(
"| `extracted/visible-text.txt` | Page text in DOM order, prefixed with HTML tag (`[h1]`, `[p]`, `[a]`). Use as context — rephrase freely. |",
);
if (hasLottie) {
tableRows.push(
"| `extracted/lottie-manifest.json` | Lottie animations with previews at `assets/lottie/previews/`. |",
);
}
if (hasShaders) {
tableRows.push("| `extracted/shaders.json` | WebGL shader source (GLSL). |");
}
// Asset contact sheets — dynamically list all pages
const assetSheetRows = contactSheetRows(
"assets",
"contact-sheet.jpg",
"Downloaded images in labeled grid — view before opening individual files",
);
if (assetSheetRows.length > 0) {
tableRows.push(...assetSheetRows);
} else {
tableRows.push("| `assets/contact-sheet.jpg` | All downloaded images in one labeled grid. |");
}
// SVG contact sheets — check both assets/svgs/ and assets/ root fallback
const svgSubdirRows = contactSheetRows(
"assets/svgs",
"contact-sheet.jpg",
"SVGs rendered as thumbnails in labeled grid",
);
const svgRootRows = contactSheetRows(
"assets",
"contact-sheet-svgs.jpg",
"SVGs rendered as thumbnails in labeled grid",
);
const svgRows = svgSubdirRows.length > 0 ? svgSubdirRows : svgRootRows;
if (svgRows.length > 0) {
tableRows.push(...svgRows);
}
tableRows.push("| `assets/` | Individual downloaded images, SVGs, and font files. |");
// Brand summary — just the essentials
const brandLines: string[] = [];
brandLines.push(`- **Colors**: ${colorSummary || "see tokens.json"}`);
brandLines.push(`- **Fonts**: ${fontSummary}`);
return `# ${title}
Source: ${url}
To create a video from this capture, use the \`product-launch-video\` skill.
## What's in This Capture
| File | Contents |
|------|----------|
${tableRows.join("\n")}
## Brand Summary
${brandLines.join("\n")}
`;
}