mirror of https://github.com/heygen-com/hyperframes.git synced 2026-09-04 07:19:52 +00:00

Files

T

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

5.6 KiB

Raw Blame History

Prompt Expansion

Run on every composition. Expansion is not about lengthening a short prompt — it's about grounding the user's intent against the design spec (frame.md or design.md) and house-style.md and producing a consistent intermediate that every downstream agent reads the same way.

Runs AFTER design direction is established (Step 1). The expansion consumes the design spec (frame.md or design.md, if present) and produces output that cites its exact values.

Prerequisites

Read before generating:

the design spec — frame.md → design.md → DESIGN.md (read the first that exists) — extract brand colors, fonts, mood, and constraints. The expansion cites these exact values (hex codes, font names); it does not invent new ones.
references/beat-direction.md — per-beat planning format (concept, mood, choreography verbs, transitions, depth layers, rhythm). The expansion outputs each scene using this format.
references/video-composition.md — video-medium rules for density, scale, and color presence. The expansion applies these automatically.
house-style.md — its rules for Background Layer (2-5 decoratives), Color, Motion, Typography apply to every scene. The expansion writes output that conforms to them.

If no design spec (frame.md or design.md) exists yet, run Step 1 (Design system) first. Expansion without a design context produces generic scene breakdowns that later agents ignore.

Why always run it

The expansion is never pass-through. Every user prompt — no matter how detailed — is a seed. The expansion's job is to enrich it into a fully-realized per-scene production spec that the scene subagents can build from directly.

Even a detailed 7-scene brief lacks things only the expansion adds:

Atmosphere layers per scene (required 2–5 from house-style: radial glows, ghost type, hairline rules, grain, thematic decoratives) — the user's prompt almost never lists these; expansion adds them.
Secondary motion for every decorative — breath, drift, pulse, orbit. A decorative without ambient motion feels dead.
Micro-details that make a scene feel real — registration marks, tick indicators, monospace coord labels, typographic accents, code snippets in the background, grid patterns. Things the user didn't think to request.
Transition choreography at the object level — not "crossfade" but "X expands outward and becomes Y". Specific duration, ease, and morph source/target.
Pacing beats within each scene — where tension builds, where a hold lets the viewer breathe, where the accent word lands.
Exact hex values, typography parameters, ease choices from the design spec — no vagueness left for the scene subagent to guess.

Expansion's job on a detailed prompt is not to summarize or pass through — it's to take what the user wrote and make it richer. The user's content stays; the atmosphere, ambient motion, and micro-details are added on top. That's what makes the difference between a scene that matches the brief and a scene that feels alive.

The quality gap between a single-pass composition and a multi-scene-pipeline composition comes from this step. Expansion front-loads the richness so every scene subagent builds from a rich brief, not a terse one.

Do not skip. Do not pass through. Single-scene compositions and trivial edits are the only exceptions.

What to generate

Expand into a full production prompt with these sections:

Title + style block — cite the design spec's exact hex values, font names, and mood. Do NOT invent a palette — quote what the design provides.
Rhythm declaration — name the scene rhythm before detailing any scene. Example: hook-PUNCH-breathe-CTA or slow-build-BUILD-PEAK-breathe-CTA. Use references/beat-direction.md for rhythm templates by video type.
Global rules — parallax layers, micro-motion requirements, transition style, primary + accent transitions. Match energy to mood (calm → slow eases, high → snappy eases).
Per-scene beats — for each scene, use the beat-direction format:
- Concept — the big idea in 2-3 sentences. What visual WORLD? What metaphor? What should the viewer FEEL?
- Mood direction — cultural/design references, not hex codes. ("Bauhaus color studies", "cinematic title sequence", "editorial calm")
- Depth layers — BG treatment, MG content, and FG accents or structural details as the concept needs. Use video-composition.md to choose density; do not force an element count or invent content to fill one.
- Animation choreography — specific verbs per element. High: SLAMS, CRASHES. Medium: CASCADE, SLIDES. Low: floats, types on, counts up. Every element gets a verb. If you can't name the verb, the element is not yet designed.
- Transition out — shader or CSS, with specific type and parameters. Not "crossfade" but "blur crossfade, 0.4s, power2.inOut."
Recurring motifs — visual threads across scenes from the brand palette.
Negative prompt — what to avoid, informed by the design spec's constraints if present.

Output

Write the expanded prompt to .hyperframes/expanded-prompt.md in the project directory. Do NOT dump it into the chat — it will be hundreds of lines.

Tell the user:

"I've expanded your prompt into a full production breakdown. Review it here: .hyperframes/expanded-prompt.md

It has [N] scenes across [duration] seconds with specific visual elements, transitions, and pacing. Edit anything you want, then let me know when you're ready to proceed."

Only move to construction after the user approves or says to continue.

5.6 KiB Raw Blame History Unescape Escape