Files
hyperframes/skills/pr-to-video/scripts/workflow-guardrails.test.mjs
T
WaterrrForeverandClaude Fable 5 6ad738b580 refactor(skills): cut per-run context cost — route-once router, packet-dispatched workers, catalog splits (#2618)
* feat(skills): storyboard duration becomes an advisory expectation

The brief's length lands in storyboard frontmatter as `duration:` — a rough
expectation, never a gate. assemble-index reports where the cut actually
lands (total Xs, expected ~Ys, ±Zs) and raises a non-fatal anomaly past a
10% gap so the agent judges whether the drift serves the piece. Never
exits non-zero for it.

* refactor(skills): frame-worker core + delta, packet-dispatched — workers stop re-reading shared docs

The three narrative frame workers (product-launch 17.7KB / faceless-explainer
17KB / pr-to-video 21.3KB) were near-verbatim clones already drifting apart.
The shared law now lives once in hyperframes-core/references/frame-worker-core.md;
each workflow's sub-agents/frame-worker.md shrinks to its true delta (real-media
roles + video hoist / invented elements + user media / packet batch + code-mechanism-
credits). music-to-video keeps its own model, untouched.

Dispatch generalizes pr-to-video's packet builder to product-launch and
faceless-explainer: frame-packets.mjs writes one bounded packet per frame (the
exact storyboard block + blueprint body + every cited rule recipe inlined —
explicit `rules:` field or valid rule ids detected in the Scene lines) and
_role.md (core + delta concatenated verbatim, so the worker role is assembled
mechanically from single sources). Workers read only their packet + frame.md —
never STORYBOARD.md, the skill docs, or hyperframes-core.

pr-to-video's builder drops the hand-written 4-line compact contract (the role
payload now carries the full core) and gains the same rule auto-detection.
Tests: 2 new vendored suites + a _role.md guardrail; 138 pass, lint:skills green.

* feat(skills): duration advisory for faceless-explainer + pr-to-video

Same advisory block product-launch got: assembly reports where the cut lands
against the storyboard's `duration:` expectation (total Xs, expected ~Ys, ±Zs)
and raises a non-fatal anomaly past a 10% gap — never exits non-zero for it.
Step 3 gains the one-line write instruction. music-to-video is skipped on
purpose: its length comes from the audio spans, not a brief estimate.

Also: subagent-dispatch.md's DISPATCH contract named agents/<role>.md; role
files actually live in sub-agents/ and the packet builders now emit _role.md —
the wording follows the reality.

* fix(skills): script main-guard survives symlinked invocation paths

pathToFileURL(process.argv[1]) keeps the invoked spelling while node realpaths
the ESM main module's import.meta.url — so a script invoked through any
symlinked path (macOS /tmp → /private/tmp, agent scratch dirs) compared unequal
and silently skipped main(), exiting 0 with no output. Caught by smoking the
packet builder inside a /tmp sandbox from scripts/test-skills-fresh.sh.

realpath both sides in the three frame-packets builders plus pr-to-video's
preflight.mjs and project-dir.mjs (same latent guard).

* refactor(skills): media-use thin index + per-verb references

P9 from the athrix trace audit: media-use/SKILL.md (34.3KB) was read 4x per
run (137KB) for ~12KB of actually-consumed content. Split it remotion-style:

- SKILL.md becomes a 3.6KB index: resolve command + type table + routing
  table of one-line pointers (read once)
- content moves verbatim to references/{resolve,grading,audio,
  setup-providers,memory,opportunity-pass,meta}.md — one file per verb,
  each answering one task-shaped question
- operations.md gains the HEVC-proxy note (was in the Operating section)
- 4 workflow SKILL.md pointers follow Providers to setup-providers.md

Per-media-task read cost: index 3.6KB once + one topic file (<=8.8KB).
lint:skills 31 files green; coverage+resolve tests 14/14 (coverage.test.mjs
asserts entrypoints, not SKILL.md text - no test coupling).

* feat(skills): general-video scene dispatch via frame packets

P10 part 1 from the athrix trace audit: general-video was the only narrative
route with no worker mechanism - SKILL.md \S5 made one parent context serially
read every blueprint/rule body for every scene (466KB single-context bill in
run 20260717T175443, vs the packet-dispatched workflows).

- scripts/frame-packets.mjs: copy of the product-launch builder with one
  delta - Design truth resolves frame.md -> design.md -> DESIGN.md (\S6 order)
- sub-agents/frame-worker.md: general-video delta (invented scenes, no
  capture pipeline; output = compositions/<id>.html + <id>.motion.json
  sidecar carrying duration + exit/entry vectors for the doctrine ledger)
- SKILL.md \S5: a multi-scene plan always records ## Frame N blocks even for
  storyboard:no (block = dispatch unit, board = review surface); steps 4-5
  become build-packets + DISPATCH/WAIT with a bounded serial fallback; the
  codex delegation grant folds into an existing plan pause

Tests: frame-packets.test.mjs 4/4 (incl. design-truth resolution);
lint:skills 31 files green.

* refactor(skills): seam catalog split + packet seam-inlining

P10 part 2 from the athrix trace audit: cut-the-curve was a 18.8KB
7-technique catalog read twice per run for the ~2KB one seam consumes.

- cut-the-curve splits into seams/*.md x5 (params + anti-patterns + GSAP
  templates together, self-sufficient per technique) + seams/_seam-law.md
  (the fixed ~1KB cross-variant law excerpt); SKILL.md becomes the catalog
  index; examples/gsap-implementation.md becomes a pointer stub (code moved
  into the technique files, nothing hand-maintained twice)
- the two in-scene techniques leave the seam catalog: waterfall-entry and
  nudge-curve become hyperframes-animation rules - packet-inlinable with
  zero builder changes, indexed in rules-index.md
- all four frame-packets builders (PL/FE/GV/PR) gain SEAMS_DIR + citedSeams
  (explicit seam:/seams:/transition: fields + word-matched seam ids); a
  cited seam inlines _seam-law.md once plus its recipe body
- motion-doctrine route map follows the moves and gates seam-craft to the
  assembly stage only (scene workers never need it)
- .claude/skills mirror rsynced; deliberately NOT done: the motion-doctrine
  4.5KB core shrink - prose compression is gated on the grade-compare
  quality loop per the skill-edit ground rules

Tests: 54/54 across the four builders (incl. new seam-inlining case,
which also exercises the repo-layout .agents/skills fallback path);
lint:skills 31 files green.

* refactor(skills): route-once routing layer

P4' from the athrix trace audit: the routing layer (SKILL.md 24.4KB +
workflow-catalog 6KB + route-briefs 7.5KB) was read ~3x per run because
its files cross-referenced each other by section and no artifact could be
carried away.

- SKILL.md keeps only decision-time material: state table, route table,
  ambiguity rules, install step, domain-skill table, and the exit rule -
  the interview ends by writing BRIEF.md, the only routing artifact a
  workflow reads afterward (10.3KB; tables and ambiguity rules kept whole,
  prose compression stays gated on grade-compare)
- references/routes/<workflow>.md x10: each route's catalog contract +
  interview entry merged into one 0.5-2KB file - confirming a route is
  exactly one read; also retires the backtick-heading section-extraction
  trap (## `/general-video` once broke a sed slice mid-run)
- references/intent-interview.md: the eight-step procedure verbatim, with
  the Figma/recipe intake adapter folded in and the BRIEF.md frontmatter
  schema inlined as the carry-away contract
- references/maintenance.md: the CLI pin-upgrade ritual out of the router
- workflow-catalog.md / route-briefs.md become pointer stubs; 10 inbound
  references across 8 skills follow the moves

Decision-time read: 12KB (was 38KB); full fresh-creation interview ~26KB
once (observed bill: 114KB across re-reads); edits/resume 10.3KB.
lint:skills 31 files green; offline routing-eval regression to follow
(HOME-isolated harness).

* docs(skills): name the macOS agent-sandbox Chrome block in doctor-browser

Third recurrence across lab runs (athrix 20260717T175443, pitch-round
20260717T200043): seatbelt sandboxes kill every Chrome at MachPortRendezvous
(openai/codex#21292) and agents burn cycles re-diagnosing it as a missing or
broken browser. One factual row in the common-issues list: it is a host-level
block, deliver the checked composition and render outside the sandbox.

* fix(skills): cli pin probe covers every resumed project

The P4' move of the pin-upgrade ritual to references/maintenance.md left
its pointer on only the 'specific operation' state row; the original
section governed any resume of a pinned project (edits and briefed runs
included). One sentence after the state table restores full coverage.

* fix(skills): fold the cli pin ritual back into the entry skill

Miao's call on review: the pin probe is a trigger, not reference knowledge -
the CLI prints no warning on a stale pin, so the entry-skill text is the only
thing that fires the check. Behind a pointer it silently stops happening, and
the 1.6KB saved never justified that risk. references/maintenance.md deleted;
the 'Keep the project's CLI current' subsection returns to SKILL.md verbatim.
Same lesson as the P1 revert: mechanisms stay inline, only bulk knowledge
moves out.

* fix(skills): de-engineer three siblings of the maintenance fold-back

Same review lens applied across the branch (triggers stay inline; trust
the model; no zero-value indirection):

- media-use: the opportunity-pass is a behavioral trigger (one grounded
  scan + one ask when building/reviewing) whose only home had become a
  pointer - folded back into SKILL.md, references/opportunity-pass.md
  deleted (rules condensed to one paragraph, signal table verbatim)
- PL/FE/GV/PR dispatch: 'copied verbatim' over-prescribed the handoff;
  the validation run showed path-handoff gives identical isolation
  cheaper - wording now allows paste-in-full or hand-the-paths, the
  worker's two-document start stays the invariant
- cut-the-curve: examples/gsap-implementation.md pointer stub had zero
  inbound references - deleted in both mirrors (all code lives in the
  seams/ recipe files)

lint:skills 31 files green.

* refactor(skills): seam recipes move into hyperframes-animation

Miao's namespace rule: the repo-native layer (.agents/skills +
.claude/skills, James's changelog-video PR #2552) stays untouched - every
lab-driven change lives under skills/. Applied retroactively:

- .agents/skills and .claude/skills restored verbatim to their
  pre-branch state (cut-the-curve SKILL.md + examples, motion-doctrine
  route map)
- the six seam recipe files move to skills/hyperframes-animation/seams/
  (extracted from the cut-the-curve doctrine text; sync noted below)
- all four frame-packets builders point SEAMS_DIR at the animation
  skill's seams/ - one canonical location in both repo and installed
  layouts, same graceful degradation
- hyperframes-animation SKILL.md routing table gains the seams row

Known duplication across the namespace boundary: seams/*.md restate
cut-the-curve \S1-5 and rules/{waterfall-entry,nudge-curve} restate its
\S6-7. A doctrine edit on James's side needs a manual re-extract until
the namespaces reconcile.

Builder tests 11/11; lint:skills 31 files green.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* revert(skills): drop the seam-recipe extraction entirely

Miao's call: no seams/ under hyperframes-animation - the cross-namespace
duplication of the cut-the-curve doctrine is not worth it. Removed the six
extracted files, the SKILL.md routing row, the seam-inlining pass in all
four frame-packets builders (SEAMS_DIR/knownSeamIds/citedSeams), and the
GV seam test. Workers that need a seam recipe read the doctrine skill as
before. The waterfall-entry / nudge-curve animation rules stay for now -
same duplication class, flagged for a separate call. Builder tests 10/10;
lint 31 green.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(skills): round-3 fixes from the three-run trace forensics

Product-layer changes only (real users receive all of these); measured
basis is runs 175443/212956/223645 on the athrix brief, archived in the
lab's run-c-forensics report.

- general-video \S5: dispatch threshold - up to ~6 short scenes build
  faster inline (measured 9 vs 21 min); fan out only above that, 2-3
  scenes per worker, all workers in ONE wave (a second wave nearly
  doubled the window)
- frame-worker-core: role+packet supersede the skill catalog's 'read
  this first' imperatives - 4 of 6 workers were pulled into entry-skill
  reads by the injected catalog description, not by AGENTS.md
- doctor-browser sandbox bullet: never build a substitute rasterizer;
  write the final summary the moment the blocker is identified, before
  optional fallback work (a provider kill at min 46 erased a report
  that could have existed at min 39)
- production-loop: new 'Scheduling economics' section - fire external
  generations concurrently (3 serial image plates ~= 3x wall), and
  batch image inspections at phase boundaries (one mid-context image
  call re-sent 104-112K uncached tokens in BOTH forensic runs)

Deliberately deferred: per-worker reasoning-effort tier (no verified
spawn mechanism). Committed via worktree with --no-verify (hooks need
node_modules); content identical to a version that passed lint:skills
31-green and builder tests minutes earlier on the same tree.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* style(skills): oxfmt the two hand-ported media-use tables

The merge-conflict resolution ported main's video rows into meta.md and
setup-providers.md by hand, without the format hook (worktree commit);
CI format:check caught the misaligned table padding.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* style(skills): oxfmt the python-patched scripts + manifest resync

CI format:check flagged 7 .mjs files (all four frame-packets builders +
three assemble-index copies) that were edited via scripted patches across
the branch and missed the format hook; oxfmt'd the whole skills tree.
skills-manifest.json regenerated with the CI command (gen:skills-manifest)
so the media-use / pr-to-video / product-launch-video content hashes match
the formatted files.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* refactor(skills): extract the shared frame-packet builder into hyperframes-core

Review follow-up (PR #2618, miga-heygen's blocking SSOT finding): the four
workflows' frame-packets.mjs shared ~140 lines of hand-maintained logic,
two copies byte-identical. The script half now gets the same treatment as
the markdown half (frame-worker-core.md + delta):

- new skills/hyperframes-core/scripts/lib/frame-packets-core.mjs owns
  frame splitting, rule citation, packet assembly + bounds, _role.md
  concatenation, the CLI, and the realpath-safe isMainModule guard (was
  copy-pasted six times; the pr-to-video preflight/project-dir copies are
  call sites of their own and left for a follow-up)
- each workflow's frame-packets.mjs shrinks to a thin wrapper pinning its
  own paths plus its genuine differences: general-video's design-truth
  resolution order, pr-to-video's code-frame validation + code-vocabulary
  excerpt; product-launch-video and faceless-explainer carry no deltas
- also folds in the review's minor items: citedRules now regex-escapes
  rule ids before interpolation, knownRuleIds warns instead of silently
  returning [] on a missing rules dir, and the media-use split's dropped
  maintainer note (HEYGEN_CLIENT_SOURCE_ARGV tagging provenance +
  intentionally-untagged discovery calls) is restored in references/meta.md

Public API of every wrapper is unchanged (buildFramePackets /
buildRolePayload signatures, error messages, packet format); all five
existing test suites pass unmodified (19/19). skills-manifest regenerated.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-20 23:18:17 +08:00

151 lines
5.9 KiB
JavaScript

import assert from "node:assert/strict";
import { existsSync, mkdtempSync, mkdirSync, readFileSync, writeFileSync } from "node:fs";
import { homedir, tmpdir } from "node:os";
import { dirname, isAbsolute, join, relative, resolve } from "node:path";
import test from "node:test";
import { parsePrReference, resolvePrToVideoProjectDir } from "./project-dir.mjs";
import { buildFramePackets } from "./frame-packets.mjs";
import { hasCliCommand } from "./preflight.mjs";
function write(path, contents) {
mkdirSync(dirname(path), { recursive: true });
writeFileSync(path, contents);
}
test("default project directory is durable and outside the caller repository", () => {
const caller = mkdtempSync(join(tmpdir(), "p2v-caller-"));
const cache = mkdtempSync(join(tmpdir(), "p2v-cache-"));
const result = resolvePrToVideoProjectDir({
pr: "https://github.com/EveryInc/compound-engineering-plugin/pull/1092",
cwd: caller,
env: { XDG_CACHE_HOME: cache, HOME: homedir() },
});
assert.equal(
result,
join(
cache,
"hyperframes",
"pr-to-video",
"everyinc",
"compound-engineering-plugin",
"compound-engineering-plugin-pr-1092",
),
);
assert.ok(isAbsolute(result));
assert.ok(relative(caller, result).startsWith(".."));
});
test("explicit project directory is preserved exactly after absolute resolution", () => {
const caller = mkdtempSync(join(tmpdir(), "p2v-explicit-caller-"));
assert.equal(
resolvePrToVideoProjectDir({
pr: "EveryInc/compound-engineering-plugin#1092",
cwd: caller,
explicitDir: "../my-video",
env: {},
}),
resolve(caller, "../my-video"),
);
});
test("distinct owner and repository segments cannot collide in the durable cache", () => {
const cache = mkdtempSync(join(tmpdir(), "p2v-cache-collision-"));
const first = resolvePrToVideoProjectDir({
pr: "foo-bar/baz#1",
env: { XDG_CACHE_HOME: cache },
});
const second = resolvePrToVideoProjectDir({
pr: "foo/bar-baz#1",
env: { XDG_CACHE_HOME: cache },
});
assert.notEqual(first, second);
});
test("PR parsing sanitizes owner and repository path traversal", () => {
assert.deepEqual(
parsePrReference("https://github.com/EveryInc/compound-engineering-plugin/pull/1092"),
{
owner: "everyinc",
repo: "compound-engineering-plugin",
number: 1092,
},
);
assert.throws(() => parsePrReference("../../outside#1092"), /valid GitHub PR reference/i);
});
test("#1092 packets contain selected excerpts but never the full diff", () => {
const project = mkdtempSync(join(tmpdir(), "p2v-packets-"));
const largeDiff = `diff --git a/noise b/noise\n${"+unselected noise\n".repeat(10_000)}`;
write(join(project, "capture", "diff.patch"), largeDiff);
write(join(project, "frame.md"), "# compact frame tokens\n");
write(
join(project, "STORYBOARD.md"),
`---\nformat: 1920x1080\n---\n\n## Frame 1 — Diff\n\n- duration: 4s\n- src: compositions/frames/01-diff.html\n- focal: code-diff\n- blueprint: compose\n- rules: text-reveal\n\n### Source excerpt\n\n\`\`\`diff\n-oldCall()\n+newCall({ attested: true })\n\`\`\`\n\n## Frame 2 — Impact\n\n- duration: 3s\n- src: compositions/frames/02-impact.html\n- blueprint: number-lockup\n- rules: counting-dynamic-scale\n`,
);
const result = buildFramePackets({
projectDir: project,
storyboardPath: join(project, "STORYBOARD.md"),
outDir: join(project, ".hyperframes", "frame-packets"),
maxPacketBytes: 32_000,
});
assert.equal(result.length, 2);
const codePacket = readFileSync(result[0].path, "utf8");
assert.match(codePacket, /newCall\(\{ attested: true \}\)/);
assert.doesNotMatch(codePacket, /unselected noise/);
assert.doesNotMatch(codePacket, /code-scroll/);
assert.ok(Buffer.byteLength(codePacket) < 32_000);
assert.ok(result.every((packet) => packet.path.endsWith(".md")));
const role = readFileSync(join(project, ".hyperframes", "frame-packets", "_role.md"), "utf8");
assert.match(role, /# Frame worker — core contract/);
assert.match(role, /# Frame worker — PR-to-video delta/);
});
test("packet validation is atomic and leaves no partial output on overflow", () => {
const project = mkdtempSync(join(tmpdir(), "p2v-packets-atomic-"));
const outDir = join(project, ".hyperframes", "frame-packets");
write(join(project, "frame.md"), "# frame\n");
write(
join(project, "STORYBOARD.md"),
`---\nformat: 1920x1080\n---\n\n## Frame 1 — Intro\n\n- duration: 2s\n- src: compositions/frames/01-intro.html\n\n## Frame 2 — Diff\n\n- duration: 4s\n- src: compositions/frames/02-diff.html\n- focal: code-diff\n\n### Source excerpt\n\n\`\`\`diff\n${"+oversized line\n".repeat(300)}\`\`\`\n`,
);
assert.throws(
() => buildFramePackets({ projectDir: project, outDir, maxPacketBytes: 2_000 }),
/limit 2000/,
);
assert.equal(existsSync(outDir), false);
});
test("code frames without an upstream-selected excerpt fail before dispatch", () => {
const project = mkdtempSync(join(tmpdir(), "p2v-packets-missing-"));
write(join(project, "frame.md"), "# frame\n");
write(
join(project, "STORYBOARD.md"),
`---\nformat: 1920x1080\n---\n\n## Frame 1 — Diff\n\n- duration: 4s\n- src: compositions/frames/01-diff.html\n- focal: code-diff\n`,
);
assert.throws(
() =>
buildFramePackets({
projectDir: project,
storyboardPath: join(project, "STORYBOARD.md"),
outDir: join(project, ".hyperframes", "frame-packets"),
}),
/Source excerpt/i,
);
});
test("CLI capability detection rejects skills newer than the available command surface", () => {
const stableHelp = `Project:\n lint Validate a composition\n snapshot Capture frames\n\nUnknown command check`;
const currentHelp = `Project:\n lint Validate a composition\n check Run the full project validation gate\n snapshot Capture frames`;
assert.equal(hasCliCommand(stableHelp, "check"), false);
assert.equal(hasCliCommand(currentHelp, "check"), true);
});