Commit Graph
20 Commits
Author SHA1 Message Date
Michael Wang 756b2fcae1 fix(cli): fixed-name outputs and history turn records replace a link, never write through it (#7911)
* fix(cli): fixed-name outputs and history turn records replace a link, never write through it

transcript.json, hyperframes.json patches, the grade-compare sheet, the batch manifest, diff and
measure outputs, lambda stack state and the history turn records are written through a temp file
renamed into place. A linked hyperframes.json is left alone, and the default .hyperframes/<tool>
output folder is used only when every folder on the way is real.

* fix(cli): measure and diff pictures and sbs.mp4 replace a link, never write through it

writeImage and the diff side-by-side now have ffmpeg write into a new private folder beside the
output, then rename the file over its name. measure frames already staged and renamed its PNGs.
2026-11-16 02:59:43 +00:00
WaterrrForever eb0a52c298 fix(cli): measure answers the four mistakes agents make most (#7443)
* fix(cli): measure answers the four mistakes agents make most

The usage errors agents hit most on `measure`: no op named, a path it
cannot read, and a flag it does not take. Some agents never get past
them to a successful measure.

- `measure <video>` with no op (alone or with --json) runs `probe` and
  says so on stderr. With other flags the op is a guess, so the
  unknown-command hint asks for one; it now names a path that does not
  exist yet too.
- When ffprobe cannot read a file, the error carries ffprobe's reason and
  a matching fix: a cut-short download, a page saved as .mp4, a
  permission.
- An unquoted path with spaces says to quote it, both where the extra
  words are rejected and where the cut path is missing.
- Window flags take --from/--to, and folder flags take -o.

* refactor(cli): keep comment share at the base in the measure files

* test(cli): expect a spaced path as the shell split it, on Windows too

* fix(cli): a cut-short MP4 says download it again, read from its header and ffprobe's specific line

* fix(cli): an unquoted spaced path reaches probe or its quote hint wherever it falls
2026-11-09 14:42:37 +00:00
Miguel Ángel 5ee9e928d5 fix(core): hlg footage tone-maps to sdr at the bt.2408 reference white (#7234)
* fix(core): hlg footage tone-maps to sdr at the bt.2408 reference white

* fix(core): an HLG clip whose stream leaves its transfer unset keeps HLG's white

An SPS with an unspecified transfer takes the stream's tag, as its frames do; a failed keyframe read is not cached; the grey test needs ffmpeg 8.
2026-11-05 13:04:56 +00:00
WaterrrForever 1fecf5b82a fix(cli): two CLI fixes from Wenbo's reverse test (paywall link, plan label) (#7099)
* feat(cli): a paywall refusal carries its page link in its own url field

An agent hit the Pro paywall, found the link only inside the fix sentence,
and handed the person a shell command instead of the page. The link now
also comes as url.

* fix(cli): auth status says hyperframes is the plan, not the HeyGen app's

An agent read user.subscription.plan (the HeyGen app's pro) as the
HyperFrames plan and ran past Free. With the HyperFrames plan read,
billing_notice now names which is which.

* fix(cli): a paywall refusal with url null names no purchase link

HeyGen sends url: null when it can't sell to this account right now. The
refusal now says so and carries no link, as reverse start does since #7031;
a missing url (older server) still gets the plans or credits page.
2026-11-05 05:50:59 +00:00
WaterrrForeverandClaude Opus 5.5 823cd126ee fix(cli): measure reads an odd-sized box exactly (#7090)
A crop on yuv420p rounds an odd size or offset down to even. readClip
split the 32x32 output as 33x33 bytes, so a 10-frame clip came back as
9.4 frames and every frame after the first was misaligned; an odd offset
also shifted the chroma. Raw reads now convert to rgb24 (or gray) before
the crop, which is exact at any size and place. extract and diff stay on
yuv and add exact=1.

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-05 05:31:40 +00:00
WaterrrForeverandClaude Opus 5.5 2daedcdafc feat(skills): style templates on the HyperFrames plan (#6842)
* fix(cli,skills): say a step's credits are its total, and keep cost out of retries

An out-of-credits refusal named what the step needs, and an agent read
that as the shortfall. It now says the number is the step's total.

After its last try, an agent told the person what was spent and what
another try would cost. The HeyGen reference now says not to.

* fix(cli): plan avatar credits from the HyperFrames price rows

An avatar's credits came from its old API price, about five times what
the plan charges, so --max-credits refused calls that fit and a top-up
asked for too much. They now use the Avatar IV photo row plus the
general avatar video row, 950 credits a minute.

* fix(cli): pin the avatar price test and keep pricing under the comment share

* fix(cli): plan avatar seconds on the Avatar IV row alone

The general avatar row is only checked at admission and billed on
seconds left after Avatar IV, so adding it to every second made a 15 s
script plan at 238 instead of 200 and a 220 limit refuse a call that fits.

* feat(skills): creator templates on the HyperFrames plan

A Pro account asks for a video in a creator's format and the agent pulls that
template on demand. The packs sit in the private bucket behind the plan-gated
bundle route, so a Free account gets a 402 and the upgrade step. A pull costs
no credits; making the film spends them as Reverse does.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* feat(skills): make creator-remix the one template skill

SKILL.md holds the catalog, the Pro openings, the pull and the credit
rules. references/remix.md is how to make the episode, from Desktop's
creator-remix with only what the app alone has swapped for the CLI.
The packs now hold only the template, so their hashes change.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* feat(skills): the creator-remix skill and its packs

SKILL.md holds the catalog, the Pro openings, the pull and the credit
rules. references/remix.md is how to make the episode, from Desktop's
creator-remix with only what the app alone has swapped for the CLI.
The packs now hold only the template, so their hashes change.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* fix(skills): word creator-remix's sign-in steps the way media-use does

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* feat(skills): a creator-remix presenter runs on the plan by default

The person's own HeyGen avatar is recommended, not required: without
one, 小Lin's presenter is made with HeyGen Video 1 from their photo.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* feat(cli): pin template packs whose voice bills the plan first

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* fix(cli): offload media named inside template tags

References in a composition's <template> were never rewritten, because the DOM
query stops at the tag and template.content does not serialize, so the file stayed
in the zip. A stem matched as a plain word and a same-named file elsewhere counted
as a mention too. A 5-minute presented film went from 196 MB to 71 MB.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* feat(cli): lipsync, and avatars that speak a finished voice

Video 1 takes audio as a reference and re-paces it, so a shot's lips follow its
own track and drift up to a second from the voice. generate --type lipsync redoes
the mouth to the exact voice. generate --type avatar takes --audio, and --avatar
for the person's own look, so the lips land on the voice from one job.

Also moves the plan rows to the 2026-10-30 price book, estimates a voice's credits
so --max-credits can hold it, logs jobs from a folder with no project, and describes
the resolve flags.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* feat(skills): presenters go avatar first, and a voice can be stock

The person's own avatar, then Avatar IV from their photo, then Video 1 with
lipsync. With no clone or recording, a stock voice named in the credits. Pins the
five rebuilt packs. The archive test keeps its ../ under GNU tar with -P.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* test(cli): fix avatar price and sfx provider tests, trim comments

A wav gives the avatar price test an exact length on every platform. The
sfx tests now expect HeyGen first. Comment share is back under the base.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* fix(core): read a font shorthand whose size nests parentheses

`font: calc(var(--size) * 1px)/1 "X"` cut at the first closing parenthesis, so a
bad family name failed the render.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* fix(cli): one ledger row per job, and search skips a template's own pictures

A job done at once logs one row, transcribe logs to the project, and resolve no
longer offers a component's file for a search. --reuse and --provider get help text.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* feat(skills): pin the tested template packs, and a board needs no voice

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* test(cli): read the transcribe ledger row as JSON, for Windows paths

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* chore(cli): pin the Big Questions pack without the film length check

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* docs(skills): call them style templates, and the docs example pulls a real slug

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* chore(cli): pin the cleaned template packs

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* docs(skills): drop the stock-presenter ban and the no-spend-before-storyboard rule

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* chore(cli): pin the Paper Trail and Long Story Short packs without the stock-presenter ban

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* feat(skills): rename creator-remix to style-remix, and the five templates to names that say the look

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* feat(skills): style-remix lists the five templates when none is named

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* chore(cli): pin the Finance Explainer pack that varies its motion graphics

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* feat(cli): media-use generate --type cutout takes a shot out of its background on the plan

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* chore(cli): pin the Finance Explainer pack without the provisional variety rule

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* chore(cli): pin the five style packs with variety rules measured on real films

Animated Science gets a worlds-and-boards budget, 3D True Crime a main board and a
brief corner note, 3D Brand caps by measured rate, Finance and Collage set pieces and
more than one look.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* docs(skills): media-use names the on-plan cutout and lipsync commands, not the heygen CLI ones

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* fix(cli): cutout retries dedupe on request_id, uploads carry their real type; style-remix is public

The background-removal route dedupes on the body's request_id and ignores the Idempotency-Key
header, so a retry after a lost answer started a second job: runJob now also sends the key in the
body for such a route. Uploads typed every non-MP4 file as audio, so WebM and MOV inputs were
refused: they now take their type from the extension. Fails without the fix: the new cutout test
in generate.test.ts sees audio/mpeg for WebM and MOV.

style-remix drops metadata.internal and is listed with the other published skills.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* chore(cli): keep the comment share of the touched files at main's

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* docs: count style-remix in the README and CLAUDE.md skill lists

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* feat(skills): rename style-remix to style-sampling

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-03 11:07:02 +00:00
Jerrai 3f42dc1c73 feat(cli): diff --offset compares the original at t with yours at t + offset (#7057)
* feat(cli): diff --offset compares the original at t with yours at t + offset

Every per-frame measure (SSIM per frame and per cell, frames.tsv, cuts,
missing content) reads yours offset seconds later, and a project folder is
captured at the shifted times. The window keeps to where both sides have
frames and says so in warnings; an offset with no overlap, or one that is
not a number, is refused with a fix. Sound keeps its own offset reading,
duration is reported as not measured, and the result echoes offset.

* refactor(cli): trim diff offset comments under the file's comment share

* fix(cli): rebase full-length diff offsets and reject overflow

Keep offset streams on a zero-based clock even when every frame is selected. Cover an untrimmed delayed render and reject non-finite offsets before file or project processing.

— Jerrai

* refactor(cli): remove redundant offset filter comment

— Jerrai
2026-11-03 10:48:47 +00:00
WaterrrForever 7ae108005a fix(cli): measure cuts reads a zoom that speeds up as a move, not a cut (#7075)
* fix(cli): measure cuts reads a zoom that speeds up as a move, not a cut

Bug bash (Stripe "pay", 0.9.6): the app window's zoom-in at 0.2 s changes
3, 9, 12, 5 grey levels a frame, and the 12 crossed a cut's level, so
measure cuts listed a cut there and diff failed the rebuild (pass: false at
0.93 similarity) for missing it.

A single-frame cut is now a fast move when the frames either side move too
(30% of its change) and the frame before, zoomed 0.8-1.25x and shifted a few
pixels, comes within 40% of its change of the frame after. A punch-in also
zooms, but out of a still picture, so it stays a cut.

* fix(cli): a zoom is a move only when the picture moves on both sides

Review (hf-review): motion on one side hid a real punch-in out of a still
picture next to a moving shot, and the mirrored punch-out. isMove now needs
both neighbours moving (min, not max). The 33-film check now changes only
Stripe's 0.2 s zoom; league-promo 95.93 s and M1000 5.43 s are cuts again.
2026-11-03 10:20:03 +00:00
WaterrrForever e9de593fe9 fix(cli): measure picks more than 100 frames on ffmpeg 8 (#7071)
* fix(cli): measure picks more than 100 frames on ffmpeg 8

ffmpeg 8 refuses a flat sum of more than 100 terms ("Error while parsing
expression"), and every frame pick in measure, diff and snapshot was one flat
sum of eq(n,k). The ffmpeg HyperFrames downloads is 8.1.2, so measure frames,
diff, face, person, drawn boxes and snapshot all failed past 100 frames.
PostHog: every such cli_error since 0.9.3 came from Windows agents on ffmpeg 8.

sumOf keeps a sum of up to 100 terms flat and nests a longer one in halves.

* fix(cli): sums nest from 51 terms, so ffmpeg 8 takes every pick count

Review (hf-review): 100-term leaves still failed on ffmpeg 8.1.2 once nested,
at 199-201 eq() picks, and snapshot's deeper terms failed at 97-100 times.
ffmpeg 8 limits how deep an expression nests, and a flat sum counts a level
a term. Leaves of 50 pass every count from 1 to 1000 in both shapes, and
1500-5000. Tests decode 199/200/237/401 picks and 97/100/199 snapshot times.
2026-11-03 10:14:37 +00:00
WaterrrForever 91e7f4d48f fix(cli): measure and diff tell an agent what to type after a wrong call (#7072)
The top measure and diff errors since 0.9.4 (PostHog, CLI project) were
agents' calls, not bad videos:

- A flag from another command: --from/--to on ops that take --start/--end
  (extract is the other way round), -o for --out. The unknown-flag error now
  names the flag that means the same here.
- measure sync without --roi stopped at citty's bare "Missing required
  argument"; diff with one video at "Missing required positional argument:
  YOURS". Both now reach their own message with the command to run.
- A Windows path whose backslashes bash dropped (D:videoclip.mp4) was only
  "no file at". The fix line now says to quote it or write it with /.
2026-11-03 09:59:39 +00:00
WaterrrForever 618c486734 fix(cli): measure and diff report why they failed, and reverse reports its runs (#6997)
* fix(cli): measure and diff report why they failed, and reverse reports its runs

Since launch, 97 people saw a bare "Command failed" from measure: runMeasure
and diff called failCommand() without the error, so telemetry kept only the
wrapper. 59 agents ran `measure <file>` with no op and got no hint. Reverse
runs had no skill tag, so nobody could count how many finished.

- runMeasure and diff pass the error to failCommand.
- An unknown word that is an existing file names the commands to put first.
- references/start.md sends skill_invoked and skill_completed beacons.

* fix(cli): the file hint stays out of the root command list

Jerrai: `hyperframes index.html` would list every top-level command. fileHint moves to
didYouMean.ts, answers only inside a command group, and has tests for the root, a missing
file and a group with no commands.
2026-11-02 10:03:08 +00:00
WaterrrForever b1316e61d1 fix(cli): diff stops counting a fast move as an extra cut (#6978)
A regenerated shot never lines up with a whip frame by frame, so diff listed every fast move.

A jump now counts only above the original's own motion around it.

fails without the fix: reads a change no stronger than the original's motion as the same fast move
2026-11-02 04:50:16 +00:00
WaterrrForever 99223d993c fix(cli): diff warns when yours runs at another frame rate (#6976)
A root without data-fps on a 24 fps film rendered at 30 fps, and nothing said so.

fails without the fix: warns about a render at another frame rate
2026-11-02 04:09:30 +00:00
Miguel Ángel de6ec3811e fix: cache paths follow HYPERFRAMES_CACHE_DIR (#6716)
* fix: cache paths follow HYPERFRAMES_CACHE_DIR

Every place HyperFrames keeps downloaded or built files now takes its
folder from one helper, hyperframesCacheDir() in @hyperframes/core. The
default stays ~/.cache/hyperframes; HYPERFRAMES_CACHE_DIR moves it.

* fix: register the cache-dir subpath for bun and node, and build inspector from core source

* test: the cache-dir override test uses a folder that is absolute on every platform

* fix: the opencv cache follows HYPERFRAMES_CACHE_DIR

* fix(cli): npm installs run in their staging dir, so no cache path reaches a command line

* fix(cli): whisper.cpp is cloned inside its build dir, so no cache path is a git argument

* test(cli): the whisper clone test finds no system whisper on Windows either
2026-11-01 22:44:11 +00:00
WaterrrForever 69400df276 fix(cli): the cut detector keeps real cuts in live footage (#6923)
* fix(cli): the cut detector keeps real cuts in live footage

#6894 left held frames out of every baseline and called any run over 3 frames a fast
move. On live footage that raised the baseline past real jump cuts and dropped blur
transitions between shots. Only animation that moves and holds in turn gets the moving
baseline now, and a run stays a cut when its tones change.

* fix(cli): a wipe through black is a cut, and a cut near a guide's edge is refused

A whip keeps its tones through every frame of the run, so that is the test, not only
the two ends: johnny's wipes between two views of one map match at the ends alone.
foldShort folds pieces of a few frames now. At 0.5 s it let a real cut through to a
paid shot, and the classifier already handles the flashes it was there for. --allow-cuts
is in the skills.

* refactor(cli): name the whip check instead of commenting it
2026-11-01 15:30:29 +00:00
Miguel Ángel 8a0b8a9c22 fix(cli): measure ink, one output-folder flag spelling, logo wordmark variant (#6891)
* feat(cli): measure ink reads text size, --out and --output both work, logo --variant wordmark

measure ink reports the bounds, size and lines of text in a region of one frame, so a rebuild can be sized without a script. measure and snapshot take --out and --output for the same folder. media-use resolve --type logo --variant wordmark returns the brand's wordmark when theSVG has one.

* fix(cli): measure ink stays under the complexity and comment limits, one projectOf

* fix(cli): snapshot and measure also accept --output-dir

* fix(cli): projectOf moves without adding comment lines

* fix(cli): measure output alias list type-checks as an argument

* fix(cli): a logo variant never answers a default logo request; test output flags

* style(cli): format the new tests
2026-10-31 22:26:35 +00:00
Miguel Ángel 5259097261 fix(cli): one cut detector that tells real cuts from flashes and fast moves (#6894)
* fix(cli): one cut detector that tells real cuts from flashes and fast moves

* fix(cli): a flash must come back within a few frames; trim comments, format

* test(cli): the cut fixture gets a 60 s timeout; format

* test(cli): drop a history comment
2026-10-31 21:40:38 +00:00
WaterrrForeverandMiguel Angel Simon Sierra f2358315e5 feat(skills): re-land reverse any video on the HyperFrames plan, with clearer credit wording (#6833)
* fix(cli,skills): say a step's credits are its total, and keep cost out of retries

An out-of-credits refusal named what the step needs, and an agent read
that as the shortfall. It now says the number is the step's total.

After its last try, an agent told the person what was spent and what
another try would cost. The HeyGen reference now says not to.

* fix(cli): plan avatar credits from the HyperFrames price rows

An avatar's credits came from its old API price, about five times what
the plan charges, so --max-credits refused calls that fit and a top-up
asked for too much. They now use the Avatar IV photo row plus the
general avatar video row, 950 credits a minute.

* fix(cli): pin the avatar price test and keep pricing under the comment share

* fix(cli): plan avatar seconds on the Avatar IV row alone

The general avatar row is only checked at admission and billed on
seconds left after Avatar IV, so adding it to every second made a 15 s
script plan at 238 instead of 200 and a 220 limit refuse a call that fits.

* fix(cli): the credits link opens the web plan page, which is live

* test(cli): pin the production credits link too

* chore(skills): regenerate the skills manifest after merging main

* docs(cli): keep the person measure's doc comments to four lines

* docs(cli): keep the measure doc comments to four lines

* docs(cli): keep the measure comment lines to 120 characters

---------

Co-authored-by: Miguel Angel Simon Sierra <miguel.sierra@heygen.com>
2026-10-31 00:47:54 +00:00
James RussoandClaude Opus 5.5 b45e602faa revert: feat(skills): reverse any video (#6754) (#6840)
* revert: feat(skills): reverse any video (#6754)

Keep the reverse-any-video skill and its CLI billing commands out of main until
web subscriptions are live (/pricing and /account/plan return 404 today).
Re-land together with #6833 once those pages ship.

This reverts commit cb2389cf35.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

* chore(scripts): allow the #6754 revert deletions

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-30 14:32:26 +00:00
cb2389cf35 feat(skills): reverse any video on the HyperFrames plan (#6754)
* feat(skills): reverse any video on the HyperFrames plan

Reverse rebuilds a video as an editable HyperFrames project and re-shoots its
people with HeyGen. It runs for a person signed in on HyperFrames Pro; Free is
told it is a Pro feature and given the upgrade step.

- skills: reverse-any-video; media-use is the one gate for HeyGen calls
  (sign-in, credits, refusals)
- cli: media-use generate (image, video shot, avatar, voice, music) with --plan
  pricing and --max-credits; measure, diff and analyze for the rebuild; the
  HyperFrames plan in auth status; billing subscribe and top-up wait on the
  plans or credits page
- remotion-to-hyperframes compares with `hyperframes diff` instead of its own
  shell scripts

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* chore(skills): satisfy CI gates for reverse-any-video

- docs: list diff, measure, analyze and billing in "Find your command" in
  docs/packages/cli.mdx, each with its own section.
- skills: bring media-use/SKILL.md under its 5120 B budget by pointing setup,
  direct-recipe and treatment detail at the references that already hold it;
  the sign-in, credits, --max-credits and billing rules stay in SKILL.md.
- comments: register transcript.json and REVERSE.md as project files for the
  citation checker, and drop a history note from face.test.ts.
- comments: cut restating prose or move it into names so every changed file is
  at or under its comment share. Allowlist the two deleted remotion scripts in
  check-no-main-deletions.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

* fix(cli): terminate measure's ffprobe options with --

probeVideo passed the input path straight after its options, so a path
starting with "-" would be read as a flag; the producer's ffprobe argv
contract test failed on it. runFfmpeg's fixed flags move to a constant
so the contract no longer mistakes that ffmpeg wrapper for a probe.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

* test(cli): split diff's video tests into three files under CI's per-file limit

The file took ~131 s on CI against the flake gate's 120 s, and its heaviest test (four
comparisons) hit the 20 s per-test limit. The video tests now live in three files sharing
diff.test-helpers.ts, and that test is two tests of two comparisons each.

analyze reads each part once and checks the bytes it read, instead of a stat then a read
(CodeQL js/file-system-race).

* fix(skills,cli): one credits rule; ask before dropping a step that won't fit

On dev with a 100-credit limit the agent priced a re-shoot with --plan and dropped it without
asking (J5), and in J6 it told the person a price. SKILL.md's Credits rule now covers both:
--plan is for the agent, and when a step won't fit (a --plan over what is left, or a refused
call) the agent says what doesn't fit and asks before dropping or shrinking it.
setup-providers.md's older confirm-before-paying rule points to it.

--plan now runs the same checks as the real call (checkRequest), so it no longer prices a
request that would be refused. The re-shoot recipe in people.md gains the --prompt it needs.
heygen.md: a sign-in also makes images, and --plan's usd is the API charge rounded to $1/60
while its credits come from the list price.

* fix(cli): auth status drops 'balance unavailable' above the plan's credits; sign-in page title

* test(cli): keep diff's video tests inside the flake gate's limits

Under the gate's CPU contention every diff test needing face detection or
optical flow paid opencv.js's 11 MB download and WebAssembly start-up, and
every diffVideos call wrote four worst-moment pictures (about 28 ffmpeg runs)
no assertion read. Tests ran 21-28 s against the 20 s limit.

- loadOpenCvFirst() stages opencv.js in a beforeAll (from this machine's
  cache, a temp copy kept between runs, else the network).
- diffVerdicts() runs diffVideos with worst: 0 for tests that only read
  verdicts; the worst-moment tests keep the pictures.
- The carried-text test is split into its dirty and clean halves.

Locally with 8 CPU burners on 8 cores: slowest test 7.7 s, files 24-30 s.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

* fix(cli): generate --plan refuses what the real call refuses

checkRequest now holds every pre-send check (the --out extension and
--mask without --motion joined the route body and guide checks), and
generate() runs it first, so --plan and the real call share one function.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

* fix(cli): plans link uses from=cli and follows HYPERFRAMES_ENV; no balance notice beside the plan

- pageUrl sets from=cli, the parameter the pricing page reads to send a
  CLI buyer back to the terminal.
- The plans and credits pages are on dev.hyperframes.dev with
  HYPERFRAMES_ENV=dev, hyperframes.studio otherwise.
- auth status --json omits the 'HyperFrames balance is unavailable' notice
  when the plan was read.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

* fix(skills): reverse-any-video re-checks sign-in on resume; REVERSE.md holds no prices

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

* test(cli): split diff-people's whole-frame reuse test into three

It ran five diff comparisons in one test and took 20.2-20.6 s under the flake
gate's contention, over the 20 s limit. Each piece now runs at most two
comparisons against a shared ledger: copy and burned-in title, footage cut
whole, and cuts that only fed a generation. Under 24 CPU burners locally the
slowest of the three takes 3.0 s, where the combined test took 4.9 s under 8.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

* fix(cli,skills): reverse resume asks after one failed retry; out-of-credits names the step's price

- media-use generate: when HeyGen refuses for credits without saying how many, the refusal
  names the CLI's own price for the call (what --plan prints) as "needs about N" and
  "billing top-up --needed N", instead of "needs more".
- reverse-any-video: never repeat auth status's plan/credits line; a step an earlier session
  gave up on gets one more try, then ask; a command stored in REVERSE.md is a note, rebuilt
  from its recipe and checked with --plan, never run as written.
- people.md / heygen.md: a refused or failed job gets one more try, test calls included,
  then stop and ask.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

* fix(cli,skills): send a failed HeyGen job again as new; resume asks if the limit still applies

- runJob: a key whose job failed or was refused is recorded in the config dir
  (heygen-failed-keys); the next run with the same inputs sends key-1, key-2, ... so HeyGen
  starts a new job. A finished or still-running job keeps its key and is picked up, so
  nothing is paid twice. "fix the request it names, then run again" now holds.
- reverse-any-video: on resume after a run under a credit limit, just ask whether it still
  applies, naming no costs or numbers.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

* refactor(cli,skills): drop what reverse-any-video no longer uses

The skill rebuilds from measure probe, cuts, frames, events and face, and checks with
diff. analyze, diff --explain and eight measure commands (trail, box, ink, rhythm,
objects, track, flow, continuity) have no caller, so they go, with their tests and docs.
Examples now use original.mp4 instead of the old .reverse/source.mp4 evidence folder,
and diff's --segments is described as a file rather than REVERSE.md.

* fix(cli): check no longer copies VP9 and AV1 videos before it starts

Chrome plays both, alpha included, and the proxy is made on demand if a browser ever
asks. Copying remove-background's VP9 cutouts took minutes on projects that have them.

* fix(cli,skills): keep paid retries, credit limits and lip sync honest

Retries keep their key after 401, 403, 408, 409, 425 and 429, which say
nothing about the job, and failed keys are scoped to the API and payer.

Credits come from the plan's video rows instead of list dollars, and
reference pictures past the first two count toward --max-credits.

Lip sync reads sound on its own timestamps, so a delayed track fails
the gate. Look and energy call two near-zero values the same.

--plan refuses a missing input as the real call does. The skills teach
the direct sign-in, its credential path and the billing commands.

* chore(cli): keep the new pricing and energy files under the comment share

* fix(cli): scope failed HeyGen keys to the signed-in account

Failed keys were scoped by the local user block, which is absent for a
host's token and display-only otherwise, so two accounts could share a
scope and one could start a second paid job.

The scope now comes from the account /v3/users/me reports for the token
in use. When that cannot be told, no failure is recorded and the key
stays the same.

* fix(cli): fix a job's sender when it starts

Failure scope was looked up again after polling, so a sign-in during a
job could record one account's failure under another and rotate its
finished key. The credential is now read once per job: it signs the POST
and owns any failure, even if someone else signs in meanwhile.

Prefer username to email, since /v3/users/me returns no user id.

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: James <james.russo@heygen.com>
2026-10-30 13:24:02 +00:00