- F-01: cost bar crit (red) state past 90% of budget
- F-02: normalize() hardens fetched board state against sparse payloads
- F-03: /thumb 404s for videos with no extractable poster frame instead
of serving raw video bytes
- F-04: checkpoint artifact path refs only resolve inside the project dir
- F-05 (board half): stall detection — in_progress stage with no disk
activity >10min renders red 'stalled?' + header badge flips to STALLED?;
verified against the real wedged why-cities-glow project
- eval harness from dogfood session committed (visual regression +
interaction smoke, capture watcher, server/gate test suites) +
regression tests for each finding; 46 backlot tests green, visual eval
green (restage-before-capture note logged)
- README 'Watch It Happen' section with four staged screenshots (fictional
demo productions, generated placeholder art — no private project content)
+ governance section notes enforced approval gates
- scripts/backlot_screenshot_stage.py: stages 4 demo projects in 4 pipeline
states against OPENMONTAGE_PROJECTS_DIR and captures the shots with
Playwright — reproducible README imagery
- lib/paths.py: OPENMONTAGE_PROJECTS_DIR env override (checkpoints, events,
and the board all follow one root); backlot/state.py now imports it
(was still defining its own copy — the exact drift the review warned of)
- undeclared-stage checkpoints (e.g. a legacy 'idea' run under a cinematic
manifest) now slot into their canonical rail position instead of dangling
after publish, drawn dashed + italic with an 'unlisted' note
- ChangeHub subscriptions filtered per project: unrelated-project bursts
can no longer flood a board's queue and starve its own change signal
- thumbnail temp files unique per request (concurrent-miss race on the
shared .tmp path corrupted the cache)
- watcher change-mapping is pure string work (no per-path resolve() in
thousand-file change batches); 'C:'-style project ids rejected
- replay: tz-naive timestamps treated as UTC; final render/script no
longer leak at t0 on storyboard-less projects; single tick chain on
rapid pause/play; drag-safe scrubber (label tracks input, board renders
on release); render-video playback survives SSE re-renders
- state: scene id 0 joins correctly, nested depth>0 events don't corrupt
generating state, out-of-project asset paths honestly unserveable,
negative durations clamped, tolerant manifest stage parse
- UI: decisions alt filter precedence fixed, activity counts parallel
same-tool runs, el() html sink removed, NaN-safe formatters
- replay mode: scrub a completed run from checkpoint history + event
timestamps — stage rail rewinds, script/storyboard/renders appear at
their real moments, generating shimmer replays; ~20s full-run playback
- stage history_entries exposed in BoardState (powers replay + versions)
- entrance choreography plays on first paint only (not on SSE refreshes)
- live-run fixes found by driving a simulated production against the
board: null rendered by native append, activity ticker showing closed
starts as running, scene-id label handling for 'scene-N' ids
- scripts/backlot_simulate_run.py: drives a fake production through the
REAL contract (init_project, in_progress heartbeats, gated
awaiting_human -> approved, per-scene events, growing manifest) —
live-board verification + demo driver
- backlot/README.md
- backlot/state.py: BoardState from disk — stage rail with gate audit
(gate_skipped detection from history/), scene_plan x script x
asset_manifest storyboard join, takes, generating-state from events,
media discovery incl. atelier root-render heuristic, degradation ladder,
library summaries
- backlot/server.py: FastAPI on 4750 — /api/projects, /api/project/{id}/state,
SSE change feeds (project + library) fed by a watchfiles watcher,
/media with range support and traversal protection, UI mounts
- backlot/__main__.py: 'python -m backlot open [project]' idempotent
launcher (spawns detached server, opens browser); 'serve' foreground
- verified against real projects: 73 listed, full state for
signal-from-tomorrow, 206 range responses, SSE change push on
filesystem write
Licensing (finding 1):
- Mocap library is now 100% CMU-sourced (free for any use). Replaced the 3
Meta/FAIR clips with CMU equivalents: wave=141_16, shuffle=77_29 (creep);
dropped the un-CMU "dab", added twist=141_12. Deleted the 4 committed FAIR
BVHs (dab/jumping/wave_hello/zombie).
- Ship Patrick Hand's SIL OFL license (assets/OFL.txt) beside the bundled font
— OFL permits embedding/redistribution; this is the required attribution.
- Add THIRD_PARTY_NOTICES.md (Patrick Hand OFL + CMU) and rewrite mocap/NOTE.md
to drop the "verify before commercial use" caveat (no longer applicable).
Stale clip names (finding 2):
- Update the /ink-art command files (.claude/.github/.cursor/.codex),
character-design-director, and the creative skills to the current catalog
(wave/twist/…), and point to add-motion.mjs.
- ink-puppet.js: console.warn on an unknown clip name instead of silent dead-time.
Examples (finding 3):
- Remove broken standalone reel.html/momentum.html (they referenced a missing
ink-theater.js and momentum shipped the subset font the fix warns against).
- Keep mocap-figure/ as the canonical self-contained, lintable example; refresh
its bundled clips.js/ink-puppet.js; add examples/README.md with the lint path.
Adds an explicit 'choose a character source' step so the agent never silently
reuses a bundled character (the 'same mascot every video' problem). Options:
user uploads a drawing; user uploads a photo -> doodle-ify (img2img) -> rig;
generate a fresh doodle (FLUX/Imagen, recommended default); or stock
(pixabay/pexels, hit-or-miss). Bundled chars are demo-only.
Ships Phases 1-3 so the feature isn't left hanging:
- Phase 1: 12-action mocap library (walk/run/jump/climb/march/kick/sit/wave/dab/
shuffle/dance_spin/dance_glide) from CMU + fair1, with mocap/catalog.json.
Fixes the '4 repeated moves' repetition problem.
- Phase 2: bvh2clip.mjs is skeleton-agnostic (fair1/CMU/Mixamo joint aliases) +
frame cap + --name; add-motion.mjs fetches/converts/rebundles any BVH by CMU
id / URL / path — self-extending, no code changes.
- Phase 3: skill guidance to read catalog.json + choreograph variedly (never
loop a clip), add-motion, and the balloon primitive.
- Engine: InkTheater.balloon() speech-balloon primitive (both audit videos
hand-built it).
- Audit fixes: /animated-drawing skill gains a motion->retarget mapping table
(2 motions crashed on the wrong config) + a 'Compositing into HyperFrames'
section (transparent output, GIF-freezes->VP9-alpha, the linter video
contract) + character-variety guidance (animate the user's/a generated
drawing, not a bundled char) + pipeline-exempt notes.
Example refreshed to the new library + full Patrick Hand TTF.
Audit finding from video production: handwriting rendered as serif everywhere
because the woff2 we downloaded was a Google-Fonts css2 subset MISSING basic-latin
(ASCII) glyphs — not because 'SVG text can't use webfonts' (the old README claim
was a misdiagnosis; prior demos were silently serif). Fix: embed the FULL font.
Bundles ink-theater/assets/patrickhand.ttf and corrects README + skill guidance
(HTML overlay divs + full TTF).
Makes the doodle-animation capability findable instead of hidden.
Routing (OpenMontage-internal):
- AGENT_GUIDE: Style Playbooks gets an ink-sketch row + a 'hand-drawn doodle'
routing note (it's a style + engine on the animation / character-animation
pipelines, NOT a new pipeline).
- animation/idea-director + character-animation/character-design-director point
to the Ink Theater / Ink Puppet skills for hand-drawn character briefs.
Cross-agent slash commands (/ink-art, /animated-drawing) for Claude Code,
Copilot, Cursor, and Codex — thin pointers to the canonical skills so they stay
in sync. /ink-art = create a vector doodle from scratch (Ink Theater + Ink
Puppet mocap); /animated-drawing = animate a SUPPLIED drawing via Meta
AnimatedDrawings (raster). New skills/creative/animated-drawing.md documents the
Path A setup/run/limits. Codex prompts are user-home only — .codex/prompts/README
explains the copy/symlink step.
.claude/commands/*.md (Claude Code)
.github/prompts/*.prompt.md (Copilot)
.cursor/commands/*.md (Cursor)
.codex/prompts/*.md + README (Codex; copy to ~/.codex/prompts)
The agent-seamless character system: motion comes from a LIBRARY of real
motion-capture clips, never hand-tuned per video. Two parts:
- mocap/bvh2clip.mjs: offline BVH(3D) -> compact 2D clip converter (FK +
projection + skeleton-rest scaling), run once per motion; bundled via clips.js.
- ink-puppet.js: runtime that draws a stick figure limb-by-limb (draw-on reveal)
and plays named clips via a declarative choreograph() API. Deterministic /
seek-safe (pose = pure fn of segment local time).
Example (examples/mocap-figure): the pencil figure draws itself, then waves /
dabs / jumps / walks from real mocap. Keeps vector white-ink + draw-on reveal
that Meta AnimatedDrawings (raster, humanoid-only, no reveal) cannot do.
Provenance/licensing: mocap/NOTE.md (prefer free CMU mocap for production).
Reusable engine (ink-theater/ink-theater.js, global InkTheater) for hand-drawn
ink-on-white animated 'moving art', authored for HyperFrames (atelier). Five
seek-safe primitives: variable-width brush strokes (inkPath/inkRibbon),
timeline-driven boil, closed-form damped-spring eases, FABRIK 2D IK + riggable
mascot, and a parametric contraption grammar (crank/gauge/hopper/slot/lever/box).
Adds skills/creative/ink-theater.md (metaphor method + mined archetypes + color
grammar) and README with the HyperFrames font gotcha (webfonts apply to HTML
divs, not SVG <text>). Two reference builds under ink-theater/examples/.
Grounded in deep-research on vector/physics/metaphor foundations (FABRIK,
bounded-biharmonic/ARAP, closed-form springs, LLM metaphor+layout planning).
Per maintainer feedback on PR #227:
- Revert success=not issues back to success=True — tool execution
succeeded even when QA finds issues; verdict lives in status/issues
- Update test to assert the real contract: success=True + status='revise'
+ issues non-empty, matching how compose-director actually gates
- Consistent with visual_qa.py: success=True, verdict in validation_passed
The skill SKILL.md files are hardlinked across .agents/skills/ and
.claude/skills/ (same inode, two paths), but git had committed divergent
blobs: the .agents/ copies carried an "Extended reference: AGENTS.md"
note that the .claude/ copies lacked. Because one physical file cannot
match two different blobs, the working tree was permanently dirty on the
three .claude/skills paths.
Stage the .claude copies so both paths commit identical content (with the
AGENTS.md reference note, the fuller intended version). Restores a clean
git status and keeps it clean across checkouts.
Affected skills: flux-best-practices, vercel-composition-patterns,
vercel-react-best-practices.
The selector path previously hid the custom-workflow feature: video_selector
filtered tools on per-operation readiness (bundled WAN models) and both
selectors only chose ToolStatus.AVAILABLE providers, so comfyui_image/
comfyui_video — DEGRADED when bundled model metadata is missing — were
dropped even when the ComfyUI server was up and the caller supplied a full
workflow_json/workflow_path plus output_node.
- Add a custom-workflow readiness path to both selectors: when a custom
workflow is supplied, eligibility is based on server availability (status
!= UNAVAILABLE) for any provider advertising supports.custom_workflow,
not on bundled-model readiness. A custom workflow also restricts routing
to custom-workflow-capable providers, since the graph JSON is ComfyUI
specific.
- Expose workflow_json, workflow_path, output_node, workflow_name,
workflow_model, and workflow_model_stack in both selector schemas so
agents can discover the feature without bypassing the selectors.
- image_selector only forwards the workflow inputs to providers that
declare them.
- Add contract tests for the new eligibility path and schema exposure.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Removed comfyui_music and its workflow. The ACE-Step model runs in
ComfyUI but the node class names differ across custom node packs
(AceStepModelLoader vs native TextEncodeAceStepAudio, etc.), so a
bundled workflow would break for most users.
Documented the reasoning in the plan doc and listed it as an open
question for future work. Users with ACE-Step working can still use
the workflow_json override on any tool.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Client queries ComfyUI /object_info to discover installed models
(checkpoints, diffusion models, VAE, CLIP, LoRAs)
- Each tool declares its required models and checks them on execute()
- get_status() returns DEGRADED when server is up but models are missing
- Clear error messages tell the user exactly which models to download
- When COMFYUI_SERVER_URL is not set, error message tells the user to
configure it in .env instead of silently failing on localhost:8188
- 8 new tests covering URL config, error messages, and model requirements
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Adds three new BaseTool providers that delegate GPU work to a running
ComfyUI server via its REST API. This avoids the need to install
PyTorch/diffusers directly, which is critical on hardware where the
ecosystem hasn't caught up (e.g. NVIDIA Blackwell / DGX Spark, aarch64
+ CUDA 13.0).
New files:
- tools/_comfyui/client.py — shared REST client (submit/poll/download)
- tools/_comfyui/workflows/ — 4 bundled workflow templates
- tools/graphics/comfyui_image.py — FLUX 2 Dev NVFP4 text-to-image
- tools/video/comfyui_video.py — WAN 2.2 14B t2v + i2v (4-step LightX2V)
- tools/audio/comfyui_music.py — ACE-Step 3.5B music generation
- tests/contracts/test_comfyui_tools.py — 41 contract tests
- docs/comfyui-adapter-plan.md — design document
Zero changes to existing tools, selectors, registry, or pipelines.
Tools are auto-discovered and selectors pick them up via capability match.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The contract test in test_character_animation_pipeline.py asserts
result.success after the QA run, implying success should reflect
whether QA passed. But CharacterAnimationReviewer always returned
success=True even when issues were found and status was 'revise'.
This creates a silent failure path: callers that gate on result.success
(the standard ToolResult contract) would treat a broken rig as a clean
pass without ever reading report['status'].
Fix: return success=not issues so result.success is False when QA finds
problems, consistent with the test contract and with how execution errors
are already handled (success=False on exception paths).
Also adds test_character_reviewer_success_false_when_qa_finds_issues to
explicitly assert this contract — a broken rig with missing joints must
produce status='revise', non-empty issues[], and success=False.
AGENT_GUIDE.md requires the music decision to be made at the proposal stage,
but the only check for the user's music_library/ folder lived in the
asset-director skills, which run later. A user could approve a creative
direction without ever being told a free, intentional music option was sitting
on disk (issue #168).
music_library/ was already referenced as a source_tool in asset artifacts but
had no backing tool. Add a small read-only tool that scans the library folder
(default <project root>/music_library, override via MUSIC_LIBRARY_DIR or a
library_dir input) and lists the audio tracks it finds, with best-effort
durations via ffprobe when present.
Because it inherits BaseTool, the registry auto-discovers it and it appears in
the preflight provider menu alongside music_gen and the stock music sources:
- AVAILABLE when the folder holds at least one audio track
- UNAVAILABLE otherwise, with install_instructions telling the user how to add
tracks
So the user sees their music options before approving creative direction, with
no orchestration code changes. Read-only: no side effects, no cost.
Closes#168
The previous attempt at matching the deer-flow Repository-of-the-Day
design used `style=for-the-badge` shields.io rendered as two wide
black/orange rectangles spanning the README width — nothing like the
small bordered pill deer-flow actually ships (a Trendshift-served badge
with a laurel-wreath "1" emblem and two lines of restrained text).
OpenMontage isn't on Trendshift, so a real Trendshift badge isn't
available. Built a custom inline SVG matching the design intent:
- Small (340x68) bordered card with rounded corners
- Laurel-wreath emblem with serif "1" inside on the left
- Two-line text on the right: "GITHUB TRENDING" (small, dimmed gray)
and "#1 Repository Of The Day" (bold, accent)
- Light + dark variants served via prefers-color-scheme picture/source
- Light: white bg, #7C3AED purple stroke/text
- Dark: #0D1117 bg, #A78BFA lavender stroke, #C4B5FD headline
Files added:
- .github/assets/repo-of-the-day-light.svg
- .github/assets/repo-of-the-day-dark.svg
- Add Star History section before License (dark-mode-aware picture/source
pattern matching calesthio/Crucix). Links to star-history.com.
- Repository of the Day badge restyled to match the deer-flow aesthetic:
dark labelColor (#0D1117 — GitHub background), gold accent (#F6B543
dark / #D9892A light), prefers-color-scheme picture variants, 48px
height for a more pill-like proportion. The current bright-purple
shields.io block was less distinctive than the surrounding YouTube/X
badges.
OpenMontage isn't currently listed on Trendshift (deer-flow's badge
provider), so the badge stays shields.io-based; design matches the
intent. If we want a real Trendshift badge later, register the repo
at trendshift.io and swap in the api/badge/repositories/<id> URL.
Adds the new atelier-mode bespoke piece (Library of Alexandria) to the
showcase block, right after THE LAST BANANA. Removes the prior 'Into the
Abyss' anime piece to keep the section focused.
Showcases the doctrine shipped in #203: every scene crafted from scratch
with no shared components — the signature device (the candle + Burning
Counter) appears in only one of five scenes (the climax), per the
scene-distinctness rule in skills/meta/bespoke-composition.md.
Building the in-a-hurry showcase video surfaced a real workflow gap:
bespoke-composition.md was Remotion-flavored throughout. A fresh agent
reading it for a music-driven hero piece would be routed straight to
Remotion atelier — missing that HyperFrames has no cut-schema and is
already atelier by its nature (every HF composition is a hand-authored
index.html with data-* timing and a GSAP timeline you write).
This commit reframes the doctrine to be runtime-aware:
- New "Atelier and the two runtimes" subsection explicitly separates
Remotion (atelier as escape hatch from cut-schema registry) from
HyperFrames (always atelier; composition_mode "atelier" is implicit).
Same principles apply in both cases; the rendering path differs.
- Step 3 (vocabulary) now routes to /hyperframes-animation for HF
projects — 36+ atomic rules (kinetic-beat-slam, 3d-text-depth-layers,
motion-blur-streak, ...), 15+ scene blueprints, 16 transition families,
7 runtime adapters (GSAP / Lottie / Three.js / Anime.js / CSS / WAAPI /
TypeGPU), and the html-in-canvas-patterns headline capability for 1–3
cinematic hero beats per video. Also points at /hyperframes-creative,
/hyperframes-media, /media-use, /hyperframes-cli.
- Step 4 (engine mechanics) adds HF-side gotchas alongside Remotion:
the data-* contract, mandatory class="clip", paused-timeline + seek
rule, lint/validate/snapshot verification primitives, stable-id
selectors over nth-of-type.
- Step 5 (render) split into per-runtime paths:
* Remotion atelier — auto-stage copy + bespoke contract (unchanged).
* HyperFrames — npx hyperframes init scaffold, beats workflow,
lint+validate+snapshot verification, npx hyperframes render.
Flags the known gap (F13): hyperframes_compose.render still requires
cuts[] from the templated path; call npx directly until the tool
grows a bespoke branch parallel to _render_via_atelier.
- Worked precedents section now lists both runtimes — Phantom Reach /
Compound Snowball / Library of Alexandria for Remotion atelier, plus
in-a-hurry for HyperFrames (kinetic-beat-slam + 3d-text-depth-layers
+ motion-blur-streak + css-distortion + html-in-canvas + Three.js
bloom).
## Remotion bump (mechanical, semver-safe)
remotion-composer: Remotion 4.0.441 → 4.0.484 (43 patch versions, all
within 4.0.x). Includes the seven core packages: remotion + @remotion/cli,
captions, google-fonts, media, player, transitions.
Smoke test: re-rendered the compound-snowball atelier composition through
the unchanged tool path; final_review status=pass, atelier checks clean.
Note: package.json also carries d3-geo@^3.1.1 forward — this line was
already in the working tree from prior unrelated WIP and is not part of
this bump. Removing it would leave package-lock mismatched, so it's
preserved as-is here; clean up separately when its consumer lands.
## HyperFrames skills re-vendor (0.4.2 → 0.7.17)
The runtime invoked by hyperframes_compose (`npx hyperframes`) was
already pulling 0.7.17 on every render, but the vendored skill docs the
agent reads were frozen at 0.4.2-era. This commit closes that gap.
Re-vendored from upstream commit 3351fb1a (tag v0.7.17, 2026-06-27):
Re-vendored core 4 (restructured upstream):
- hyperframes (slim entry; deep content moved to focused skills)
- hyperframes-cli (1 → 7 files; covers validate/inspect/snapshot/
benchmark/lambda natively, dropping the obsolete
OM-local validate patch)
- hyperframes-registry
- website-to-video (renamed upstream from website-to-hyperframes)
Newly vendored (8 strategic additions in 0.5–0.7):
- hyperframes-core composition contract (data-*/tracks/sub-comps)
- hyperframes-creative palette, type, narration, beat planning
- hyperframes-media TTS, BGM, SFX, transcription, captions, bg-remove
- hyperframes-animation all motion knowledge (rules, blueprints,
transitions, 7 runtime adapters)
- media-use agent Media OS (one `resolve` verb for
BGM/SFX/image/icon; project + global cache)
- motion-graphics short design-led motion patterns
- remotion-to-hyperframes migration guidance (directly relevant since
OpenMontage runs both runtimes)
- music-to-video beat-synced video using `hyperframes beats`
Intentionally NOT vendored (HF-workflow-specific; would compete with
OpenMontage pipeline routing): embedded-captions, faceless-explainer,
general-video, pr-to-video, product-launch-video, slideshow,
talking-head-recut. Re-evaluate per pipeline need.
PROVENANCE.md refreshed with the new vendor point + re-sync instructions.
## GSAP CDN pin
.agents/skills/hyperframes/SKILL.md: gsap@3.14.2 → gsap@3 (auto-latest 3.x
on jsdelivr; avoids future drift without breaking the API surface).
## Doctrine updates routing to new skill structure
- skills/INDEX.md — HyperFrames row expanded to enumerate the 12 vendored
skills and their roles.
- skills/meta/animation-runtime-selector.md — runtime decision matrix
updated for the rename (website-to-hyperframes → website-to-video) and
three new rows added: beat-synced music videos, Remotion→HF porting,
and the media-use resolve verb. The HyperFrames composition row in the
animation-library matrix split into four (core/creative/media/animation)
per the upstream skill structure.
- skills/core/hyperframes.md — Layer-2 routing skill rewritten to point at
the new focused skills and all website-to-hyperframes references renamed.
F12 — Hero-component spine is a templating anti-pattern. The first
atelier proof (alexandria-fire) leaned on a single candle as scaffolding
under every scene with different text below — same hero, different
caption — which is exactly the "branded slides" pattern atelier was
supposed to break. The signature device is meant to appear in ONE or
at most two beats (typically the climactic moment), not as the visual
scaffolding of every scene. Each scene must earn its own composition:
a different primary visual subject, a different scale, a different motion
register. Doctrine added as step 1.5 in skills/meta/bespoke-composition.md
("Plan each scene as its own composition") plus a reviewer
scene_distinctness gate enforced at compose stage — the reviewer samples
one representative frame per scene and refuses to pass if two or more
scenes share their primary visual subject.
F9 — Captions/on-screen-text dedup. When a SerifLine reads the script
verbatim AND auto-captions emit the same text, the piece looks amateurish
even when the rest is beautiful. Rule added under engine mechanics: decide
once per piece whether captions add meaning (numbers, names, translations,
attributions) or are accessibility subtitles echoing narration — never
both for the same content. Reviewer gate at compose stage compares active
caption text against on-screen text in the same time window.
Both gates are CRITICAL; the publish-stage check was updated to expect
six (was four) resolved atelier findings.
Self-audit of alexandria-fire under the new rules: 4 of 5 scenes share
the candle as their primary visual subject — would now flag CRITICAL
scene_distinctness and require re-planning. (Re-author the piece in a
follow-up; the doctrine is the deliverable here.)
Closes the remaining three atelier audit gaps.
F1 — atelier projects live under repo-root projects/<slug>/ (the
established OpenMontage convention), not under remotion-composer/.
_render_via_atelier now auto-stages source files into
remotion-composer/projects/<slug>/ via mtime-skip copy when the entry
isn't already under the composer tree. Originally tried a directory
junction, but webpack walks up from the entry's REAL location to
resolve node_modules — junctions get dereferenced and module resolution
fails. Copy keeps source-of-truth under projects/, is invisible to the
user's project view, and is cheap (typical project is a few small .tsx
files). Output stays wherever output_path says. effective_entry is
returned in tool data for transparency.
F3 — scripts/scaffold_atelier_project.py generates the engine
boilerplate (index.tsx / Root.tsx / Composition.tsx / art-direction.md /
props template / README) ONLY. No creative content emitted — the
Composition.tsx is a deliberately blank black placeholder with prominent
TODOs. This removes the friction that nudged agents back to templated
mode while making it impossible to ship the scaffold unauthored (review
correctly flags black frames / silent audio as 'revise'). Verified
end-to-end: scaffold → render → review fires the right warnings.
F5 — schemas extended to know about atelier:
- decision_log: 'composition_mode' added to category enum.
- proposal_packet.production_plan: composition_mode + art_direction.
- edit_decisions: composition_mode + bespoke{entry, composition_id,
art_direction, props_path, public_dir, scale, crf, concurrency}.
- final_review.checks: 'atelier' block (stock_reuse_detected,
offending_imports[], art_direction_declared, art_direction).
- final_review.recommended_action: 're_author' added.
- final_review.transcript_comparison: allow null word_accuracy /
transcript_matches_script (pre-existing latent bug surfaced here).
Both pass and fail shapes of the atelier render's final_review now
validate against the updated schema.
Closes the two biggest gaps from the atelier audit: hero bespoke renders
were skipping every automated quality gate, and the templated→atelier
inversion was advisory rather than enforced.
F6 — _render_via_atelier now runs the full _run_final_review (technical
probe + visual spotcheck + audio spotcheck + duration drift + transcript
comparison) plus two atelier-specific doctrine checks:
- stock_reuse_check: rglobs the bespoke project tree for imports from
the stock creative registry (src/components, src/Explainer, etc.).
Any hit fails the render with status="fail" and names the offending
file — the doctrine bypass is now mechanically caught.
- art_direction_check: requires edit_decisions.bespoke.art_direction.
Missing → warning surfaced in final_review.issues_found; forcing
function for step 1 of skills/meta/bespoke-composition.md.
Verified end-to-end on the compound-snowball proof render: positive case
status=pass, atelier checks clean; negative case (deliberate stock import
+ missing art_direction) returns status=fail with both findings named.
F7 — skills/meta/reviewer.md gets a "Composition Authoring Mode Review"
section that enforces the inversion at every stage:
- proposal: composition_mode must be a presented decision with both
options; hero briefs default to atelier; templated for hero requires
an explicit sanctioned reason.
- scene_plan/edit: any stock cut.type in an atelier piece is CRITICAL;
bespoke.{entry, composition_id, art_direction} required.
- compose: consumes final_review.checks.atelier from F6; mandates a
recorded distinctness review (the human taste call the tool can't
automate — its absence is itself CRITICAL).
- publish: blocks ship on any unresolved atelier finding.
Engine knowledge stays reusable; creative components don't.
Introduce a hand-authored, project-local Remotion render path that bypasses
the cut-schema and the stock scene-type registry, for hero/bespoke videos
that must look distinct from one another.
- video_compose: composition_mode="atelier" (or renderer_family="bespoke")
routes to _render_via_atelier, which renders a project-local entry under
remotion-composer/projects/<slug>/ with an optional per-project public_dir
(skips copying the bloated shared public/). No cut-schema, no stock registry.
- skills/meta/bespoke-composition.md: routing skill — art direction
(visual-style) -> motion principles (Disney 12) -> engine mechanics
(remotion-best-practices + stock components read only as a mechanics codex)
-> atelier render. Doctrine: reuse engine knowledge, never creative components.
- AGENT_GUIDE: "Composition Authoring Mode" (templated vs atelier); default
atelier for hero work; scene-type catalog reframed as a mechanics codex.
- animation-runtime-selector + INDEX: authoring-mode-first pointers.
- base_tool.run_command: decode subprocess output as UTF-8/replace (Windows
cp1252 crashed the reader thread on Remotion's Unicode progress output).
- .gitignore: remotion-composer/projects/ (throwaway bespoke compositions).
The compose target resolution was resolved from `profile` (and documented as
overridable via edit_decisions.metadata.compose_target) but the per-segment
scale/pad filter hardcoded 1920x1080. As a result, vertical profiles such as
`tiktok` / `youtube_shorts` / `instagram_reels` silently produced landscape
1920x1080 output instead of 1080x1920 — a silent dimension bug, no error raised.
- Use the resolved target width/height in the per-segment scale/pad filter.
- Implement the previously-stubbed `metadata.compose_target` extension point:
{"width", "height", "fit"} where fit="pad" (letterbox, default, unchanged
behavior) or fit="cover" (scale-to-fill + centre-crop, ideal for vertical).
- Default with no profile/target stays 1920x1080 (backward compatible).
Adds tests/tools/test_video_compose_vertical.py covering default landscape,
profile=tiktok vertical, and compose_target cover override.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
